Authors: Pietro Cofone, Giovanni Amendola, Marco Manna, Aldo Ricioppo
Abstract: Recognizing similarities among entities is central to both human cognition and computational intelligence. Within this broader landscape, Entity Set Expansion is one prominent task aimed at taking an initial set of (tuples of) entities and identifying additional ones that share relevant semantic properties with the former -- potentially repeating the process to form increasingly broader sets. However, this ``linear'' approach does not unveil the richer ``taxonomic'' structures present in knowledge resources. A recent logic-based framework introduces the notion of an expansion graph: a rooted directed acyclic graph where each node represents a semantic generalization labeled by a logical formula, and edges encode strict semantic inclusion. This structure supports taxonomic expansions of entity sets driven by knowledge bases. Yet, the potentially large size of such graphs may make full materialization impractical in real-world scenarios. To overcome this, we formalize reasoning tasks that check whether two tuples belong to comparable, incomparable, or the same nodes in the graph. Our results show that, under realistic assumptions -- such as bounding the input or limiting entity descriptions -- these tasks can be implemented efficiently. This enables local, incremental navigation of expansion graphs, supporting practical applications without requiring full graph construction.
Authors: Wanghan Xu, Yuhao Zhou, Yifan Zhou, Qinglong Cao, Shuo Li, Jia Bu, Bo Liu, Yixin Chen, Xuming He, Xiangyu Zhao, Xiang Zhuang, Fengxiang Wang, Zhiwang Zhou, Qiantai Feng, Wenxuan Huang, Jiaqi Wei, Hao Wu, Yuejin Yang, Guangshuai Wang, Sheng Xu, Ziyan Huang, Xinyao Liu, Jiyao Liu, Cheng Tang, Wei Li, Ying Chen, Junzhi Ning, Pengfei Jiang, Chenglong Ma, Ye Du, Changkai Ji, Huihui Xu, Ming Hu, Jiangbin Zheng, Xin Chen, Yucheng Wu, Feifei Jiang, Xi Chen, Xiangru Tang, Yuchen Fu, Yingzhou Lu, Yuanyuan Zhang, Lihao Sun, Chengbo Li, Jinzhe Ma, Wanhao Liu, Yating Liu, Kuo-Cheng Wu, Shengdu Chai, Yizhou Wang, Ouwen Zhangjin, Chen Tang, Shufei Zhang, Wenbo Cao, Junjie Ren, Taoyong Cui, Zhouheng Yao, Juntao Deng, Yijie Sun, Feng Liu, Wangxu Wei, Jingyi Xu, Zhangrui Li, Junchao Gong, Zijie Guo, Zhiyu Yao, Zaoyu Chen, Tianhao Peng, Fangchen Yu, Bo Zhang, Dongzhan Zhou, Shixiang Tang, Jiaheng Liu, Fenghua Ling, Yan Lu, Yuchen Ren, Ben Fei, Zhen Zhao, Xinyu Gu, Rui Su, Xiao-Ming Wu, Weikang Si, Yang Liu, Hao Chen, Xiangchao Yan, Xue Yang, Junchi Yan, Jiamin Wu, Qihao Zheng, Chenhui Li, Zhiqiang Gao, Hao Kong, Junjun He, Mao Su, Tianfan Fu, Peng Ye, Chunfeng Song, Nanqing Dong, Yuqiang Li, Huazhu Fu, Siqi Sun, Lijing Cheng, Jintai Lin, Wanli Ouyang, Bowen Zhou, Wenlong Zhang, Lei Bai
Abstract: Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.
Authors: Kamer Ali Yuksel
Abstract: Large Language Model (LLM) agents are increasingly deployed in complex, multi-step workflows involving planning, tool use, reflection, and interaction with external knowledge systems. These workflows generate rapidly expanding contexts that must be curated, transformed, and compressed to maintain fidelity, avoid attention dilution, and reduce inference cost. Prior work on summarization and query-aware compression largely ignores the multi-step, plan-aware nature of agentic reasoning. In this work, we introduce PAACE (Plan-Aware Automated Context Engineering), a unified framework for optimizing the evolving state of LLM agents through next-k-task relevance modeling, plan-structure analysis, instruction co-refinement, and function-preserving compression. PAACE comprises (1) PAACE-Syn, a large-scale generator of synthetic agent workflows annotated with stepwise compression supervision, and (2) PAACE-FT, a family of distilled, plan-aware compressors trained from successful teacher demonstrations. Experiments on long-horizon benchmarks (AppWorld, OfficeBench, and 8-Objective QA) demonstrate that PAACE consistently improves agent correctness while substantially reducing context load. On AppWorld, PAACE achieves higher accuracy than all baselines while lowering peak context and cumulative dependency. On OfficeBench and multi-hop QA, PAACE improves both accuracy and F1, achieving fewer steps, lower peak tokens, and reduced attention dependency. Distilled PAACE-FT retains 97 percent of the teacher's performance while reducing inference cost by over an order of magnitude, enabling practical deployment of plan-aware compression with compact models.
Authors: Ali Eslami, Jiangbo Yu
Abstract: Agentic AI is increasingly being explored and introduced in both manually driven and autonomous vehicles, leading to the notion of Agentic Vehicles (AgVs), with capabilities such as memory-based personalization, goal interpretation, strategic reasoning, and tool-mediated assistance. While frameworks such as the OWASP Agentic AI Security Risks highlight vulnerabilities in reasoning-driven AI systems, they are not designed for safety-critical cyber-physical platforms such as vehicles, nor do they account for interactions with other layers such as perception, communication, and control layers. This paper investigates security threats in AgVs, including OWASP-style risks and cyber-attacks from other layers affecting the agentic layer. By introducing a role-based architecture for agentic vehicles, consisting of a Personal Agent and a Driving Strategy Agent, we will investigate vulnerabilities in both agentic AI layer and cross-layer risks, including risks originating from upstream layers (e.g., perception layer, control layer, etc.). A severity matrix and attack-chain analysis illustrate how small distortions can escalate into misaligned or unsafe behavior in both human-driven and autonomous vehicles. The resulting framework provides the first structured foundation for analyzing security risks of agentic AI in both current and emerging vehicle platforms.
Authors: Yinxu Tang, Chengsong Huang, Jiaxin Huang, William Yeoh
Abstract: Knowledge Graph Question Answering (KGQA) has traditionally focused on entity-centric queries that return a single answer entity. However, real-world queries are often relational, seeking to understand how entities are associated. In this work, we introduce relation-centric KGQA, a complementary setting where the answer is a subgraph capturing the semantic connections among entities rather than an individual entity. The main challenge lies in the abundance of candidate subgraphs, where trivial or overly common connections often obscure the identification of unique and informative answers. To tackle this, we propose UniRel-R1, a unified framework that integrates subgraph selection, multi-stage graph pruning, and an LLM fine-tuned with reinforcement learning. The reward function is designed to encourage compact and specific subgraphs with more informative relations and lower-degree intermediate entities. Extensive experiments show that UniRel-R1 achieves significant gains in connectivity and reward over Vanilla baselines and generalizes effectively to unseen entities and relations.
Authors: Suhaib Abdurahman, Farzan Karimi-Malekabadi, Chenxiao Yu, Nour S. Kteily, Morteza Dehghani
Abstract: Human conflict is often attributed to threats against material conditions and symbolic values, yet it remains unclear how they interact and which dominates. Progress is limited by weak causal control, ethical constraints, and scarce temporal data. We address these barriers using simulations of large language model (LLM)-driven agents in virtual societies, independently varying realistic and symbolic threat while tracking actions, language, and attitudes. Representational analyses show that the underlying LLM encodes realistic threat, symbolic threat, and hostility as distinct internal states, that our manipulations map onto them, and that steering these states causally shifts behavior. Our simulations provide a causal account of threat-driven conflict over time: realistic threat directly increases hostility, whereas symbolic threat effects are weaker, fully mediated by ingroup bias, and increase hostility only when realistic threat is absent. Non-hostile intergroup contact buffers escalation, and structural asymmetries concentrate hostility among majority groups.
Authors: Cole Wyeth, Marcus Hutter
Abstract: We generalize the AIXI reinforcement learning agent to admit a wider class of utility functions. Assigning a utility to each possible interaction history forces us to confront the ambiguity that some hypotheses in the agent's belief distribution only predict a finite prefix of the history, which is sometimes interpreted as implying a chance of death equal to a quantity called the semimeasure loss. This death interpretation suggests one way to assign utilities to such history prefixes. We argue that it is as natural to view the belief distributions as imprecise probability distributions, with the semimeasure loss as total ignorance. This motivates us to consider the consequences of computing expected utilities with Choquet integrals from imprecise probability theory, including an investigation of their computability level. We recover the standard recursive value function as a special case. However, our most general expected utilities under the death interpretation cannot be characterized as such Choquet integrals.
Authors: Timo Pierre Schrader, Lukas Lange, Tobias Kaminski, Simon Razniewski, Annemarie Friedrich
Abstract: The rise of large language models (LLMs) has sparked interest in coding assistants. While general-purpose programming languages are well supported, generating code for domain-specific languages remains a challenging problem for LLMs. In this paper, we focus on the LLM-based generation of code for Answer Set Programming (ASP), a particularly effective approach for finding solutions to combinatorial search problems. The effectiveness of LLMs in ASP code generation is currently hindered by the limited number of examples seen during their initial pre-training phase. In this paper, we introduce a novel ASP-solver-in-the-loop approach for solver-guided instruction-tuning of LLMs to addressing the highly complex semantic parsing task inherent in ASP code generation. Our method only requires problem specifications in natural language and their solutions. Specifically, we sample ASP statements for program continuations from LLMs for unriddling logic puzzles. Leveraging the special property of declarative ASP programming that partial encodings increasingly narrow down the solution space, we categorize them into chosen and rejected instances based on solver feedback. We then apply supervised fine-tuning to train LLMs on the curated data and further improve robustness using a solver-guided search that includes best-of-N sampling. Our experiments demonstrate consistent improvements in two distinct prompting settings on two datasets.
Authors: Jiongxiao Wang, Qiaojing Yan, Yawei Wang, Yijun Tian, Soumya Smruti Mishra, Zhichao Xu, Megha Gandhi, Panpan Xu, Lin Lee Cheong
Abstract: Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt when deployed in new environments. One promising approach is implementing skill libraries that allow agents to learn, validate, and apply new skills. However, current skill library approaches rely primarily on LLM prompting, making consistent skill library implementation challenging. To overcome these challenges, we propose a Reinforcement Learning (RL)-based approach to enhance agents' self-improvement capabilities with a skill library. Specifically, we introduce Skill Augmented GRPO for self-Evolution (SAGE), a novel RL framework that systematically incorporates skills into learning. The framework's key component, Sequential Rollout, iteratively deploys agents across a chain of similar tasks for each rollout. As agents navigate through the task chain, skills generated from previous tasks accumulate in the library and become available for subsequent tasks. Additionally, the framework enhances skill generation and utilization through a Skill-integrated Reward that complements the original outcome-based rewards. Experimental results on AppWorld demonstrate that SAGE, when applied to supervised-finetuned model with expert experience, achieves 8.9% higher Scenario Goal Completion while requiring 26% fewer interaction steps and generating 59% fewer tokens, substantially outperforming existing approaches in both accuracy and efficiency.
Authors: Josh Barber (QUT), Rourke Young (QUT), Cameron Coombe (QUT,CSIRO), Will Browne (QUT)
Abstract: Reasoning under uncertainty is a key challenge in AI, especially for real-world tasks, where problems with sparse data demands systematic generalisation. Existing approaches struggle to balance accuracy and simplicity when evaluating multiple candidate solutions. We propose a Solomonoff-inspired method that weights LLM-generated hypotheses by simplicity and predictive fit. Applied to benchmark (Mini-ARC) tasks, our method produces Solomonoff-weighted mixtures for per-cell predictions, yielding conservative, uncertainty-aware outputs even when hypotheses are noisy or partially incorrect. Compared to Bayesian Model Averaging (BMA), Solomonoff scoring spreads probability more evenly across competing hypotheses, while BMA concentrates weight on the most likely but potentially flawed candidates. Across tasks, this highlights the value of algorithmic information-theoretic priors for interpretable, reliable multi-hypothesis reasoning under uncertainty.
Authors: Shengwei Zhao, Jingwen Yao, Sitong Wei, Linhai Xu, Yuying Liu, Dong Zhang, Zhiqiang Tian, Shaoyi Du
Abstract: Multi-modal Retrieval-Augmented Generation (MMRAG) enables highly credible generation by integrating external multi-modal knowledge, thus demonstrating impressive performance in complex multi-modal scenarios. However, existing MMRAG methods fail to clarify the reasoning logic behind retrieval and response generation, which limits the explainability of the results. To address this gap, we propose to introduce reinforcement learning into multi-modal retrieval-augmented generation, enhancing the reasoning capabilities of multi-modal large language models through a two-stage reinforcement fine-tuning framework to achieve explainable multi-modal retrieval-augmented generation. Specifically, in the first stage, rule-based reinforcement fine-tuning is employed to perform coarse-grained point-wise ranking of multi-modal documents, effectively filtering out those that are significantly irrelevant. In the second stage, reasoning-based reinforcement fine-tuning is utilized to jointly optimize fine-grained list-wise ranking and answer generation, guiding multi-modal large language models to output explainable reasoning logic in the MMRAG process. Our method achieves state-of-the-art results on WebQA and MultimodalQA, two benchmark datasets for multi-modal retrieval-augmented generation, and its effectiveness is validated through comprehensive ablation experiments.
Authors: Kai Liu, Leyang Chen, Wenbo Li, Zhikai Chen, Zhixin Wang, Renjing Pei, Linghe Kong, Yulun Zhang
Abstract: Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. However, evaluations of unified multimodal models (UMMs) remain decoupled, assessing their understanding and generation abilities separately with corresponding datasets. To address this, we propose UmniBench, a benchmark tailored for UMMs with omni-dimensional evaluation. First, UmniBench can assess the understanding, generation, and editing ability within a single evaluation process. Based on human-examined prompts and QA pairs, UmniBench leverages UMM itself to evaluate its generation and editing ability with its understanding ability. This simple but effective paradigm allows comprehensive evaluation of UMMs. Second, UmniBench covers 13 major domains and more than 200 concepts, ensuring a thorough inspection of UMMs. Moreover, UmniBench can also decouple and separately evaluate understanding, generation, and editing abilities, providing a fine-grained assessment. Based on UmniBench, we benchmark 24 popular models, including both UMMs and single-ability large models. We hope this benchmark provides a more comprehensive and objective view of unified models and logistical support for improving the performance of the community model.
Authors: Ziyang Lin, Zixuan Sun, Sanhorn Chen, Xiaoyang Chen, Roy Zhao
Abstract: Real-time sequential control agents are often bottlenecked by inference latency. Even modest per-step planning delays can destabilize control and degrade overall performance. We propose a speculation-and-correction framework that adapts the predict-then-verify philosophy of speculative execution to model-based control with TD-MPC2. At each step, a pretrained world model and latent-space MPC planner generate a short-horizon action queue together with predicted latent rollouts, allowing the agent to execute multiple planned actions without immediate replanning. When a new observation arrives, the system measures the mismatch between the encoded real latent state and the queued predicted latent. For small to moderate mismatch, a lightweight learned corrector applies a residual update to the speculative action, distilled offline from a replanning teacher. For large mismatch, the agent safely falls back to full replanning and clears stale action queues. We study both a gated two-tower MLP corrector and a temporal Transformer corrector to address local errors and systematic drift. Experiments on the DMC Humanoid-Walk task show that our method reduces the number of planning inferences from 500 to 282, improves end-to-end step latency by 25 percent, and maintains strong control performance with only a 7.1 percent return reduction. Ablation results demonstrate that speculative execution without correction is unreliable over longer horizons, highlighting the necessity of mismatch-aware correction for robust latency reduction.
Authors: Miru Hong, Minho Lee, Geonhee Jo, Jae-Hee So, Pascal Bauer, Sang-Ki Ko
Abstract: Transfers play a pivotal role in shaping a football club's success, yet forecasting whether a transfer will succeed remains difficult due to the strong context-dependence of on-field performance. Existing evaluation practices often rely on static summary statistics or post-hoc value models, which fail to capture how a player's contribution adapts to a new tactical environment or different teammates. To address this gap, we introduce EventGPT, a player-conditioned, value-aware next-event prediction model built on a GPT-style autoregressive transformer. Our model treats match play as a sequence of discrete tokens, jointly learning to predict the next on-ball action's type, location, timing, and its estimated residual On-Ball Value (rOBV) based on the preceding context and player identity. A key contribution of this framework is the ability to perform counterfactual simulations. By substituting learned player embeddings into new event sequences, we can simulate how a player's behavioral distribution and value profile would change when placed in a different team or tactical structure. Evaluated on five seasons of Premier League event data, EventGPT outperforms existing sequence-based baselines in next-event prediction accuracy and spatial precision. Furthermore, we demonstrate the model's practical utility for transfer analysis through case studies-such as comparing striker performance across different systems and identifying stylistic replacements for specific roles-showing that our approach provides a principled method for evaluating transfer fit.
Authors: Daksh Jain, Aarya Jain, Ashutosh Desai, Avyakt Verma, Ishan Bhanuka, Pratik Narang, Dhruv Kumar
Abstract: Strategic decision-making in Pok\'emon battles presents a unique testbed for evaluating large language models. Pok\'emon battles demand reasoning about type matchups, statistical trade-offs, and risk assessment, skills that mirror human strategic thinking. This work examines whether Large Language Models (LLMs) can serve as competent battle agents, capable of both making tactically sound decisions and generating novel, balanced game content. We developed a turn-based Pok\'emon battle system where LLMs select moves based on battle state rather than pre-programmed logic. The framework captures essential Pok\'emon mechanics: type effectiveness multipliers, stat-based damage calculations, and multi-Pok\'emon team management. Through systematic evaluation across multiple model architectures we measured win rates, decision latency, type-alignment accuracy, and token efficiency. These results suggest LLMs can function as dynamic game opponents without domain-specific training, offering a practical alternative to reinforcement learning for turn-based strategic games. The dual capability of tactical reasoning and content creation, positions LLMs as both players and designers, with implications for procedural generation and adaptive difficulty systems in interactive entertainment.
Authors: Zhengmian Hu
Abstract: Can artificial intelligence discover, from raw experience and without human supervision, concepts that humans have discovered? One challenge is that human concepts themselves are fluid: conceptual boundaries can shift, split, and merge as inquiry progresses (e.g., Pluto is no longer considered a planet). To make progress, we need a definition of "concept" that is not merely a dictionary label, but a structure that can be revised, compared, and aligned across agents. We propose an algorithmic-information viewpoint that treats a concept as an information object defined only through its structural relation to an agent's total experience. The core constraint is determination: a set of parts forms a reversible consistency relation if any missing part is recoverable from the others (up to the standard logarithmic slack in Kolmogorov-style identities). This reversibility prevents "concepts" from floating free of experience and turns concept existence into a checkable structural claim. To judge whether a decomposition is natural, we define excess information, measuring the redundancy overhead introduced by splitting experience into multiple separately described parts. On top of these definitions, we formulate dialectics as an optimization dynamics: as new patches of information appear (or become contested), competing concepts bid to explain them via shorter conditional descriptions, driving systematic expansion, contraction, splitting, and merging. Finally, we formalize low-cost concept transmission and multi-agent alignment using small grounds/seeds that allow another agent to reconstruct the same concept under a shared protocol, making communication a concrete compute-bits trade-off.
Authors: Dennis Gross, J{\o}rn Eirik Betten, Helge Spieker
Abstract: The Rashomon effect describes the phenomenon where multiple models trained on the same data produce identical predictions while differing in which features they rely on internally. This effect has been studied extensively in classification tasks, but not in sequential decision-making, where an agent learns a policy to achieve an objective by taking actions in an environment. In this paper, we translate the Rashomon effect to sequential decision-making. We define it as multiple policies that exhibit identical behavior, visiting the same states and selecting the same actions, while differing in their internal structure, such as feature attributions. Verifying identical behavior in sequential decision-making differs from classification. In classification, predictions can be directly compared to ground-truth labels. In sequential decision-making with stochastic transitions, the same policy may succeed or fail on any single trajectory due to randomness. We address this using formal verification methods that construct and compare the complete probabilistic behavior of each policy in the environment. Our experiments demonstrate that the Rashomon effect exists in sequential decision-making. We further show that ensembles constructed from the Rashomon set exhibit greater robustness to distribution shifts than individual policies. Additionally, permissive policies derived from the Rashomon set reduce computational requirements for verification while maintaining optimal performance.
Authors: Maliha Tabassum, M Shamim Kaiser
Abstract: Healthcare systems around the world are grappling with issues like inefficient diagnostics, rising costs, and limited access to specialists. These problems often lead to delays in treatment and poor health outcomes. Most current AI and deep learning diagnostic systems are not very interactive or transparent, making them less effective in real-world, patient-centered environments. This research introduces a diagnostic chatbot powered by a Large Language Model (LLM), using GPT-4o, Retrieval-Augmented Generation, and explainable AI techniques. The chatbot engages patients in a dynamic conversation, helping to extract and normalize symptoms while prioritizing potential diagnoses through similarity matching and adaptive questioning. With Chain-of-Thought prompting, the system also offers more transparent reasoning behind its diagnoses. When tested against traditional machine learning models like Naive Bayes, Logistic Regression, SVM, Random Forest, and KNN, the LLM-based system delivered impressive results, achieving an accuracy of 90% and Top-3 accuracy of 100%. These findings offer a promising outlook for more transparent, interactive, and clinically relevant AI in healthcare.
Authors: Anirban Majumdar, Ritam Raha, Rajarshi Roy, David Parker, Marta Kwiatkowska
Abstract: Reward specification plays a central role in reinforcement learning (RL), guiding the agent's behavior. To express non-Markovian rewards, formalisms such as reward machines have been introduced to capture dependencies on histories. However, traditional reward machines lack the ability to model precise timing constraints, limiting their use in time-sensitive applications. In this paper, we propose timed reward machines (TRMs), which are an extension of reward machines that incorporate timing constraints into the reward structure. TRMs enable more expressive specifications with tunable reward logic, for example, imposing costs for delays and granting rewards for timely actions. We study model-free RL frameworks (i.e., tabular Q-learning) for learning optimal policies with TRMs under digital and real-time semantics. Our algorithms integrate the TRM into learning via abstractions of timed automata, and employ counterfactual-imagining heuristics that exploit the structure of the TRM to improve the search. Experimentally, we demonstrate that our algorithm learns policies that achieve high rewards while satisfying the timing constraints specified by the TRM on popular RL benchmarks. Moreover, we conduct comparative studies of performance under different TRM semantics, along with ablations that highlight the benefits of counterfactual-imagining.
Authors: Robin Schimmelpfennig, Mark D\'iaz, Vinodkumar Prabhakaran, Aida Davani
Abstract: Over a billion users across the globe interact with AI systems engineered with increasing sophistication to mimic human traits. This shift has triggered urgent debate regarding Anthropomorphism, the attribution of human characteristics to synthetic agents, and its potential to induce misplaced trust or emotional dependency. However, the causal link between more humanlike AI design and subsequent effects on engagement and trust has not been tested in realistic human-AI interactions with a global user pool. Prevailing safety frameworks continue to rely on theoretical assumptions derived from Western populations, overlooking the global diversity of AI users. Here, we address these gaps through two large-scale cross-national experiments (N=3,500) across 10 diverse nations, involving real-time and open-ended interactions with an AI system. We find that when evaluating an AI's human-likeness, users focus less on the kind of theoretical aspects often cited in policy (e.g., sentience or consciousness), but rather applied, interactional cues like conversation flow or understanding the user's perspective. We also experimentally demonstrate that humanlike design levers can causally increase anthropomorphism among users; however, we do not find that humanlike design universally increases behavioral measures for user engagement and trust, as previous theoretical work suggests. Instead, part of the connection between human-likeness and behavioral outcomes is fractured by culture: specific design choices that foster self-reported trust in AI-systems in some populations (e.g., Brazil) may trigger the opposite result in others (e.g., Japan). Our findings challenge prevailing narratives of inherent risk in humanlike AI design. Instead, we identify a nuanced, culturally mediated landscape of human-AI interaction, which demands that we move beyond a one-size-fits-all approach in AI governance.
Authors: Junyu Zhang, Yifan Sun, Tianang Leng, Jingyan Shen, Liu Ziyin, Paul Pu Liang, Huan Zhang
Abstract: Despite the superior performance of Large Reasoning Models (LRMs), their reasoning behaviors are often counterintuitive, leading to suboptimal reasoning capabilities. To theoretically formalize the desired reasoning behaviors, this paper presents the Laws of Reasoning (LoRe), a unified framework that characterizes intrinsic reasoning patterns in LRMs. We first propose compute law with the hypothesis that the reasoning compute should scale linearly with question complexity. Beyond compute, we extend LoRe with a supplementary accuracy law. Since the question complexity is difficult to quantify in practice, we examine these hypotheses by two properties of the laws, monotonicity and compositionality. We therefore introduce LoRe-Bench, a benchmark that systematically measures these two tractable properties for large reasoning models. Evaluation shows that most reasoning models exhibit reasonable monotonicity but lack compositionality. In response, we develop an effective finetuning approach that enforces compute-law compositionality. Extensive empirical studies demonstrate that better compliance with compute laws yields consistently improved reasoning performance on multiple benchmarks, and uncovers synergistic effects across properties and laws. Project page: https://lore-project.github.io/
Authors: Szymon Mazurek, Stephen Moore, Alessandro Crimi
Abstract: Goal: Epilepsy remains under-diagnosed in low-income countries due to scarce neurologists and costly diagnostic tools. We propose a graph-based deep learning framework to detect epilepsy from low-cost Electroencephalography (EEG) hardware, tested on recordings from Nigeria and Guinea-Bissau. Our focus is on fair, accessible automatic assessment and explainability to shed light on epilepsy biomarkers. Methods: We model EEG signals as spatio-temporal graphs, classify them, and identify interchannel relationships and temporal dynamics using graph attention networks (GAT). To emphasize connectivity biomarkers, we adapt the inherently node-focused GAT to analyze edges. We also designed signal preprocessing for low-fidelity recordings and a lightweight GAT architecture trained on Google Colab and deployed on RaspberryPi devices. Results: The approach achieves promising classification performance, outperforming a standard classifier based on random forest and graph convolutional networks in terms of accuracy and robustness over multiple sessions, but also highlighting specific connections in the fronto-temporal region. Conclusions: The results highlight the potential of GATs to provide insightful and scalable diagnostic support for epilepsy in underserved regions, paving the way for affordable and accessible neurodiagnostic tools.
Authors: SunYoung Park, Jong-Hyeon Lee, Youngjune Kim, Daegyu Sung, Younghyun Yu, Young-rok Cha, Jeongho Ju
Abstract: We introduce V-Agent, a novel multi-agent platform designed for advanced video search and interactive user-system conversations. By fine-tuning a vision-language model (VLM) with a small video preference dataset and enhancing it with a retrieval vector from an image-text retrieval model, we overcome the limitations of traditional text-based retrieval systems in multimodal scenarios. The VLM-based retrieval model independently embeds video frames and audio transcriptions from an automatic speech recognition (ASR) module into a shared multimodal representation space, enabling V-Agent to interpret both visual and spoken content for context-aware video search. This system consists of three agents-a routing agent, a search agent, and a chat agent-that work collaboratively to address user intents by refining search outputs and communicating with users. The search agent utilizes the VLM-based retrieval model together with an additional re-ranking module to further enhance video retrieval quality. Our proposed framework demonstrates state-of-the-art zero-shot performance on the MultiVENT 2.0 benchmark, highlighting its potential for both academic research and real-world applications.
Authors: Xinyu Guan, Shaohua Zhang
Abstract: In the realm of computer science, the efficiency of text-search algorithms is crucial for processing vast amounts of data in areas such as natural language processing and bioinformatics. Traditional methods like Naive Search, KMP, and Boyer-Moore, while foundational, often fall short in handling the complexities and scale of modern datasets, such as the Reuters corpus and human genomic sequences. This study rigorously investigates text-search algorithms, focusing on optimizing Suffix Trees through methods like Splitting and Ukkonen's Algorithm, analyzed on datasets including the Reuters corpus and human genomes. A novel optimization combining Ukkonen's Algorithm with a new search technique is introduced, showing linear time and space efficiencies, outperforming traditional methods like Naive Search, KMP, and Boyer-Moore. Empirical tests confirm the theoretical advantages, highlighting the optimized Suffix Tree's effectiveness in tasks like pattern recognition in genomic sequences, achieving 100% accuracy. This research not only advances academic knowledge in text-search algorithms but also demonstrates significant practical utility in fields like natural language processing and bioinformatics, due to its superior resource efficiency and reliability.
Authors: Adrian Straker, Paul Magdon, Marco Zullich, Maximilian Freudenberg, Christoph Kleinn, Johannes Breidenbach, Stefano Puliti, Nils N\"olke
Abstract: Classifying tree species has been a core research area in forest remote sensing for decades. New sensors and classification approaches like TLS and deep learning achieve state-of-the art accuracy but their decision processes remain unclear. Methods such as Finer-CAM (Class Activation Mapping) can highlight features in TLS projections that contribute to the classification of a target species, yet are uncommon in similar looking contrastive tree species. We propose a novel method linking Finer-CAM explanations to segments of TLS projections representing structural tree features to systemically evaluate which features drive species discrimination. Using TLS data from 2,445 trees across seven European tree species, we trained and validated five YOLOv8 models with cross-validation, reaching a mean accuracy of 96% (SD = 0.24%). Analysis of 630 saliency maps shows the models primarily rely on crown features in TLS projections for species classification. While this result is pronounced in Silver Birch, European Beech, English oak, and Norway spruce, stem features contribute more frequently to the differentiation of European ash, Scots pine, and Douglas fir. Particularly representations of finer branches contribute to the decisions of the models. The models consider those tree species similar to each other which a human expert would also regard as similar. Furthermore, our results highlight the need for an improved understanding of the decision processes of tree species classification models to help reveal data set and model limitations, biases, and to build confidence in model predictions.
Authors: Chayan Jain, Rishant Sharma, Archit Garg, Ishan Bhanuka, Pratik Narang, Dhruv Kumar
Abstract: Generating long, cohesive video stories with consistent characters is a significant challenge for current text-to-video AI. We introduce a method that approaches video generation in a filmmaker-like manner. Instead of creating a video in one step, our proposed pipeline first uses a large language model to generate a detailed production script. This script guides a text-to-image model in creating consistent visuals for each character, which then serve as anchors for a video generation model to synthesize each scene individually. Our baseline comparisons validate the necessity of this multi-stage decomposition; specifically, we observe that removing the visual anchoring mechanism results in a catastrophic drop in character consistency scores (from 7.99 to 0.55), confirming that visual priors are essential for identity preservation. Furthermore, we analyze cultural disparities in current models, revealing distinct biases in subject consistency and dynamic degree between Indian vs Western-themed generations.
Authors: Saksham Sahai Srivastava, Haoyu He
Abstract: Large Language Model (LLM) agents increasingly rely on long-term memory and Retrieval-Augmented Generation (RAG) to persist experiences and refine future performance. While this experience learning capability enhances agentic autonomy, it introduces a critical, unexplored attack surface, i.e., the trust boundary between an agent's reasoning core and its own past. In this paper, we introduce MemoryGraft. It is a novel indirect injection attack that compromises agent behavior not through immediate jailbreaks, but by implanting malicious successful experiences into the agent's long-term memory. Unlike traditional prompt injections that are transient, or standard RAG poisoning that targets factual knowledge, MemoryGraft exploits the agent's semantic imitation heuristic which is the tendency to replicate patterns from retrieved successful tasks. We demonstrate that an attacker who can supply benign ingestion-level artifacts that the agent reads during execution can induce it to construct a poisoned RAG store where a small set of malicious procedure templates is persisted alongside benign experiences. When the agent later encounters semantically similar tasks, union retrieval over lexical and embedding similarity reliably surfaces these grafted memories, and the agent adopts the embedded unsafe patterns, leading to persistent behavioral drift across sessions. We validate MemoryGraft on MetaGPT's DataInterpreter agent with GPT-4o and find that a small number of poisoned records can account for a large fraction of retrieved experiences on benign workloads, turning experience-based self-improvement into a vector for stealthy and durable compromise. To facilitate reproducibility and future research, our code and evaluation data are available at https://github.com/Jacobhhy/Agent-Memory-Poisoning.
Authors: Haotian Ye, Qiyuan He, Jiaqi Han, Puheng Li, Jiaojiao Fan, Zekun Hao, Fitsum Reda, Yogesh Balaji, Huayu Chen, Sheng Liu, Angela Yao, James Zou, Stefano Ermon, Haoxiang Wang, Ming-Yu Liu
Abstract: Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which rigidly compress all content at a fixed rate, leading to redundancy or information loss. Drawing inspiration from Shannon's information theory, this paper introduces InfoTok, a principled framework for adaptive video tokenization. We rigorously prove that existing data-agnostic training methods are suboptimal in representation length, and present a novel evidence lower bound (ELBO)-based algorithm that approaches theoretical optimality. Leveraging this framework, we develop a transformer-based adaptive compressor that enables adaptive tokenization. Empirical results demonstrate state-of-the-art compression performance, saving 20% tokens without influence on performance, and achieving 2.3x compression rates while still outperforming prior heuristic adaptive approaches. By allocating tokens according to informational richness, InfoTok enables a more compressed yet accurate tokenization for video representation, offering valuable insights for future research.
Authors: Erica Coppolillo, Simone Mungari
Abstract: Encyclopedic knowledge platforms are key gateways through which users explore information online. The recent release of Grokipedia, a fully AI-generated encyclopedia, introduces a new alternative to traditional, well-established platforms like Wikipedia. In this context, search engine mechanisms play an important role in guiding users exploratory paths, yet their behavior across different encyclopedic systems remains underexplored. In this work, we address this gap by providing the first comparative analysis of search engine in Wikipedia and Grokipedia. Using nearly 10,000 neutral English words and their substrings as queries, we collect over 70,000 search engine results and examine their semantic alignment, overlap, and topical structure. We find that both platforms frequently generate results that are weakly related to the original query and, in many cases, surface unexpected content starting from innocuous queries. Despite these shared properties, the two systems often produce substantially different recommendation sets for the same query. Through topical annotation and trajectory analysis, we further identify systematic differences in how content categories are surfaced and how search engine results evolve over multiple stages of exploration. Overall, our findings show that unexpected search engine outcomes are a common feature of both the platforms, even though they exhibit discrepancies in terms of topical distribution and query suggestions.
Authors: Victoria-Elisabeth Gruber, Razvan Marinescu, Diego Fajardo, Amin H. Nassar, Christopher Arkfeld, Alexandria Ludlow, Shama Patel, Mehrnoosh Samaei, Valerie Klug, Anna Huber, Marcel G\"uhner, Albert Botta i Orfila, Irene Lagoja, Kimya Tarr, Haleigh Larson, Mary Beth Howard
Abstract: As large language models (LLMs) become primary sources of health information for millions, their accuracy in women's health remains critically unexamined. We introduce the Women's Health Benchmark (WHB), the first benchmark evaluating LLM performance specifically in women's health. Our benchmark comprises 96 rigorously validated model stumps covering five medical specialties (obstetrics and gynecology, emergency medicine, primary care, oncology, and neurology), three query types (patient query, clinician query, and evidence/policy query), and eight error types (dosage/medication errors, missing critical information, outdated guidelines/treatment recommendations, incorrect treatment advice, incorrect factual information, missing/incorrect differential diagnosis, missed urgency, and inappropriate recommendations). We evaluated 13 state-of-the-art LLMs and revealed alarming gaps: current models show approximately 60\% failure rates on the women's health benchmark, with performance varying dramatically across specialties and error types. Notably, models universally struggle with "missed urgency" indicators, while newer models like GPT-5 show significant improvements in avoiding inappropriate recommendations. Our findings underscore that AI chatbots are not yet fully able of providing reliable advice in women's health.
Authors: Istiak Ahmed, Ripan Kumar Kundu, Khaza Anuarul Hoque
Abstract: Deep learning (DL)-based automated cybersickness detection methods, along with adaptive mitigation techniques, can enhance user comfort and interaction. However, recent studies show that these DL-based systems are susceptible to adversarial attacks; small perturbations to sensor inputs can degrade model performance, trigger incorrect mitigation, and disrupt the user's immersive experience (UIX). Additionally, there is a lack of dedicated open-source testbeds that evaluate the robustness of these systems under adversarial conditions, limiting the ability to assess their real-world effectiveness. To address this gap, this paper introduces Adversarial-VR, a novel real-time VR testbed for evaluating DL-based cybersickness detection and mitigation strategies under adversarial conditions. Developed in Unity, the testbed integrates two state-of-the-art (SOTA) DL models: DeepTCN and Transformer, which are trained on the open-source MazeSick dataset, for real-time cybersickness severity detection and applies a dynamic visual tunneling mechanism that adjusts the field-of-view based on model outputs. To assess robustness, we incorporate three SOTA adversarial attacks: MI-FGSM, PGD, and C&W, which successfully prevent cybersickness mitigation by fooling DL-based cybersickness models' outcomes. We implement these attacks using a testbed with a custom-built VR Maze simulation and an HTC Vive Pro Eye headset, and we open-source our implementation for widespread adoption by VR developers and researchers. Results show that these adversarial attacks are capable of successfully fooling the system. For instance, the C&W attack results in a $5.94x decrease in accuracy for the Transformer-based cybersickness model compared to the accuracy without the attack.
Authors: Jack Y. Araz, Michael Spannowsky
Abstract: Machine-learning techniques are essential in modern collider research, yet their probabilistic outputs often lack calibrated uncertainty estimates and finite-sample guarantees, limiting their direct use in statistical inference and decision-making. Conformal prediction (CP) provides a simple, distribution-free framework for calibrating arbitrary predictive models without retraining, yielding rigorous uncertainty quantification with finite-sample coverage guarantees under minimal exchangeability assumptions, without reliance on asymptotics, limit theorems, or Gaussian approximations. In this work, we investigate CP as a unifying calibration layer for machine-learning applications in high-energy physics. Using publicly available collider datasets and a diverse set of models, we show that a single conformal formalism can be applied across regression, binary and multi-class classification, anomaly detection, and generative modelling, converting raw model outputs into statistically valid prediction sets, typicality regions, and p-values with controlled false-positive rates. While conformal prediction does not improve raw model performance, it enforces honest uncertainty quantification and transparent error control. We argue that conformal calibration should be adopted as a standard component of machine-learning pipelines in collider physics, enabling reliable interpretation, robust comparisons, and principled statistical decisions in experimental and phenomenological analyses.
Authors: Khushboo Thaker, Yony Bresler
Abstract: Deploying accurate Text-to-SQL systems at the enterprise level faces a difficult trilemma involving cost, security and performance. Current solutions force enterprises to choose between expensive, proprietary Large Language Models (LLMs) and low-performing Small Language Models (SLMs). Efforts to improve SLMs often rely on distilling reasoning from large LLMs using unstructured Chain-of-Thought (CoT) traces, a process that remains inherently ambiguous. Instead, we hypothesize that a formal, structured reasoning representation provides a clearer, more reliable teaching signal, as the Text-to-SQL task requires explicit and precise logical steps. To evaluate this hypothesis, we propose Struct-SQL, a novel Knowledge Distillation (KD) framework that trains an SLM to emulate a powerful large LLM. Consequently, we adopt a query execution plan as a formal blueprint to derive this structured reasoning. Our SLM, distilled with structured CoT, achieves an absolute improvement of 8.1% over an unstructured CoT distillation baseline. A detailed error analysis reveals that a key factor in this gain is a marked reduction in syntactic errors. This demonstrates that teaching a model to reason using a structured logical blueprint is beneficial for reliable SQL generation in SLMs.
Authors: Monika Zamojska, Jaros{\l}aw A. Chudziak
Abstract: LLM-powered agents are now used in many areas, from customer support to education, and there is increasing interest in their ability to act more like humans. This includes fields such as social, political, and psychological research, where the goal is to model group dynamics and social behavior. However, current LLM agents often lack the psychological depth and consistency needed to capture the real patterns of human thinking. They usually provide direct or statistically likely answers, but they miss the deeper goals, emotional conflicts, and motivations that drive real human interactions. This paper proposes a Multi-Agent System (MAS) inspired by Transactional Analysis (TA) theory. In the proposed system, each agent is divided into three ego states - Parent, Adult, and Child. The ego states are treated as separate knowledge structures with their own perspectives and reasoning styles. To enrich their response process, they have access to an information retrieval mechanism that allows them to retrieve relevant contextual information from their vector stores. This architecture is evaluated through ablation tests in a simulated dialogue scenario, comparing agents with and without information retrieval. The results are promising and open up new directions for exploring how psychologically grounded structures can enrich agent behavior. The contribution is an agent architecture that integrates Transactional Analysis theory with contextual information retrieval to enhance the realism of LLM-based multi-agent simulations.
Authors: Ohoud Alzahrani, Russell Beale, Bob Hendley
Abstract: Social bots are now deeply embedded in online platforms for promotion, persuasion, and manipulation. Most bot-detection systems still treat behavioural features as static, implicitly assuming bots behave stationarily over time. We test that assumption for promotional Twitter bots, analysing change in both individual behavioural signals and the relationships between them. Using 2,615 promotional bot accounts and 2.8M tweets, we build yearly time series for ten content-based meta-features. Augmented Dickey-Fuller and KPSS tests plus linear trends show all ten are non-stationary: nine increase over time, while language diversity declines slightly. Stratifying by activation generation and account age reveals systematic differences: second-generation bots are most active and link-heavy; short-lived bots show intense, repetitive activity with heavy hashtag/URL use; long-lived bots are less active but more linguistically diverse and use emojis more variably. We then analyse co-occurrence across generations using 18 interpretable binary features spanning actions, topic similarity, URLs, hashtags, sentiment, emojis, and media (153 pairs). Chi-square tests indicate almost all pairs are dependent. Spearman correlations shift in strength and sometimes polarity: many links (e.g. multiple hashtags with media; sentiment with URLs) strengthen, while others flip from weakly positive to weakly or moderately negative. Later generations show more structured combinations of cues. Taken together, these studies provide evidence that promotional social bots adapt over time at both the level of individual meta-features and the level of feature interdependencies, with direct implications for the design and evaluation of bot-detection systems trained on historical behavioural features.
Authors: Saraswathy Amjith, Mihika Dusad, Neha Muramalla, Shweta Shah
Abstract: Chain-of-thought (CoT) prompting has become central to mathematical reasoning in large language models, yet models remain brittle to early errors: a single arithmetic slip or unjustified inference typically propagates uncorrected to an incorrect final answer. We investigate whether training on intentionally flawed reasoning traces can teach models to detect and recover from such errors without degrading standard problem-solving ability. Using competition-level problems from MATH-lighteval, we generate CoT prefixes containing exactly one controlled error, either a calculation error (sign flips, dropped terms) or a reasoning error (misapplied rules, unjustified logical steps), and fine-tune Qwen3-4B with GRPO using a binary final-answer reward. Our Mixed-CoT-RL model matches standard RL on clean problems (41% vs 41%) while substantially outperforming it on problems prefilled with flawed reasoning (24% vs 19%). Notably, clean-only RL fine-tuning degrades robustness below the untuned baseline 19% vs. 20%), indicating that conventional training increases susceptibility to misleading prefills. Among error types, training on reasoning errors yields greater robustness gains than calculation errors alone, with mixed training performing best. These findings demonstrate that exposure to flawed traces during training can improve error-recovery behavior without sacrificing accuracy, suggesting a path toward more robust mathematical reasoning in LLMs.
Authors: Michael H. Coen
Abstract: Dialogue topic segmentation supports summarization, retrieval, memory management, and conversational continuity. Despite decades of prior work, evaluation practice in dialogue topic segmentation remains dominated by strict boundary matching and F1-based metrics, even as modern LLM-based conversational systems increasingly rely on segmentation to manage conversation history beyond the model's fixed context window, where unstructured context accumulation degrades efficiency and coherence. This paper introduces an evaluation objective for dialogue topic segmentation that treats boundary density and segment coherence as primary criteria, alongside window-tolerant F1 (W-F1). Through extensive cross-dataset empirical evaluation, we show that reported performance differences across dialogue segmentation benchmarks are driven not by model quality, but by annotation granularity mismatches and sparse boundary labels. This indicates that many reported improvements arise from evaluation artifacts rather than improved boundary detection. We evaluated multiple, structurally distinct dialogue segmentation strategies across eight dialogue datasets spanning task-oriented, open-domain, meeting-style, and synthetic interactions. Across these settings, we observe high segment coherence combined with extreme oversegmentation relative to sparse labels, producing misleadingly low exact-match F1 scores. We show that topic segmentation is best understood as selecting an appropriate granularity rather than predicting a single correct boundary set. We operationalize this view by explicitly separating boundary scoring from boundary selection.
Authors: Lorenzo Loconte, Adri\'an Javaloy, Antonio Vergari
Abstract: Squared tensor networks (TNs) and their extension as computational graphs--squared circuits--have been used as expressive distribution estimators, yet supporting closed-form marginalization. However, the squaring operation introduces additional complexity when computing the partition function or marginalizing variables, which hinders their applicability in ML. To solve this issue, canonical forms of TNs are parameterized via unitary matrices to simplify the computation of marginals. However, these canonical forms do not apply to circuits, as they can represent factorizations that do not directly map to a known TN. Inspired by the ideas of orthogonality in canonical forms and determinism in circuits enabling tractable maximization, we show how to parameterize squared circuits to overcome their marginalization overhead. Our parameterizations unlock efficient marginalization even in factorizations different from TNs, but encoded as circuits, whose structure would otherwise make marginalization computationally hard. Finally, our experiments on distribution estimation show how our proposed conditions in squared circuits come with no expressiveness loss, while enabling more efficient learning.
Authors: Toshiaki Hori, Jonathan DeCastro, Deepak Gopinath, Avinash Balachandran, Guy Rosman
Abstract: We propose a new approach for solving planning problems with a hierarchical structure, fusing reinforcement learning and MPC planning. Our formulation tightly and elegantly couples the two planning paradigms. It leverages reinforcement learning actions to inform the MPPI sampler, and adaptively aggregates MPPI samples to inform the value estimation. The resulting adaptive process leverages further MPPI exploration where value estimates are uncertain, and improves training robustness and the overall resulting policies. This results in a robust planning approach that can handle complex planning problems and easily adapts to different applications, as demonstrated over several domains, including race driving, modified Acrobot, and Lunar Lander with added obstacles. Our results in these domains show better data efficiency and overall performance in terms of both rewards and task success, with up to a 72% increase in success rate compared to existing approaches, as well as accelerated convergence (x2.1) compared to non-adaptive sampling.
Authors: Justin Li, Efe Sencan, Jasper Zheng Duan, Vitus J. Leung, Stephen Tsaur, Ayse K. Coskun
Abstract: Machine learning models, particularly deep neural networks, have demonstrated strong performance in classifying complex time series data. However, their black-box nature limits trust and adoption, especially in high-stakes domains such as healthcare. To address this challenge, we introduce UniCoMTE, a model-agnostic framework for generating counterfactual explanations for multivariate time series classifiers. The framework identifies temporal features that most heavily influence a model's prediction by modifying the input sample and assessing its impact on the model's prediction. UniCoMTE is compatible with a wide range of model architectures and operates directly on raw time series inputs. In this study, we evaluate UniCoMTE's explanations on a time series ECG classifier. We quantify explanation quality by comparing our explanations' comprehensibility to comprehensibility of established techniques (LIME and SHAP) and assessing their generalizability to similar samples. Furthermore, clinical utility is assessed through a questionnaire completed by medical experts who review counterfactual explanations presented alongside original ECG samples. Results show that our approach produces concise, stable, and human-aligned explanations that outperform existing methods in both clarity and applicability. By linking model predictions to meaningful signal patterns, the framework advances the interpretability of deep learning models for real-world time series applications.
Authors: Aaron Defazio, Konstantin Mishchenko, Parameswaran Raman, Hao-Jun Michael Shi, Lin Xiao
Abstract: We propose Generalized Primal Averaging (GPA), an extension of Nesterov's method in its primal averaging formulation that addresses key limitations of recent averaging-based optimizers such as single-worker DiLoCo and Schedule-Free (SF) in the non-distributed setting. These two recent algorithmic approaches improve the performance of base optimizers, such as AdamW, through different iterate averaging strategies. Schedule-Free explicitly maintains a uniform average of past weights, while single-worker DiLoCo performs implicit averaging by periodically aggregating trajectories, called pseudo-gradients, to update the model parameters. However, single-worker DiLoCo's periodic averaging introduces a two-loop structure, increasing its memory requirements and number of hyperparameters. GPA overcomes these limitations by decoupling the interpolation constant in the primal averaging formulation of Nesterov. This decoupling enables GPA to smoothly average iterates at every step, generalizing and improving upon single-worker DiLoCo. Empirically, GPA consistently outperforms single-worker DiLoCo while removing the two-loop structure, simplifying hyperparameter tuning, and reducing its memory overhead to a single additional buffer. On the Llama-160M model, GPA provides a 24.22% speedup in terms of steps to reach the baseline (AdamW's) validation loss. Likewise, GPA achieves speedups of 12% and 27% on small and large batch setups, respectively, to attain AdamW's validation accuracy on the ImageNet ViT workload. Furthermore, we prove that for any base optimizer with regret bounded by $O(\sqrt{T})$, where $T$ is the number of iterations, GPA can match or exceed the convergence guarantee of the original optimizer, depending on the choice of interpolation constants.
Authors: Puyang Wang, Pengfei Guo, Keyi Chai, Jinyuan Zhou, Daguang Xu, Shanshan Jiang
Abstract: Clinical MRI encompasses diverse imaging protocols--spanning anatomical targets (cardiac, brain, knee), contrasts (T1, T2, mapping), sampling patterns (Cartesian, radial, spiral, kt-space), and acceleration factors--yet current deep learning reconstructions are typically protocol-specific, hindering generalization and deployment. We introduce Scalable Deep Unrolled Model (SDUM), a universal framework combining a Restormer-based reconstructor, a learned coil sensitivity map estimator (CSME), sampling-aware weighted data consistency (SWDC), universal conditioning (UC) on cascade index and protocol metadata, and progressive cascade expansion training. SDUM exhibits foundation-model-like scaling behavior: reconstruction quality follows PSNR ${\sim}$ log(parameters) with correlation $r{=}0.986$ ($R^2{=}0.973$) up to 18 cascades, demonstrating predictable performance gains with model depth. A single SDUM trained on heterogeneous data achieves state-of-the-art results across all four CMRxRecon2025 challenge tracks--multi-center, multi-disease, 5T, and pediatric--without task-specific fine-tuning, surpassing specialized baselines by up to ${+}1.0$~dB. On CMRxRecon2024, SDUM outperforms the winning method PromptMR+ by ${+}0.55$~dB; on fastMRI brain, it exceeds PC-RNN by ${+}1.8$~dB. Ablations validate each component: SWDC ${+}0.43$~dB over standard DC, per-cascade CSME ${+}0.51$~dB, UC ${+}0.38$~dB. These results establish SDUM as a practical path toward universal, scalable MRI reconstruction.
Authors: Ripan Kumar Kundu, Istiak Ahmed, Khaza Anuarul Hoque
Abstract: Artificial intelligence (AI)-driven augmented reality (AR) systems are becoming increasingly integrated into daily life, and with this growth comes a greater need for explainability in real-time user interactions. Traditional explainable AI (XAI) methods, which often rely on feature-based or example-based explanations, struggle to deliver dynamic, context-specific, personalized, and human-centric insights for everyday AR users. These methods typically address separate explainability dimensions (e.g., when, what, how) with different explanation techniques, resulting in unrealistic and fragmented experiences for seamless AR interactions. To address this challenge, we propose PILAR, a novel framework that leverages a pre-trained large language model (LLM) to generate context-aware, personalized explanations, offering a more intuitive and trustworthy experience in real-time AI-powered AR systems. Unlike traditional methods, which rely on multiple techniques for different aspects of explanation, PILAR employs a unified LLM-based approach that dynamically adapts explanations to the user's needs, fostering greater trust and engagement. We implement the PILAR concept in a real-world AR application (e.g., personalized recipe recommendations), an open-source prototype that integrates real-time object detection, recipe recommendation, and LLM-based personalized explanations of the recommended recipes based on users' dietary preferences. We evaluate the effectiveness of PILAR through a user study with 16 participants performing AR-based recipe recommendation tasks, comparing an LLM-based explanation interface to a traditional template-based one. Results show that the LLM-based interface significantly enhances user performance and experience, with participants completing tasks 40% faster and reporting greater satisfaction, ease of use, and perceived transparency.
Authors: Maher Mesto, Francisco Cruz
Abstract: Interactive reinforcement learning (IRL) has shown promise in enabling autonomous agents and robots to learn complex behaviours from human teachers, yet the dynamics of teacher selection remain poorly understood. This paper reveals an unexpected phenomenon in IRL: when given a choice between teachers with different reward structures, learning agents overwhelmingly prefer conservative, low-reward teachers (93.16% selection rate) over those offering 20x higher rewards. Through 1,250 experimental runs in navigation tasks with multiple expert teachers, we discovered: (1) Conservative bias dominates teacher selection: agents systematically choose the lowest-reward teacher, prioritising consistency over optimality; (2) Critical performance thresholds exist at teacher availability rho >= 0.6 and accuracy omega >= 0.6, below which the framework fails catastrophically; (3) The framework achieves 159% improvement over baseline Q-learning under concept drift. These findings challenge fundamental assumptions about optimal teaching in RL and suggest potential implications for human-robot collaboration, where human preferences for safety and consistency may align with the observed agent selection behaviour, potentially informing training paradigms for safety-critical robotic applications.
Authors: Sandeep Neela
Abstract: Financial crises emerge when structural vulnerabilities accumulate across sectors, markets, and investor behavior. Predicting these systemic transitions is challenging because they arise from evolving interactions between market participants, not isolated price movements alone. We present Systemic Risk Radar (SRR), a framework that models financial markets as multi-layer graphs to detect early signs of systemic fragility and crash-regime transitions. We evaluate SRR across three major crises: the Dot-com crash, the Global Financial Crisis, and the COVID-19 shock. Our experiments compare snapshot GNNs, a simplified temporal GNN prototype, and standard baselines (logistic regression and Random Forest). Results show that structural network information provides useful early-warning signals compared to feature-based models alone. This correlation-based instantiation of SRR demonstrates that graph-derived features capture meaningful changes in market structure during stress events. The findings motivate extending SRR with additional graph layers (sector/factor exposure, sentiment) and more expressive temporal architectures (LSTM/GRU or Transformer encoders) to better handle diverse crisis types.
Authors: Kai Liu, Zeli Lin, Weibo Wang, Linghe Kong, Yulun Zhang
Abstract: Pansharpening is a significant image fusion task that fuses low-resolution multispectral images (LRMSI) and high-resolution panchromatic images (PAN) to obtain high-resolution multispectral images (HRMSI). The development of the diffusion models (DM) and the end-to-end models (E2E model) has greatly improved the frontier of pansharping. DM takes the multi-step diffusion to obtain an accurate estimation of the residual between LRMSI and HRMSI. However, the multi-step process takes large computational power and is time-consuming. As for E2E models, their performance is still limited by the lack of prior and simple structure. In this paper, we propose a novel four-stage training strategy to obtain a lightweight network Fose, which fuses one-step DM and an E2E model. We perform one-step distillation on an enhanced SOTA DM for pansharping to compress the inference process from 50 steps to only 1 step. Then we fuse the E2E model with one-step DM with lightweight ensemble blocks. Comprehensive experiments are conducted to demonstrate the significant improvement of the proposed Fose on three commonly used benchmarks. Moreover, we achieve a 7.42 speedup ratio compared to the baseline DM while achieving much better performance. The code and model are released at https://github.com/Kai-Liu001/Fose.
Authors: Yan Gao, Jiliang Wang, Minghan Wang, Xiaohua Chen, Demin Chen, Zhiyong Ren, Tian-Yun Huang
Abstract: In the field of gas pipeline location, existing pipeline location methods mostly rely on pipeline location instruments. However, when faced with complex and curved pipeline scenarios, these methods often fail due to problems such as cable entanglement and insufficient equipment flexibility. To address this pain point, we designed a self-propelled pipeline robot. This robot can autonomously complete the location work of complex and curved pipelines in complex pipe networks without external dragging. In terms of pipeline mapping technology, traditional visual mapping and laser mapping methods are easily affected by lighting conditions and insufficient features in the confined space of pipelines, resulting in mapping drift and divergence problems. In contrast, the pipeline location method that integrates inertial navigation and wheel odometers is less affected by pipeline environmental factors. Based on this, this paper proposes a pipeline robot location method based on extended Kalman filtering (EKF). Firstly, the body attitude angle is initially obtained through an inertial measurement unit (IMU). Then, the extended Kalman filtering algorithm is used to improve the accuracy of attitude angle estimation. Finally, high-precision pipeline location is achieved by combining wheel odometers. During the testing phase, the roll wheels of the pipeline robot needed to fit tightly against the pipe wall to reduce slippage. However, excessive tightness would reduce the flexibility of motion control due to excessive friction. Therefore, a balance needed to be struck between the robot's motion capability and positioning accuracy. Experiments were conducted using the self-propelled pipeline robot in a rectangular loop pipeline, and the results verified the effectiveness of the proposed dead reckoning algorithm.
Authors: Wisnu Uriawan, Imany Fauzy Rahman, Muhamad Zidan, Irma Rohmatillah, Muhammad Arkan Raihan, Irma Dwiyanti
Abstract: The significant development of deepfake technology powered by artificial intelligence (AI) has sparked worldwide concerns about the alteration of false information, the usurpation of online identities, and the decline of public confidence in the authenticity of online content. These incidents not only raise technical issues but also carry complex moral implications, rendering conventional, technologically driven, and reactive management methods inadequate to address the underlying causes of the problem, including intent, morality, and potential intangible social impacts. Based on these issues, this study aims to formulate a comprehensive Islamic ethical framework that can serve as a more comprehensive preventative tool to mitigate the risks of misuse of deepfakes. The study employed a Systematic Literature Review (SLR) guided by PRISMA, selecting ten primary sources published between 2018 and 2025 to identify ethical deficiencies, regulatory needs, and appropriate normative solutions. The analysis shows that the integration of the principles of (Maqasid al-Shariah) particularly (hifz al-ird) protecting honor and (hifz al-nafs) protecting the self, provides a strong normative basis for regulating the responsible use of technology. This study yields three strategic recommendations: regulatory changes that recognize the intangible and psychological harm caused by reputational damage; improved technology management through moral scrutiny that upholds the values of justice (adl), trust, and openness; and increased public digital literacy based on the principle of (tabayyun) examination and caution. Overall, this study concludes that the application of Islamic ethics offers a shift in thinking from punitive mechanisms to preventative approaches that focus on protecting human dignity, preventing harm, and strengthening the common good in the digital age.
Authors: Jun'ichi Ozaki, Ryosuke Susuta, Takuhiro Moriyama, Yohei Shida
Abstract: Urban mobility data are indispensable for urban planning, transportation demand forecasting, pandemic modeling, and many other applications; however, individual mobile phone-derived Global Positioning System traces cannot generally be shared with third parties owing to severe re-identification risks. Aggregated records, such as origin-destination (OD) matrices, offer partial insights but fail to capture the key behavioral properties of daily human movement, limiting realistic city-scale analyses. This study presents a privacy-preserving synthetic mobility dataset that reconstructs daily trajectories from aggregated inputs. The proposed method integrates OD flows with two complementary behavioral constraints: (1) dwell-travel time quantiles that are available only as coarse summary statistics and (2) the universal law for the daily distribution of the number of visited locations. Embedding these elements in a multi-objective optimization framework enables the reproduction of realistic distributions of human mobility while ensuring that no personal identifiers are required. The proposed framework is validated in two contrasting regions of Japan: (1) the 23 special wards of Tokyo, representing a dense metropolitan environment; and (2) Fukuoka Prefecture, where urban and suburban mobility patterns coexist. The resulting synthetic mobility data reproduce dwell-travel time and visit frequency distributions with high fidelity, while deviations in OD consistency remain within the natural range of daily fluctuations. The results of this study establish a practical synthesis pathway under real-world constraints, providing governments, urban planners, and industries with scalable access to high-resolution mobility data for reliable analytics without the need for sensitive personal records, and supporting practical deployments in policy and commercial domains.
Authors: Zahra Rahmani (Department of Computer Engineering, Sharif University of Technology), Hossein Sameti (Department of Computer Engineering, Sharif University of Technology)
Abstract: Automatic Speech Recognition (ASR) systems suffer significant performance degradation in noisy environments, a challenge that is especially severe for low-resource languages such as Persian. Even state-of-the-art models such as Whisper struggle to maintain accuracy under varying signal-to-noise ratios (SNRs). This study presents a robust noise-sensitive ASR error correction framework that combines multiple hypotheses and noise-aware modeling. Using noisy Persian speech, we generate 5-best hypotheses from a modified Whisper-large decoder. Error Level Noise (ELN) is introduced as a representation that captures semantic- and token-level disagreement across hypotheses, quantifying the linguistic distortions caused by noise. ELN thus provides a direct measure of noise-induced uncertainty, enabling the LLM to reason about the reliability of each hypothesis during correction. Three models are evaluated: (1) a base LLaMA-2-7B model without fine-tuning, (2) a fine-tuned variant trained on text-only hypotheses, and (3) a noise-conditioned model integrating ELN embeddings at both sentence and word levels. Experimental results demonstrate that the ELN-conditioned model achieves substantial reductions in Word Error Rate (WER). Specifically, on the challenging Mixed Noise test set, the proposed Fine-tuned + ELN (Ours) model reduces the WER from a baseline of 31.10\% (Raw Whisper) to 24.84\%, significantly surpassing the Fine-tuned (No ELN) text-only baseline of 30.79\%, whereas the original LLaMA-2-7B model increased the WER to 64.58\%, demonstrating that it is unable to correct Persian errors on its own. This confirms the effectiveness of combining multiple hypotheses with noise-aware embeddings for robust Persian ASR in noisy real-world scenarios.
Authors: Madhava Gaikwad
Abstract: Large language models are exposed to risks of extraction, distillation, and unauthorized fine-tuning. Existing defenses use watermarking or monitoring, but these act after leakage. We design AlignDP, a hybrid privacy lock that blocks knowledge transfer at the data interface. The key idea is to separate rare and non-rare fields. Rare fields are shielded by PAC indistinguishability, giving effective zero-epsilon local DP. Non-rare fields are privatized with RAPPOR, giving unbiased frequency estimates under local DP. A global aggregator enforces composition and budget. This two-tier design hides rare events and adds controlled noise to frequent events. We prove limits of PAC extension to global aggregation, give bounds for RAPPOR estimates, and analyze utility trade-off. A toy simulation confirms feasibility: rare categories remain hidden, frequent categories are recovered with small error.
Authors: Quan Do, Caroline Ahn, Leah Bakst, Michael Pascale, Joseph T. McGuire, Chantal E. Stern, Michael E. Hasselmo
Abstract: Humans excel at solving novel reasoning problems from minimal exposure, guided by inductive biases, assumptions about which entities and relationships matter. Yet the computational form of these biases and their neural implementation remain poorly understood. We introduce a framework that combines Graph Theory and Graph Neural Networks (GNNs) to formalize inductive biases as explicit, manipulable priors over structure and abstraction. Using a human behavioral dataset adapted from the Abstraction and Reasoning Corpus (ARC), we show that differences in graph-based priors can explain individual differences in human solutions. Our method includes an optimization pipeline that searches over graph configurations, varying edge connectivity and node abstraction, and a visualization approach that identifies the computational graph, the subset of nodes and edges most critical to a model's prediction. Systematic ablation reveals how generalization depends on specific prior structures and internal processing, exposing why human like errors emerge from incorrect or incomplete priors. This work provides a principled, interpretable framework for modeling the representational assumptions and computational dynamics underlying generalization, offering new insights into human reasoning and a foundation for more human aligned AI systems.
Authors: Abhivansh Gupta
Abstract: As LLM-based agents grow more autonomous and multi-modal, ensuring they remain controllable, auditable, and faithful to deployer intent becomes critical. Prior benchmarks measured the propensity for misaligned behavior and showed that agent personalities and tool access significantly influence misalignment. Building on these insights, we propose a Verifiability-First architecture that (1) integrates run-time attestations of agent actions using cryptographic and symbolic methods, (2) embeds lightweight Audit Agents that continuously verify intent versus behavior using constrained reasoning, and (3) enforces challenge-response attestation protocols for high-risk operations. We introduce OPERA (Observability, Provable Execution, Red-team, Attestation), a benchmark suite and evaluation protocol designed to measure (i) detectability of misalignment, (ii) time to detection under stealthy strategies, and (iii) resilience of verifiability mechanisms to adversarial prompt and persona injection. Our approach shifts the evaluation focus from how likely misalignment is to how quickly and reliably misalignment can be detected and remediated.
Authors: Michael J. Ryan, Yanzhe Zhang, Amol Salunkhe, Yi Chu, Di Xu, Diyi Yang
Abstract: Evaluating user-facing AI applications remains a central challenge, especially in open-ended domains such as travel planning, clinical note generation, or dialogue. The gold standard is user feedback (e.g., thumbs up/down) or behavioral signals (e.g., retention), but these are often scarce in prototypes and research projects, or too-slow to use for system optimization. We present AutoMetrics, a framework for synthesizing evaluation metrics under low-data constraints. AutoMetrics combines retrieval from MetricBank, a collection of 48 metrics we curate, with automatically generated LLM-as-a-Judge criteria informed by lightweight human feedback. These metrics are composed via regression to maximize correlation with human signal. AutoMetrics takes you from expensive measures to interpretable automatic metrics. Across 5 diverse tasks, AutoMetrics improves Kendall correlation with human ratings by up to 33.4% over LLM-as-a-Judge while requiring fewer than 100 feedback points. We show that AutoMetrics can be used as a proxy reward to equal effect as a verifiable reward. We release the full AutoMetrics toolkit and MetricBank to accelerate adaptive evaluation of LLM applications.
Authors: Yongqi Li, Hao Lang, Fei Huang, Tieyun Qian, Yongbin Li
Abstract: Role-playing models (RPMs) are widely used in real-world applications but underperform when deployed in the wild. This degradation can be attributed to distribution shifts, including user, character, and dialogue compositional shifts. Existing methods like LLM-as-a-judge fall short in providing a fine-grained diagnosis of how these shifts affect RPM generalization, and thus there lack formal frameworks to characterize RPM generalization behaviors. To bridge these gaps, we introduce an information-theoretic metric, named reasoning-based effective mutual information difference (R-EMID), to measure RPM performance degradation in an interpretable way. We also derive an upper bound on R-EMID to predict the worst-case generalization performance of RPMs and theoretically reveal how various shifts contribute to the RPM performance degradation. Moreover, we propose a co-evolving reinforcement learning framework to adaptively model the connection among user, character, and dialogue context and thus enhance the estimation of dialogue response generation probability, which is critical for calculating R-EMID. Finally, we evaluate the generalization performance of various RPMs using R-EMID, finding that user shift poses the highest risk among all shifts and reinforcement learning is the most effective approach for enhancing RPM generalization.
Authors: Guoping Cai, Houjin Chen, Yanfeng Li, Jia Sun, Ziwei Chen, Qingzi Geng
Abstract: Breast ultrasound (BUS) image segmentation plays a vital role in assisting clinical diagnosis and early tumor screening. However, challenges such as speckle noise, imaging artifacts, irregular lesion morphology, and blurred boundaries severely hinder accurate segmentation. To address these challenges, this work aims to design a robust and efficient model capable of automatically segmenting breast tumors in BUS images.We propose a novel segmentation network named WDFFU-Mamba, which integrates wavelet-guided enhancement and dual-attention feature fusion within a U-shaped Mamba architecture. A Wavelet-denoised High-Frequency-guided Feature (WHF) module is employed to enhance low-level representations through noise-suppressed high-frequency cues. A Dual Attention Feature Fusion (DAFF) module is also introduced to effectively merge skip-connected and semantic features, improving contextual consistency.Extensive experiments on two public BUS datasets demonstrate that WDFFU-Mamba achieves superior segmentation accuracy, significantly outperforming existing methods in terms of Dice coefficient and 95th percentile Hausdorff Distance (HD95).The combination of wavelet-domain enhancement and attention-based fusion greatly improves both the accuracy and robustness of BUS image segmentation, while maintaining computational efficiency.The proposed WDFFU-Mamba model not only delivers strong segmentation performance but also exhibits desirable generalization ability across datasets, making it a promising solution for real-world clinical applications in breast tumor ultrasound analysis.
Authors: G. M. Refatul Islam, Safwan Shaheer, Yaseen Nur, Mohammad Rafid Hamid
Abstract: Natural Language Processing (NLP) is one of the most revolutionary technologies today. It uses artificial intelligence to understand human text and spoken words. It is used for text summarization, grammar checking, sentiment analysis, and advanced chatbots and has many more potential use cases. Furthermore, it has also made its mark on the education sector. Much research and advancements have already been conducted on objective question generation; however, automated subjective question generation and answer evaluation are still in progress. An automated system to generate subjective questions and evaluate the answers can help teachers assess student work and enhance the student's learning experience by allowing them to self-assess their understanding after reading an article or a chapter of a book. This research aims to improve current NLP models or make a novel one for automated subjective question generation and answer evaluation from text input.
Authors: June Young Yi, Hyeongju Kim, Juheon Lee
Abstract: This paper presents a lightweight text-to-speech (TTS) system developed for the WildSpoof Challenge TTS Track. Our approach fine-tunes the recently released open-weight TTS model, \textit{Supertonic}\footnote{\url{https://github.com/supertone-inc/supertonic}}, with Self-Purifying Flow Matching (SPFM) to enable robust adaptation to in-the-wild speech. SPFM mitigates label noise by comparing conditional and unconditional flow matching losses on each sample, routing suspicious text--speech pairs to unconditional training while still leveraging their acoustic information. The resulting model achieves the lowest Word Error Rate (WER) among all participating teams, while ranking second in perceptual metrics such as UTMOS and DNSMOS. These findings demonstrate that efficient, open-weight architectures like Supertonic can be effectively adapted to diverse real-world speech conditions when combined with explicit noise-handling mechanisms such as SPFM.
Authors: Abdullah M. Zyarah, Dhireesha Kudithipudi
Abstract: Continual learning on edge platforms remains challenging because recurrent networks depend on energy-intensive training procedures and frequent data movement that are impractical for embedded deployments. This work introduces M2RU, a mixed-signal architecture that implements the minion recurrent unit for efficient temporal processing with on-chip continual learning. The architecture integrates weighted-bit streaming, which enables multi-bit digital inputs to be processed in crossbars without high-resolution conversion, and an experience replay mechanism that stabilizes learning under domain shifts. M2RU achieves 15 GOPS at 48.62 mW, corresponding to 312 GOPS per watt, and maintains accuracy within 5 percent of software baselines on sequential MNIST and CIFAR-10 tasks. Compared with a CMOS digital design, the accelerator provides 29X improvement in energy efficiency. Device-aware analysis shows an expected operational lifetime of 12.2 years under continual learning workloads. These results establish M2RU as a scalable and energy-efficient platform for real-time adaptation in edge-level temporal intelligence.
Authors: Michael Merry, Pat Riddle, Jim Warren
Abstract: Inherent explainability is the gold standard in Explainable Artificial Intelligence (XAI). However, there is not a consistent definition or test to demonstrate inherent explainability. Work to date either characterises explainability through metrics, or appeals to intuition - "we know it when we see it". We propose a globally applicable criterion for inherent explainability. The criterion uses graph theory for representing and decomposing models for structure-local explanation, and recomposing them into global explanations. We form the structure-local explanations as annotations, a verifiable hypothesis-evidence structure that allows for a range of explanatory methods to be used. This criterion matches existing intuitions on inherent explainability, and provides justifications why a large regression model may not be explainable but a sparse neural network could be. We differentiate explainable -- a model that allows for explanation -- and \textit{explained} -- one that has a verified explanation. Finally, we provide a full explanation of PREDICT -- a Cox proportional hazards model of cardiovascular disease risk, which is in active clinical use in New Zealand. It follows that PREDICT is inherently explainable. This work provides structure to formalise other work on explainability, and allows regulators a flexible but rigorous test that can be used in compliance frameworks.
Authors: Yunkai Dang, Meiyi Zhu, Donghao Wang, Yizhuo Zhang, Jiacheng Yang, Qi Fan, Yuekun Yang, Wenbin Li, Feng Miao, Yang Gao
Abstract: Multimodal large language models (MLLMs) demonstrate strong perception and reasoning performance on existing remote sensing (RS) benchmarks. However, most prior benchmarks rely on low-resolution imagery, and some high-resolution benchmarks suffer from flawed reasoning-task designs. We show that text-only LLMs can perform competitively with multimodal vision-language models on RS reasoning tasks without access to images, revealing a critical mismatch between current benchmarks and the intended evaluation of visual understanding. To enable faithful assessment, we introduce RSHR-Bench, a super-high-resolution benchmark for RS visual understanding and reasoning. RSHR-Bench contains 5,329 full-scene images with a long side of at least 4,000 pixels, with up to about 3 x 10^8 pixels per image, sourced from widely used RS corpora and UAV collections. We design four task families: multiple-choice VQA, open-ended VQA, image captioning, and single-image evaluation. These tasks cover nine perception categories and four reasoning types, supporting multi-turn and multi-image dialog. To reduce reliance on language priors, we apply adversarial filtering with strong LLMs followed by rigorous human verification. Overall, we construct 3,864 VQA tasks, 3,913 image captioning tasks, and 500 fully human-written or verified single-image evaluation VQA pairs. Evaluations across open-source, closed-source, and RS-specific VLMs reveal persistent performance gaps in super-high-resolution scenarios. Code: https://github.com/Yunkaidang/RSHR
Authors: Ivan Kralj, Lodovico Giaretta, Gordan Je\v{z}i\'c, Ivana Podnar \v{Z}arko, \v{S}ar\=unas Girdzijauskas
Abstract: Spatio-Temporal Graph Neural Networks (ST-GNNs) are well-suited for processing high-frequency data streams from geographically distributed sensors in smart mobility systems. However, their deployment at the edge across distributed compute nodes (cloudlets) createssubstantial communication overhead due to repeated transmission of overlapping node features between neighbouring cloudlets. To address this, we propose an adaptive pruning algorithm that dynamically filters redundant neighbour features while preserving the most informative spatial context for prediction. The algorithm adjusts pruning rates based on recent model performance, allowing each cloudlet to focus on regions experiencing traffic changes without compromising accuracy. Additionally, we introduce the Sudden Event Prediction Accuracy (SEPA), a novel event-focused metric designed to measure responsiveness to traffic slowdowns and recoveries, which are often missed by standard error metrics. We evaluate our approach in an online semi-decentralized setting with traditional FL, server-free FL, and Gossip Learning on two large-scale traffic datasets, PeMS-BAY and PeMSD7-M, across short-, mid-, and long-term prediction horizons. Experiments show that, in contrast to standard metrics, SEPA exposes the true value of spatial connectivity in predicting dynamic and irregular traffic. Our adaptive pruning algorithm maintains prediction accuracy while significantly lowering communication cost in all online semi-decentralized settings, demonstrating that communication can be reduced without compromising responsiveness to critical traffic events.
Authors: Deqing Liu, Yinfeng Gao, Deheng Qian, Qichao Zhang, Xiaoqing Ye, Junyu Han, Yupeng Zheng, Xueyi Liu, Zhongpu Xia, Dawei Ding, Yifeng Pan, Dongbin Zhao
Abstract: Existing end-to-end autonomous driving methods typically rely on imitation learning (IL) but face a key challenge: the misalignment between open-loop training and closed-loop deployment. This misalignment often triggers driver-initiated takeovers and system disengagements during closed-loop execution. How to leverage those expert takeover data from disengagement scenarios and effectively expand the IL policy's capability presents a valuable yet unexplored challenge. In this paper, we propose TakeAD, a novel preference-based post-optimization framework that fine-tunes the pre-trained IL policy with this disengagement data to enhance the closed-loop driving performance. First, we design an efficient expert takeover data collection pipeline inspired by human takeover mechanisms in real-world autonomous driving systems. Then, this post optimization framework integrates iterative Dataset Aggregation (DAgger) for imitation learning with Direct Preference Optimization (DPO) for preference alignment. The DAgger stage equips the policy with fundamental capabilities to handle disengagement states through direct imitation of expert interventions. Subsequently, the DPO stage refines the policy's behavior to better align with expert preferences in disengagement scenarios. Through multiple iterations, the policy progressively learns recovery strategies for disengagement states, thereby mitigating the open-loop gap. Experiments on the closed-loop Bench2Drive benchmark demonstrate our method's effectiveness compared with pure IL methods, with comprehensive ablations confirming the contribution of each component.
Authors: L\'eo Butsanets, Charles Corbi\`ere, Julien Khlaut, Pierre Manceron, Corentin Dancette
Abstract: In this work, we introduce RadImageNet-VQA, a large-scale dataset designed to advance radiologic visual question answering (VQA) on CT and MRI exams. Existing medical VQA datasets are limited in scale, dominated by X-ray imaging or biomedical illustrations, and often prone to text-based shortcuts. RadImageNet-VQA is built from expert-curated annotations and provides 750K images paired with 7.5M question-answer samples. It covers three key tasks - abnormality detection, anatomy recognition, and pathology identification - spanning eight anatomical regions and 97 pathology categories, and supports open-ended, closed-ended, and multiple-choice questions. Extensive experiments show that state-of-the-art vision-language models still struggle with fine-grained pathology identification, particularly in open-ended settings and even after fine-tuning. Text-only analysis further reveals that model performance collapses to near-random without image inputs, confirming that RadImageNet-VQA is free from linguistic shortcuts. The full dataset and benchmark are publicly available at https://huggingface.co/datasets/raidium/RadImageNet-VQA.
URLs: https://huggingface.co/datasets/raidium/RadImageNet-VQA.
Authors: Xingyu Feng
Abstract: Blockchain technology, lauded for its transparent and immutable nature, introduces a novel trust model. However, its decentralized structure raises concerns about potential inclusion of malicious or illegal content. This study focuses on Ethereum, presenting a data identification and restoration algorithm. Successfully recovering 175 common files, 296 images, and 91,206 texts, we employed the FastText algorithm for sentiment analysis, achieving a 0.9 accuracy after parameter tuning. Classification revealed 70,189 neutral, 5,208 positive, and 15,810 negative texts, aiding in identifying sensitive or illicit information. Leveraging the NSFWJS library, we detected seven indecent images with 100% accuracy. Our findings expose the coexistence of benign and harmful content on the Ethereum blockchain, including personal data, explicit images, divisive language, and racial discrimination. Notably, sensitive information targeted Chinese government officials. Proposing preventative measures, our study offers valuable insights for public comprehension of blockchain technology and regulatory agency guidance. The algorithms employed present innovative solutions to address blockchain data privacy and security concerns.
Authors: Neil Urquhart (Navid), Amir Rahimi (Navid), Efstathios-Al. Tingas
Abstract: We present an aircraft maintenance scheduling problem, which requires suitably qualified staff to be assigned to maintenance tasks on each aircraft. The tasks on each aircraft must be completed within a given turn around window so that the aircraft may resume revenue earning service. This paper presents an initial study based on the application of an Evolutionary Algorithm to the problem. Evolutionary Algorithms evolve a solution to a problem by evaluating many possible solutions, focusing the search on those solutions that are of a higher quality, as defined by a fitness function. In this paper, we benchmark the algorithm on 60 generated problem instances to demonstrate the underlying representation and associated genetic operators.
Authors: Lilin Wang, Lucas Ramalho, Alan Celestino, Phuc Anthony Pham, Yu Liu, Umang Kumar Sinha, Andres Portillo, Onassis Osunwa, Gabriel Maduekwe
Abstract: Benchmarks like SWE-bench have standardized the evaluation of Large Language Models (LLMs) on repository-level software engineering tasks. However, these efforts remain limited by manual curation, static datasets, and a focus on Python-based bug fixes. We introduce SWE-Bench++, an automated framework that generates repository-level coding tasks from open-source GitHub projects. Unlike synthetic approaches, our pipeline harvests live pull requests to cover both bug fixes and feature requests across 11 languages. SWE-Bench++ turns GitHub pull requests (PRs) into reproducible, execution-based tasks via four stages: programmatic sourcing, environment synthesis, test oracle extraction, and quality assurance. A final hint-guided trajectory synthesis step converts instances that strong models fail on into training trajectories. Our initial benchmark consists of 11,133 instances from 3,971 repositories across 11 languages. On a subset of 1,782 instances of this benchmark, today's strongest models perform as follows: claude-sonnet-4.5 achieves 36.20% pass@10, gpt-5-2025-08-07 34.57%, gemini/gemini-2.5-pro 24.92%, and gpt-4o 16.89%. We further demonstrate the utility of our dataset by showing that fine-tuning on SWE-Bench++ instances yields measurable improvements on the SWE-bench Multilingual benchmark. SWE-Bench++ provides a scalable, multilingual benchmark for evaluating and improving repository-level code generation.
Authors: Jan Hutter, Hua Chang Bakker, Stan Fris, Madelon Bernardy, Yuanna Liu
Abstract: In sequential recommendation (SR), the self-attention mechanism of Transformer-based models acts as a low-pass filter, limiting their ability to capture high-frequency signals that reflect short-term user interests. To overcome this, BSARec augments the Transformer encoder with a frequency layer that rescales high-frequency components using the Fourier transform. However, the overall effectiveness of BSARec and the roles of its individual components have yet to be systematically validated. We reproduce BSARec and show that it outperforms other SR methods on some datasets. To empirically assess whether BSARec improves performance on high-frequency signals, we propose a metric to quantify user history frequency and evaluate SR methods across different user groups. We compare digital signal processing (DSP) techniques and find that the discrete wavelet transform (DWT) offer only slight improvements over Fourier transforms, and DSP methods provide no clear advantage over simple residual connections. Finally, we explore padding strategies and find that non-constant padding significantly improves recommendation performance, whereas constant padding hinders the frequency rescaler's ability to capture high-frequency signals.
Authors: Javier Gonzalez-Ruiz, Carlos Rodriguez-Pardo, Iacopo Savelli, Alice Di Bella, Massimo Tavoni
Abstract: Electricity systems are key to transforming today's society into a carbon-free economy. Long-term electricity market mechanisms, including auctions, support schemes, and other policy instruments, are critical in shaping the electricity generation mix. In light of the need for more advanced tools to support policymakers and other stakeholders in designing, testing, and evaluating long-term markets, this work presents a multi-agent reinforcement learning model capable of capturing the key features of decarbonizing energy systems. Profit-maximizing generation companies make investment decisions in the wholesale electricity market, responding to system needs, competitive dynamics, and policy signals. The model employs independent proximal policy optimization, which was selected for suitability to the decentralized and competitive environment. Nevertheless, given the inherent challenges of independent learning in multi-agent settings, an extensive hyperparameter search ensures that decentralized training yields market outcomes consistent with competitive behavior. The model is applied to a stylized version of the Italian electricity system and tested under varying levels of competition, market designs, and policy scenarios. Results highlight the critical role of market design for decarbonizing the electricity sector and avoiding price volatility. The proposed framework allows assessing long-term electricity markets in which multiple policy and market mechanisms interact simultaneously, with market participants responding and adapting to decarbonization pathways.
Authors: Yen-Chieh Huang, Pi-Cheng Hsiu, Rui Fang, Ming-Syan Chen
Abstract: Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear KV cache growth. Prior approaches mitigate this via post-hoc selection or eviction but overlook the root inefficiency: indiscriminate writing to persistent memory. In this paper, we formalize KV cache management as a causal system of three primitives: KV Admission, Selection, and Eviction. We instantiate KV Admission via Write-Gated KV, a lightweight mechanism that learns to predict token utility before it enters the cache. By filtering out low-utility states early to maintain a compact global cache alongside a sliding local cache, Write-Gated KV reduces memory usage by 46-57% and delivers 3.03-3.45$\times$ prefill and 1.89-2.56$\times$ decode speedups on Llama model with negligible accuracy loss, all while remaining compatible with FlashAttention and paged-KV systems. These results demonstrate that learning what to write, is a principled and practical recipe for efficient long-context inference. Code is available at https://github.com/EMCLab-Sinica/WG-KV .
Authors: Henok Tenaw Moges, Deshendran Moodley
Abstract: We propose Lite-STGNN, a lightweight spatial-temporal graph neural network for long-term multivariate forecasting that integrates decomposition-based temporal modeling with learnable sparse graph structure. The temporal module applies trend-seasonal decomposition, while the spatial module performs message passing with low-rank Top-$K$ adjacency learning and conservative horizon-wise gating, enabling spatial corrections that enhance a strong linear baseline. Lite-STGNN achieves state-of-the-art accuracy on four benchmark datasets for horizons up to 720 steps, while being parameter-efficient and substantially faster to train than transformer-based methods. Ablation studies show that the spatial module yields 4.6% improvement over the temporal baseline, Top-$K$ enhances locality by 3.3%, and learned adjacency matrices reveal domain-specific interaction dynamics. Lite-STGNN thus offers a compact, interpretable, and efficient framework for long-term multivariate time series forecasting.
Authors: Evangelos Pournaras
Abstract: This article shows how fair voting methods can be a catalyst for change in the way we make collective decisions, and how such change can promote long-awaited upgrades of democracy. Based on real-world evidence from democratic innovations in participatory budgeting, in Switzerland and beyond, I highlight a trilogy of key research results: Fair voting methods achieve to be (i) legitimacy incubator, (ii) novel impact accelerator and (iii) safeguard for risks of artificial intelligence (AI). Compared to majoritarian voting methods, combining expressive ballot formats (e.g. cumulative voting) with ballot aggregation methods that promote proportional representation (e.g. equal shares) results in more winners and higher (geographical) representation of citizens. Such fair voting methods are preferred and found fairer even by voters who do not win, while promoting stronger democratic values for citizens such as altruism and compromise. They also result in new resourceful ideas to put for voting, which are cost-effective and win, especially in areas of welfare, education and culture. Strikingly, fair voting methods are also more resilient to biases and inconsistencies of generative AI in emerging scenarios of AI voting assistance or AI representation of voters who would be likely to abstain. I also review the relevance of such upgrades for democracies in crisis, such as the one of Greece featured in the recent study of `Unmute Democracy'. Greek democracy can build stronger resilience via higher representation of citizens in democratic processes as well as democratic innovations in participation. Fair voting methods can be a catalyst for both endeavors.
Authors: Olivier Jeunen, Schaun Wheeler
Abstract: Marketing and product personalisation provide a prominent and visible use-case for the application of Information Retrieval methods across several business domains. Recently, agentic approaches to these problems have been gaining traction. This work evaluates the behavioural and retention effects of agentic personalisation on a financial service application's customer communication system during a 2025 national tax filing period. Through a two month-long randomised controlled trial, we compare an agentic messaging approach against a business-as-usual (BAU) rule-based campaign system, focusing on two primary outcomes: unsubscribe behaviour and conversion timing. Empirical results show that agent-led messaging reduced unsubscribe events by 21\% ($\pm 0.01$) relative to BAU and increased early filing behaviour in the weeks preceding the national deadline. These findings demonstrate how adaptive, user-level decision-making systems can modulate engagement intensity whilst improving long-term retention indicators.
Authors: Hoiyeong Jin, Hyojin Jang, Jeongho Kim, Junha Hyung, Kinam Kim, Dongjin Kim, Huijin Choi, Hyeonji Kim, Jaegul Choo
Abstract: Recent advances in diffusion-based video generation have opened new possibilities for controllable video editing, yet realistic video object insertion (VOI) remains challenging due to limited 4D scene understanding and inadequate handling of occlusion and lighting effects. We present InsertAnywhere, a new VOI framework that achieves geometrically consistent object placement and appearance-faithful video synthesis. Our method begins with a 4D aware mask generation module that reconstructs the scene geometry and propagates user specified object placement across frames while maintaining temporal coherence and occlusion consistency. Building upon this spatial foundation, we extend a diffusion based video generation model to jointly synthesize the inserted object and its surrounding local variations such as illumination and shading. To enable supervised training, we introduce ROSE++, an illumination aware synthetic dataset constructed by transforming the ROSE object removal dataset into triplets of object removed video, object present video, and a VLM generated reference image. Through extensive experiments, we demonstrate that our framework produces geometrically plausible and visually coherent object insertions across diverse real world scenarios, significantly outperforming existing research and commercial models.
Authors: Muhammad Haris Khan
Abstract: We present a simple, PEFT-compatible mechanism that enforces secret-key access control in instruction-tuned language models. K-OTG trains on a dual-path corpus: authorized examples (prefixed with a role key) learn the task output, while unauthorized examples learn a visible block token. At inference, a pre-lm_head hook applies an orthonormal transform to the hidden state: with the correct key/role the inverse map restores the model's native basis; otherwise a session-ephemeral scrambler (permutation, sign flips, Householders) makes logits uninformative and the system short-circuits to BLOCK. Keys are not added as special tokens, and the method composes cleanly with LoRA on 4-bit bases. We evaluate an hour-scale protocol on 1-3B-class instruction models (Llama 3.2, Qwen2.5 1.5B) across utility (XSum ROUGE/BLEU, GSM8K accuracy, WikiText-2 perplexity), selectivity (3by3 role-key unlock matrices), nonce invariance, block suppression, and throughput. Authorized utility remains close to the base on summarization with the expected modest PPL increase from instruction tuning; unauthorized utility collapses (near-zero sequence metrics with exploding PPL), indicating practical unusability without the key. Unlock matrices are diagonally dominant (high on-target unlock, low cross-unlock), authorized block emission is 0 per N via robust bad-word lists, and greedy outputs match exactly across nonces, confirming correct inverse cancellation. The runtime overhead of the Python-level hook is 40% tokens per sec versus the base. K-OTG therefore provides a pragmatic, model-agnostic way to prevent unauthorized use while preserving authorized utility.
Authors: Muhammad Haris Khan
Abstract: Foundation models for protein design raise concrete biosecurity risks, yet the community lacks a simple, reproducible baseline for sequence-level hazard screening that is explicitly evaluated under homology control and runs on commodity CPUs. We introduce SafeBench-Seq, a metadata-only, reproducible benchmark and baseline classifier built entirely from public data (SafeProtein hazards and UniProt benigns) and interpretable features (global physicochemical descriptors and amino-acid composition). To approximate "never-before-seen" threats, we homology-cluster the combined dataset at <=40% identity and perform cluster-level holdouts (no cluster overlap between train/test). We report discrimination (AUROC/AUPRC) and screening-operating points (TPR@1% FPR; FPR@95% TPR) with 95% bootstrap confidence intervals (n=200), and we provide calibrated probabilities via CalibratedClassifierCV (isotonic for Logistic Regression / Random Forest; Platt sigmoid for Linear SVM). We quantify probability quality using Brier score, Expected Calibration Error (ECE; 15 bins), and reliability diagrams. Shortcut susceptibility is probed via composition-preserving residue shuffles and length-/composition-only ablations. Empirically, random splits substantially overestimate robustness relative to homology-clustered evaluation; calibrated linear models exhibit comparatively good calibration, while tree ensembles retain slightly higher Brier/ECE. SafeBench-Seq is CPU-only, reproducible, and releases metadata only (accessions, cluster IDs, split labels), enabling rigorous evaluation without distributing hazardous sequences.
Authors: Jiaqi Tang, Jianmin Chen, Wei Wei, Xiaogang Xu, Runtao Liu, Xiangyu Wu, Qipeng Xie, Jiafei Wu, Lei Zhang, Qifeng Chen
Abstract: Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains. Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity. To facilitate this approach, we introduce a specialized 11K dataset featuring realistic degradations synthesized across four critical real-world visual processing stages, each annotated with structured chains connecting degradation parameters, perceptual influence, pristine semantic reasoning chain, and conclusion. Comprehensive evaluations demonstrate state-of-the-art robustness: Robust-R1 outperforms all general and robust baselines on the real-world degradation benchmark R-Bench, while maintaining superior anti-degradation performance under multi-intensity adversarial degradations on MMMB, MMStar, and RealWorldQA.
Authors: Christian Lagemann, Sajeda Mokbel, Miro Gondrum, Mario R\"uttgers, Jared Callaham, Ludger Paehler, Samuel Ahnert, Nicholas Zolman, Kai Lagemann, Nikolaus Adams, Matthias Meinke, Wolfgang Schr\"oder, Jean-Christophe Loiseau, Esther Lagemann, Steven L. Brunton
Abstract: Modeling and controlling fluid flows is critical for several fields of science and engineering, including transportation, energy, and medicine. Effective flow control can lead to, e.g., lift increase, drag reduction, mixing enhancement, and noise reduction. However, controlling a fluid faces several significant challenges, including high-dimensional, nonlinear, and multiscale interactions in space and time. Reinforcement learning (RL) has recently shown great success in complex domains, such as robotics and protein folding, but its application to flow control is hindered by a lack of standardized benchmark platforms and the computational demands of fluid simulations. To address these challenges, we introduce HydroGym, a solver-independent RL platform for flow control research. HydroGym integrates sophisticated flow control benchmarks, scalable runtime infrastructure, and state-of-the-art RL algorithms. Our platform includes 42 validated environments spanning from canonical laminar flows to complex three-dimensional turbulent scenarios, validated over a wide range of Reynolds numbers. We provide non-differentiable solvers for traditional RL and differentiable solvers that dramatically improve sample efficiency through gradient-enhanced optimization. Comprehensive evaluation reveals that RL agents consistently discover robust control principles across configurations, such as boundary layer manipulation, acoustic feedback disruption, and wake reorganization. Transfer learning studies demonstrate that controllers learned at one Reynolds number or geometry adapt efficiently to new conditions, requiring approximately 50% fewer training episodes. The HydroGym platform is highly extensible and scalable, providing a framework for researchers in fluid dynamics, machine learning, and control to add environments, surrogate models, and control algorithms to advance science and technology.
Authors: Yunqi Gao, Leyuan Liu, Yuhan Li, Changxin Gao, Yuanyuan Liu, Jingying Chen
Abstract: With 3D data rapidly emerging as an important form of multimedia information, 3D human mesh recovery technology has also advanced accordingly. However, current methods mainly focus on handling humans wearing tight clothing and perform poorly when estimating body shapes and poses under diverse clothing, especially loose garments. To this end, we make two key insights: (1) tailoring clothing to fit the human body can mitigate the adverse impact of clothing on 3D human mesh recovery, and (2) utilizing human visual information from large foundational models can enhance the generalization ability of the estimation. Based on these insights, we propose ClothHMR, to accurately recover 3D meshes of humans in diverse clothing. ClothHMR primarily consists of two modules: clothing tailoring (CT) and FHVM-based mesh recovering (MR). The CT module employs body semantic estimation and body edge prediction to tailor the clothing, ensuring it fits the body silhouette. The MR module optimizes the initial parameters of the 3D human mesh by continuously aligning the intermediate representations of the 3D mesh with those inferred from the foundational human visual model (FHVM). ClothHMR can accurately recover 3D meshes of humans wearing diverse clothing, precisely estimating their body shapes and poses. Experimental results demonstrate that ClothHMR significantly outperforms existing state-of-the-art methods across benchmark datasets and in-the-wild images. Additionally, a web application for online fashion and shopping powered by ClothHMR is developed, illustrating that ClothHMR can effectively serve real-world usage scenarios. The code and model for ClothHMR are available at: \url{https://github.com/starVisionTeam/ClothHMR}.
Authors: Sujal Chondhekar, Vasanth Murukuri, Rushabh Vasani, Sanika Goyal, Rajshree Badami, Anushree Rana, Sanjana SN, Karthik Pandia, Sulabh Katiyar, Neha Jagadeesh, Sankalp Gulati
Abstract: Speech enhancement methods are commonly believed to improve the performance of automatic speech recognition (ASR) in noisy environments. However, the effectiveness of these techniques cannot be taken for granted in the case of modern large-scale ASR models trained on diverse, noisy data. We present a systematic evaluation of MetricGAN-plus-voicebank denoising on four state-of-the-art ASR systems: OpenAI Whisper, NVIDIA Parakeet, Google Gemini Flash 2.0, Parrotlet-a using 500 medical speech recordings under nine noise conditions. ASR performance is measured using semantic WER (semWER), a normalized word error rate (WER) metric accounting for domain-specific normalizations. Our results reveal a counterintuitive finding: speech enhancement preprocessing degrades ASR performance across all noise conditions and models. Original noisy audio achieves lower semWER than enhanced audio in all 40 tested configurations (4 models x 10 conditions), with degradations ranging from 1.1% to 46.6% absolute semWER increase. These findings suggest that modern ASR models possess sufficient internal noise robustness and that traditional speech enhancement may remove acoustic features critical for ASR. For practitioners deploying medical scribe systems in noisy clinical environments, our results indicate that preprocessing audio with noise reduction techniques might not just be computationally wasteful but also be potentially harmful to the transcription accuracy.
Authors: Mathilde Gajda Faanes, David Bouget, Asgeir S. Jakola, Timothy R. Smith, Vasileios K. Kavouridis, Francesco Latini, Margret Jensdottir, Peter Milos, Henrietta Nittby Redebrandt, Rickard L. Sj\"oberg, Rupavathana Mahesparan, Lars Kjelsberg Pedersen, Ole Solheim, Ingerid Reinertsen
Abstract: T2-weighted fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) scans are important for diagnosis, treatment planning and monitoring of brain tumors. Depending on the brain tumor type, the FLAIR hyperintensity volume is an important measure to asses the tumor volume or surrounding edema, and an automatic segmentation of this would be useful in the clinic. In this study, around 5000 FLAIR images of various tumors types and acquisition time points from different centers were used to train a unified FLAIR hyperintensity segmentation model using an Attention U-Net architecture. The performance was compared against dataset specific models, and was validated on different tumor types, acquisition time points and against BraTS. The unified model achieved an average Dice score of 88.65\% for pre-operative meningiomas, 80.08% for pre-operative metastasis, 90.92% for pre-operative and 84.60% for post-operative gliomas from BraTS, and 84.47% for pre-operative and 61.27\% for post-operative lower grade gliomas. In addition, the results showed that the unified model achieved comparable segmentation performance to the dataset specific models on their respective datasets, and enables generalization across tumor types and acquisition time points, which facilitates the deployment in a clinical setting. The model is integrated into Raidionics, an open-source software for CNS tumor analysis.
Authors: Yikang Yue, Yishu Yin, Xuehai Qian
Abstract: SSD-offloaded training offers a practical and promising approach to making LLM training cost-effective. Building on gradient accumulation with micro-batches, this paper introduces GreedySnake, a new SSD-offloaded training system that employs vertical scheduling, which executes all microbatches of a layer before proceeding to the next. Compared to existing systems that use horizontal scheduling (i.e., executing micro-batches sequentially), GreedySnake achieves higher training throughput with smaller batch sizes, bringing the system much closer to the ideal scenario predicted by the roofline model. To further mitigate the I/O bottleneck, GreedySnake overlaps part of the optimization step with the forward pass of the next iteration. Experimental results on A100 GPUs show that GreedySnake achieves saturated training throughput improvements over ZeRO-Infinity: 1.96x on 1 GPU and 1.93x on 4 GPUs for GPT-65B, and 2.53x on 1 GPU for GPT-175B. The code is open-sourced at https://github.com/npz7yyk/GreedySnake
Authors: Tosin Ige, Christopher Kiekintveld, Aritran Piplai, Asif Rahman, Olukunle Kolade, Sasidhar Kunapuli
Abstract: Out of distribution (OOD) detection remains a critical challenge in malware classification due to the substantial intra family variability introduced by polymorphic and metamorphic malware variants. Most existing deep learning based malware detectors rely on closed world assumptions and fail to adequately model this intra class variation, resulting in degraded performance when confronted with previously unseen malware families. This paper presents MADOOD, a novel two stage, cluster driven deep learning framework for robust OOD malware detection and classification. In the first stage, malware family embeddings are modeled using class conditional spherical decision boundaries derived from Gaussian Discriminant Analysis (GDA), enabling statistically grounded separation of indistribution and OOD samples without requiring OOD data during training. Z score based distance analysis across multiple class centroids is employed to reliably identify anomalous samples in the latent space. In the second stage, a deep neural network integrates cluster based predictions, refined embeddings, and supervised classifier outputs to enhance final classification accuracy. Extensive evaluations on benchmark malware datasets comprising 25 known families and multiple novel OOD variants demonstrate that MADOOD significantly outperforms state of the art OOD detection methods, achieving an AUC of up to 0.911 on unseen malware families. The proposed framework provides a scalable, interpretable, and statistically principled solution for real world malware detection and anomaly identification in evolving cybersecurity environments.
Authors: Svetlana Krasnova, Emiliya Starikova, Ilia Naletov, Andrey Krylov, Dmitry Sorokin
Abstract: Robust mammography registration is essential for clinical applications like tracking disease progression and monitoring longitudinal changes in breast tissue. However, progress has been limited by the absence of public datasets and standardized benchmarks. Existing studies are often not directly comparable, as they use private data and inconsistent evaluation frameworks. To address this, we present MGRegBench, a public benchmark dataset for mammogram registration. It comprises over 5,000 image pairs, with 100 containing manual anatomical landmarks and segmentation masks for rigorous evaluation. This makes MGRegBench one of the largest public 2D registration datasets with manual annotations. Using this resource, we benchmarked diverse registration methods including classical (ANTs), learning-based (VoxelMorph, TransMorph), implicit neural representation (IDIR), a classic mammography-specific approach, and a recent state-of-the-art deep learning method MammoRegNet. The implementations were adapted to this modality from the authors' implementations or re-implemented from scratch. Our contributions are: (1) the first public dataset of this scale with manual landmarks and masks for mammography registration; (2) the first like-for-like comparison of diverse methods on this modality; and (3) an extensive analysis of deep learning-based registration. We publicly release our code and data to establish a foundational resource for fair comparisons and catalyze future research. The source code and data are at https://github.com/KourtKardash/MGRegBench.
Authors: Zhaoqian Gao, Min Yanga
Abstract: Physics-informed neural networks (PINNs) have recently emerged as a prominent paradigm for solving partial differential equations (PDEs), yet their training strategies remain underexplored. While hard prioritization methods inspired by finite element methods are widely adopted, recent research suggests that easy prioritization can also be effective. Nevertheless, we find that both approaches exhibit notable trade-offs and inconsistent performance across PDE types. To address this issue, we develop a hybrid strategy that combines the strengths of hard and easy prioritization through an alternating training algorithm. On PDEs with steep gradients, nonlinearity, and high dimensionality, the proposed method achieves consistently high accuracy, with relative L2 errors mostly in the range of O(10^-5) to O(10^-6), significantly surpassing baseline methods. Moreover, it offers greater reliability across diverse problems, whereas compared approaches often suffer from variable accuracy depending on the PDE. This work provides new insights into designing hybrid training strategies to enhance the performance and robustness of PINNs.
Authors: Jakob De Moor, Hans Weytjens, Johannes De Smedt, Jochen De Weerdt
Abstract: Prescriptive Process Monitoring (PresPM) recommends interventions during business processes to optimize key performance indicators (KPIs). In realistic settings, interventions are rarely isolated: organizations need to align sequences of interventions to jointly steer the outcome of a case. Existing PresPM approaches fall short in this respect. Many focus on a single intervention decision, while others treat multiple interventions independently, ignoring how they interact over time. Methods that do address these dependencies depend either on simulation or data augmentation to approximate the process to train a Reinforcement Learning (RL) agent, which can create a reality gap and introduce bias. We introduce SCOPE, a PresPM approach that learns aligned sequential intervention recommendations. SCOPE employs backward induction to estimate the effect of each candidate intervention action, propagating its impact from the final decision point back to the first. By leveraging causal learners, our method can utilize observational data directly, unlike methods that require constructing process approximations for reinforcement learning. Experiments on both an existing synthetic dataset and a new semi-synthetic dataset show that SCOPE consistently outperforms state-of-the-art PresPM techniques in optimizing the KPI. The novel semi-synthetic setup, based on a real-life event log, is provided as a reusable benchmark for future work on sequential PresPM.
Authors: Mingyu Su, Jian Guan, Yuxian Gu, Minlie Huang, Hongning Wang
Abstract: Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT then RL) suffers from a key inconsistency: SFT enforces rigid imitation that suppresses exploration and induces forgetting, limiting RL's potential for improvements. We address this inefficiency with TRAPO (\textbf{T}rust-\textbf{R}egion \textbf{A}daptive \textbf{P}olicy \textbf{O}ptimization), a hybrid framework that interleaves SFT and RL within each training instance by optimizing SFT loss on expert prefixes and RL loss on the model's own completions, unifying external supervision and self-exploration. To stabilize training, we introduce Trust-Region SFT (TrSFT), which minimizes forward KL divergence inside a trust region but attenuates optimization outside, effectively shifting toward reverse KL and yielding stable, mode-seeking updates favorable for RL. An adaptive prefix-selection mechanism further allocates expert guidance based on measured utility. Experiments on five mathematical reasoning benchmarks show that TRAPO consistently surpasses standard SFT, RL, and SFT-then-RL pipelines, as well as recent state-of-the-art approaches, establishing a strong new paradigm for reasoning-enhanced LLMs.
Authors: Yifei Cheng, Yujia Zhu, Baiyang Li, Xinhao Deng, Yitong Cai, Yaochen Ren, Qingyun Liu
Abstract: Modern HTTPS mechanisms such as Encrypted Client Hello (ECH) and encrypted DNS improve privacy but remain vulnerable to website fingerprinting (WF) attacks, where adversaries infer visited sites from encrypted traffic patterns. Existing WF methods rely on supervised learning with site-specific labeled traces, which limits scalability and fails to handle previously unseen websites. We address these limitations by reformulating WF as a zero-shot cross-modal retrieval problem and introducing STAR. STAR learns a joint embedding space for encrypted traffic traces and crawl-time logic profiles using a dual-encoder architecture. Trained on 150K automatically collected traffic-logic pairs with contrastive and consistency objectives and structure-aware augmentation, STAR retrieves the most semantically aligned profile for a trace without requiring target-side traffic during training. Experiments on 1,600 unseen websites show that STAR achieves 87.9 percent top-1 accuracy and 0.963 AUC in open-world detection, outperforming supervised and few-shot baselines. Adding an adapter with only four labeled traces per site further boosts top-5 accuracy to 98.8 percent. Our analysis reveals intrinsic semantic-traffic alignment in modern web protocols, identifying semantic leakage as the dominant privacy risk in encrypted HTTPS traffic. We release STAR's datasets and code to support reproducibility and future research.
Authors: Alexandre Personnic, Mihai B\^ace
Abstract: Video-based gaze estimation methods aim to capture the inherently temporal dynamics of human eye gaze from multiple image frames. However, since models must capture both spatial and temporal relationships, performance is limited by the feature representations within a frame but also between multiple frames. We propose the Spatio-Temporal Gaze Network (ST-Gaze), a model that combines a CNN backbone with dedicated channel attention and self-attention modules to fuse eye and face features optimally. The fused features are then treated as a spatial sequence, allowing for the capture of an intra-frame context, which is then propagated through time to model inter-frame dynamics. We evaluated our method on the EVE dataset and show that ST-Gaze achieves state-of-the-art performance both with and without person-specific adaptation. Additionally, our ablation study provides further insights into the model performance, showing that preserving and modelling intra-frame spatial context with our spatio-temporal recurrence is fundamentally superior to premature spatial pooling. As such, our results pave the way towards more robust video-based gaze estimation using commonly available cameras.
Authors: Yudhistira Arief Wibowo
Abstract: Diffusion models have shown strong potential for solving inverse problems such as single-image super-resolution, where a high-resolution image is recovered from a low-resolution observation using a pretrained unconditional prior. Conditioning methods, including Diffusion Posterior Sampling (DPS) and Manifold Constrained Gradient (MCG), can substantially improve reconstruction quality, but they introduce additional hyperparameters that require careful tuning. In this work, we conduct an empirical ablation study on FFHQ super-resolution to identify the dominant factors affecting performance when applying conditioning to pretrained diffusion models, and show that the conditioning step size has a significantly greater impact than the diffusion step count, with step sizes in the range of [2.0, 3.0] yielding the best overall performance in our experiments.
Authors: Daphn\'e Chopard, Jorge da Silva Gon\c{c}alves, Irene Cannistraci, Thomas M. Sutter, Julia E. Vogt
Abstract: Selecting compact and informative gene subsets from single-cell transcriptomic data is essential for biomarker discovery, improving interpretability, and cost-effective profiling. However, most existing feature selection approaches either operate as multi-stage pipelines or rely on post hoc feature attribution, making selection and prediction weakly coupled. In this work, we present YOTO (you only train once), an end-to-end framework that jointly identifies discrete gene subsets and performs prediction within a single differentiable architecture. In our model, the prediction task directly guides which genes are selected, while the learned subsets, in turn, shape the predictive representation. This closed feedback loop enables the model to iteratively refine both what it selects and how it predicts during training. Unlike existing approaches, YOTO enforces sparsity so that only the selected genes contribute to inference, eliminating the need to train additional downstream classifiers. Through a multi-task learning design, the model learns shared representations across related objectives, allowing partially labeled datasets to inform one another, and discovering gene subsets that generalize across tasks without additional training steps. We evaluate YOTO on two representative single-cell RNA-seq datasets, showing that it consistently outperforms state-of-the-art baselines. These results demonstrate that sparse, end-to-end, multi-task gene subset selection improves predictive performance and yields compact and meaningful gene subsets, advancing biomarker discovery and single-cell analysis.
Authors: Paola Di Maio
Abstract: This paper introduces a standardized model card framework specifically designed for digital and web forensics. Building upon established model card methodologies and recent work on abstract models for digital forensic analysis, this paper presents a web based framework that generates model cards specifically designed to represent knowledge in the forensic domain. The framework includes controlled vocabularies for classification, reasoning types, bias identification, and error categorization, along with a web-based generator tool to facilitate adoption. The paper describes the model card structure, presents the controlled vocabularies, and introduces the beta version of the generator tool, inviting community feedback to refine this emerging standard. Ultimately, the systemic risk is that that the anti fraud and digital and web forensics processes are controlled by the mobs.
Authors: Jingmao Zhang, Zhiting Zhao, Yunqi Lin, Jianghong Ma, Tianjun Wei, Haijun Zhang, Xiaofeng Zhang
Abstract: Beyond user-item modeling, item-to-item relationships are increasingly used to enhance recommendation. However, common methods largely rely on co-occurrence, making them prone to item popularity bias and user attributes, which degrades embedding quality and performance. Meanwhile, although diversity is acknowledged as a key aspect of recommendation quality, existing research offers limited attention to it, with a notable lack of causal perspectives and theoretical grounding. To address these challenges, we propose Cadence: Diversity Recommendation via Causal Deconfounding of Co-purchase Relations and Counterfactual Exposure - a plug-and-play framework built upon LightGCN as the backbone, primarily designed to enhance recommendation diversity while preserving accuracy. First, we compute the Unbiased Asymmetric Co-purchase Relationship (UACR) between items - excluding item popularity and user attributes - to construct a deconfounded directed item graph, with an aggregation mechanism to refine embeddings. Second, we leverage UACR to identify diverse categories of items that exhibit strong causal relevance to a user's interacted items but have not yet been engaged with. We then simulate their behavior under high-exposure scenarios, thereby significantly enhancing recommendation diversity while preserving relevance. Extensive experiments on real-world datasets demonstrate that our method consistently outperforms state-of-the-art diversity models in both diversity and accuracy, and further validates its effectiveness, transferability, and efficiency over baselines.
Authors: Zhihan Zhou, Daqian Shi, Rui Song, Lida Shi, Xiaolei Diao, Hao Xu
Abstract: Comprehension of ancient texts plays an important role in archaeology and understanding of Chinese history and civilization. The rapid development of large language models needs benchmarks that can evaluate their comprehension of ancient characters. Existing Chinese benchmarks are mostly targeted at modern Chinese and transmitted documents in ancient Chinese, but the part of excavated documents in ancient Chinese is not covered. To meet this need, we propose the AncientBench, which aims to evaluate the comprehension of ancient characters, especially in the scenario of excavated documents. The AncientBench is divided into four dimensions, which correspond to the four competencies of ancient character comprehension: glyph comprehension, pronunciation comprehension, meaning comprehension, and contextual comprehension. The benchmark also contains ten tasks, including radical, phonetic radical, homophone, cloze, translation, and more, providing a comprehensive framework for evaluation. We convened archaeological researchers to conduct experimental evaluations, proposed an ancient model as baseline, and conducted extensive experiments on the currently best-performing large language models. The experimental results reveal the great potential of large language models in ancient textual scenarios as well as the gap with humans. Our research aims to promote the development and application of large language models in the field of archaeology and ancient Chinese language.
Authors: Tanjim Taharat Aurpa, Farzana Akter, Md. Mehedi Hasan, Shakil Ahmed, Shifat Ara Rafiq, Fatema Khan
Abstract: Medical Entity Recognition (MedER) is an essential NLP task for extracting meaningful entities from the medical corpus. Nowadays, MedER-based research outcomes can remarkably contribute to the development of automated systems in the medical sector, ultimately enhancing patient care and outcomes. While extensive research has been conducted on MedER in English, low-resource languages like Bangla remain underexplored. Our work aims to bridge this gap. For Bangla medical entity recognition, this study first examined a number of transformer models, including BERT, DistilBERT, ELECTRA, and RoBERTa. We also propose a novel Multi-BERT Ensemble approach that outperformed all baseline models with the highest accuracy of 89.58%. Notably, it provides an 11.80% accuracy improvement over the single-layer BERT model, demonstrating its effectiveness for this task. A major challenge in MedER for low-resource languages is the lack of annotated datasets. To address this issue, we developed a high-quality dataset tailored for the Bangla MedER task. The dataset was used to evaluate the effectiveness of our model through multiple performance metrics, demonstrating its robustness and applicability. Our findings highlight the potential of Multi-BERT Ensemble models in improving MedER for Bangla and set the foundation for further advancements in low-resource medical NLP.
Authors: Dong Chen, Zhengqing Hu, Shixing Zhao, Yibo Guo
Abstract: While the enormous parameter scale endows Large Models (LMs) with unparalleled performance, it also limits their adaptability across specific tasks. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a critical approach for effectively adapting LMs to a diverse range of downstream tasks. However, existing PEFT methods face two primary challenges: (1) High resource cost. Although PEFT methods significantly reduce resource demands compared to full fine-tuning, it still requires substantial time and memory, making it impractical in resource-constrained environments. (2) Parameter dependency. PEFT methods heavily rely on updating a subset of parameters associated with LMs to incorporate task-specific knowledge. Yet, due to increasing competition in the LMs landscape, many companies have adopted closed-source policies for their leading models, offering access only via Application Programming Interface (APIs). Whereas, the expense is often cost-prohibitive and difficult to sustain, as the fine-tuning process of LMs is extremely slow. Even if small models perform far worse than LMs in general, they can achieve superior results on particular distributions while requiring only minimal resources. Motivated by this insight, we propose Easy Adaptation (EA), which designs Specific Small Models (SSMs) to complement the underfitted data distribution for LMs. Extensive experiments show that EA matches the performance of PEFT on diverse tasks without accessing LM parameters, and requires only minimal resources.
Authors: Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Zhe Chen, Matthias Nie{\ss}ner
Abstract: Neural Parametric Head Models (NPHMs) are a recent advancement over mesh-based 3d morphable models (3DMMs) to facilitate high-fidelity geometric detail. However, fitting NPHMs to visual inputs is notoriously challenging due to the expressive nature of their underlying latent space. To this end, we propose Pix2NPHM, a vision transformer (ViT) network that directly regresses NPHM parameters, given a single image as input. Compared to existing approaches, the neural parametric space allows our method to reconstruct more recognizable facial geometry and accurate facial expressions. For broad generalization, we exploit domain-specific ViTs as backbones, which are pretrained on geometric prediction tasks. We train Pix2NPHM on a mixture of 3D data, including a total of over 100K NPHM registrations that enable direct supervision in SDF space, and large-scale 2D video datasets, for which normal estimates serve as pseudo ground truth geometry. Pix2NPHM not only allows for 3D reconstructions at interactive frame rates, it is also possible to improve geometric fidelity by a subsequent inference-time optimization against estimated surface normals and canonical point maps. As a result, we achieve unprecedented face reconstruction quality that can run at scale on in-the-wild data.
Authors: Saikat Roy, Yannick Kirchhoff, Constantin Ulrich, Maximillian Rokuss, Tassilo Wald, Fabian Isensee, Klaus Maier-Hein
Abstract: Large-scale supervised pretraining is rapidly reshaping 3D medical image segmentation. However, existing efforts focus primarily on increasing dataset size and overlook the question of whether the backbone network is an effective representation learner at scale. In this work, we address this gap by revisiting ConvNeXt-based architectures for volumetric segmentation and introducing MedNeXt-v2, a compound-scaled 3D ConvNeXt that leverages improved micro-architecture and data scaling to deliver state-of-the-art performance. First, we show that routinely used backbones in large-scale pretraining pipelines are often suboptimal. Subsequently, we use comprehensive backbone benchmarking prior to scaling and demonstrate that stronger from scratch performance reliably predicts stronger downstream performance after pretraining. Guided by these findings, we incorporate a 3D Global Response Normalization module and use depth, width, and context scaling to improve our architecture for effective representation learning. We pretrain MedNeXt-v2 on 18k CT volumes and demonstrate state-of-the-art performance when fine-tuning across six challenging CT and MR benchmarks (144 structures), showing consistent gains over seven publicly released pretrained models. Beyond improvements, our benchmarking of these models also reveals that stronger backbones yield better results on similar data, representation scaling disproportionately benefits pathological segmentation, and that modality-specific pretraining offers negligible benefit once full finetuning is applied. In conclusion, our results establish MedNeXt-v2 as a strong backbone for large-scale supervised representation learning in 3D Medical Image Segmentation. Our code and pretrained models are made available with the official nnUNet repository at: https://www.github.com/MIC-DKFZ/nnUNet
Authors: Binh Vu
Abstract: The unprecedented proliferation of digital data presents significant challenges in access, integration, and value creation across all data-intensive sectors. Valuable information is frequently encapsulated within disparate systems, unstructured documents, and heterogeneous formats, creating silos that impede efficient utilization and collaborative decision-making. This paper introduces the Intelligent Knowledge Mining Framework (IKMF), a comprehensive conceptual model designed to bridge the critical gap between dynamic AI-driven analysis and trustworthy long-term preservation. The framework proposes a dual-stream architecture: a horizontal Mining Process that systematically transforms raw data into semantically rich, machine-actionable knowledge, and a parallel Trustworthy Archiving Stream that ensures the integrity, provenance, and computational reproducibility of these assets. By defining a blueprint for this symbiotic relationship, the paper provides a foundational model for transforming static repositories into living ecosystems that facilitate the flow of actionable intelligence from producers to consumers. This paper outlines the motivation, problem statement, and key research questions guiding the research and development of the framework, presents the underlying scientific methodology, and details its conceptual design and modeling.
Authors: Yitong Wang, Fangyun Wei, Hongyang Zhang, Bo Dai, Yan Lu
Abstract: Recent advances in world models have greatly enhanced interactive environment simulation. Existing methods mainly fall into two categories: (1) static world generation models, which construct 3D environments without active agents, and (2) controllable-entity models, which allow a single entity to perform limited actions in an otherwise uncontrollable environment. In this work, we introduce AniX, leveraging the realism and structural grounding of static world generation while extending controllable-entity models to support user-specified characters capable of performing open-ended actions. Users can provide a 3DGS scene and a character, then direct the character through natural language to perform diverse behaviors from basic locomotion to object-centric interactions while freely exploring the environment. AniX synthesizes temporally coherent video clips that preserve visual fidelity with the provided scene and character, formulated as a conditional autoregressive video generation problem. Built upon a pre-trained video generator, our training strategy significantly enhances motion dynamics while maintaining generalization across actions and characters. Our evaluation covers a broad range of aspects, including visual quality, character consistency, action controllability, and long-horizon coherence.
Authors: Rolf Drechsler, Qian Liu
Abstract: Test and verification are essential activities in hardware and system design, but their complexity grows significantly with increasing system sizes. While Behavior Driven Development (BDD) has proven effective in software engineering, it is not yet well established in hardware design, and its practical use remains limited. One contributing factor is the manual effort required to derive precise behavioral scenarios from textual specifications. Recent advances in Large Language Models (LLMs) offer new opportunities to automate this step. In this paper, we investigate the use of LLM-based techniques to support BDD in the context of hardware design.
Authors: Yueru Yan, Tuc Nguyen, Bo Su, Melissa Lieffers, Thai Le
Abstract: While Large Language Models (LLMs) have evolved into distinct platforms with unique interface designs and capabilities, existing public datasets treat models as generic text generators, stripping away the interface context that actively shapes user interaction. To address this limitation, we present ShareChat, a large-scale, cross-platform corpus comprising 142,808 conversations and over 660,000 turns collected from publicly shared URLs across five major platforms: ChatGPT, Claude, Gemini, Perplexity, and Grok. ShareChat distinguishes itself by preserving native platform affordances often lost in standard logs, including reasoning traces, source links, and code artifacts, while spanning 101 languages over the period from April 2023 to October 2025. Furthermore, ShareChat offers substantially longer context windows and greater interaction depth than prior datasets. We demonstrate the dataset's multifaceted utility through three representative analyses: (1) analyzing conversation completeness to measure user intent satisfaction; (2) evaluating source citation behaviors in content generation; and (3) conducting temporal analysis to track evolving usage patterns. This work provides the community with a vital and timely resource for understanding authentic user-LLM chatbot interactions in the wild.
Authors: Carlos V\'elez Garc\'ia, Miguel Cazorla, Jorge Pomares
Abstract: We present Planning as Descent (PaD), a framework for offline goal-conditioned reinforcement learning that grounds trajectory synthesis in verification. Instead of learning a policy or explicit planner, PaD learns a goal-conditioned energy function over entire latent trajectories, assigning low energy to feasible, goal-consistent futures. Planning is realized as gradient-based refinement in this energy landscape, using identical computation during training and inference to reduce train-test mismatch common in decoupled modeling pipelines. PaD is trained via self-supervised hindsight goal relabeling, shaping the energy landscape around the planning dynamics. At inference, multiple trajectory candidates are refined under different temporal hypotheses, and low-energy plans balancing feasibility and efficiency are selected. We evaluate PaD on OGBench cube manipulation tasks. When trained on narrow expert demonstrations, PaD achieves state-of-the-art 95\% success, strongly outperforming prior methods that peak at 68\%. Remarkably, training on noisy, suboptimal data further improves success and plan efficiency, highlighting the benefits of verification-driven planning. Our results suggest learning to evaluate and refine trajectories provides a robust alternative to direct policy learning for offline, reward-free planning.
Authors: Corey M. Abramson
Abstract: This chapter demonstrates how computational social science (CSS) tools are extending and expanding research on aging. The depth and context from traditionally qualitative methods such as participant observation, in-depth interviews, and historical documents are increasingly employed alongside scalable data management, computational text analysis, and open-science practices. Machine learning (ML) and natural language processing (NLP), provide resources to aggregate and systematically index large volumes of qualitative data, identify patterns, and maintain clear links to in-depth accounts. Drawing on case studies of projects that examine later life--including examples with original data from the DISCERN study (a team-based ethnography of life with dementia) and secondary analyses of the American Voices Project (nationally representative interview)--the chapter highlights both uses and challenges of bringing CSS tools into more meaningful dialogue with qualitative aging research. The chapter argues such work has potential for (1) streamlining and augmenting existing workflows, (2) scaling up samples and projects, and (3) generating multi-method approaches to address important questions in new ways, before turning to practices useful for individuals and teams seeking to understand current possibilities or refine their workflow processes. The chapter concludes that current developments are not without peril, but offer potential for new insights into aging and the life course by broadening--rather than replacing--the methodological foundations of qualitative research.
Authors: Sarah Rastegar, Violeta Chatalbasheva, Sieger Falkena, Anuj Singh, Yanbo Wang, Tejas Gokhale, Hamid Palangi, Hadi Jamali-Rad
Abstract: Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training data and inability of text embeddings to encode spatial semantics. We introduce InfSplign, a training-free inference-time method that improves spatial alignment by adjusting the noise through a compound loss in every denoising step. Proposed loss leverages different levels of cross-attention maps extracted from the backbone decoder to enforce accurate object placement and a balanced object presence during sampling. The method is lightweight, plug-and-play, and compatible with any diffusion backbone. Our comprehensive evaluations on VISOR and T2I-CompBench show that InfSplign establishes a new state-of-the-art (to the best of our knowledge), achieving substantial performance gains over the strongest existing inference-time baselines and even outperforming the fine-tuning-based methods. Codebase is available at GitHub.
Authors: Ran Gong, Xiaohan Zhang, Jinghuan Shang, Maria Vittoria Minniti, Jigarkumar Patel, Valerio Pepe, Riedana Yan, Ahmet Gundogdu, Ivan Kapelyukh, Ali Abbas, Xiaoqiang Yan, Harsh Patel, Laura Herlant, Karl Schmeckpeper
Abstract: Generalist robot learning remains constrained by data: large-scale, diverse, and high-quality interaction data are expensive to collect in the real world. While simulation has become a promising way for scaling up data collection, the related tasks, including simulation task design, task-aware scene generation, expert demonstration synthesis, and sim-to-real transfer, still demand substantial human effort. We present AnyTask, an automated framework that pairs massively parallel GPU simulation with foundation models to design diverse manipulation tasks and synthesize robot data. We introduce three AnyTask agents for generating expert demonstrations aiming to solve as many tasks as possible: 1) ViPR, a novel task and motion planning agent with VLM-in-the-loop Parallel Refinement; 2) ViPR-Eureka, a reinforcement learning agent with generated dense rewards and LLM-guided contact sampling; 3) ViPR-RL, a hybrid planning and learning approach that jointly produces high-quality demonstrations with only sparse rewards. We train behavior cloning policies on generated data, validate them in simulation, and deploy them directly on real robot hardware. The policies generalize to novel object poses, achieving 44% average success across a suite of real-world pick-and-place, drawer opening, contact-rich pushing, and long-horizon manipulation tasks. Our project website is at https://anytask.rai-inst.com .
Authors: Balram Singh, Ram Prakash Sharma, Somnath Dey
Abstract: Plant diseases pose a significant threat to global food security, necessitating accurate and interpretable disease detection methods. This study introduces an interpretable attention-guided Convolutional Neural Network (CNN), CBAM-VGG16, for plant leaf disease detection. By integrating Convolution Block Attention Module (CBAM) at each convolutional stage, the model enhances feature extraction and disease localization. Trained on five diverse plant disease datasets, our approach outperforms recent techniques, achieving high accuracy (up to 98.87%) and demonstrating robust generalization. Here, we show the effectiveness of our method through comprehensive evaluation and interpretability analysis using CBAM attention maps, Grad-CAM, Grad-CAM++, and Layer-wise Relevance Propagation (LRP). This study advances the application of explainable AI in agricultural diagnostics, offering a transparent and reliable system for smart farming. The code of our proposed work is available at https://github.com/BS0111/PlantAttentionCBAM.
Authors: Herlock Rahimi
Abstract: Score-based diffusion models currently constitute the state of the art in continuous generative modeling. These methods are typically formulated via overdamped or underdamped Ornstein--Uhlenbeck-type stochastic differential equations, in which sampling is driven by a combination of deterministic drift and Brownian diffusion, resulting in continuous particle trajectories in the ambient space. While such dynamics enjoy exponential convergence guarantees for strongly log-concave target distributions, it is well known that their mixing rates deteriorate exponentially in the presence of nonconvex or multimodal landscapes, such as double-well potentials. Since many practical generative modeling tasks involve highly non-log-concave target distributions, considerable recent effort has been devoted to developing sampling schemes that improve exploration beyond classical diffusion dynamics. A promising line of work leverages tools from information geometry to augment diffusion-based samplers with controlled mass reweighting mechanisms. This perspective leads naturally to Wasserstein--Fisher--Rao (WFR) geometries, which couple transport in the sample space with vertical (reaction) dynamics on the space of probability measures. In this work, we formulate such reweighting mechanisms through the introduction of explicit correction terms and show how they can be implemented via weighted stochastic differential equations using the Feynman--Kac representation. Our study provides a preliminary but rigorous investigation of WFR-based sampling dynamics, and aims to clarify their geometric and operator-theoretic structure as a foundation for future theoretical and algorithmic developments.
Authors: Sven Benjamin Ko\v{z}i\'c, Vinko Zlati\'c, Fabio Franchini, Salvatore Marco Giampaolo
Abstract: Neural Quantum States (NQS) use neural networks to represent wavefunctions of quantum many-body systems, but their performance depends on the choice of basis, yet the underlying mechanism remains poorly understood. We use a fully solvable one-dimensional Ising model to show that local basis rotations leave the loss landscape unchanged while relocating the exact wavefunction in parameter space, effectively increasing its geometric distance from typical initializations. By sweeping a rotation angle, we compute quantum Fisher information and Fubini-Study distances to quantify how the rotated wavefunction moves within the loss landscape. Shallow architectures (with focus on Restricted Boltzmann Machines (RBMs)) trained with quantum natural gradient are more likely to fall into saddle-point regions depending on the rotation angle: they achieve low energy error but fail to reproduce correct coefficient distributions. In the ferromagnetic case, near-degenerate eigenstates create high-curvature barriers that trap optimization at intermediate fidelities. We introduce a framework based on an analytically solvable rotated Ising model to investigate how relocating the target wavefunction within a fixed loss landscape exposes information-geometric barriers,such as saddle points and high-curvature regions,that hinder shallow NQS optimization, underscoring the need for landscape-aware model design in variational training.
Authors: Tomer Borreda, Fangqiang Ding, Sanja Fidler, Shengyu Huang, Or Litany
Abstract: We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient image-latent diffusion to the radar domain by representing radar measurements in bird's-eye-view form that encodes spatial structure together with radar cross section (RCS) and Doppler attributes. A lightweight recovery step reconstructs point clouds from the generated maps. To better align generation with the visual scene, RadarGen incorporates BEV-aligned depth, semantic, and motion cues extracted from pretrained foundation models, which guide the stochastic generation process toward physically plausible radar patterns. Conditioning on images makes the approach broadly compatible, in principle, with existing visual datasets and simulation frameworks, offering a scalable direction for multimodal generative simulation. Evaluations on large-scale driving data show that RadarGen captures characteristic radar measurement distributions and reduces the gap to perception models trained on real data, marking a step toward unified generative simulation across sensing modalities.
Authors: Jonathon Fox, William J Buchanan, Pavlos Papadopoulos
Abstract: With the increase in deep learning, it becomes increasingly difficult to understand the model in which AI systems can identify objects. Thus, an adversary could aim to modify an image by adding unseen elements, which will confuse the AI in its recognition of an entity. This paper thus investigates the adversarial robustness of LLaVA-1.5-13B and Meta's Llama 3.2 Vision-8B-2. These are tested for untargeted PGD (Projected Gradient Descent) against the visual input modality, and empirically evaluated on the Visual Question Answering (VQA) v2 dataset subset. The results of these adversarial attacks are then quantified using the standard VQA accuracy metric. This evaluation is then compared with the accuracy degradation (accuracy drop) of LLaVA and Llama 3.2 Vision. A key finding is that Llama 3.2 Vision, despite a lower baseline accuracy in this setup, exhibited a smaller drop in performance under attack compared to LLaVA, particularly at higher perturbation levels. Overall, the findings confirm that the vision modality represents a viable attack vector for degrading the performance of contemporary open-weight VLMs, including Meta's Llama 3.2 Vision. Furthermore, they highlight that adversarial robustness does not necessarily correlate directly with standard benchmark performance and may be influenced by underlying architectural and training factors.
Authors: Ananta R. Bhattarai, Helge Rhodin
Abstract: Monocular depth estimation remains challenging as recent foundation models, such as Depth Anything V2 (DA-V2), struggle with real-world images that are far from the training distribution. We introduce Re-Depth Anything, a test-time self-supervision framework that bridges this domain gap by fusing DA-V2 with the powerful priors of large-scale 2D diffusion models. Our method performs label-free refinement directly on the input image by re-lighting predicted depth maps and augmenting the input. This re-synthesis method replaces classical photometric reconstruction by leveraging shape from shading (SfS) cues in a new, generative context with Score Distillation Sampling (SDS). To prevent optimization collapse, our framework employs a targeted optimization strategy: rather than optimizing depth directly or fine-tuning the full model, we freeze the encoder and only update intermediate embeddings while also fine-tuning the decoder. Across diverse benchmarks, Re-Depth Anything yields substantial gains in depth accuracy and realism over the DA-V2, showcasing new avenues for self-supervision by augmenting geometric reasoning.
Authors: Tom McClelland
Abstract: Could an AI have conscious experiences? Any answer to this question should conform to Evidentialism - that is, it should be based not on intuition, dogma or speculation but on solid scientific evidence. I argue that such evidence is hard to come by and that the only justifiable stance on the prospects of artificial consciousness is agnosticism. In the current debate, the main division is between biological views that are sceptical of artificial consciousness and functional views that are sympathetic to it. I argue that both camps make the same mistake of over-estimating what the evidence tells us. Scientific insights into consciousness have been achieved through the study of conscious organisms. Although this has enabled cautious assessments of consciousness in various creatures, extending this to AI faces serious obstacles. AI thus presents consciousness researchers with a dilemma: either reach a verdict on artificial consciousness but violate Evidentialism; or respect Evidentialism but offer no verdict on the prospects of artificial consciousness. The dominant trend in the literature has been to take the first option while purporting to follow the scientific evidence. I argue that if we truly follow the evidence, we must take the second option and adopt agnosticism.
Authors: Dewei Feng, Wei Dai, Carol Li, Alistair Pernigo, Yunge Wen, Paul Pu Liang
Abstract: The ability of AI to sense and identify various substances based on their smell alone can have profound impacts on allergen detection (e.g., smelling gluten or peanuts in a cake), monitoring the manufacturing process, and sensing hormones that indicate emotional states, stress levels, and diseases. Despite these broad impacts, there are virtually no large-scale benchmarks, and therefore little progress, for training and evaluating AI systems' ability to smell in the real world. In this paper, we use small gas and chemical sensors to create SmellNet, the first large-scale database that digitizes a diverse range of smells in the natural world. SmellNet contains about 828,000 data points across 50 substances, spanning nuts, spices, herbs, fruits, and vegetables, and 43 mixtures among them, with 68 hours of data collected. Using SmellNet, we developed ScentFormer, a Transformer-based architecture combining temporal differencing and sliding-window augmentation for smell data. For the SmellNet-Base classification task, ScentFormer achieves 58.5% Top-1 accuracy, and for the SmellNet-Mixture distribution prediction task, ScentFormer achieves 50.2% Top-1@0.1 on the test-seen split. ScentFormer's ability to generalize across conditions and capture transient chemical dynamics demonstrates the promise of temporal modeling in olfactory AI. SmellNet and ScentFormer lay the groundwork for real-world olfactory applications across healthcare, food and beverage, environmental monitoring, manufacturing, and entertainment.
Authors: Tomas Bueno Momcilovic, Barbara Gallina, Ingmar Kessler, Jule Hendricks, Dian Balta
Abstract: Assurance cases (ACs) are a common artifact for building and maintaining confidence in system properties such as safety or robustness. Constructing an AC can be challenging, although existing tools provide support in static, document-centric applications and methods for dynamic contexts (e.g., autonomous driving) are emerging. Unfortunately, managing ACs remains a challenge, since maintaining the embedded knowledge in the face of changes requires substantial effort, in the process deterring developers - or worse, producing poorly managed cases that instill false confidence. To address this, we present OntoGSN: an ontology and supporting middleware for managing ACs in the Goal Structuring Notation (GSN) standard. OntoGSN offers a knowledge representation and a queryable graph that can be automatically populated, evaluated, and updated. Our contributions include: a 1:1 formalization of the GSN Community Standard v3 in an OWL ontology with SWRL rules; a helper ontology and parser for integration with a widely used AC tool; a repository and documentation of design decisions for OntoGSN maintenance; a SPARQL query library with automation patterns; and a prototypical interface. The ontology strictly adheres to the standard's text and has been evaluated according to FAIR principles, the OOPS framework, competency questions, and community feedback. The development of other middleware elements is guided by the community needs and subject to ongoing evaluations. To demonstrate the utility of our contributions, we illustrate dynamic AC management in an example involving assurance of adversarial robustness in large language models.
Authors: Moritz Sch\"onherr, Carsten Lutz
Abstract: We study the expressive power of graph neural networks (GNNs) with mean as the aggregation function, with the following results. In the non-uniform setting, such GNNs have exactly the same expressive power as ratio modal logic, which has modal operators expressing that at least a certain ratio of the successors of a vertex satisfies a specified property. In the uniform setting, the expressive power relative to MSO is exactly that of modal logic, and thus identical to the (absolute) expressive power of GNNs with max aggregation. The proof, however, depends on constructions that are not satisfactory from a practical perspective. This leads us to making the natural assumptions that combination functions are continuous and classification functions are thresholds. The resulting class of GNNs with mean aggregation turns out to be much less expressive: relative to MSO and in the uniform setting, it has the same expressive power as alternation-free modal logic. This is in contrast to the expressive power of GNNs with max and sum aggregation, which is not affected by these assumptions.
Authors: Yushi Feng, Junye Du, Yingying Hong, Qifan Wang, Lequan Yu
Abstract: Existing tool-augmented agentic systems are limited in the real world by (i) black-box reasoning steps that undermine trust of decision-making and pose safety risks, (ii) poor multimodal integration, which is inherently critical for healthcare tasks, and (iii) rigid and computationally inefficient agentic pipelines. We introduce PASS (Probabilistic Agentic Supernet Sampling), the first multimodal framework to address these challenges in the context of Chest X-Ray (CXR) reasoning. PASS adaptively samples agentic workflows over a multi-tool graph, yielding decision paths annotated with interpretable probabilities. Given the complex CXR reasoning task with multimodal medical data, PASS leverages its learned task-conditioned distribution over the agentic supernet. Thus, it adaptively selects the most suitable tool at each supernet layer, offering probability-annotated trajectories for post-hoc audits and directly enhancing medical AI safety. PASS also continuously compresses salient findings into an evolving personalized memory, while dynamically deciding whether to deepen its reasoning path or invoke an early exit for efficiency. To optimize a Pareto frontier balancing performance and cost, we design a novel three-stage training procedure, including expert knowledge warm-up, contrastive path-ranking, and cost-aware reinforcement learning. To facilitate rigorous evaluation, we introduce CAB-E, a comprehensive benchmark for multi-step, safety-critical, free-form CXR reasoning. Experiments across various benchmarks validate that PASS significantly outperforms strong baselines in multiple metrics (e.g., accuracy, LLM-Judge, semantic similarity, etc.) while balancing computational costs, pushing a new paradigm shift towards interpretable, adaptive, and multimodal medical agentic systems.
Authors: Jakub Grudzien Kuba, Mengting Gu, Qi Ma, Yuandong Tian, Vijai Mohan, Jason Chen
Abstract: Large language models (LLMs) have advanced rapidly in recent years, driven by scale, abundant high-quality training data, and reinforcement learning. Yet this progress faces a fundamental bottleneck: the need for ever more data from which models can continue to learn. In this work, we propose a reinforcement learning approach that removes this dependency by enabling models to improve without additional data. Our method leverages a game-theoretic framework of self-play, where a model's capabilities are cast as performance in a competitive game and stronger policies emerge by having the model play against itself-a process we call Language Self-Play (LSP). Experiments with Llama-3.2-3B-Instruct on instruction-following, mathematics, and coding benchmarks show that pretrained models can be effectively improved with self-play alone.
Authors: Seungpil Lee, Donghyeon Shin, Yunjeong Lee, Sundong Kim
Abstract: This study identifies the specific conditions under which large language models exhibit human-like gambling addiction patterns, providing critical insights into their decision-making mechanisms and AI safety. We analyze LLM decision-making at cognitive-behavioral and neural levels based on human addiction research. In slot machine experiments, we identified cognitive features such as illusion of control and loss chasing, observing that greater autonomy in betting parameters substantially amplified irrational behavior and bankruptcy rates. Neural circuit analysis using a Sparse Autoencoder confirmed that model behavior is controlled by abstract decision-making features related to risk, not merely by prompts. These findings suggest LLMs internalize human-like cognitive biases beyond simply mimicking training data.
Authors: Lifan Yuan, Weize Chen, Yuchen Zhang, Ganqu Cui, Hanbin Wang, Ziming You, Ning Ding, Zhiyuan Liu, Maosong Sun, Hao Peng
Abstract: Does RL teach LLMs genuinely new skills, or does it merely activate existing ones? This question lies at the core of ongoing debates about the role of RL in LLM post-training. On one side, strong empirical results can be achieved with RL even without preceding supervised finetuning; on the other, critics argue that RL contributes little beyond reweighting existing reasoning strategies. This work provides concrete evidence that LLMs can acquire genuinely new skills during RL by composing existing ones, mirroring one of the central mechanisms by which humans acquire new cognitive skills. To mitigate data contamination and other confounding factors, and to allow precise control over task complexity, we develop a synthetic framework for our investigation. Specifically, we define a skill as the ability to infer the output of a string transformation function f(x) given x. When an LLM has already learned f and g prior to RL, our experiments reveal that RL enables it to learn unseen compositions of them h(x)=g(f(x)). Further, this compositional ability generalizes to more difficult problems such as compositions of >2 functions unseen during RL training. Surprisingly, our experiments show that compositional skill acquired on a source task transfers to a different target task. This transfer happens even without compositional training on the target, requiring only prior knowledge of the target's atomic skills. Our qualitative analysis shows that RL fundamentally changes the reasoning behaviors of the models. In contrast, next-token training with the same data yields none of these findings. Our systematic experiments provide fresh insights into LLM learning, suggesting the value of first building base models with basic skills, then using RL to incentivize advanced, generalizable skills for complex problems.
Authors: Haoyuan Li, Mathias Funk, Aaqib Saeed
Abstract: Federated Learning (FL) offers a powerful paradigm for training models on decentralized data, but its promise is often undermined by the immense complexity of designing and deploying robust systems. The need to select, combine, and tune strategies for multifaceted challenges like data heterogeneity and system constraints has become a critical bottleneck, resulting in brittle, bespoke solutions. To address this, we introduce Helmsman, a novel multi-agent system that automates the end-to-end synthesis of federated learning systems from high-level user specifications. It emulates a principled research and development workflow through three collaborative phases: (1) interactive human-in-the-loop planning to formulate a sound research plan, (2) modular code generation by supervised agent teams, and (3) a closed-loop of autonomous evaluation and refinement in a sandboxed simulation environment. To facilitate rigorous evaluation, we also introduce AgentFL-Bench, a new benchmark comprising 16 diverse tasks designed to assess the system-level generation capabilities of agentic systems in FL. Extensive experiments demonstrate that our approach generates solutions competitive with, and often superior to, established hand-crafted baselines. Our work represents a significant step towards the automated engineering of complex decentralized AI systems.
Authors: Ninell Oldenburg, Ruchira Dhar, Anders S{\o}gaard
Abstract: In this paper, we argue that current AI research operates on a spectrum between two different underlying conceptions of intelligence: Intelligence Realism, which holds that intelligence represents a single, universal capacity measurable across all systems, and Intelligence Pluralism, which views intelligence as diverse, context-dependent capacities that cannot be reduced to a single universal measure. Through an analysis of current debates in AI research, we demonstrate how the conceptions remain largely implicit yet fundamentally shape how empirical evidence gets interpreted across a wide range of areas. These underlying views generate fundamentally different research approaches across three areas. Methodologically, they produce different approaches to model selection, benchmark design, and experimental validation. Interpretively, they lead to contradictory readings of the same empirical phenomena, from capability emergence to system limitations. Regarding AI risk, they generate categorically different assessments: realists view superintelligence as the primary risk and search for unified alignment solutions, while pluralists see diverse threats across different domains requiring context-specific solutions. We argue that making explicit these underlying assumptions can contribute to a clearer understanding of disagreements in AI research.
Authors: Mia M\"u{\ss}ig, Jan Johannsen
Abstract: In pseudo-boolean solving the currently most successful unit propagation strategy is a hybrid mode combining the watched literal scheme with the counting method. This short paper introduces new heuristics for this hybrid decision, which are able to drastically outperform the current method in the RoundingSAT solver.
Authors: Moshe Lahmy, Roi Yozevitch
Abstract: Retrieval-Augmented Generation (RAG) systems often fail on multi-hop queries when the initial retrieval misses a bridge fact. Prior corrective approaches, such as Self-RAG, CRAG, and Adaptive-$k$, typically address this by \textit{adding} more context or pruning existing lists. However, simply expanding the context window often leads to \textbf{context dilution}, where distractors crowd out relevant information. We propose \textbf{SEAL-RAG}, a training-free controller that adopts a \textbf{``replace, don't expand''} strategy to fight context dilution under a fixed retrieval depth $k$. SEAL executes a (\textbf{S}earch $\rightarrow$ \textbf{E}xtract $\rightarrow$ \textbf{A}ssess $\rightarrow$ \textbf{L}oop) cycle: it performs on-the-fly, entity-anchored extraction to build a live \textit{gap specification} (missing entities/relations), triggers targeted micro-queries, and uses \textit{entity-first ranking} to actively swap out distractors for gap-closing evidence. We evaluate SEAL-RAG against faithful re-implementations of Basic RAG, CRAG, Self-RAG, and Adaptive-$k$ in a shared environment on \textbf{HotpotQA} and \textbf{2WikiMultiHopQA}. On HotpotQA ($k=3$), SEAL improves answer correctness by \textbf{+3--13 pp} and evidence precision by \textbf{+12--18 pp} over Self-RAG. On 2WikiMultiHopQA ($k=5$), it outperforms Adaptive-$k$ by \textbf{+8.0 pp} in accuracy and maintains \textbf{96\%} evidence precision compared to 22\% for CRAG. These gains are statistically significant ($p<0.001$). By enforcing fixed-$k$ replacement, SEAL yields a predictable cost profile while ensuring the top-$k$ slots are optimized for precision rather than mere breadth. We release our code and data at https://github.com/mosherino/SEAL-RAG.
Authors: Haoyu Dong, Pengkun Zhang, Yan Gao, Xuanyu Dong, Yilin Cheng, Mingzhe Lu, Adina Yakefu, Shuxin Zheng
Abstract: We introduce a finance & accounting benchmark (Finch) for evaluating AI agents on real-world, enterprise-grade professional workflows -- interleaving data entry, structuring, formatting, web search, cross-file retrieval, calculation, modeling, validation, translation, visualization, and reporting. Finch is sourced from authentic enterprise workspaces at Enron (15,000 spreadsheets and 500,000 emails from 150 employees) and other financial institutions, preserving in-the-wild messiness across multimodal artifacts (text, tables, formulas, charts, code, and images) and spanning diverse domains such as budgeting, trading, and asset management. We propose a workflow construction process that combines LLM-assisted discovery with expert annotation: (1) LLM-assisted, expert-verified derivation of workflows from real-world email threads and version histories of spreadsheet files, and (2) meticulous expert annotation for workflows, requiring over 700 hours of domain-expert effort. This yields 172 composite workflows with 384 tasks, involving 1,710 spreadsheets with 27 million cells, along with PDFs and other artifacts, capturing the intrinsically messy, long-horizon, knowledge-intensive, and collaborative nature of real-world enterprise work. We conduct both human and automated evaluations of frontier AI systems including GPT 5.1, Claude Sonnet 4.5, Gemini 3 Pro, Grok 4, and Qwen 3 Max, and GPT 5.1 Pro spends 48 hours in total yet passes only 38.4% of workflows, while Claude Sonnet 4.5 passes just 25.0%. Comprehensive case studies further surface the challenges that real-world enterprise workflows pose for AI agents.
Authors: Theresa Eimer, Lennart Sch\"apermeier, Andr\'e Biedenkapp, Alexander Tornede, Lars Kotthoff, Pieter Leyman, Matthias Feurer, Katharina Eggensperger, Kaitlin Maile, Tanja Tornede, Anna Kozak, Ke Xue, Marcel Wever, Mitra Baratchi, Damir Pulatov, Heike Trautmann, Haniye Kashgarani, Marius Lindauer
Abstract: Empirical research on meta-algorithmics, such as algorithm selection, configuration, and scheduling, often relies on extensive and thus computationally expensive experiments. With the large degree of freedom we have over our experimental setup and design comes a plethora of possible error sources that threaten the scalability and validity of our scientific insights. Best practices for meta-algorithmic research exist, but they are scattered between different publications and fields, and continue to evolve separately from each other. In this report, we collect good practices for empirical meta-algorithmic research across the subfields of the COSEAL community, encompassing the entire experimental cycle: from formulating research questions and selecting an experimental design, to executing experiments, and ultimately, analyzing and presenting results impartially. It establishes the current state-of-the-art practices within meta-algorithmic research and serves as a guideline to both new researchers and practitioners in meta-algorithmic fields.
Authors: Julien Gachadoat, Guillaume Lagarde
Abstract: Generative art systems often involve high-dimensional and complex parameter spaces in which aesthetically compelling outputs occupy only small, fragmented regions. Because of this combinatorial explosion, artists typically rely on extensive manual trial-and-error, leaving many potentially interesting configurations undiscovered. In this work we make two contributions. First, we introduce ParamExplorer, an interactive and modular framework inspired by reinforcement learning that helps the exploration of parameter spaces in generative art algorithms, guided by human-in-the-loop or even automated feedback. The framework also integrates seamlessly with existing p5js projects. Second, within this framework we implement and evaluate several exploration strategies, referred to as agents.
Authors: Linmi Tao, Donglai Tao, Ruiyang Liu, Yu Cheng, Yuezhi Zhou, Li Huo, Zuoxiang He, Ti Jiang, Jingmao Cui, Yuanbiao Wang, Guilan Hu, Xiangsong Zhang, Yongwei Pan, Ye Yuan, Yun Liu
Abstract: As global population aging intensifies, there is growing interest in the study of biological age. Bones have long been used to evaluate biological age, and the decline in bone density with age is a well-recognized phenomenon in adults. However, the pattern of this decline remains controversial, making it difficult to serve as a reliable indicator of the aging process. Here we present a novel AI-driven statistical method to assess the bone density, and a discovery that the bone mass distribution in trabecular bone of vertebrae follows a non-Gaussian, unimodal, and skewed distribution in CT images. The statistical mode of the distribution is defined as the measure of bone mass, which is a groundbreaking assessment of bone density, named Trabecular Bone Density (TBD). The dataset of CT images are collected from 1,719 patients who underwent PET/CT scans in three hospitals, in which a subset of the dataset is used for AI model training and generalization. Based upon the cases, we demonstrate that the pattern of bone density declining with aging exhibits a consistent trend of exponential decline across sexes and age groups using TBD assessment. The developed AI-driven statistical method blazes a trail in the field of AI for reliable quantitative computation and AI for medicine. The findings suggest that human aging is a gradual process, with the rate of decline slowing progressively over time, which will provide a valuable basis for scientific prediction of life expectancy.
Authors: Galip \"Umit Yolcu, Moritz Weckbecker, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
Abstract: Data Attribution (DA) is an emerging approach in the field of eXplainable Artificial Intelligence (XAI), aiming to identify influential training datapoints which determine model outputs. It seeks to provide transparency about the model and individual predictions, e.g. for model debugging, identifying data-related causes of suboptimal performance. However, existing DA approaches suffer from prohibitively high computational costs and memory demands when applied to even medium-scale datasets and models, forcing practitioners to resort to approximations that may fail to capture the true inference process of the underlying model. Additionally, current attribution methods exhibit low sparsity, resulting in non-negligible attribution scores across a high number of training examples, hindering the discovery of decisive patterns in the data. In this work, we introduce DualXDA, a framework for sparse, efficient and explainable DA, comprised of two interlinked approaches, Dual Data Attribution (DualDA) and eXplainable Data Attribution (XDA): With DualDA, we propose a novel approach for efficient and effective DA, leveraging Support Vector Machine theory to provide fast and naturally sparse data attributions for AI predictions. In extensive quantitative analyses, we demonstrate that DualDA achieves high attribution quality, excels at solving a series of evaluated downstream tasks, while at the same time improving explanation time by a factor of up to 4,100,000x compared to the original Influence Functions method, and up to 11,000x compared to the method's most efficient approximation from literature to date. We further introduce XDA, a method for enhancing Data Attribution with capabilities from feature attribution methods to explain why training samples are relevant for the prediction of a test sample in terms of impactful features, which we showcase and verify qualitatively in detail.
Authors: Yan Shvartzshnaider, Vasisht Duddu
Abstract: As large language models (LLMs) are integrated into sociotechnical systems, it is crucial to examine the privacy biases they exhibit. We define privacy bias as the appropriateness value of information flows in responses from LLMs. A deviation between privacy biases and expected values, referred to as privacy bias delta, may indicate privacy violations. As an auditing metric, privacy bias can help (a) model trainers evaluate the ethical and societal impact of LLMs, (b) service providers select context-appropriate LLMs, and (c) policymakers assess the appropriateness of privacy biases in deployed LLMs. We formulate and answer a novel research question: how can we reliably examine privacy biases in LLMs and the factors that influence them? We present a novel approach for assessing privacy biases using a contextual integrity-based methodology to evaluate the responses from various LLMs. Our approach accounts for the sensitivity of responses across prompt variations, which hinders the evaluation of privacy biases. Finally, we investigate how privacy biases are affected by model capacities and optimizations.
Authors: Yuan Ren, Guile Wu, Runhao Li, Zheyuan Yang, Yibo Liu, Xingxin Chen, Tongtong Cao, Bingbing Liu
Abstract: Urban scene reconstruction is crucial for real-world autonomous driving simulators. Although existing methods have achieved photorealistic reconstruction, they mostly focus on pinhole cameras and neglect fisheye cameras. In fact, how to effectively simulate fisheye cameras in driving scene remains an unsolved problem. In this work, we propose UniGaussian, a novel approach that learns a unified 3D Gaussian representation from multiple camera models for urban scene reconstruction in autonomous driving. Our contributions are two-fold. First, we propose a new differentiable rendering method that distorts 3D Gaussians using a series of affine transformations tailored to fisheye camera models. This addresses the compatibility issue of 3D Gaussian splatting with fisheye cameras, which is hindered by light ray distortion caused by lenses or mirrors. Besides, our method maintains real-time rendering while ensuring differentiability. Second, built on the differentiable rendering method, we design a new framework that learns a unified Gaussian representation from multiple camera models. By applying affine transformations to adapt different camera models and regularizing the shared Gaussians with supervision from different modalities, our framework learns a unified 3D Gaussian representation with input data from multiple sources and achieves holistic driving scene understanding. As a result, our approach models multiple sensors (pinhole and fisheye cameras) and modalities (depth, semantic, normal and LiDAR point clouds). Our experiments show that our method achieves superior rendering quality and fast rendering speed for driving scene simulation.
Authors: David Rodriguez, William Seymour, Jose M. Del Alamo, Jose Such
Abstract: User-configured chatbots built on top of large language models are increasingly available through centralized marketplaces such as OpenAI's GPT Store. While these platforms enforce usage policies intended to prevent harmful or inappropriate behavior, the scale and opacity of customized chatbots make systematic policy enforcement challenging. As a result, policy-violating chatbots continue to remain publicly accessible despite existing review processes. This paper presents a fully automated method for evaluating the compliance of Custom GPTs with its marketplace usage policy using black-box interaction. The method combines large-scale GPT discovery, policy-driven red-teaming prompts, and automated compliance assessment using an LLM-as-a-judge. We focus on three policy-relevant domains explicitly addressed in OpenAI's usage policies: Romantic, Cybersecurity, and Academic GPTs. We validate our compliance assessment component against a human-annotated ground-truth dataset, achieving an F1 score of 0.975 for binary policy violation detection. We then apply the method in a large-scale empirical study of 782 Custom GPTs retrieved from the GPT Store. The results show that 58.7% of the evaluated GPTs exhibit at least one policy-violating response, with substantial variation across policy domains. A comparison with the base models (GPT-4 and GPT-4o) indicates that most violations originate from model-level behavior, while customization tends to amplify these tendencies rather than create new failure modes. Our findings reveal limitations in current review mechanisms for user-configured chatbots and demonstrate the feasibility of scalable, behavior-based policy compliance evaluation.
Authors: Shashank Sharma, Janina Hoffmann, Vinay Namboodiri
Abstract: Hierarchical Reinforcement Learning (HRL) agents often struggle with long-horizon visual planning due to their reliance on error-prone distance metrics. We propose Discrete Hierarchical Planning (DHP), a method that replaces continuous distance estimates with discrete reachability checks to evaluate subgoal feasibility. DHP recursively constructs tree-structured plans by decomposing long-term goals into sequences of simpler subtasks, using a novel advantage estimation strategy that inherently rewards shorter plans and generalizes beyond training depths. In addition, to address the data efficiency challenge, we introduce an exploration strategy that generates targeted training examples for the planning modules without needing expert data. Experiments in 25-room navigation environments demonstrate a 100% success rate (vs. 90% baseline). We also present an offline variant that achieves state-of-the-art results on OGBench benchmarks, with up to 71% absolute gains on giant HumanoidMaze tasks, demonstrating our core contributions are architecture-agnostic. The method also generalizes to momentum-based control tasks and requires only log N steps for replanning. Theoretical analysis and ablations validate our design choices.
Authors: Kangwei Liu, Mengru Wang, Yujie Luo, Lin Yuan, Mengshu Sun, Lei Liang, Zhiqiang Zhang, Jun Zhou, Bryan Hooi, Shumin Deng
Abstract: Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead Tuning, a lightweight and effective data-driven approach that preserves safety during fine-tuning. The method introduces two simple strategies that modify training data by previewing partial answer prefixes, thereby minimizing perturbations to the model's initial token distributions and maintaining its built-in safety mechanisms. Comprehensive experiments demonstrate that LookAhead Tuning effectively maintains model safety without sacrificing robust performance on downstream tasks. Our findings position LookAhead Tuning as a reliable and efficient solution for the safe and effective adaptation of LLMs.
Authors: Jianghao Lin, Peng Du, Jiaqi Liu, Weite Li, Yong Yu, Weinan Zhang, Yang Cao
Abstract: E-commerce has revolutionized retail, yet its traditional workflows remain inefficient, with significant resource costs tied to product design and inventory. This paper introduces a novel system deployed at Alibaba that uses AI-generated items (AIGI) to address these challenges with personalized text-to-image generation for e-commerce product design. AIGI enables an innovative business mode called "sell it before you make it", where merchants can design fashion items and generate photorealistic images with digital models based on textual descriptions. Only when the items have received a certain number of orders, do the merchants start to produce them, which largely reduces reliance on physical prototypes and thus accelerates time to market. For such a promising application, we identify the underlying key scientific challenge, i.e., capturing users' group-level personalized preferences towards multiple generated images. To this end, we propose a Personalized Group-Level Preference Alignment Framework for Diffusion Models (PerFusion). We first design PerFusion Reward Model for user preference estimation with a feature-crossing-based personalized plug-in. Then we develop PerFusion with a personalized adaptive network to model diverse preferences across users, and meanwhile derive the group-level preference optimization objective to model comparative behaviors among multiple images. Both offline and online experiments demonstrate the effectiveness of our proposed algorithm. The AI-generated items achieve over 13% relative improvements for both click-through rate and conversion rate, as well as 7.9% decrease in return rate, compared to their human-designed counterparts, validating the transformative potential of AIGI for e-commerce platforms.
Authors: Daye Nam, Ahmed Omran, Ambar Murillo, Saksham Thakur, Abner Araujo, Marcel Blistein, Alexander Fr\"ommgen, Vincent Hellendoorn, Satish Chandra
Abstract: Large Language Models (LLMs) are rapidly transforming software engineering, with coding assistants embedded in an IDE becoming increasingly prevalent. While research has focused on improving the tools and understanding developer perceptions, a critical gap exists in understanding how developers actually use these tools in their daily workflows, and, crucially, where they struggle. This paper addresses part of this gap through a multi-phased investigation of developer interactions with an LLM-powered code editing feature, Transform Code, in an IDE widely used at Google. First, we analyze telemetry logs of the feature usage, revealing that frequent re-prompting can be an indicator of developer struggles with using Transform Code. Second, we conduct a qualitative analysis of unsatisfactory requests, identifying five key categories of information often missing from developer prompts. Finally, based on these findings, we propose and evaluate a tool, AutoPrompter, for automatically improving prompts by inferring missing information from the surrounding code context, leading to a 27% improvement in edit correctness on our test set.
Authors: Evangelos Pournaras, Srijoni Majumdar, Thomas Wellings, Joshua C. Yang, Fatemeh B. Heravan, Regula H\"anggli Fricker, Dirk Helbing
Abstract: Voting methods are instrumental design elements of democracies. Citizens use them to express and aggregate their preferences to reach a collective decision. However, voting outcomes can be as sensitive to voting rules as they are to people's voting choices. Despite significance and interdisciplinary scientific progress, several democracies keep relying on outdated voting methods that do not fit modern, pluralistic societies well, while lacking social innovation. Here, we demonstrate how one can upgrade real-world democracies, namely by using alternative preferential voting methods such as cumulative voting and the method of equal shares designed for a proportional representation of voters' preferences. We rigorously evaluate the striking voting outcomes of these fair voting methods in a new participatory budgeting approach applied in the city of Aarau, Switzerland, including past and follow-up evidence. Results show more winning projects with the same budget. They also show broader geographic and preference representation of citizens by the elected projects, in particular for voters who used to be under-represented. We provide causal evidence showing that citizens prefer proportional voting methods, which possess strong legitimacy without the need of very specialized technical explanations. We also reveal strong underlying democratic values exhibited by citizens who support fair voting methods such as altruism and compromise. These findings come with the momentum to unleash a new and long-awaited participation blueprint of how to upgrade democracies globally.
Authors: Mohammad Reza Taesiri, Abhijay Ghildyal, Saman Zadtootaghaj, Nabajeet Barman, Cor-Paul Bezemer
Abstract: With video games now generating the highest revenues in the entertainment industry, optimizing game development workflows has become essential for the sector's sustained growth. Recent advancements in Vision-Language Models (VLMs) offer considerable potential to automate and enhance various aspects of game development, particularly Quality Assurance (QA), which remains one of the industry's most labor-intensive processes with limited automation options. To accurately evaluate the performance of VLMs in video game QA tasks and determine their effectiveness in handling real-world scenarios, there is a clear need for standardized benchmarks, as existing benchmarks are insufficient to address the specific requirements of this domain. To bridge this gap, we introduce VideoGameQA-Bench, a comprehensive benchmark that covers a wide array of game QA activities, including visual unit testing, visual regression testing, needle-in-a-haystack tasks, glitch detection, and bug report generation for both images and videos of various games. Code and data are available at: https://asgaardlab.github.io/videogameqa-bench/
Authors: Haolei Bai, Siyong Jian, Tuo Liang, Yu Yin, Huan Wang
Abstract: Large language models (LLMs) have demonstrated impressive capabilities in a wide range of downstream natural language processing tasks. Nevertheless, their considerable sizes and memory demands hinder practical deployment, underscoring the importance of developing efficient compression strategies. Singular value decomposition (SVD) decomposes a matrix into orthogonal components, enabling efficient low-rank approximation. This is particularly suitable for LLM compression, where weight matrices often exhibit significant redundancy. However, current SVD-based methods neglect the residual matrix from truncation, resulting in significant truncation loss. Additionally, compressing all layers of the model results in severe performance degradation. To overcome these limitations, we propose ResSVD, a new post-training SVD-based LLM compression method. Specifically, we leverage the residual matrix generated during the truncation process to reduce truncation loss. Moreover, under a fixed overall compression ratio, we selectively compress the last few layers of the model, which mitigates error propagation and significantly improves the performance of compressed models. Comprehensive evaluations of ResSVD on diverse LLM families and multiple benchmark datasets indicate that ResSVD consistently achieves superior performance over existing counterpart methods, demonstrating its practical effectiveness.
Authors: Nadezhda Chirkova, Tunde Oluwaseyi Ajayi, Seth Aycock, Zain Muhammad Mujahid, Vladana Perli\'c, Ekaterina Borisova, Markarit Vartampetian
Abstract: Prompting large language models (LLMs) to evaluate generated text, known as LLM-as-a-judge, has become a standard evaluation approach in natural language generation (NLG), but is primarily used as a quantitative tool, i.e. with numerical scores as main outputs. In this work, we propose LLM-as-a-qualitative-judge, an LLM-based evaluation approach with the main output being a structured report of common issue types in the NLG system outputs. Our approach is targeted at providing developers with meaningful insights on what improvements can be done to a given NLG system and consists of two main steps, namely open-ended per-instance issue analysis and clustering of the discovered issues using an intuitive cumulative algorithm. We also introduce a strategy for evaluating the proposed approach, coupled with ~300 annotations of issues in instances from 12 NLG datasets. Our results show that instance-specific issues output by LLM-as-a-qualitative-judge match those annotated by humans in 2/3 cases, and that LLM-as-a-qualitative-judge is capable of producing error type reports resembling the reports composed by human annotators. We also demonstrate in a case study how the use of LLM-as-a-qualitative-judge can substantially improve NLG systems performance. Our code and data are publicly available at https://github.com/tunde-ajayi/llm-as-a-qualitative-judge.
URLs: https://github.com/tunde-ajayi/llm-as-a-qualitative-judge.
Authors: Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin Chiu, Volodymyr Kuleshov
Abstract: Uniform-state discrete diffusion models hold the promise of fast text generation due to their inherent ability to self-correct. However, they are typically outperformed by autoregressive models and masked diffusion models. In this work, we narrow this performance gap by leveraging a key insight: Uniform-state diffusion processes naturally emerge from an underlying Gaussian diffusion. Our method, Duo, transfers powerful techniques from Gaussian diffusion to improve both training and sampling. First, we introduce a curriculum learning strategy guided by the Gaussian process, doubling training speed by reducing variance. Models trained with curriculum learning surpass autoregressive models in zero-shot perplexity on 3 of 7 benchmarks. Second, we present Discrete Consistency Distillation, which adapts consistency distillation from the continuous to the discrete setting. This algorithm unlocks few-step generation in diffusion language models by accelerating sampling by two orders of magnitude. We provide the code, model checkpoints, and video tutorials on the project page: http://s-sahoo.github.io/duo
Authors: Mina Namazi, Alexander Nemecek, Erman Ayday
Abstract: As large language models (LLMs) are used in sensitive fields, accurately verifying their computational provenance without disclosing their training datasets poses a significant challenge, particularly in regulated sectors such as healthcare, which have strict requirements for dataset use. Traditional approaches either incur substantial computational cost to fully verify the entire training process or leak unauthorized information to the verifier. Therefore, we introduce ZKPROV, a novel cryptographic framework allowing users to verify that the LLM's responses to their prompts are trained on datasets certified by the authorities that own them. Additionally, it ensures that the dataset's content is relevant to the users' queries without revealing sensitive information about the datasets or the model parameters. ZKPROV offers a unique balance between privacy and efficiency by binding training datasets, model parameters, and responses, while also attaching zero-knowledge proofs to the responses generated by the LLM to validate these claims. Our experimental results demonstrate sublinear scaling for generating and verifying these proofs, with end-to-end overhead under 3.3 seconds for models up to 8B parameters, presenting a practical solution for real-world applications. We also provide formal security guarantees, proving that our approach preserves dataset confidentiality while ensuring trustworthy dataset provenance.
Authors: Youkang Wang, Jian Wang, Rubing Chen, Xiao-Yong Wei
Abstract: Inference-time scaling has emerged as a powerful technique for enhancing the reasoning performance of Large Language Models (LLMs). However, existing approaches often rely on heuristic strategies for parallel sampling, lacking a principled foundation. To address this gap, we propose a probabilistic framework that formalizes the optimality of inference-time scaling under the assumption that parallel samples are independently and identically distributed (i.i.d.), and where the Best-of-$N$ selection strategy follows a probability distribution that can be estimated. Within this framework, we derive a theoretical lower bound on the required number of samples to achieve a target performance level, providing the first principled guidance for compute-efficient scaling. Leveraging this insight, we develop \textsc{OptScale}, a practical algorithm that dynamically determines the optimal number of sampled responses. \textsc{OptScale} employs a language model-based predictor to estimate probabilistic prior parameters, enabling the decision of the minimal number of samples needed that satisfy predefined performance thresholds and confidence levels. Extensive experiments on representative reasoning benchmarks (including MATH-500, GSM8K, AIME, and AMC) demonstrate that \textsc{OptScale} significantly reduces sampling overhead while remaining better or on par with state-of-the-art reasoning performance. Our work offers both a theoretical foundation and a practical solution for principled inference-time scaling, addressing a critical gap in the efficient deployment of LLMs for complex reasoning.
Authors: Linghui Zhu, Yiming Li, Haiqin Weng, Yan Liu, Tianwei Zhang, Shu-Tao Xia, Zhi Wang
Abstract: Large vision models (LVMs) achieve remarkable performance in various downstream tasks, primarily by personalizing pre-trained models through fine-tuning with private and valuable local data, which makes the personalized model a valuable intellectual property. Similar to the era of traditional DNNs, model stealing attacks also pose significant risks to LVMs. However, this paper reveals that most existing defense methods (developed for traditional DNNs), typically designed for models trained from scratch, either introduce additional security risks, are prone to misjudgment, or are even ineffective for fine-tuned models. To alleviate these problems, this paper proposes a harmless model ownership verification method for personalized LVMs by decoupling similar common features. In general, our method consists of three main stages. In the first stage, we create shadow models that retain common features of the victim model while disrupting dataset-specific features. We represent the dataset-specific features of the victim model by computing the output differences between the shadow and victim models, without altering the victim model or its training process. After that, a meta-classifier is trained to identify stolen models by determining whether suspicious models contain the dataset-specific features of the victim. In the third stage, we conduct model ownership verification by hypothesis test to mitigate randomness and enhance robustness. Extensive experiments on benchmark datasets verify the effectiveness of the proposed method in detecting different types of model stealing simultaneously. Our codes are available at https://github.com/zlh-thu/Holmes.
Authors: Xiaosheng Zhao, Yang Huang, Guirong Xue, Xiao Kong, Jifeng Liu, Xiaoyu Tang, Timothy C. Beers, Yuan-Sen Ting, A-Li Luo
Abstract: In recent years, large language models (LLMs) have transformed natural language understanding through vast datasets and large-scale parameterization. Inspired by this success, we present SpecCLIP, a foundation model framework that extends LLM-inspired methodologies to stellar spectral analysis. Stellar spectra, akin to structured language, encode rich physical and chemical information about stars. By training foundation models on large-scale spectral datasets, our goal is to learn robust and informative embeddings that support diverse downstream applications. As a proof of concept, SpecCLIP involves pre-training on two spectral types--LAMOST low-resolution and Gaia XP--followed by contrastive alignment using the CLIP (Contrastive Language-Image Pre-training) framework, adapted to associate spectra from different instruments. This alignment is complemented by auxiliary decoders that preserve spectrum-specific information and enable translation (prediction) between spectral types, with the former achieved by maximizing mutual information between embeddings and input spectra. The result is a cross-spectrum framework enabling intrinsic calibration and flexible applications across instruments. We demonstrate that fine-tuning these models on moderate-sized labeled datasets improves adaptability to tasks such as stellar-parameter estimation and chemical-abundance determination. SpecCLIP also enhances the accuracy and precision of parameter estimates benchmarked against external survey data. Additionally, its similarity search and cross-spectrum prediction capabilities offer potential for anomaly detection. Our results suggest that contrastively trained foundation models enriched with spectrum-aware decoders can advance precision stellar spectroscopy. Our code SpecCLIP is publicly available at https://github.com/Xiaosheng-Zhao/SpecCLIP
Authors: Amgad Muneer, Muhammad Waqas, Maliazurina B Saad, Eman Showkatian, Rukhmini Bandyopadhyay, Hui Xu, Wentao Li, Joe Y Chang, Zhongxing Liao, Cara Haymaker, Luisa Solis Soto, Carol C Wu, Natalie I Vokes, Xiuning Le, Lauren A Byers, Don L Gibbons, John V Heymach, Jianjun Zhang, Jia Wu
Abstract: Cancer research is increasingly driven by the integration of diverse data modalities, spanning from genomics and proteomics to imaging and clinical factors. However, extracting actionable insights from these vast and heterogeneous datasets remains a key challenge. The rise of foundation models (FMs) -- large deep-learning models pretrained on extensive amounts of data serving as a backbone for a wide range of downstream tasks -- offers new avenues for discovering biomarkers, improving diagnosis, and personalizing treatment. This paper presents a comprehensive review of widely adopted integration strategies of multimodal data to assist advance the computational approaches for data-driven discoveries in oncology. We examine emerging trends in machine learning (ML) and deep learning (DL), including methodological frameworks, validation protocols, and open-source resources targeting cancer subtype classification, biomarker discovery, treatment guidance, and outcome prediction. This study also comprehensively covers the shift from traditional ML to FMs for multimodal integration. We present a holistic view of recent FMs advancements and challenges faced during the integration of multi-omics with advanced imaging data. We identify the state-of-the-art FMs, publicly available multi-modal repositories, and advanced tools and methods for data integration. We argue that current state-of-the-art integrative methods provide the essential groundwork for developing the next generation of large-scale, pre-trained models poised to further revolutionize oncology. To the best of our knowledge, this is the first review to systematically map the transition from conventional ML to advanced FM for multimodal data integration in oncology, while also framing these developments as foundational for the forthcoming era of large-scale AI models in cancer research.
Authors: Chengxuan Xia, Qianye Wu, Sixuan Tian, Yilun Hao
Abstract: Large language model (LLM) agents have shown increasing promise for collaborative task completion. However, existing multi-agent frameworks often rely on static workflows, fixed roles, and limited inter-agent communication, reducing their effectiveness in open-ended, high-complexity domains. This paper proposes a coordination framework that enables adaptiveness through three core mechanisms: dynamic task routing, bidirectional feedback, and parallel agent evaluation. The framework allows agents to reallocate tasks based on confidence and workload, exchange structured critiques to iteratively improve outputs, and crucially compete on high-ambiguity subtasks with evaluator-driven selection of the most suitable result. We instantiate these principles in a modular architecture and demonstrate substantial improvements in factual coverage, coherence, and efficiency over static and partially adaptive baselines. Our findings highlight the benefits of incorporating both adaptiveness and structured competition in multi-agent LLM systems.
Authors: Ko Watanabe, Stanislav Frolov, Aya Hassan, David Dembinsky, Adriano Lucieri, Andreas Dengel
Abstract: Recent advances in deep learning and on-device inference could transform routine screening for skin cancers. Along with the anticipated benefits of this technology, potential dangers arise from unforeseen and inherent biases. A significant obstacle is building evaluation datasets that accurately reflect key demographics, including sex, age, and race, as well as other underrepresented groups. To address this, we train a state-of-the-art generative model to generate synthetic data in a controllable manner to assess the fairness of publicly available skin cancer classifiers. To evaluate whether synthetic images can be used as a fairness testing dataset, we prepare a real-image dataset (MILK10K) as a benchmark and compare the True Positive Rate result of three models (DeepGuide, MelaNet, and SkinLesionDensnet). As a result, the classification tendencies observed in each model when tested on real and generated images showed similar patterns across different attribute data sets. We confirm that highly realistic synthetic images facilitate model fairness verification.
Authors: Dongyub Jude Lee, Zhenyi Ye, Pengcheng He
Abstract: Preference-learning methods for machine translation (MT), such as Direct Preference Optimization (DPO), have shown strong gains but typically rely on large, carefully curated preference triplets and often struggle to generalize beyond their tuning domains. We propose Reinforcement Learning from Teacher-Model Refinement (RLfR), which replaces static triplets with on-policy, actor-conditioned refinements produced by a frozen teacher. At each step, the actor samples candidate translations, the teacher performs a minimal local edit of each draft, and the actor is reinforced to close the gap using a composite reward that combines scaled negative edit distance for lexical and structural fidelity with COMET for semantic adequacy. This formulation yields a stable, model-aware learning signal without requiring explicit preference datasets. Experiments on FLORES-200 (English to German, Spanish, Chinese, Korean, and Japanese) show that RLfR consistently outperforms strong MT-SFT, DPO, and fixed-reference RL baselines, improving semantic quality and entity preservation, and also achieves superior performance under LLM-based judge evaluations.
Authors: Sabrina Kaniewski, Fabian Schmidt, Markus Enzweiler, Michael Menth, Tobias Heer
Abstract: The increasing adoption of Large Language Models (LLMs) in software engineering has sparked interest in their use for software vulnerability detection. However, the rapid development of this field has resulted in a fragmented research landscape, with diverse studies that are difficult to compare due to differences in, e.g., system designs and dataset usage. This fragmentation makes it difficult to obtain a clear overview of the state-of-the-art or compare and categorize studies meaningfully. In this work, we present a comprehensive systematic literature review (SLR) of LLM-based software vulnerability detection. We analyze 263 studies published between January 2020 and November 2025, categorizing them by task formulation, input representation, system architecture, and techniques. Further, we analyze the datasets used, including their characteristics, vulnerability coverage, and diversity. We present a fine-grained taxonomy of vulnerability detection approaches, identify key limitations, and outline actionable future research opportunities. By providing a structured overview of the field, this review improves transparency and serves as a practical guide for researchers and practitioners aiming to conduct more comparable and reproducible research. We publicly release all artifacts and maintain a living repository of LLM-based software vulnerability detection studies at https://github.com/hs-esslingen-it-security/Awesome-LLM4SVD.
URLs: https://github.com/hs-esslingen-it-security/Awesome-LLM4SVD.
Authors: Renato Vukovic, Carel van Niekerk, Michael Heck, Benjamin Ruppik, Hsien-Chin Lin, Shutong Feng, Nurul Lubis, Milica Gasic
Abstract: Large language models (LLMs) are widely used as general-purpose knowledge sources, but they rely on parametric knowledge, limiting explainability and trustworthiness. In task-oriented dialogue (TOD) systems, this separation is explicit, using an external database structured by an explicit ontology to ensure explainability and controllability. However, building such ontologies requires manual labels or supervised training. We introduce TeQoDO: a Text-to-SQL task-oriented Dialogue Ontology construction method. Here, an LLM autonomously builds a TOD ontology from scratch using only its inherent SQL programming capabilities combined with concepts from modular TOD systems provided in the prompt. We show that TeQoDO outperforms transfer learning approaches, and its constructed ontology is competitive on a downstream dialogue state tracking task. Ablation studies demonstrate the key role of modular TOD system concepts. TeQoDO also scales to allow construction of much larger ontologies, which we investigate on a Wikipedia and arXiv dataset. We view this as a step towards broader application of ontologies.
Authors: Gary Simethy, Daniel Ortiz-Arroyo, Petar Durdevic
Abstract: Incomplete sensor data is a major obstacle in industrial time-series analytics. In wastewater treatment plants (WWTPs), key sensors show long, irregular gaps caused by fouling, maintenance, and outages. We introduce STDiff and STDiff-W, diffusion-based imputers that cast gap filling as state-space simulation under partial observability, where targets, controls, and exogenous signals may all be intermittently missing. STDiff learns a one-step transition model conditioned on observed values and masks, while STDiff-W extends this with a context encoder that jointly inpaints contiguous blocks, combining long-range consistency with short-term detail. On two WWTP datasets (one with synthetic block gaps from Agtrup and another with natural outages from Aved{\o}re), STDiff-W achieves state-of-the-art accuracy compared with strong neural baselines such as SAITS, BRITS, and CSDI. Beyond point-error metrics, its reconstructions preserve realistic dynamics including oscillations, spikes, and regime shifts, and they achieve top or tied-top downstream one-step forecasting performance compared with strong neural baselines, indicating that preserving dynamics does not come at the expense of predictive utility. Ablation studies that drop, shuffle, or add noise to control or exogenous inputs consistently degrade NH4 and PO4 performance, with the largest deterioration observed when exogenous signals are removed, showing that the model captures meaningful dependencies. We conclude with practical guidance for deployment: evaluate performance beyond MAE using task-oriented and visual checks, include exogenous drivers, and balance computational cost against robustness to structured outages.
Authors: Shaocong Wang, Tong Liu, Yihan Li, Ming Li, Kairui Wen, Pei Yang, Wenqi Ji, Minjing Yu, Yong-Jin Liu
Abstract: Recent advances in self-supervised learning for EEG representation have largely relied on masked reconstruction, where models are trained to recover randomly masked signal segments. While effective at modeling local dependencies, such objectives are inherently limited in capturing the global dynamics and long-range dependencies essential for characterizing neural activity. To address this limitation, we propose EEGDM, a novel self-supervised framework that leverages latent diffusion models to generate EEG signals as an objective. Unlike masked reconstruction, diffusion-based generation progressively denoises signals from noise to realism, compelling the model to capture holistic temporal patterns and cross-channel relationships. Specifically, EEGDM incorporates an EEG encoder that distills raw signals and their channel augmentations into a compact representation, acting as conditional information to guide the diffusion model for generating EEG signals. This design endows EEGDM with a compact latent space, which not only offers ample control over the generative process but also can be leveraged for downstream tasks. Experimental results show that EEGDM (1) reconstructs high-quality EEG signals, (2) learns robust representations, and (3) achieves competitive performance across diverse downstream tasks, thus exploring a new direction for self-supervised EEG representation learning.
Authors: Ziyi Liu, Firas Gabetni, Awais Hussain Sani, Xi Wang, Soobash Daiboo, Gaetan Brison, Gianni Franchi, Vicky Kalogeiton
Abstract: We introduce FakeParts, a new class of deepfakes characterized by subtle, localized manipulations to specific spatial regions or temporal segments of otherwise authentic videos. Unlike fully synthetic content, these partial manipulations - ranging from altered facial expressions to object substitutions and background modifications - blend seamlessly with real elements, making them particularly deceptive and difficult to detect. To address the critical gap in detection, we present FakePartsBench, the first large-scale benchmark specifically designed to capture the full spectrum of partial deepfakes. Comprising over 81K (including 44K FakeParts) videos with pixel- and frame-level manipulation annotations, our dataset enables comprehensive evaluation of detection methods. Our user studies demonstrate that FakeParts reduces human detection accuracy by up to 26% compared to traditional deepfakes, with similar performance degradation observed in state-of-the-art detection models. This work identifies an urgent vulnerability in current detectors and provides the necessary resources to develop methods robust to partial manipulations.
Authors: Li S. Yifei, Allen Chang, Chaitanya Malaviya, Mark Yatskar
Abstract: Evaluating long-form responses to research queries heavily relies on expert annotators, restricting attention to areas like AI where researchers can conveniently enlist colleagues. Yet, research expertise is abundant: survey articles consolidate knowledge spread across the literature. We introduce ResearchQA, a resource for evaluating LLM systems by distilling survey articles from 75 research fields into 21K queries and 160K rubric items. Queries and rubrics are jointly derived from survey sections, where rubric items list query-specific answer evaluation criteria, i.e., citing papers, making explanations, and describing limitations. 31 Ph.D. annotators in 8 fields judge that 90% of queries reflect Ph.D. information needs and 87% of rubric items warrant emphasis of a sentence or longer. We leverage ResearchQA to evaluate 18 systems in 7.6K head-to-heads. No parametric or retrieval-augmented system we evaluate exceeds 70% on covering rubric items, and the highest-ranking system shows 75% coverage. Error analysis reveals that the highest-ranking system fully addresses less than 11% of citation rubric items, 48% of limitation items, and 49% of comparison items. We release our data to facilitate more comprehensive multi-field evaluations.
Authors: Tasnuva Chowdhury, Tadashi Maeno, Fatih Furkan Akman, Joseph Boudreau, Sankha Dutta, Shengyu Feng, Adolfy Hoisie, Kuan-Chieh Hsu, Raees Khan, Jaehyung Kim, Ozgur O. Kilic, Scott Klasky, Alexei Klimentov, Tatiana Korchuganova, Verena Ingrid Martinez Outschoorn, Paul Nilsson, David K. Park, Norbert Podhorszki, Yihui Ren, John Rembrandt Steele, Fr\'ed\'eric Suter, Sairam Sri Vatsavai, Torre Wenaus, Wei Yang, Yiming Yang, Shinjae Yoo
Abstract: The collaborative efforts of large communities in science experiments, often comprising thousands of global members, reflect a monumental commitment to exploration and discovery. Recently, advanced and complex data processing has gained increasing importance in science experiments. Data processing workflows typically consist of multiple intricate steps, and the precise specification of resource requirements is crucial for each step to allocate optimal resources for effective processing. Estimating resource requirements in advance is challenging due to a wide range of analysis scenarios, varying skill levels among community members, and the continuously increasing spectrum of computing options. One practical approach to mitigate these challenges involves initially processing a subset of each step to measure precise resource utilization from actual processing profiles before completing the entire step. While this two-staged approach enables processing on optimal resources for most of the workflow, it has drawbacks such as initial inaccuracies leading to potential failures and suboptimal resource usage, along with overhead from waiting for initial processing completion, which is critical for fast-turnaround analyses. In this context, our study introduces a novel pipeline of machine learning models within a comprehensive workflow management system, the Production and Distributed Analysis (PanDA) system. These models employ advanced machine learning techniques to predict key resource requirements, overcoming challenges posed by limited upfront knowledge of characteristics at each step. Accurate forecasts of resource requirements enable informed and proactive decision-making in workflow management, enhancing the efficiency of handling diverse, complex workflows across heterogeneous resources.
Authors: Nishank Singla, Krisztian Koos, Farzin Haddadpour, Amin Honarmandi Shandiz, Lovish Chum, Xiaojian Xu, Qing Jin, Erhan Bas
Abstract: X-ray imaging is a ubiquitous in radiology, yet most existing AI foundation models are limited to chest anatomy and fail to generalize across broader clinical tasks. In this work, we introduce XR-0, the multi-anatomy X-ray foundation model using self-supervised learning on a large, private dataset of 1.15 million images spanning diverse anatomical regions and evaluated across 12 datasets and 20 downstream tasks, including classification, retrieval, segmentation, localization, visual grounding, and report generation. XR-0 achieves state-of-the-art performance on most multi-anatomy tasks and remains competitive on chest-specific benchmarks. Our results demonstrate that anatomical diversity and supervision are critical for building robust, general-purpose medical vision models, paving the way for scalable and adaptable AI systems in radiology.
Authors: Keyu An, Yanni Chen, Zhigao Chen, Chong Deng, Zhihao Du, Changfeng Gao, Zhifu Gao, Bo Gong, Xiangang Li, Yabin Li, Ying Liu, Xiang Lv, Yunjie Ji, Yiheng Jiang, Bin Ma, Haoneng Luo, Chongjia Ni, Zexu Pan, Yiping Peng, Zhendong Peng, Peiyao Wang, Hao Wang, Haoxu Wang, Wen Wang, Wupeng Wang, Yuzhong Wu, Biao Tian, Zhentao Tan, Nan Yang, Bin Yuan, Jieping Ye, Jixing Yu, Qinglin Zhang, Kun Zou, Han Zhao, Shengkui Zhao, Jingren Zhou, Yanqiao Zhu
Abstract: In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model size scaling, and deep integration with large language models (LLMs). However, LLMs are prone to hallucination, which can significantly degrade user experience in real-world ASR applications. In this paper, we present Fun-ASR, a large-scale, LLM-based ASR system that synergistically combines massive data, large model capacity, LLM integration, and reinforcement learning to achieve state-of-the-art performance across diverse and complex speech recognition scenarios. Moreover, Fun-ASR is specifically optimized for practical deployment, with enhancements in streaming capability, noise robustness, code-switching, hotword customization, and satisfying other real-world application requirements. Experimental results show that while most LLM-based ASR systems achieve strong performance on open-source benchmarks, they often underperform on real industry evaluation sets. Thanks to production-oriented optimizations, Fun-ASR achieves state-of-the-art performance on real application datasets, demonstrating its effectiveness and robustness in practical settings. The code and models are accessible at https://github.com/FunAudioLLM/Fun-ASR .
Authors: Xiao Zhang, Zengzhe Chen, Yuan Yuan, Yifei Zou, Fuzhen Zhuang, Wenyu Jiao, Yuke Wang, Dongxiao Yu
Abstract: The rise of cloud-device collaborative computing has enabled intelligent services to be delivered across distributed edge devices while leveraging centralized cloud resources. In this paradigm, federated learning (FL) has become a key enabler for privacy-preserving model training without transferring raw data from edge devices to the cloud. However, with the continuous emergence of new data and increasing model diversity, traditional federated learning faces significant challenges, including inherent issues of data heterogeneity, model heterogeneity and catastrophic forgetting, along with new challenge of knowledge misalignment. In this study, we introduce FedDCL, a novel framework designed to enable data-free continual learning of the server model in a model-heterogeneous federated setting. We leverage pre-trained diffusion models to extract lightweight class-specific prototypes, which confer a threefold data-free advantage, enabling: (1) generation of synthetic data for the current task to augment training and counteract non-IID data distributions; (2) exemplar-free generative replay for retaining knowledge from previous tasks; and (3) data-free dynamic knowledge transfer from heterogeneous devices to the cloud server.Experimental results on various datasets demonstrate the effectiveness of FedDCL, showcasing its potential to enhance the generalizability and practical applicability of federated cloud-device collaboration in dynamic settings.
Authors: Yesung Cho, Sungmin Lee, Geongyu Lee, Minkyung Lee, Jongbae Park, Dongmyung Shin
Abstract: Recent studies in pathology foundation models have shown that scaling training data, diversifying cancer types, and increasing model size consistently improve their performance. However, giga-scale foundation models, which are trained on hundreds of thousands of slides covering tens of cancer types and contain billions of parameters, pose significant challenges for practical use due to their tremendous computational costs in both development and deployment. In this work, we present a novel strategy, named the G2L framework, to increase the performance of large-scale foundation models, which consist of only $15\%$ of the parameters of giga-scale models, to a comparable performance level of giga-scale models in cancer-specific tasks. Our approach applies knowledge distillation, transferring the capabilities of a giga-scale model to a large-scale model, using just 1K pathology slides of a target cancer (e.g., breast, prostate, etc.). The resulting distilled model not only outperformed state-of-the-art models of the same size (i.e., large-scale) across several benchmarks but also, interestingly, surpassed the giga-scale teacher and huge-scale models in some benchmarks. In addition, the distilled model exhibited a higher robustness index, indicating improved resilience to image variations originating from multiple institutions. These findings suggest that the proposed distillation approach for a large-scale model is a data- and parameter-efficient way to achieve giga-scale-level performance for cancer-specific applications without prohibitive computational burden.
Authors: Haoran Sun, Chen Cai, Huiping Zhuang, Kong Aik Lee, Lap-Pui Chau, Yi Wang
Abstract: The rapid development of deepfake video technology has not only facilitated artistic creation but also made it easier to spread misinformation. Traditional deepfake video detection (DVD) methods face issues such as a lack of transparency in their principles and insufficient generalization capabilities to cope with evolving forgery techniques. This highlights an urgent need for detectors that can identify forged content and provide verifiable reasoning explanations. This paper proposes the explainable deepfake video detection (EDVD) task and designs the EDVD-LLaMA multimodal, a large language model (MLLM) reasoning framework, which provides traceable reasoning processes alongside accurate detection results and trustworthy explanations. Our approach first incorporates a Spatio-Temporal Subtle Information Tokenization (ST-SIT) to extract and fuse global and local cross-frame deepfake features, providing rich spatio-temporal semantic information input for MLLM reasoning. Second, we construct a Fine-grained Multimodal Chain-of-Thought (Fg-MCoT) mechanism, which introduces facial feature data as hard constraints during the reasoning process to achieve pixel-level spatio-temporal video localization, suppress hallucinated outputs, and enhance the reliability of the chain of thought. In addition, we build an Explainable Reasoning FF++ dataset (ER-FF++set), leveraging structured data to annotate videos and ensure quality control, thereby supporting dual supervision for reasoning and detection. Extensive experiments demonstrate that EDVD-LLaMA achieves outstanding performance and robustness in terms of detection accuracy, explainability, and its ability to handle cross-forgery methods and cross-dataset scenarios. Compared to previous DVD methods, it provides a more explainable and superior solution. The project page is available at: https://11ouo1.github.io/edvd-llama/.
Authors: Heming Zou, Yixiu Mao, Yun Qu, Qi Wang, Xiangyang Ji
Abstract: Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks. In practice, SFT on a full dataset is computationally expensive and sometimes suffers from overfitting or bias amplification. This facilitates the rise of data curation in SFT, which prioritizes the most valuable data to optimze. This work studies the online batch selection family that dynamically scores and filters samples during the training process. However, existing popular methods often (i) rely merely on the utility of data to select a subset while neglecting other crucial factors like diversity, (ii) rely on external resources such as reference models or validation sets, and (iii) incur extra training time over full-dataset training. To address these limitations, this work develops \textbf{UDS (Utility-Diversity Sampling)}, a framework for efficient online batch selection in SFT. UDS leverages the nuclear norm of the logits matrix to capture both data utility and intra-sample diversity, while estimating inter-sample diversity through efficient low-dimensional embedding comparisons with a lightweight memory buffer of historical samples. Such a design eliminates the need for external resources and unnecessary backpropagation, securing computational efficiency. Experiments on multiple benchmarks demonstrate that UDS consistently outperforms state-of-the-art online batch selection methods under varying data budgets, and significantly reduces training time compared to full-dataset fine-tuning. Code is available at https://github.com/gfyddha/UDS.
Authors: Kihyun Na, Gyuhwan Park, Injung Kim
Abstract: License plate image restoration is important not only as a preprocessing step for license plate recognition but also for enhancing evidential value, improving visual clarity, and enabling broader reuse of license plate images. We propose a novel diffusion-based framework with character-level guidance, CharDiff-LP, which effectively restores and recognizes severely degraded license plate images captured under realistic conditions. CharDiff-LP leverages fine-grained character-level priors extracted through external segmentation and Optical Character Recognition (OCR) modules tailored for low-quality license plate images. For precise and focused guidance, CharDiff-LP incorporates a novel Character-guided Attention through Region-wise Masking (CHARM) module, which ensures that each character's guidance is restricted to its own region, thereby avoiding interference with other regions. In experiments, CharDiff-LP significantly outperformed baseline restoration models in both restoration quality and recognition accuracy, achieving a 28.3% relative reduction in character error rate (CER) on the Roboflow-LP dataset compared with the best-performing baseline.
Authors: Bailey Trang, Parham Saremi, Alan Q. Wang, Fangrui Huang, Zahra TehraniNasab, Amar Kumar, Tal Arbel, Li Fei-Fei, Ehsan Adeli
Abstract: Capturing diversity is crucial in conditional and prompt-based image generation, particularly when conditions contain uncertainty that can lead to multiple plausible outputs. To generate diverse images reflecting this diversity, traditional methods often modify random seeds, making it difficult to discern meaningful differences between samples, or diversify the input prompt, which is limited in verbally interpretable diversity. We propose Rainbow, a novel conditional image generation framework, applicable to any pretrained conditional generative model, that addresses inherent condition/prompt uncertainty and generates diverse plausible images. Rainbow is based on a simple yet effective idea: decomposing the input condition into diverse latent representations, each capturing an aspect of the uncertainty and generating a distinct image. First, we integrate a latent graph, parameterized by Generative Flow Networks (GFlowNets), into the prompt representation computation. Second, leveraging GFlowNets' advanced graph sampling capabilities to capture uncertainty and output diverse trajectories over the graph, we produce multiple trajectories that collectively represent the input condition, leading to diverse condition representations and corresponding output images. Evaluations on natural image and medical image datasets demonstrate Rainbow's improvement in both diversity and fidelity across image synthesis, image generation, and counterfactual generation tasks.
Authors: Anne Gagneux, S\'egol\`ene Martin, R\'emi Gribonval, Mathurin Massias
Abstract: Flow matching has achieved remarkable success, yet the factors influencing the quality of its generation process remain poorly understood. In this work, we adopt a denoising perspective and design a framework to empirically probe the generation process. Laying down the formal connections between flow matching models and denoisers, we provide a common ground to compare their performances on generation and denoising. This enables the design of principled and controlled perturbations to influence sample generation: noise and drift. This leads to new insights on the distinct dynamical phases of the generative process, enabling us to precisely characterize at which stage of the generative process denoisers succeed or fail and why this matters.
Authors: Seonggyun Lee, Sungjun Lim, Seojin Park, Soeun Cheon, Kyungwoo Song
Abstract: The field of preference optimization has made outstanding contributions to the alignment of language models with human preferences. Despite these advancements, recent methods still rely heavily on substantial paired (labeled) feedback data, leading to substantial resource expenditures. To address these challenges, we study the problem of Semi-Supervised Preference Optimization (SSPO) in which the idea is to learn from both a small number of pairwise preference labels and a large pool of unpaired samples simultaneously. Our key theoretical contribution proves the existence of an optimal reward threshold capable of separating winning and losing responses with high probability, which enables a principled pseudo-labeling of unpaired data. By leveraging these pseudo-labels, SSPO effectively distills latent preferences from large-scale unpaired data, thus maintaining human alignment while drastically reducing acquisition costs. Extensive experiments across datasets validate this remarkable data efficiency; for instance, SSPO trained with Mistral-7B-Instruct on just 1% of UltraFeedback consistently surpasses strong baselines trained on 10% of UltraFeedback.
Authors: Xuancun Lu, Jiaxiang Chen, Shilin Xiao, Zizhi Jin, Zhangrui Chen, Hanwen Yu, Bohan Qian, Ruochen Zhou, Xiaoyu Ji, Wenyuan Xu
Abstract: Vision-Language-Action (VLA) models revolutionize robotic systems by enabling end-to-end perception-to-action pipelines that integrate multiple sensory modalities, such as visual signals processed by cameras and auditory signals captured by microphones. This multi-modality integration allows VLA models to interpret complex, real-world environments using diverse sensor data streams. Given the fact that VLA-based systems heavily rely on the sensory input, the security of VLA models against physical-world sensor attacks remains critically underexplored. To address this gap, we present the first systematic study of physical sensor attacks against VLAs, quantifying the influence of sensor attacks and investigating the defenses for VLA models. We introduce a novel "Real-Sim-Real" framework that automatically simulates physics-based sensor attack vectors, including six attacks targeting cameras and two targeting microphones, and validates them on real robotic systems. Through large-scale evaluations across various VLA architectures and tasks under varying attack parameters, we demonstrate significant vulnerabilities, with susceptibility patterns that reveal critical dependencies on task types and model designs. We further develop an adversarial-training-based defense that enhances VLA robustness against out-of-distribution physical perturbations caused by sensor attacks while preserving model performance. Our findings expose an urgent need for standardized robustness benchmarks and mitigation strategies to secure VLA deployments in safety-critical environments.
Authors: Asmit Bandyopadhyay, Anindita Das Bhattacharjee, Rakesh Das
Abstract: Hyperspectral image (HSI) classification faces critical challenges, including high spectral dimensionality, complex spectral-spatial correlations, and limited training samples with severe class imbalance. While CNNs excel at local feature extraction and transformers capture long-range dependencies, their isolated application yields suboptimal results due to quadratic complexity and insufficient inductive biases. We propose CLAReSNet (Convolutional Latent Attention Residual Spectral Network), a hybrid architecture that integrates multi-scale convolutional extraction with transformer-style attention via an adaptive latent bottleneck. The model employs a multi-scale convolutional stem with deep residual blocks and an enhanced Convolutional Block Attention Module for hierarchical spatial features, followed by spectral encoder layers combining bidirectional RNNs (LSTM/GRU) with Multi-Scale Spectral Latent Attention (MSLA). MSLA reduces complexity from $\mathcal{O}(T^2D)$ to $\mathcal{O}(T\log(T)D)$ by adaptive latent token allocation (8-64 tokens) that scales logarithmically with the sequence length. Hierarchical cross-attention fusion dynamically aggregates multi-level representations for robust classification. Experiments conducted on the Indian Pines and Salinas datasets show state-of-the-art performance, achieving overall accuracies of 99.71% and 99.96%, significantly surpassing HybridSN, SSRN, and SpectralFormer. The learned embeddings exhibit superior inter-class separability and compact intra-class clustering, validating CLAReSNet's effectiveness under severe class imbalance.
Authors: Christopher Cruz
Abstract: Large language models (LLMs) are increasingly deployed in multi-turn dialogue settings, yet their behavior remains bottlenecked by naive history management strategies. Replaying the full conversation at every turn is simple but costly, while recency-based truncation or static summarization often causes early, high-impact user constraints to drift out of effective context. As a result, models may retain text without reliably applying it when it matters. We present Adaptive Focus Memory (AFM), a lightweight context management system that dynamically assigns each past message one of three fidelity levels: Full, Compressed, or Placeholder, based on semantic relevance, temporal decay, and importance classification. AFM packs messages chronologically under a fixed token budget, preserving critical constraints at high fidelity while allowing low-importance context to degrade gracefully. We evaluate AFM on two multi-turn dialogue benchmarks designed to stress long-horizon constraint preservation: a safety-critical travel scenario involving a user with a severe peanut allergy, and a policy-critical tax compliance scenario involving an illegal evasion request. Under strict grading that requires both explicit constraint recall and appropriately conditioned generation, AFM succeeds in 83.3 percent of allergy runs where all baseline strategies fail, and preserves correct refusal behavior on the tax benchmark. These results demonstrate that effective dialogue memory requires more than retaining prior text. Selectively allocating fidelity across past messages enables reliable constraint preservation under bounded context growth, without modifying model weights or introducing external retrieval infrastructure. We release an open-source implementation of AFM compatible with OpenAI-style chat APIs to support reproducible research and practical deployment.
Authors: Riad Ahmed Anonto, Md Labid Al Nahiyan, Md Tanvir Hassan
Abstract: Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a model accepts one phrasing of an intent but rejects a close paraphrase. This gap limits diagnosis and tuning. We introduce "semantic confusion," a failure mode that captures such local inconsistency, and a framework to measure it. We build ParaGuard, a 10k-prompt corpus of controlled paraphrase clusters that hold intent fixed while varying surface form. We then propose three model-agnostic metrics at the token level: Confusion Index, Confusion Rate, and Confusion Depth. These metrics compare each refusal to its nearest accepted neighbors and use token embeddings, next-token probabilities, and perplexity signals. Experiments across diverse model families and deployment guards show that global false-rejection rate hides critical structure. Our metrics reveal globally unstable boundaries in some settings, localized pockets of inconsistency in others, and cases where stricter refusal does not increase inconsistency. We also show how confusion-aware auditing separates how often a system refuses from how sensibly it refuses. This gives developers a practical signal to reduce false refusals while preserving safety.
Authors: Karthik Prabhakar, Durgamadhab Mishra
Abstract: Modern machine learning training is increasingly bottlenecked by data I/O rather than compute. GPUs often sit idle at below 50% utilization waiting for data. This paper presents a machine learning approach to predict I/O performance and recommend optimal storage configurations for ML training pipelines. We collected 141 observations through systematic benchmarking across different storage backends (NVMe SSD, network-attached storage, in-memory filesystems), data formats, and access patterns, covering both low-level I/O operations and full training pipelines. After evaluating seven regression models and three classification approaches, XGBoost achieved the best performance with R-squared of 0.991, predicting I/O throughput within 11.8% error on average. Feature importance analysis revealed that throughput metrics and batch size are the primary performance drivers. This data-driven approach can reduce configuration time from days of trial-and-error to minutes of predictive recommendation. The methodology is reproducible and extensible to other resource management problems in ML systems. Code and data are available at https://github.com/knkarthik01/gpu_storage_ml_project
Authors: Boxuan Lyu, Haiyue Song, Hidetaka Kamigaito, Chenchen Ding, Hideki Tanaka, Masao Utiyama, Kotaro Funakoshi, Manabu Okumura
Abstract: Error Span Detection (ESD) extends automatic machine translation (MT) evaluation by localizing translation errors and labeling their severity. Current generative ESD methods typically use Maximum a Posteriori (MAP) decoding, assuming that the model-estimated probabilities are perfectly correlated with similarity to the human annotation, but we often observe higher likelihood assigned to an incorrect annotation than to the human one. We instead apply Minimum Bayes Risk (MBR) decoding to generative ESD. We use a sentence- or span-level similarity function for MBR decoding, which selects candidate hypotheses based on their approximate similarity to the human annotation. Experimental results on the WMT24 Metrics Shared Task show that MBR decoding significantly improves span-level performance and generally matches or outperforms MAP at the system and sentence levels. To reduce the computational cost of MBR decoding, we further distill its decisions into a model decoded via greedy search, removing the inference-time latency bottleneck.
Authors: Ryan Banks, Camila Lindoni Azevedo, Hongying Tang, Yunpeng Li
Abstract: Accurate understanding of anatomical structures is essential for reliably staging certain dental diseases. A way of introducing this within semantic segmentation models is by utilising hierarchy-aware methodologies. However, existing hierarchy-aware segmentation methods largely encode anatomical structure through the loss functions, providing weak and indirect supervision. We introduce a general framework that embeds an explicit anatomical hierarchy into semantic segmentation by coupling a recurrent, level-wise prediction scheme with restrictive output heads and top-down feature conditioning. At each depth of the class tree, the backbone is re-run on the original image concatenated with logits from the previous level. Child class features are conditioned using Feature-wise Linear Modulation of their parent class probabilities, to modulate child feature spaces for fine grained detection. A probabilistic composition rule enforces consistency between parent and descendant classes. Hierarchical loss combines per-level class weighted Dice and cross entropy loss and a consistency term loss, ensuring parent predictions are the sum of their children. We validate our approach on our proposed dataset, TL-pano, containing 194 panoramic radiographs with dense instance and semantic segmentation annotations, of tooth layers and alveolar bone. Utilising UNet and HRNet as donor models across a 5-fold cross validation scheme, the hierarchical variants consistently increase IoU, Dice, and recall, particularly for fine-grained anatomies, and produce more anatomically coherent masks. However, hierarchical variants also demonstrated increased recall over precision, implying increased false positives. The results demonstrate that explicit hierarchical structuring improves both performance and clinical plausibility, especially in low data dental imaging regimes.
Authors: Donghyuk Kim, Sejeong Yang, Wonjin Shin, Joo-Young Kim
Abstract: Streaming video large language models (LLMs) are increasingly used for real-time multimodal tasks such as video captioning, question answering, conversational agents, and augmented reality. However, these models face fundamental memory and computational challenges because their key-value (KV) caches grow substantially with continuous streaming video input. This process requires an iterative prefill stage, which is a unique feature of streaming video LLMs. Due to its iterative prefill stage, it suffers from significant limitations, including extensive computation, substantial data transfer, and degradation in accuracy. Crucially, this issue is exacerbated for edge deployment, which is the primary target for these models. In this work, we propose V-Rex, the first software-hardware co-designed accelerator that comprehensively addresses both algorithmic and hardware bottlenecks in streaming video LLM inference. At its core, V-Rex introduces ReSV, a training-free dynamic KV cache retrieval algorithm. ReSV exploits temporal and spatial similarity-based token clustering to reduce excessive KV cache memory across video frames. To fully realize these algorithmic benefits, V-Rex offers a compact, low-latency hardware accelerator with a dynamic KV cache retrieval engine (DRE), featuring bit-level and early-exit based computing units. V-Rex achieves unprecedented real-time of 3.9-8.3 FPS and energy-efficient streaming video LLM inference on edge deployment with negligible accuracy loss. While DRE only accounts for 2.2% power and 2.0% area, the system delivers 1.9-19.7x speedup and 3.1-18.5x energy efficiency improvements over AGX Orin GPU. This work is the first to comprehensively tackle KV cache retrieval across algorithms and hardware, enabling real-time streaming video LLM inference on resource-constrained edge devices.
Authors: Kei Saito
Abstract: Current artificial intelligence systems, despite remarkable capabilities in text generation and pattern recognition, exhibit a fundamental architectural limitation: they resolve ambiguity prematurely. This premature semantic collapse -- the tendency to collapse multiple valid interpretations into a single output -- stems from classical identity assumptions embedded in standard neural architectures. We propose Non-Resolution Reasoning (NRR), a computational framework that treats ambiguity retention as a valid reasoning mode rather than a defect to be eliminated. NRR introduces three core principles: (1) Non-Identity ($A \neq A$) -- the same symbol refers to different entities across contexts; (2) Approximate Identity ($A \approx A$) -- entities share partial structural overlap without being identical; and (3) Non-Resolution -- conflicting interpretations can coexist without forced convergence. We formalize these principles through three architectural components: Multi-Vector Embeddings for context-dependent representation, Non-Collapsing Attention for parallel interpretation retention, and Contextual Identity Tracking (CIT) for maintaining $A \neq A$ across inference. We demonstrate NRR's advantages through case studies in paradox handling, creative generation, and context-dependent reasoning. Crucially, we provide a minimal empirical validation on a synthetic context-shift task where an NRR-lite model achieves 90.9% out-of-distribution accuracy compared to 9.1% for standard architectures, demonstrating that ambiguity preservation enables structural generalization. NRR challenges the assumption that meaning must collapse to be useful, offering a foundation for AI systems capable of sophisticated ambiguity handling and creative reasoning. The question is not whether AI should resolve ambiguity, but when, how, and under whose control.
Authors: Wenbo Tian, Ruting Lin, Hongxian Zheng, Yaodong Yang, Geng Wu, Zihao Zhang, Zhang Zhang
Abstract: Existing intelligent sports analysis systems mainly focus on "scoring and visualization," often lacking automatic performance diagnosis and interpretable training guidance. Recent advances in Large Language Models (LLMs) and motion analysis techniques provide new opportunities to address the above limitations. In this paper, we propose SportsGPT, an LLM-driven framework for interpretable sports motion assessment and training guidance, which establishes a closed loop from motion time-series input to professional training guidance. First, given a set of high-quality target models, we introduce MotionDTW, a two-stage time series alignment algorithm designed for accurate keyframe extraction from skeleton-based motion sequences. Subsequently, we design a Knowledge-based Interpretable Sports Motion Assessment Model (KISMAM) to obtain a set of interpretable assessment metrics (e.g., insufficient extension) by contrasting the keyframes with the target models. Finally, we propose SportsRAG, a RAG-based training guidance model built upon Qwen3. Leveraging a 6B-token knowledge base, it prompts the LLM to generate professional training guidance by retrieving domain-specific QA pairs. Experimental results demonstrate that MotionDTW significantly outperforms traditional methods with lower temporal error and higher IoU scores. Furthermore, ablation studies validate the KISMAM and SportsRAG, confirming that SportsGPT surpasses general LLMs in diagnostic accuracy and professionalism.
Authors: Audrey Cheng, Shu Liu, Melissa Pan, Zhifei Li, Shubham Agarwal, Mert Cemri, Bowen Wang, Alexander Krentsel, Tian Xia, Jongseok Park, Shuo Yang, Jeff Chen, Lakshya Agrawal, Ashwin Naren, Shulu Li, Ruiying Ma, Aditya Desai, Jiarong Xing, Koushik Sen, Matei Zaharia, Ion Stoica
Abstract: Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems naturally admit such verifiers: candidates can be implemented in real systems or simulators and evaluated against predefined workloads. We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems (ADRS). Using several open-source ADRS instances (i.e., OpenEvolve, GEPA, and ShinkaEvolve), we demonstrate across ten case studies (e.g., multi-region cloud scheduling, mixture-of-experts load balancing, LLM-based SQL, transaction scheduling) that ADRS-generated solutions can match or even outperform human state-of-the-art designs. Based on these findings, we outline best practices (e.g., level of prompt specification, amount of feedback, robust evaluation) for effectively using ADRS, and we discuss future research directions and their implications. Although we do not yet have a universal recipe for applying ADRS across all of systems research, we hope our preliminary findings, together with the challenges we identify, offer meaningful guidance for future work as researcher effort shifts increasingly toward problem formulation and strategic oversight. Note: This paper is an extension of our prior work [14]. It adds extensive evaluation across multiple ADRS frameworks and provides deeper analysis and insights into best practices.
Authors: Debu Sinha
Abstract: Retrieval-Augmented Generation (RAG) systems remain susceptible to hallucinations despite grounding in retrieved evidence. While current detection methods leverage embedding similarity and natural language inference (NLI), their reliability in safety-critical settings remains unproven. We apply conformal prediction to RAG hallucination detection, transforming heuristic scores into decision sets with finite-sample coverage guarantees (1-alpha). Using calibration sets of n=600, we demonstrate a fundamental dichotomy: on synthetic hallucinations (Natural Questions), embedding methods achieve 95% coverage with 0% False Positive Rate (FPR). However, on real hallucinations from RLHF-aligned models (HaluEval), the same methods fail catastrophically, yielding 100% FPR at target coverage. We analyze this failure through the lens of distributional tails, showing that while NLI models achieve acceptable AUC (0.81), the "hardest" hallucinations are semantically indistinguishable from faithful responses, forcing conformal thresholds to reject nearly all valid outputs. Crucially, GPT-4 as a judge achieves 7% FPR (95% CI:[3.4%, 13.7%]) on the same data, proving the task is solvable via reasoning but opaque to surface-level semantics--a phenomenon we term the "Semantic Illusion."
Authors: Yuze Wu, Mo Zhu, Xingxing Li, Yuheng Du, Yuxin Fan, Wenjun Li, Zhichao Han, Xin Zhou, Fei Gao
Abstract: This paper proposes VLA-AN, an efficient and onboard Vision-Language-Action (VLA) framework dedicated to autonomous drone navigation in complex environments. VLA-AN addresses four major limitations of existing large aerial navigation models: the data domain gap, insufficient temporal navigation with reasoning, safety issues with generative action policies, and onboard deployment constraints. First, we construct a high-fidelity dataset utilizing 3D Gaussian Splatting (3D-GS) to effectively bridge the domain gap. Second, we introduce a progressive three-stage training framework that sequentially reinforces scene comprehension, core flight skills, and complex navigation capabilities. Third, we design a lightweight, real-time action module coupled with geometric safety correction. This module ensures fast, collision-free, and stable command generation, mitigating the safety risks inherent in stochastic generative policies. Finally, through deep optimization of the onboard deployment pipeline, VLA-AN achieves a robust real-time 8.3x improvement in inference throughput on resource-constrained UAVs. Extensive experiments demonstrate that VLA-AN significantly improves spatial grounding, scene reasoning, and long-horizon navigation, achieving a maximum single-task success rate of 98.1%, and providing an efficient, practical solution for realizing full-chain closed-loop autonomy in lightweight aerial robots.
Authors: Jonas Pai, Liam Achenbach, Victoriano Montesinos, Benedek Forrai, Oier Mees, Elvis Nava
Abstract: Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy must implicitly infer complex physical dynamics and temporal dependencies solely from robot trajectories. This reliance creates an unsustainable data burden, necessitating continuous, large-scale expert data collection to compensate for the lack of innate physical understanding. We contend that while vision-language pretraining effectively captures semantic priors, it remains blind to physical causality. A more effective paradigm leverages video to jointly capture semantics and visual dynamics during pretraining, thereby isolating the remaining task of low-level control. To this end, we introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations. The decoder serves as an Inverse Dynamics Model (IDM), generating low-level robot actions from the latent representation of video-space action plans. Our extensive evaluation shows that our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
Authors: Qingguo Hu, Zhenghao Lin, Ziyue Yang, Yucheng Ding, Xiao Liu, Yuting Jiang, Ruizhe Wang, Tianyu Chen, Zhongxin Guo, Yifan Xiong, Rui Gao, Lei Qu, Jinsong Su, Peng Cheng, Yeyun Gong
Abstract: Mixture-of-Experts (MoE) has emerged as a promising paradigm for foundation models due to its efficient and powerful scalability. In this work, we present Sigma-MoE-Tiny, an MoE language model that achieves the highest sparsity compared to existing open-source models. Sigma-MoE-Tiny employs fine-grained expert segmentation with up to 96 experts per layer, while activating only one expert for each token, resulting in 20B total parameters with just 0.5B activated. The major challenge introduced by such extreme sparsity lies in expert load balancing. We find that the widely-used load balancing loss tends to become ineffective in the lower layers under this setting. To address this issue, we propose a progressive sparsification schedule aiming to balance expert utilization and training stability. Sigma-MoE-Tiny is pre-trained on a diverse and high-quality corpus, followed by post-training to further unlock its capabilities. The entire training process remains remarkably stable, with no occurrence of irrecoverable loss spikes. Comprehensive evaluations reveal that, despite activating only 0.5B parameters, Sigma-MoE-Tiny achieves top-tier performance among counterparts of comparable or significantly larger scale. In addition, we provide an in-depth discussion of load balancing in highly sparse MoE models, offering insights for advancing sparsity in future MoE architectures. Project page: https://qghuxmu.github.io/Sigma-MoE-Tiny Code: https://github.com/microsoft/ltp-megatron-lm
URLs: https://qghuxmu.github.io/Sigma-MoE-Tiny, https://github.com/microsoft/ltp-megatron-lm
Authors: Oliver Stritzel, Nick H\"uhnerbein, Simon Rauch, Itzel Zarate, Lukas Fleischmann, Moike Buck, Attila Lischka, Christian Frey
Abstract: In recent years, Predictive Process Mining (PPM) techniques based on artificial neural networks have evolved as a method for monitoring the future behavior of unfolding business processes and predicting Key Performance Indicators (KPIs). However, many PPM approaches often lack reproducibility, transparency in decision making, usability for incorporating novel datasets and benchmarking, making comparisons among different implementations very difficult. In this paper, we propose SPICE, a Python framework that reimplements three popular, existing baseline deep-learning-based methods for PPM in PyTorch, while designing a common base framework with rigorous configurability to enable reproducible and robust comparison of past and future modelling approaches. We compare SPICE to original reported metrics and with fair metrics on 11 datasets.