Authors: Ilche Georgievski, Marco Aiello
Abstract: Service composition remains a central challenge in building adaptive and intelligent software systems, often constrained by limited reasoning capabilities or brittle execution mechanisms. This paper explores the integration of two emerging paradigms enabled by large language models: Large Reasoning Models (LRMs) and Large Action Models (LAMs). We argue that LRMs address the challenges of semantic reasoning and ecosystem complexity while LAMs excel in dynamic action execution and system interoperability. However, each paradigm has complementary limitations - LRMs lack grounded action capabilities, and LAMs often struggle with deep reasoning. We propose an integrated LRM-LAM architectural framework as a promising direction for advancing automated service composition. Such a system can reason about service requirements and constraints while dynamically executing workflows, thus bridging the gap between intention and execution. This integration has the potential to transform service composition into a fully automated, user-friendly process driven by high-level natural language intent.
Authors: Fatima Al-Ani, Molly Wang, Jevon Charles, Aaron Ong, Joshua Forday, Vinayak Modi
Abstract: This study focuses on the development of a simulation-driven reinforcement learning (RL) framework for optimizing routing decisions in complex queueing network systems, with a particular emphasis on manufacturing and communication applications. Recognizing the limitations of traditional queueing methods, which often struggle with dynamic, uncertain environments, we propose a robust RL approach leveraging Deep Deterministic Policy Gradient (DDPG) combined with Dyna-style planning (Dyna-DDPG). The framework includes a flexible and configurable simulation environment capable of modeling diverse queueing scenarios, disruptions, and unpredictable conditions. Our enhanced Dyna-DDPG implementation incorporates separate predictive models for next-state transitions and rewards, significantly improving stability and sample efficiency. Comprehensive experiments and rigorous evaluations demonstrate the framework's capability to rapidly learn effective routing policies that maintain robust performance under disruptions and scale effectively to larger network sizes. Additionally, we highlight strong software engineering practices employed to ensure reproducibility and maintainability of the framework, enabling practical deployment in real-world scenarios.
Authors: Alex Noviello, Claas Beger, Jacob Groner, Kevin Ellis, Weinan Sun
Abstract: Systematic compositional generalization - constructing and understanding novel combinations of known building blocks - remains a core challenge for AI systems. Human cognition achieves this flexibility via the interplay of the hippocampus (HPC) and prefrontal cortex (PFC): the hippocampus rapidly encodes episodes, and the prefrontal cortex consolidates them into reusable schemas for reasoning. Drawing on these insights, we present MIRAGE (Meta-Inference with Rules and Abstractions from Generalized Experience), a framework that achieves systematic generalization on compositional tasks. MIRAGE has two interacting modules mirroring the brain's deliberative HPC-PFC loop and intuitive neocortical pattern recognition. (1) The meta-trained Transformer Neural Decomposer, paralleling neocortical "System 1" computation, is trained on a task-agnostic stream of randomly sampled compositional grammars and applies one decomposition step per pass, with successive passes iteratively refining the sequence representation. (2) The Schema Engine, analogous to the HPC-PFC "System 2" loop, dynamically extracts, ranks, and applies reusable schemas, storing variable bindings in episodic memory and expanding them when needed. By explicitly equipping the Transformer component of MIRAGE with actively managed schematic structures, our model performs systematic compositional operations through explicit schema application and transformation, relying solely on frozen weights when solving entirely novel tasks. This approach demonstrates systematic compositional generalization on the SCAN benchmark, achieving > 99% accuracy on all task splits with only 1.19M parameters in the transformer module. Ablation studies confirm that MIRAGE's systematicity critically depends on the quality of extracted schemas and the model's iterative refinement process.
Authors: Wuhao Wang, Zhiyong Chen
Abstract: Reinforcement learning has been widely applied to robotic control, but effective policy learning under partial observability remains a major challenge, especially in high-dimensional tasks like humanoid locomotion. To date, no prior work has demonstrated stable training of humanoid policies with incomplete state information in the benchmark Gymnasium Humanoid-v4 environment. The objective in this environment is to walk forward as fast as possible without falling, with rewards provided for staying upright and moving forward, and penalties incurred for excessive actions and external contact forces. This research presents the first successful instance of learning under partial observability in this environment. The learned policy achieves performance comparable to state-of-the-art results with full state access, despite using only one-third to two-thirds of the original states. Moreover, the policy exhibits adaptability to robot properties, such as variations in body part masses. The key to this success is a novel history encoder that processes a fixed-length sequence of past observations in parallel. Integrated into a standard model-free algorithm, the encoder enables performance on par with fully observed baselines. We hypothesize that it reconstructs essential contextual information from recent observations, thereby enabling robust decision-making.
Authors: Mehrnoosh Mirtaheri, Ryan A. Rossi, Sungchul Kim, Kanak Mahadik, Tong Yu, Xiang Chen, Mohammad Rostami
Abstract: Temporal Knowledge Graph (TKG) completion models traditionally assume access to the entire graph during training. This overlooks challenges stemming from the evolving nature of TKGs, such as: (i) the model's requirement to generalize and assimilate new knowledge, and (ii) the task of managing new or unseen entities that often have sparse connections. In this paper, we present an incremental training framework specifically designed for TKGs, aiming to address entities that are either not observed during training or have sparse connections. Our approach combines a model-agnostic enhancement layer with a weighted sampling strategy, that can be augmented to and improve any existing TKG completion method. The enhancement layer leverages a broader, global definition of entity similarity, which moves beyond mere local neighborhood proximity of GNN-based methods. The weighted sampling strategy employed in training accentuates edges linked to infrequently occurring entities. We evaluate our method on two benchmark datasets, and demonstrate that our framework outperforms existing methods in total link prediction, inductive link prediction, and in addressing long-tail entities. Notably, our method achieves a 10\% improvement and a 15\% boost in MRR for these datasets. The results underscore the potential of our approach in mitigating catastrophic forgetting and enhancing the robustness of TKG completion methods, especially in an incremental training context
Authors: Shuhao Li, Weidong Yang, Yue Cui, Xiaoxing Liu, Lingkai Meng, Lipeng Ma, Fan Zhang
Abstract: Fine-grained traffic management and prediction are fundamental to key applications such as autonomous driving, lane change guidance, and traffic signal control. However, obtaining lane-level traffic data has become a critical bottleneck for data-driven models due to limitations in the types and number of sensors and issues with the accuracy of tracking algorithms. To address this, we propose the Fine-grained Road Traffic Inference (FRTI) task, which aims to generate more detailed lane-level traffic information using limited road data, providing a more energy-efficient and cost-effective solution for precise traffic management. This task is abstracted as the first scene of the spatio-temporal graph node generation problem. We designed a two-stage framework--RoadDiff--to solve the FRTI task. solve the FRTI task. This framework leverages the Road-Lane Correlation Autoencoder-Decoder and the Lane Diffusion Module to fully utilize the limited spatio-temporal dependencies and distribution relationships of road data to accurately infer fine-grained lane traffic states. Based on existing research, we designed several baseline models with the potential to solve the FRTI task and conducted extensive experiments on six datasets representing different road conditions to validate the effectiveness of the RoadDiff model in addressing the FRTI task. The relevant datasets and code are available at https://github.com/ShuhaoLii/RoadDiff.
Authors: No\'e Lallouet, Tristan Cazenave, Cyrille Enderli
Abstract: We introduce Pareto-NRPA, a new Monte-Carlo algorithm designed for multi-objective optimization problems over discrete search spaces. Extending the Nested Rollout Policy Adaptation (NRPA) algorithm originally formulated for single-objective problems, Pareto-NRPA generalizes the nested search and policy update mechanism to multi-objective optimization. The algorithm uses a set of policies to concurrently explore different regions of the solution space and maintains non-dominated fronts at each level of search. Policy adaptation is performed with respect to the diversity and isolation of sequences within the Pareto front. We benchmark Pareto-NRPA on two classes of problems: a novel bi-objective variant of the Traveling Salesman Problem with Time Windows problem (MO-TSPTW), and a neural architecture search task on well-known benchmarks. Results demonstrate that Pareto-NRPA achieves competitive performance against state-of-the-art multi-objective algorithms, both in terms of convergence and diversity of solutions. Particularly, Pareto-NRPA strongly outperforms state-of-the-art evolutionary multi-objective algorithms on constrained search spaces. To our knowledge, this work constitutes the first adaptation of NRPA to the multi-objective setting.
Authors: Xuetian Chen, Yinghao Chen, Xinfeng Yuan, Zhuo Peng, Lu Chen, Yuekeng Li, Zhoujia Zhang, Yingqian Huang, Leyan Huang, Jiaqing Liang, Tianbao Xie, Zhiyong Wu, Qiushi Sun, Biqing Qi, Bowen Zhou
Abstract: Computer-using agents have shown strong potential to boost human productivity and enable new application forms across platforms. While recent advances have led to usable applications, existing benchmarks fail to account for the internal task heterogeneity and the corresponding agent capabilities, as well as their alignment with actual user demands-hindering both targeted capability development and the reliable transition of research progress into practical deployment. To bridge the gap, we present OS-MAP, a benchmark for daily computer-using automation that organizes its 416 realistic tasks across 15 applications along two key dimensions: a five-level taxonomy of automation and a generalization scope derived from a real-world user demand hierarchy. To enable fine-grained analysis of required capabilities and alignment with real-world scenarios, OS-MAP evaluates agents along two dimensions: automation level across a five-level taxonomy, and generalization scope across a demand hierarchy. This design captures varying levels of required agent autonomy and generalization, forming a performance-generalization evaluation matrix for structured and comprehensive assessment. Experiments show that even State-of-the-Art agents with VLM backbones struggle with higher-level tasks involving perception, reasoning, and coordination-highlighting the need for a deeper understanding of current strengths and limitations to drive the future progress in computer-using agents research and deployment. All code, environments, baselines, and data are publicly available at https://github.com/OS-Copilot/OS-Map.
Authors: Jiyao Wang, Xiao Yang, Qingyong Hu, Jiankai Tang, Can Liu, Dengbo He, Yuntao Wang, Yingcong Chen, Kaishun Wu
Abstract: Robust and unobtrusive in-vehicle physiological monitoring is crucial for ensuring driving safety and user experience. While remote physiological measurement (RPM) offers a promising non-invasive solution, its translation to real-world driving scenarios is critically constrained by the scarcity of comprehensive datasets. Existing resources are often limited in scale, modality diversity, the breadth of biometric annotations, and the range of captured conditions, thereby omitting inherent real-world challenges in driving. Here, we present PhysDrive, the first large-scale multimodal dataset for contactless in-vehicle physiological sensing with dedicated consideration on various modality settings and driving factors. PhysDrive collects data from 48 drivers, including synchronized RGB, near-infrared camera, and raw mmWave radar data, accompanied with six synchronized ground truths (ECG, BVP, Respiration, HR, RR, and SpO2). It covers a wide spectrum of naturalistic driving conditions, including driver motions, dynamic natural light, vehicle types, and road conditions. We extensively evaluate both signal-processing and deep-learning methods on PhysDrive, establishing a comprehensive benchmark across all modalities, and release full open-source code with compatibility for mainstream public toolboxes. We envision PhysDrive will serve as a foundational resource and accelerate research on multimodal driver monitoring and smart-cockpit systems.
Authors: Kuncheng Zou, Jiahao Mai, Yonggang Zhang, Yuyi Wang, Ond\v{r}ej Ku\v{z}elka, Yuanhong Wang, Yi Chang
Abstract: We investigate lifted inference on ordered domains with predecessor relations, where the elements of the domain respect a total (cyclic) order, and every element has a distinct (clockwise) predecessor. Previous work has explored this problem through weighted first-order model counting (WFOMC), which computes the weighted sum of models for a given first-order logic sentence over a finite domain. In WFOMC, the order constraint is typically encoded by the linear order axiom introducing a binary predicate in the sentence to impose a linear ordering on the domain elements. The immediate and second predecessor relations are then encoded by the linear order predicate. Although WFOMC with the linear order axiom is theoretically tractable, existing algorithms struggle with practical applications, particularly when the predecessor relations are involved. In this paper, we treat predecessor relations as a native part of the axiom and devise a novel algorithm that inherently supports these relations. The proposed algorithm not only provides an exponential speedup for the immediate and second predecessor relations, which are known to be tractable, but also handles the general k-th predecessor relations. The extensive experiments on lifted inference tasks and combinatorics math problems demonstrate the efficiency of our algorithm, achieving speedups of a full order of magnitude.
Authors: Osama Almurshed, Ashish Kaushal, Asmail Muftah, Nitin Auluck, Omer Rana
Abstract: The increasing adoption of Artificial Intelligence (AI) has led to larger, more complex models with numerous parameters that require substantial computing power -- resources often unavailable in many real-world application scenarios. Our paper addresses this challenge by introducing knowledge grafting, a novel mechanism that optimizes AI models for resource-constrained environments by transferring selected features (the scion) from a large donor model to a smaller rootstock model. The approach achieves an 88.54% reduction in model size (from 64.39 MB to 7.38 MB), while improving generalization capability of the model. Our new rootstock model achieves 89.97% validation accuracy (vs. donor's 87.47%), maintains lower validation loss (0.2976 vs. 0.5068), and performs exceptionally well on unseen test data with 90.45% accuracy. It addresses the typical size vs performance trade-off, and enables deployment of AI frameworks on resource-constrained devices with enhanced performance. We have tested our approach on an agricultural weed detection scenario, however, it can be extended across various edge computing scenarios, potentially accelerating AI adoption in areas with limited hardware/software support -- by mirroring in a similar manner the horticultural grafting enables productive cultivation in challenging agri-based environments.
Authors: Achille Morenville, \'Eric Piette
Abstract: In imperfect-information games, agents must make decisions based on partial knowledge of the game state. The Belief Stochastic Game model addresses this challenge by delegating state estimation to the game model itself. This allows agents to operate on externally provided belief states, thereby reducing the need for game-specific inference logic. This paper investigates two approaches to represent beliefs in games with hidden piece identities: a constraint-based model using Constraint Satisfaction Problems and a probabilistic extension using Belief Propagation to estimate marginal probabilities. We evaluated the impact of both representations using general-purpose agents across two different games. Our findings indicate that constraint-based beliefs yield results comparable to those of probabilistic inference, with minimal differences in agent performance. This suggests that constraint-based belief states alone may suffice for effective decision-making in many settings.
Authors: Patrick Taillandier, Jean Daniel Zucker, Arnaud Grignard, Benoit Gaudou, Nghi Quang Huynh, Alexis Drogoul
Abstract: This position paper examines the use of Large Language Models (LLMs) in social simulation, analyzing both their potential and their limitations from a computational social science perspective. The first part reviews recent findings on the ability of LLMs to replicate key aspects of human cognition, including Theory of Mind reasoning and social inference, while also highlighting significant limitations such as cognitive biases, lack of true understanding, and inconsistencies in behavior. The second part surveys emerging applications of LLMs in multi-agent simulation frameworks, focusing on system architectures, scale, and validation strategies. Notable projects such as Generative Agents (Smallville) and AgentSociety are discussed in terms of their design choices, empirical grounding, and methodological innovations. Particular attention is given to the challenges of behavioral fidelity, calibration, and reproducibility in large-scale LLM-driven simulations. The final section distinguishes between contexts where LLMs, like other black-box systems, offer direct value-such as interactive simulations and serious games-and those where their use is more problematic, notably in explanatory or predictive modeling. The paper concludes by advocating for hybrid approaches that integrate LLMs into traditional agent-based modeling platforms (GAMA, Netlogo, etc), enabling modelers to combine the expressive flexibility of language-based reasoning with the transparency and analytical rigor of classical rule-based systems.
Authors: Flavio Petruzzellis, Alberto Testolin, Alessandro Sperduti
Abstract: Building neural systems that can learn to execute symbolic algorithms is a challenging open problem in artificial intelligence, especially when aiming for strong generalization and out-of-distribution performance. In this work, we introduce a general framework for learning convergent term rewriting systems using a neuro-symbolic architecture inspired by the rewriting algorithm itself. We present two modular implementations of such architecture: the Neural Rewriting System (NRS) and the Fast Neural Rewriting System (FastNRS). As a result of algorithmic-inspired design and key architectural elements, both models can generalize to out-of-distribution instances, with FastNRS offering significant improvements in terms of memory efficiency, training speed, and inference time. We evaluate both architectures on four tasks involving the simplification of mathematical formulas and further demonstrate their versatility in a multi-domain learning scenario, where a single model is trained to solve multiple types of problems simultaneously. The proposed system significantly outperforms two strong neural baselines: the Neural Data Router, a recent transformer variant specifically designed to solve algorithmic problems, and GPT-4o, one of the most powerful general-purpose large-language models. Moreover, our system matches or outperforms the latest o1-preview model from OpenAI that excels in reasoning benchmarks.
Authors: Amir Fard, Arnold X. -X. Yuan
Abstract: Budget planning and maintenance optimization are crucial for infrastructure asset management, ensuring cost-effectiveness and sustainability. However, the complexity arising from combinatorial action spaces, diverse asset deterioration, stringent budget constraints, and environmental uncertainty significantly limits existing methods' scalability. This paper proposes a Hierarchical Deep Reinforcement Learning methodology specifically tailored to multi-year infrastructure planning. Our approach decomposes the problem into two hierarchical levels: a high-level Budget Planner allocating annual budgets within explicit feasibility bounds, and a low-level Maintenance Planner prioritizing assets within the allocated budget. By structurally separating macro-budget decisions from asset-level prioritization and integrating linear programming projection within a hierarchical Soft Actor-Critic framework, the method efficiently addresses exponential growth in the action space and ensures rigorous budget compliance. A case study evaluating sewer networks of varying sizes (10, 15, and 20 sewersheds) illustrates the effectiveness of the proposed approach. Compared to conventional Deep Q-Learning and enhanced genetic algorithms, our methodology converges more rapidly, scales effectively, and consistently delivers near-optimal solutions even as network size grows.
Authors: Pingjing Yang, Jennifer Cromley, Jana Diesner
Abstract: Understanding how novices acquire and hone visual search skills is crucial for developing and optimizing training methods across domains. Network analysis methods can be used to analyze graph representations of visual expertise. This study investigates the relationship between eye-gaze movements and learning outcomes among undergraduate dentistry students who were diagnosing dental radiographs over multiple semesters. We use network analysis techniques to model eye-gaze scanpaths as directed graphs and examine changes in network metrics over time. Using time series clustering on each metric, we identify distinct patterns of visual search strategies and explore their association with students' diagnostic performance. Our findings suggest that the network metric of transition entropy is negatively correlated with performance scores, while the number of nodes and edges as well as average PageRank are positively correlated with performance scores. Changes in network metrics for individual students over time suggest a developmental shift from intermediate to expert-level processing. These insights contribute to understanding expertise acquisition in visual tasks and can inform the design of AI-assisted learning interventions.
Authors: Rizal Khoirul Anam
Abstract: The widespread adoption of large language models (LLMs) such as ChatGPT, Gemini, and DeepSeek has significantly changed how people approach tasks in education, professional work, and creative domains. This paper investigates how the structure and clarity of user prompts impact the effectiveness and productivity of LLM outputs. Using data from 243 survey respondents across various academic and occupational backgrounds, we analyze AI usage habits, prompting strategies, and user satisfaction. The results show that users who employ clear, structured, and context-aware prompts report higher task efficiency and better outcomes. These findings emphasize the essential role of prompt engineering in maximizing the value of generative AI and provide practical implications for its everyday use.
Authors: Thomas Roca, Anthony Cintron Roman, Jeh\'u Torres Vega, Marcelo Duarte, Pengce Wang, Kevin White, Amit Misra, Juan Lavista Ferres
Abstract: As AI-powered image generation improves, a key question is how well human beings can differentiate between "real" and AI-generated or modified images. Using data collected from the online game "Real or Not Quiz.", this study investigates how effectively people can distinguish AI-generated images from real ones. Participants viewed a randomized set of real and AI-generated images, aiming to identify their authenticity. Analysis of approximately 287,000 image evaluations by over 12,500 global participants revealed an overall success rate of only 62\%, indicating a modest ability, slightly above chance. Participants were most accurate with human portraits but struggled significantly with natural and urban landscapes. These results highlight the inherent challenge humans face in distinguishing AI-generated visual content, particularly images without obvious artifacts or stylistic cues. This study stresses the need for transparency tools, such as watermarks and robust AI detection tools to mitigate the risks of misinformation arising from AI-generated content
Authors: Milan Maksimovic, Anna Bohdanets, Immaculate Motsi-Omoijiade, Guido Governatori, Ivan S. Maksymov
Abstract: Prior work has demonstrated that incorporating well-known quantum tunnelling (QT) probability into neural network models effectively captures important nuances of human perception, particularly in the recognition of ambiguous objects and sentiment analysis. In this paper, we employ novel QT-based neural networks and assess their effectiveness in distinguishing customised CIFAR-format images of military and civilian vehicles, as well as sentiment, using a proprietary military-specific vocabulary. We suggest that QT-based models can enhance multimodal AI applications in battlefield scenarios, particularly within human-operated drone warfare contexts, imbuing AI with certain traits of human reasoning.
Authors: Nicholas Fidalgo, Aaron Contreras, Katherine Harvey, Johnny Ni
Abstract: This project investigates the use of multimodal AI-driven approaches to automate and enhance suspect sketching. Three pipelines were developed and evaluated: (1) baseline image-to-image Stable Diffusion model, (2) same model integrated with a pre-trained CLIP model for text-image alignment, and (3) novel approach incorporating LoRA fine-tuning of the CLIP model, applied to self-attention and cross-attention layers, and integrated with Stable Diffusion. An ablation study confirmed that fine-tuning both self- and cross-attention layers yielded the best alignment between text descriptions and sketches. Performance testing revealed that Model 1 achieved the highest structural similarity (SSIM) of 0.72 and a peak signal-to-noise ratio (PSNR) of 25 dB, outperforming Model 2 and Model 3. Iterative refinement enhanced perceptual similarity (LPIPS), with Model 3 showing improvement over Model 2 but still trailing Model 1. Qualitatively, sketches generated by Model 1 demonstrated the clearest facial features, highlighting its robustness as a baseline despite its simplicity.
Authors: Donghee Han, Daehee Kim, Minjun Lee, Daeyoung Roh, Keejun Han, Mun Yong Yi
Abstract: The rise of online learning has led to the development of various knowledge tracing (KT) methods. However, existing methods have overlooked the problem of increasing computational cost when utilizing large graphs and long learning sequences. To address this issue, we introduce Dual Graph Attention-based Knowledge Tracing (DGAKT), a graph neural network model designed to leverage high-order information from subgraphs representing student-exercise-KC relationships. DGAKT incorporates a subgraph-based approach to enhance computational efficiency. By processing only relevant subgraphs for each target interaction, DGAKT significantly reduces memory and computational requirements compared to full global graph models. Extensive experimental results demonstrate that DGAKT not only outperforms existing KT models but also sets a new standard in resource efficiency, addressing a critical need that has been largely overlooked by prior KT approaches.
Authors: Ning Liao, Xiaoxing Wang, Zehao Lin, Weiyang Guo, Feng Hong, Shixiang Song, Geng Yu, Zihua Zhao, Sitao Xie, Longxuan Wei, Xiangqi Jin, Xiaohan Qin, Jiale Ma, Kai Chen, Jiangchao Yao, Zhouhan Lin, Junchi Yan, Zhiyu Li, Feiyu Xiong, Yanfeng Wang, Linfeng Zhang
Abstract: A large language model (LLM) with knowledge in both scientific and general tasks is the foundation of science general intelligence. However, directly continued pretraining an LLM using science data usually leads to catastrophic forgetting, which indicates severe degradation in general ability. In this report, we present Innovator, which solves this problem by upcycling a pre-trained dense LLM into a fine-grained Mixtures-of-Experts model during continued pretraining, where different experts are expected to learn science knowledge in different disciplines, and a shared expert is utilized for general tasks. Innovator introduces a four-stage upcycle training paradigm: (1) Scientific Expert Induction on discipline-specific data, (2) Fine-grained Expert Splitting via FFN dimension decomposition, (3) Science-Aware Routing warmup, and (4) Generalist-Scientist Integration training on hybrid datasets. Such a paradigm enables knowledge in the general domain, and different scientific disciplines can be decoupled, avoiding the negative influence among knowledge in different domains. With 53.3B total parameters and 13.3B activated, Innovator extends Qwen2.5-7B using a shared general expert and 64 specialized scientific experts with 8 activated. Trained on 300B tokens with tri-level quality-controlled data, Innovator achieves 25% average improvement across 30 scientific tasks with a win rate as 70%, while retaining 99% performance in general tasks. Furthermore, Innovator-Reason, which is post-trained from Innovator for reasoning boosting, exhibits excellent reasoning performance in solving complex scientific problems with improvements over 30%.
Authors: Xingyu Miao, Haoran Duan, Quanhao Qian, Jiuniu Wang, Yang Long, Ling Shao, Deli Zhao, Ran Xu, Gongjie Zhang
Abstract: Spatial intelligence is emerging as a transformative frontier in AI, yet it remains constrained by the scarcity of large-scale 3D datasets. Unlike the abundant 2D imagery, acquiring 3D data typically requires specialized sensors and laborious annotation. In this work, we present a scalable pipeline that converts single-view images into comprehensive, scale- and appearance-realistic 3D representations - including point clouds, camera poses, depth maps, and pseudo-RGBD - via integrated depth estimation, camera calibration, and scale calibration. Our method bridges the gap between the vast repository of imagery and the increasing demand for spatial scene understanding. By automatically generating authentic, scale-aware 3D data from images, we significantly reduce data collection costs and open new avenues for advancing spatial intelligence. We release two generated spatial datasets, i.e., COCO-3D and Objects365-v2-3D, and demonstrate through extensive experiments that our generated data can benefit various 3D tasks, ranging from fundamental perception to MLLM-based reasoning. These results validate our pipeline as an effective solution for developing AI systems capable of perceiving, understanding, and interacting with physical environments.
Authors: \'Oscar Fern\'andez Vicente
Abstract: This thesis presents the results of a comprehensive research project focused on applying Reinforcement Learning (RL) to the problem of market making in financial markets. Market makers (MMs) play a fundamental role in providing liquidity, yet face significant challenges arising from inventory risk, competition, and non-stationary market dynamics. This research explores how RL, particularly Deep Reinforcement Learning (DRL), can be employed to develop autonomous, adaptive, and profitable market making strategies. The study begins by formulating the MM task as a reinforcement learning problem, designing agents capable of operating in both single-agent and multi-agent settings within a simulated financial environment. It then addresses the complex issue of inventory management using two complementary approaches: reward engineering and Multi-Objective Reinforcement Learning (MORL). While the former uses dynamic reward shaping to guide behavior, the latter leverages Pareto front optimization to explicitly balance competing objectives. To address the problem of non-stationarity, the research introduces POW-dTS, a novel policy weighting algorithm based on Discounted Thompson Sampling. This method allows agents to dynamically select and combine pretrained policies, enabling continual adaptation to shifting market conditions. The experimental results demonstrate that the proposed RL-based approaches significantly outperform traditional and baseline algorithmic strategies across various performance metrics. Overall, this research thesis contributes new methodologies and insights for the design of robust, efficient, and adaptive market making agents, reinforcing the potential of RL to transform algorithmic trading in complex financial systems.
Authors: Manuel de Sousa Ribeiro, Afonso Leote, Jo\~ao Leite
Abstract: Concept probing has recently gained popularity as a way for humans to peek into what is encoded within artificial neural networks. In concept probing, additional classifiers are trained to map the internal representations of a model into human-defined concepts of interest. However, the performance of these probes is highly dependent on the internal representations they probe from, making identifying the appropriate layer to probe an essential task. In this paper, we propose a method to automatically identify which layer's representations in a neural network model should be considered when probing for a given human-defined concept of interest, based on how informative and regular the representations are with respect to the concept. We validate our findings through an exhaustive empirical analysis over different neural network models and datasets.
Authors: Yang Xiao, Gen Li, Jie Ji, Ruimeng Ye, Xiaolong Ma, Bo Hui
Abstract: Machine unlearning aims to efficiently eliminate the memory about deleted data from trained models and address the right to be forgotten. Despite the success of existing unlearning algorithms, unlearning in sparse models has not yet been well studied. In this paper, we empirically find that the deleted data has an impact on the pruned topology in a sparse model. Motivated by the observation and the right to be forgotten, we define a new terminology ``un-pruning" to eliminate the impact of deleted data on model pruning. Then we propose an un-pruning algorithm to approximate the pruned topology driven by retained data. We remark that any existing unlearning algorithm can be integrated with the proposed un-pruning workflow and the error of un-pruning is upper-bounded in theory. Also, our un-pruning algorithm can be applied to both structured sparse models and unstructured sparse models. In the experiment, we further find that Membership Inference Attack (MIA) accuracy is unreliable for assessing whether a model has forgotten deleted data, as a small change in the amount of deleted data can produce arbitrary MIA results. Accordingly, we devise new performance metrics for sparse models to evaluate the success of un-pruning. Lastly, we conduct extensive experiments to verify the efficacy of un-pruning with various pruning methods and unlearning algorithms. Our code is released at https://anonymous.4open.science/r/UnlearningSparseModels-FBC5/.
URLs: https://anonymous.4open.science/r/UnlearningSparseModels-FBC5/.
Authors: Amir Fard, Arnold X. -X. Yuan
Abstract: Infrastructure asset management is essential for sustaining the performance of public infrastructure such as road networks, bridges, and utility networks. Traditional maintenance and rehabilitation planning methods often face scalability and computational challenges, particularly for large-scale networks with thousands of assets under budget constraints. This paper presents a novel deep reinforcement learning (DRL) framework that optimizes asset management strategies for large infrastructure networks. By decomposing the network-level Markov Decision Process (MDP) into individual asset-level MDPs while using a unified neural network architecture, the proposed framework reduces computational complexity, improves learning efficiency, and enhances scalability. The framework directly incorporates annual budget constraints through a budget allocation mechanism, ensuring maintenance plans are both optimal and cost-effective. Through a case study on a large-scale pavement network of 68,800 segments, the proposed DRL framework demonstrates significant improvements over traditional methods like Progressive Linear Programming and genetic algorithms, both in efficiency and network performance. This advancement contributes to infrastructure asset management and the broader application of reinforcement learning in complex, large-scale environments.
Authors: Serban C. Tudosie, Valerio Gandolfi, Shivaprasad Varakkoth, Andrea Farina, Cosimo D'Andrea, Simon Arridge
Abstract: Single-pixel imaging has emerged as a key technique in fluorescence microscopy, where fast acquisition and reconstruction are crucial. In this context, images are reconstructed from linearly compressed measurements. In practice, total variation minimisation is still used to reconstruct the image from noisy measurements of the inner product between orthogonal sampling pattern vectors and the original image data. However, data can be leveraged to learn the measurement vectors and the reconstruction process, thereby enhancing compression, reconstruction quality, and speed. We train an autoencoder through self-supervision to learn an encoder (or measurement matrix) and a decoder. We then test it on physically acquired multispectral and intensity data. During acquisition, the learned encoder becomes part of the physical device. Our approach can enhance single-pixel imaging in fluorescence microscopy by reducing reconstruction time by two orders of magnitude, achieving superior image quality, and enabling multispectral reconstructions. Ultimately, learned single-pixel fluorescence microscopy could advance diagnosis and biological research, providing multispectral imaging at a fraction of the cost.
Authors: V\'ictor Gallego
Abstract: Language models (LMs) are susceptible to in-context reward hacking, where they exploit flaws in tainted or faulty written specifications or rubrics to achieve high scores without fulfilling the user's true intent. We introduce Specification Self-Correction (SSC), a novel, test-time framework that enables an LM to identify and correct flaws within its own guiding specification. SSC employs a multi-step inference process where the model first generates a response based on a potentially tainted specification, critiques its output, and then revises the specification itself to remove the exploitable loophole. A final, more robust response is then generated using this self-corrected specification. Across experiments spanning creative writing and agentic coding tasks with several LMs, we demonstrate that while models initially game tainted specifications in 50-70\% of cases, the SSC process reduces this vulnerability by over 90\%. This dynamic repair occurs at inference time, requires no weight modification, and leads to more robustly aligned model behavior. Code at https://github.com/vicgalle/specification-self-correction .
URLs: https://github.com/vicgalle/specification-self-correction
Authors: Chandra Maddila, Adam Tait, Claire Chang, Daniel Cheng, Nauman Ahmad, Vijayaraghavan Murali, Marshall Roch, Arnaud Avondet, Aaron Meltzer, Victor Montalvao, Michael Hopko, Chris Waterson, Parth Thakkar, Renuka Fernandez, Kristian Kristensen, Sivan Barzily, Sherry Chen, Rui Abreu, Nachiappan Nagappan, Payam Shodjai, Killian Murphy, James Everingham, Aparna Ramani, Peter C. Rigby
Abstract: Aim: With the advent of LLMs, sophisticated agentic program repair has become viable at large organizations with large codebases. In this work, we develop an Engineering Agent that fixes the source code based on test failures at scale across diverse software offerings internally. Method: Using Llama as the base, we employ the ReAct harness to develop an agent. We start with a test failure that was triaged by a rule-based test failure bot. We then set up an agentic harness and allow the agent to reason and run a set of 15 actions from reading a file to generating a patch. We provide feedback to the agent through static analysis and test failures so it can refine its solution. We leverage an LLM-as-a-Judge to ensure that the patch conforms to the standards followed by a human review to land fixes. Benchmark Findings: We curated offline benchmarks for our patch generator, the Engineering Agent loop, and the LLM-as-a-Judge. In offline evaluations we found that a specialized 70B model is highly competitive with the much larger but vanilla Llama-405B. In an ablation study, we found that the ReAct harness (neural model) benefited from the symbolic information from static analysis tools and test execution traces. A model that strikes a balance between the solve rate and error rate vs the cost and latency has a benchmark solve rate of 42.3% using an average 11.8 feedback iterations. Production Findings: In a three month period, 80% of the generated fixes were reviewed, of which 31.5% were landed (25.5% of the total number of generated fixes). Feedback from Engineers: We used open coding to extract qualitative themes from engineers' feedback. We saw positive feedback in the form of quick approvals, gratitude, and surprise. We also found mixed feedback when the Engineering Agent's solution was partially correct and it served as a good starting point.
Authors: Hitesh Kumar Gupta
Abstract: Image captioning, a task at the confluence of computer vision and natural language processing, requires a sophisticated understanding of both visual scenes and linguistic structure. While modern approaches are dominated by large-scale Transformer architectures, this paper documents a systematic, iterative development of foundational image captioning models, progressing from a simple CNN-LSTM encoder-decoder to a competitive attention-based system. We present a series of five models, beginning with Genesis and concluding with Nexus, an advanced model featuring an EfficientNetV2B3 backbone and a dynamic attention mechanism. Our experiments chart the impact of architectural enhancements and demonstrate a key finding within the classic CNN-LSTM paradigm: merely upgrading the visual backbone without a corresponding attention mechanism can degrade performance, as the single-vector bottleneck cannot transmit the richer visual detail. This insight validates the architectural shift to attention. Trained on the MS COCO 2017 dataset, our final model, Nexus, achieves a BLEU-4 score of 31.4, surpassing several foundational benchmarks and validating our iterative design process. This work provides a clear, replicable blueprint for understanding the core architectural principles that underpin modern vision-language tasks.
Authors: Danqing Shi, Furui Cheng, Tino Weinkauf, Antti Oulasvirta, Mennatallah El-Assady
Abstract: Human preferences are widely used to align large language models (LLMs) through methods such as reinforcement learning from human feedback (RLHF). However, the current user interfaces require annotators to compare text paragraphs, which is cognitively challenging when the texts are long or unfamiliar. This paper contributes by studying the decomposition principle as an approach to improving the quality of human feedback for LLM alignment. This approach breaks down the text into individual claims instead of directly comparing two long-form text responses. Based on the principle, we build a novel user interface DxHF. It enhances the comparison process by showing decomposed claims, visually encoding the relevance of claims to the conversation and linking similar claims. This allows users to skim through key information and identify differences for better and quicker judgment. Our technical evaluation shows evidence that decomposition generally improves feedback accuracy regarding the ground truth, particularly for users with uncertainty. A crowdsourcing study with 160 participants indicates that using DxHF improves feedback accuracy by an average of 5%, although it increases the average feedback time by 18 seconds. Notably, accuracy is significantly higher in situations where users have less certainty. The finding of the study highlights the potential of HCI as an effective method for improving human-AI alignment.
Authors: Yiping Jia, Zhen Ming Jiang, Shayan Noei, Ying Zou
Abstract: With the widespread adoption of Large Language Models (LLMs) such as GitHub Copilot and ChatGPT, developers increasingly rely on AI-assisted tools to support code generation. While LLMs can generate syntactically correct solutions for well-structured programming tasks, they often struggle with challenges that require iterative debugging, error handling, or adaptation to diverse problem structures. Existing approaches such as fine-tuning or self-repair strategies either require costly retraining or lack mechanisms to accumulate and reuse knowledge from previous attempts. To address these limitations, we propose MemoCoder, a multi-agent framework that enables collaborative problem solving and persistent learning from past fixes. At the core of MemoCoder is a Fixing Knowledge Set, which stores successful repairs and supports retrieval for future tasks. A central Mentor Agent supervises the repair process by identifying recurring error patterns and refining high-level fixing strategies, providing a novel supervisory role that guides the self-repair loop. We evaluate MemoCoder across three public benchmarks -- MBPP, HumanEval, and LiveCodeBench -- spanning a range of problem complexities. Experimental results show that MemoCoder consistently outperforms both zero-shot prompting and a Self-Repair strategy, with improvements ranging from 3.1% to 12.1% in Pass@10 and from 1.4% to 14.5% in Pass@50, demonstrating its effectiveness in iterative refinement and knowledge-guided code generation.
Authors: Benjamin Carter, Nathan Dilla, Micheal Callahan, Atuhaire Ambala
Abstract: The rise of deepfake technology brings forth new questions about the authenticity of various forms of media found online today. Videos and images generated by artificial intelligence (AI) have become increasingly more difficult to differentiate from genuine media, resulting in the need for new models to detect artificially-generated media. While many models have attempted to solve this, most focus on direct image processing, adapting a convolutional neural network (CNN) or a recurrent neural network (RNN) that directly interacts with the video image data. This paper introduces an approach of using solely facial landmarks for deepfake detection. Using a dataset consisting of both deepfake and genuine videos of human faces, this paper describes an approach for extracting facial landmarks for deepfake detection, focusing on identifying subtle inconsistencies in facial movements instead of raw image processing. Experimental results demonstrated that this feature extraction technique is effective in various neural network models, with the same facial landmarks tested on three neural network models, with promising performance metrics indicating its potential for real-world applications. The findings discussed in this paper include RNN and artificial neural network (ANN) models with accuracy between 96% and 93%, respectively, with a CNN model hovering around 78%. This research challenges the assumption that raw image processing is necessary to identify deepfake videos by presenting a facial feature extraction approach compatible with various neural network models while requiring fewer parameters.
Authors: Fabio De Sousa Ribeiro, Omar Todd, Charles Jones, Avinash Kori, Raghav Mehta, Ben Glocker
Abstract: We introduce the Flow Stochastic Segmentation Network (Flow-SSN), a generative segmentation model family featuring discrete-time autoregressive and modern continuous-time flow variants. We prove fundamental limitations of the low-rank parameterisation of previous methods and show that Flow-SSNs can estimate arbitrarily high-rank pixel-wise covariances without assuming the rank or storing the distributional parameters. Flow-SSNs are also more efficient to sample from than standard diffusion-based segmentation models, thanks to most of the model capacity being allocated to learning the base distribution of the flow, constituting an expressive prior. We apply Flow-SSNs to challenging medical imaging benchmarks and achieve state-of-the-art results. Code available: https://github.com/biomedia-mira/flow-ssn.
Authors: Pinhao Song, Yutong Hu, Pengteng Li, Renaud Detry
Abstract: We propose a new volumetric grasp model that is equivariant to rotations around the vertical axis, leading to a significant improvement in sample efficiency. Our model employs a tri-plane volumetric feature representation -- i.e., the projection of 3D features onto three canonical planes. We introduce a novel tri-plane feature design in which features on the horizontal plane are equivariant to 90{\deg} rotations, while the sum of features from the other two planes remains invariant to the same transformations. This design is enabled by a new deformable steerable convolution, which combines the adaptability of deformable convolutions with the rotational equivariance of steerable ones. This allows the receptive field to adapt to local object geometry while preserving equivariance properties. We further develop equivariant adaptations of two state-of-the-art volumetric grasp planners, GIGA and IGD. Specifically, we derive a new equivariant formulation of IGD's deformable attention mechanism and propose an equivariant generative model of grasp orientations based on flow matching. We provide a detailed analytical justification of the proposed equivariance properties and validate our approach through extensive simulated and real-world experiments. Our results demonstrate that the proposed projection-based design significantly reduces both computational and memory costs. Moreover, the equivariant grasp models built on top of our tri-plane features consistently outperform their non-equivariant counterparts, achieving higher performance with only a modest computational overhead. Video and code can be viewed in: https://mousecpn.github.io/evg-page/
Authors: Beidi Zhao, SangMook Kim, Hao Chen, Chen Zhou, Zu-hua Gao, Gang Wang, Xiaoxiao Li
Abstract: Multiple Instance Learning (MIL) has advanced WSI analysis but struggles with the complexity and heterogeneity of WSIs. Existing MIL methods face challenges in aggregating diverse patch information into robust WSI representations. While ViTs and clustering-based approaches show promise, they are computationally intensive and fail to capture task-specific and slide-specific variability. To address these limitations, we propose PTCMIL, a novel Prompt Token Clustering-based ViT for MIL aggregation. By introducing learnable prompt tokens into the ViT backbone, PTCMIL unifies clustering and prediction tasks in an end-to-end manner. It dynamically aligns clustering with downstream tasks, using projection-based clustering tailored to each WSI, reducing complexity while preserving patch heterogeneity. Through token merging and prototype-based pooling, PTCMIL efficiently captures task-relevant patterns. Extensive experiments on eight datasets demonstrate its superior performance in classification and survival analysis tasks, outperforming state-of-the-art methods. Systematic ablation studies confirm its robustness and strong interpretability. The code is released at https://github.com/ubc-tea/PTCMIL.
Authors: Mohammad Kachuee, Teja Gollapudi, Minseok Kim, Yin Huang, Kai Sun, Xiao Yang, Jiaqi Wang, Nirav Shah, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong
Abstract: Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning framework, called PrismRAG, that (i) trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages, and (ii) instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without relying on extensive human engineered instructions. Evaluated across 12 open-book RAG QA benchmarks spanning diverse application domains and scenarios, PrismRAG improves average factuality by 5.4%, outperforming state-of-the-art solutions.
Authors: Xuefei Wu, Xiao Yin, Yuanyang Zhu, Chunlin Chen
Abstract: Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense individual rewards to guide the agents toward efficient exploration. However, individual rewards generally rely on manually engineered shaping-reward functions that lack high-order intelligence, thus it behaves ineffectively than humans regarding learning and generalization in complex problems. To tackle these issues, we combine the above two paradigms and propose a novel framework, LIGHT (Learning Individual Intrinsic reward via Incorporating Generalized Human experTise), which can integrate human knowledge into MARL algorithms in an end-to-end manner. LIGHT guides each agent to avoid unnecessary exploration by considering both individual action distribution and human expertise preference distribution. Then, LIGHT designs individual intrinsic rewards for each agent based on actionable representational transformation relevant to Q-learning so that the agents align their action preferences with the human expertise while maximizing the joint action value. Experimental results demonstrate the superiority of our method over representative baselines regarding performance and better knowledge reusability across different sparse-reward tasks on challenging scenarios.
Authors: Meriem Zerkouk, Miloud Mihoubi, Belkacem Chikhaoui
Abstract: AI-based Intelligent Tutoring Systems (ITS) have significant potential to transform teaching and learning. As efforts continue to design, develop, and integrate ITS into educational contexts, mixed results about their effectiveness have emerged. This paper provides a comprehensive review to understand how ITS operate in real educational settings and to identify the associated challenges in their application and evaluation. We use a systematic literature review method to analyze numerous qualified studies published from 2010 to 2025, examining domains such as pedagogical strategies, NLP, adaptive learning, student modeling, and domain-specific applications of ITS. The results reveal a complex landscape regarding the effectiveness of ITS, highlighting both advancements and persistent challenges. The study also identifies a need for greater scientific rigor in experimental design and data analysis. Based on these findings, suggestions for future research and practical implications are proposed.
Authors: Rongkun Xue, Yazhe Niu, Shuai Hu, Zixin Yin, Yongqiang Yao, Jing Yang
Abstract: Discrete speech tokenization is a fundamental component in speech codecs. However, in large-scale speech-to-speech systems, the complexity of parallel streams from multiple quantizers and the computational cost of high-time-dimensional codecs pose significant challenges. In this paper, we introduce HH-Codec, a neural codec that achieves extreme compression at 24 tokens per second for 24 kHz audio while relying on single-quantizer inference. Our approach involves a carefully designed Vector Quantization space for Spoken Language Modeling, optimizing compression efficiency while minimizing information loss. Building on this, we propose an asymmetric encoder-decoder architecture (Audio-VQ-Mel-Audio) that leverages dual supervision and progressive training to enhance reconstruction stability and fidelity. HH-Codec achieves state-of-the-art performance in speech reconstruction with an ultra-low bandwidth of 0.3 kbps. We further evaluate its effectiveness in codebook utilization and generative model adaptation, with extensive ablations validating the necessity of each module. HH-Codec is available at https://github.com/opendilab/HH-Codec.
Authors: Richmond Sin Jing Xuan, Jalil Huseynov, Yang Zhang
Abstract: Multilingual large language models (LLMs) exhibit strong cross-linguistic generalization, yet medium to low resource languages underperform on common benchmarks such as ARC-Challenge, MMLU, and HellaSwag. We analyze activation patterns in Gemma-2-2B across all 26 residual layers and 10 languages: Chinese (zh), Russian (ru), Spanish (es), Italian (it), medium to low resource languages including Indonesian (id), Catalan (ca), Marathi (mr), Malayalam (ml), and Hindi (hi), with English (en) as the reference. Using Sparse Autoencoders (SAEs), we reveal systematic disparities in activation patterns. Medium to low resource languages receive up to 26.27 percent lower activations in early layers, with a persistent gap of 19.89 percent in deeper layers. To address this, we apply activation-aware fine-tuning via Low-Rank Adaptation (LoRA), leading to substantial activation gains, such as 87.69 percent for Malayalam and 86.32 percent for Hindi, while maintaining English retention at approximately 91 percent. After fine-tuning, benchmark results show modest but consistent improvements, highlighting activation alignment as a key factor in enhancing multilingual LLM performance.
Authors: Heitor R. Medeiros, Atif Belal, Masih Aminbeidokhti, Eric Granger, Marco Pedersoli
Abstract: Object detection (OD) in infrared (IR) imagery is critical for low-light and nighttime applications. However, the scarcity of large-scale IR datasets forces models to rely on weights pre-trained on RGB images. While fine-tuning on IR improves accuracy, it often compromises robustness under distribution shifts due to the inherent modality gap between RGB and IR. To address this, we introduce LLVIP-C and FLIR-C, two cross-modality out-of-distribution (OOD) benchmarks built by applying corruption to standard IR datasets. Additionally, to fully leverage the complementary knowledge from RGB and infrared trained models, we propose WiSE-OD, a weight-space ensembling method with two variants: WiSE-OD$_{ZS}$, which combines RGB zero-shot and IR fine-tuned weights, and WiSE-OD$_{LP}$, which blends zero-shot and linear probing. Evaluated across three RGB-pretrained detectors and two robust baselines, WiSE-OD improves both cross-modality and corruption robustness without any additional training or inference cost.
Authors: Jian Chen, Yuxuan Hu, Haifeng Lu, Wei Wang, Min Yang, Chengming Li, Xiping Hu
Abstract: Although pre-trained visual models with text have demonstrated strong capabilities in visual feature extraction, sticker emotion understanding remains challenging due to its reliance on multi-view information, such as background knowledge and stylistic cues. To address this, we propose a novel multi-granularity hierarchical fusion transformer (MGHFT), with a multi-view sticker interpreter based on Multimodal Large Language Models. Specifically, inspired by the human ability to interpret sticker emotions from multiple views, we first use Multimodal Large Language Models to interpret stickers by providing rich textual context via multi-view descriptions. Then, we design a hierarchical fusion strategy to fuse the textual context into visual understanding, which builds upon a pyramid visual transformer to extract both global and local sticker features at multiple stages. Through contrastive learning and attention mechanisms, textual features are injected at different stages of the visual backbone, enhancing the fusion of global- and local-granularity visual semantics with textual guidance. Finally, we introduce a text-guided fusion attention mechanism to effectively integrate the overall multimodal features, enhancing semantic understanding. Extensive experiments on 2 public sticker emotion datasets demonstrate that MGHFT significantly outperforms existing sticker emotion recognition approaches, achieving higher accuracy and more fine-grained emotion recognition. Compared to the best pre-trained visual models, our MGHFT also obtains an obvious improvement, 5.4% on F1 and 4.0% on accuracy. The code is released at https://github.com/cccccj-03/MGHFT_ACMMM2025.
Authors: Takuya Inoue (Meteorological Research Institute, Tsukuba, Japan), Takuya Kawabata (Meteorological Research Institute, Tsukuba, Japan)
Abstract: This study proposes a method that integrates convolutional neural networks (CNNs) with ensemble numerical weather prediction (NWP) models, enabling surface temperature forecasting at lead times beyond the short-range (five-day) forecast period. Owing to limited computational resources, operational medium-range temperature forecasts typically rely on low-resolution NWP models, which are prone to systematic and random errors. To resolve these limitations, the proposed method first reduces systematic errors through CNN-based post-processing (bias correction and spatial super-resolution) on each ensemble member, reconstructing high-resolution temperature fields from low-resolution model outputs. Second, it reduces random errors through ensemble averaging of the CNN-corrected members. This study also investigates whether the sequence of CNN correction and ensemble averaging affects the forecast accuracy. For comparison with the proposed method, we additionally conducted experiments with the CNN trained on ensemble-averaged forecasts. The first approach--CNN correction before ensemble averaging--consistently achieved higher accuracy than the reverse approach. Although based on low-resolution ensemble forecasts, the proposed method notably outperformed the high-resolution deterministic NWP models. These findings indicate that combining CNN-based correction with ensemble averaging effectively reduces both the systematic and random errors in NWP model outputs. The proposed approach is a practical and scalable solution for improving medium-range temperature forecasts, and is particularly valuable at operational centers with limited computational resources.
Authors: Zijian Zhang, Pan Chen, Fangshi Du, Runlong Ye, Oliver Huang, Michael Liut, Al\'an Aspuru-Guzik
Abstract: Efficiently navigating and understanding academic papers is crucial for scientific progress. Traditional linear formats like PDF and HTML can cause cognitive overload and obscure a paper's hierarchical structure, making it difficult to locate key information. While LLM-based chatbots offer summarization, they often lack nuanced understanding of specific sections, may produce unreliable information, and typically discard the document's navigational structure. Drawing insights from a formative study on academic reading practices, we introduce TreeReader, a novel language model-augmented paper reader. TreeReader decomposes papers into an interactive tree structure where each section is initially represented by an LLM-generated concise summary, with underlying details accessible on demand. This design allows users to quickly grasp core ideas, selectively explore sections of interest, and verify summaries against the source text. A user study was conducted to evaluate TreeReader's impact on reading efficiency and comprehension. TreeReader provides a more focused and efficient way to navigate and understand complex academic literature by bridging hierarchical summarization with interactive exploration.
Authors: UMMPK Nawarathne, HMNS Kumari, HMLS Kumari
Abstract: Underwater pollution is one of today's most significant environmental concerns, with vast volumes of garbage found in seas, rivers, and landscapes around the world. Accurate detection of these waste materials is crucial for successful waste management, environmental monitoring, and mitigation strategies. In this study, we investigated the performance of five cutting-edge object recognition algorithms, namely YOLO (You Only Look Once) models, including YOLOv7, YOLOv8, YOLOv9, YOLOv10, and Faster Region-Convolutional Neural Network (R-CNN), to identify which model was most effective at recognizing materials in underwater situations. The models were thoroughly trained and tested on a large dataset containing fifteen different classes under diverse conditions, such as low visibility and variable depths. From the above-mentioned models, YOLOv8 outperformed the others, with a mean Average Precision (mAP) of 80.9%, indicating a significant performance. This increased performance is attributed to YOLOv8's architecture, which incorporates advanced features such as improved anchor-free mechanisms and self-supervised learning, allowing for more precise and efficient recognition of items in a variety of settings. These findings highlight the YOLOv8 model's potential as an effective tool in the global fight against pollution, improving both the detection capabilities and scalability of underwater cleanup operations.
Authors: Bohan Yao, Vikas Yadav
Abstract: Augmenting large language models (LLMs) with external tools is a promising avenue for developing high-performance mathematical reasoning systems. Prior tool-augmented approaches typically finetune an LLM to select and invoke a single tool at each reasoning step and show promising results on simpler math reasoning benchmarks such as GSM8K. However, these approaches struggle with more complex math problems that require precise reasoning over multiple steps. To address this limitation, in this work, we propose Multi-TAG, a Multi-Tool AGgregation-based framework. Instead of relying on a single tool, Multi-TAG guides an LLM to concurrently invoke multiple tools at each reasoning step. It then aggregates their diverse outputs to verify and refine the reasoning process, enhancing solution robustness and accuracy. Notably, Multi-TAG is a finetuning-free, inference-only framework, making it readily applicable to any LLM backbone, including large open-weight models which are computationally expensive to finetune and proprietary frontier models which cannot be finetuned with custom recipes. We evaluate Multi-TAG on four challenging benchmarks: MATH500, AIME, AMC, and OlympiadBench. Across both open-weight and closed-source LLM backbones, Multi-TAG consistently and substantially outperforms state-of-the-art baselines, achieving average improvements of 6.0% to 7.5% over state-of-the-art baselines.
Authors: HMNS Kumari, HMLS Kumari, UMMPK Nawarathne
Abstract: Differentiated thyroid cancer DTC recurrence is a major public health concern, requiring classification and predictive models that are not only accurate but also interpretable and uncertainty aware. This study introduces a comprehensive framework for DTC recurrence classification using a dataset containing 383 patients and 16 clinical and pathological variables. Initially, 11 machine learning ML models were employed using the complete dataset, where the Support Vector Machines SVM model achieved the highest accuracy of 0.9481. To reduce complexity and redundancy, feature selection was carried out using the Boruta algorithm, and the same ML models were applied to the reduced dataset, where it was observed that the Logistic Regression LR model obtained the maximum accuracy of 0.9611. However, these ML models often lack uncertainty quantification, which is critical in clinical decision making. Therefore, to address this limitation, the Bayesian Neural Networks BNN with six varying prior distributions, including Normal 0,1, Normal 0,10, Laplace 0,1, Cauchy 0,1, Cauchy 0,2.5, and Horseshoe 1, were implemented on both the complete and reduced datasets. The BNN model with Normal 0,10 prior distribution exhibited maximum accuracies of 0.9740 and 0.9870 before and after feature selection, respectively.
Authors: Maxence Bouvier, Ryan Amaudruz, Felix Arnold, Renzo Andri, Lukas Cavigelli
Abstract: As AI workloads proliferate, optimizing arithmetic units is becoming increasingly important to reduce the footprint of digital systems. Conventional design flows, which often rely on manual or heuristics-based optimization, are limited in their ability to thoroughly explore the vast design space. In this paper, we introduce GENIAL, a machine learning-based framework for the automatic generation and optimization of arithmetic units, more specifically multipliers. At the core of GENIAL is a Transformer-based surrogate model trained in two stages, involving self-supervised pretraining followed by supervised finetuning, to robustly forecast key hardware metrics such as power and area from abstracted design representations. By inverting the surrogate model, GENIAL efficiently searches for new operand encodings that directly minimize power consumption in arithmetic units for specific input data distributions. Extensive experiments on large datasets demonstrate that GENIAL is consistently more sample efficient than other methods, and converges faster towards optimized designs. This enables to deploy a high-effort logic synthesis optimization flow in the loop, improving the accuracy of the surrogate model. Notably, GENIAL automatically discovers encodings that achieve up to 18% switching activity savings within multipliers on representative AI workloads compared with the conventional two's complement. We also demonstrate the versatility of our approach by achieving significant improvements on Finite State Machines, highlighting GENIAL's applicability for a wide spectrum of logic functions. Together, these advances mark a significant step toward automated Quality-of-Results-optimized combinational circuit generation for digital systems.
Authors: Gihun Kim, Sun-Yong Choi, Yeoneung Kim
Abstract: We propose a novel diffusion-based generative framework for financial time series that incorporates geometric Brownian motion (GBM), the foundation of the Black--Scholes theory, into the forward noising process. Unlike standard score-based models that treat price trajectories as generic numerical sequences, our method injects noise proportionally to asset prices at each time step, reflecting the heteroskedasticity observed in financial time series. By accurately balancing the drift and diffusion terms, we show that the resulting log-price process reduces to a variance-exploding stochastic differential equation, aligning with the formulation in score-based generative models. The reverse-time generative process is trained via denoising score matching using a Transformer-based architecture adapted from the Conditional Score-based Diffusion Imputation (CSDI) framework. Empirical evaluations on historical stock data demonstrate that our model reproduces key stylized facts heavy-tailed return distributions, volatility clustering, and the leverage effect more realistically than conventional diffusion models.
Authors: Siyi Xun, Yue Sun, Jingkun Chen, Zitong Yu, Tong Tong, Xiaohong Liu, Mingxiang Wu, Tao Tan
Abstract: Rapid advances in medical imaging technology underscore the critical need for precise and automated image quality assessment (IQA) to ensure diagnostic accuracy. Existing medical IQA methods, however, struggle to generalize across diverse modalities and clinical scenarios. In response, we introduce MedIQA, the first comprehensive foundation model for medical IQA, designed to handle variability in image dimensions, modalities, anatomical regions, and types. We developed a large-scale multi-modality dataset with plentiful manually annotated quality scores to support this. Our model integrates a salient slice assessment module to focus on diagnostically relevant regions feature retrieval and employs an automatic prompt strategy that aligns upstream physical parameter pre-training with downstream expert annotation fine-tuning. Extensive experiments demonstrate that MedIQA significantly outperforms baselines in multiple downstream tasks, establishing a scalable framework for medical IQA and advancing diagnostic workflows and clinical decision-making.
Authors: Laingjun Feng, Chenyi Pan, Xinjie Guo, Fei Mei, Benzhe Ning, Jianxiang Zhang, Xinyang Liu, Beirong Zhou, Zeng Shu, Chang Liu, Guang Yang, Zhenyu Han, Jiangben Wang, Bo Wang
Abstract: Reinforcement learning (RL) is a paradigm increasingly used to align large language models. Popular RL algorithms utilize multiple workers and can be modeled as a graph, where each node is the status of a worker and each edge represents dataflow between nodes. Owing to the heavy cross-node dependencies, the RL training system usually suffers from poor cluster scalability and low memory utilization. In this article, we introduce MindSpeed RL, an effective and efficient system for large-scale RL training. Unlike existing centralized methods, MindSpeed RL organizes the essential data dependencies in RL training, i.e., sample flow and resharding flow, from a distributed view. On the one hand, a distributed transfer dock strategy, which sets controllers and warehouses on the basis of the conventional replay buffer, is designed to release the dispatch overhead in the sample flow. A practical allgather--swap strategy is presented to eliminate redundant memory usage in resharding flow. In addition, MindSpeed RL further integrates numerous parallelization strategies and acceleration techniques for systematic optimization. Compared with existing state-of-the-art systems, comprehensive experiments on the RL training of popular Qwen2.5-Dense-7B/32B, Qwen3-MoE-30B, and DeepSeek-R1-MoE-671B show that MindSpeed RL increases the throughput by 1.42 ~ 3.97 times. Finally, we open--source MindSpeed RL and perform all the experiments on a super pod of Ascend with 384 neural processing units (NPUs) to demonstrate the powerful performance and reliability of Ascend.
Authors: Jitindra Fartiyal, Pedro Freire, Yasmeen Whayeb, James S. Wolffsohn, Sergei K. Turitsyn, Sergei G. Sokolov
Abstract: Medical imaging plays a critical role in modern healthcare, enabling clinicians to accurately diagnose diseases and develop effective treatment plans. However, noise, often introduced by imaging devices, can degrade image quality, leading to misinterpretation and compromised clinical outcomes. Existing denoising approaches typically rely either on noise characteristics or on contextual information from the image. Moreover, they are commonly developed and evaluated for a single imaging modality and noise type. Motivated by Geng et.al CNCL, which integrates both noise and context, this study introduces a Dual-Pathway Learning (DPL) model architecture that effectively denoises medical images by leveraging both sources of information and fusing them to generate the final output. DPL is evaluated across multiple imaging modalities and various types of noise, demonstrating its robustness and generalizability. DPL improves PSNR by 3.35% compared to the baseline UNet when evaluated on Gaussian noise and trained across all modalities. The code is available at 10.5281/zenodo.15836053.
Authors: Binxu Li, Yuhui Zhang, Xiaohan Wang, Weixin Liang, Ludwig Schmidt, Serena Yeung-Levy
Abstract: Mixed modality search -- retrieving information across a heterogeneous corpus composed of images, texts, and multimodal documents -- is an important yet underexplored real-world application. In this work, we investigate how contrastive vision-language models, such as CLIP, perform on the mixed modality search task. Our analysis reveals a critical limitation: these models exhibit a pronounced modality gap in the embedding space, where image and text embeddings form distinct clusters, leading to intra-modal ranking bias and inter-modal fusion failure. To address this issue, we propose GR-CLIP, a lightweight post-hoc calibration method that removes the modality gap in CLIP's embedding space. Evaluated on MixBench -- the first benchmark specifically designed for mixed modality search -- GR-CLIP improves NDCG@10 by up to 26 percentage points over CLIP, surpasses recent vision-language generative embedding models by 4 percentage points, while using 75x less compute.
Authors: Mohammad Naeimi, Mostafa Haghir Chehreghani
Abstract: Recommender systems, especially those based on graph neural networks (GNNs), have achieved remarkable success in capturing user-item interaction patterns. However, they remain susceptible to popularity bias--the tendency to over-recommend popular items--resulting in reduced content diversity and compromised fairness. In this paper, we propose PBiLoss, a novel regularization-based loss function designed to counteract popularity bias in graph-based recommender models explicitly. PBiLoss augments traditional training objectives by penalizing the model's inclination toward popular items, thereby encouraging the recommendation of less popular but potentially more personalized content. We introduce two sampling strategies: Popular Positive (PopPos) and Popular Negative (PopNeg), which respectively modulate the contribution of the positive and negative popular items during training. We further explore two methods to distinguish popular items: one based on a fixed popularity threshold and another without any threshold, making the approach flexible and adaptive. Our proposed method is model-agnostic and can be seamlessly integrated into state-of-the-art graph-based frameworks such as LightGCN and its variants. Comprehensive experiments across multiple real-world datasets demonstrate that PBiLoss significantly improves fairness, as demonstrated by reductions in the Popularity-Rank Correlation for Users (PRU) and Popularity-Rank Correlation for Items (PRI), while maintaining or even enhancing standard recommendation accuracy and ranking metrics. These results highlight the effectiveness of directly embedding fairness objectives into the optimization process, providing a practical and scalable solution for balancing accuracy and equitable content exposure in modern recommender systems.
Authors: Francisco Caetano, Lemar Abdi, Christiaan Viviers, Amaan Valiuddin, Fons van der Sommen
Abstract: Reliable medical image classification requires accurate predictions and well-calibrated uncertainty estimates, especially in high-stakes clinical settings. This work presents MedSymmFlow, a generative-discriminative hybrid model built on Symmetrical Flow Matching, designed to unify classification, generation, and uncertainty quantification in medical imaging. MedSymmFlow leverages a latent-space formulation that scales to high-resolution inputs and introduces a semantic mask conditioning mechanism to enhance diagnostic relevance. Unlike standard discriminative models, it naturally estimates uncertainty through its generative sampling process. The model is evaluated on four MedMNIST datasets, covering a range of modalities and pathologies. The results show that MedSymmFlow matches or exceeds the performance of established baselines in classification accuracy and AUC, while also delivering reliable uncertainty estimates validated by performance improvements under selective prediction.
Authors: Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating retrieved information. Standard retrieval process prioritized relevance, focusing on topical alignment between queries and passages. In contrast, in RAG, the emphasis has shifted to utility, which considers the usefulness of passages for generating accurate answers. Despite empirical evidence showing the benefits of utility-based retrieval in RAG, the high computational cost of using LLMs for utility judgments limits the number of passages evaluated. This restriction is problematic for complex queries requiring extensive information. To address this, we propose a method to distill the utility judgment capabilities of LLMs into smaller, more efficient models. Our approach focuses on utility-based selection rather than ranking, enabling dynamic passage selection tailored to specific queries without the need for fixed thresholds. We train student models to learn pseudo-answer generation and utility judgments from teacher LLMs, using a sliding window method that dynamically selects useful passages. Our experiments demonstrate that utility-based selection provides a flexible and cost-effective solution for RAG, significantly reducing computational costs while improving answer quality. We present the distillation results using Qwen3-32B as the teacher model for both relevance ranking and utility-based selection, distilled into RankQwen1.7B and UtilityQwen1.7B. Our findings indicate that for complex questions, utility-based selection is more effective than relevance ranking in enhancing answer generation performance. We will release the relevance ranking and utility-based selection annotations for the MS MARCO dataset, supporting further research in this area.
Authors: Shweta Ramesh, Joy Bose, Hamender Singh, A K Raghavan, Sujoy Roychowdhury, Giriprasad Sridhara, Nishrith Saini, Ricardo Britto
Abstract: Code review is one of the primary means of assuring the quality of released software along with testing and static analysis. However, code review requires experienced developers who may not always have the time to perform an in-depth review of code. Thus, automating code review can help alleviate the cognitive burden on experienced software developers allowing them to focus on their primary activities of writing code to add new features and fix bugs. In this paper, we describe our experience in using Large Language Models towards automating the code review process in Ericsson. We describe the development of a lightweight tool using LLMs and static program analysis. We then describe our preliminary experiments with experienced developers in evaluating our code review tool and the encouraging results.
Authors: Muhao Guo, Jiaqi Wu, Yang Weng, Yizheng Liao, Shengzhe Chen
Abstract: Ensuring privacy in large-scale open datasets is increasingly challenging under regulations such as the General Data Protection Regulation (GDPR). While differential privacy (DP) provides strong theoretical guarantees, it primarily focuses on noise injection during model training, neglecting privacy preservation at the data publishing stage. Existing privacy-preserving data publishing (PPDP) approaches struggle to balance privacy and utility, particularly when data publishers and users are distinct entities. To address this gap, we focus on the graph recovery problem and propose a novel privacy-preserving estimation framework for open graph data, leveraging Gaussian DP (GDP) with a structured noise-injection mechanism. Unlike traditional methods that perturb gradients or model updates, our approach ensures unbiased graph structure recovery while enforcing DP at the data publishing stage. Moreover, we provide theoretical guarantees on estimation accuracy and extend our method to discrete-variable graphs, a setting often overlooked in DP research. Experimental results in graph learning demonstrate robust performance, offering a viable solution for privacy-conscious graph analysis.
Authors: Yanghong Liu, Xingping Dong, Ming Li, Weixing Zhang, Yidong Lou
Abstract: Pedestrian trajectory prediction is crucial for autonomous driving and robotics. While existing point-based and grid-based methods expose two key limitations: insufficiently modeling human motion dynamics, as they fail to balance local motion details with long-range spatiotemporal dependencies, and the time representation lacks interaction with the frequency domain in modeling trajectory sequences. To address these challenges, we propose PatchTraj, a dynamic patch-based trajectory prediction framework that unifies time-domain and frequency-domain representations. Specifically, we decompose the trajectory into raw time sequences and frequency components, employing dynamic patch partitioning for multi-scale trajectory segmentation to capture hierarchical motion patterns. Each patch is processed by an adaptive embedding layer with scale-aware feature extraction, followed by hierarchical feature aggregation to model both fine-grained and long-range dependencies. The outputs of two branches interact via cross-modal attention, enabling complementary fusion of temporal and spectral cues. Finally, a Transformer encoder-decoder integrates both modalities to autoregressively predict future trajectories. Extensive experiments on ETH-UCY, SDD, NBA, and JRDB datasets demonstrate that our method achieves state-of-the-art performance with high efficiency.
Authors: Alice Zhang, Skanda Muralidhar, Daniel Gatica-Perez, Mathew Magimai-Doss
Abstract: Prior research indicates that users prefer assistive technologies whose personalities align with their own. This has sparked interest in automatic personality perception (APP), which aims to predict an individual's perceived personality traits. Previous studies in APP have treated personalities as static traits, independent of context. However, perceived personalities can vary by context and situation as shown in psychological research. In this study, we investigate the relationship between conversational speech and perceived personality for participants engaged in two work situations (a neutral interview and a stressful client interaction). Our key findings are: 1) perceived personalities differ significantly across interactions, 2) loudness, sound level, and spectral flux features are indicative of perceived extraversion, agreeableness, conscientiousness, and openness in neutral interactions, while neuroticism correlates with these features in stressful contexts, 3) handcrafted acoustic features and non-verbal features outperform speaker embeddings in inference of perceived personality, and 4) stressful interactions are more predictive of neuroticism, aligning with existing psychological research.
Authors: Muhao Guo, Yang Weng
Abstract: Accurate detection and localization of solar photovoltaic (PV) panels in satellite imagery is essential for optimizing microgrids and active distribution networks (ADNs), which are critical components of renewable energy systems. Existing methods lack transparency regarding their underlying algorithms or training datasets, rely on large, high-quality PV training data, and struggle to generalize to new geographic regions or varied environmental conditions without extensive re-training. These limitations lead to inconsistent detection outcomes, hindering large-scale deployment and data-driven grid optimization. In this paper, we investigate how large language models (LLMs) can be leveraged to overcome these challenges. Despite their promise, LLMs face several challenges in solar panel detection, including difficulties with multi-step logical processes, inconsistent output formatting, frequent misclassification of visually similar objects (e.g., shadows, parking lots), and low accuracy in complex tasks such as spatial localization and quantification. To overcome these issues, we propose the PV Assessment with LLMs (PVAL) framework, which incorporates task decomposition for more efficient workflows, output standardization for consistent and scalable formatting, few-shot prompting to enhance classification accuracy, and fine-tuning using curated PV datasets with detailed annotations. PVAL ensures transparency, scalability, and adaptability across heterogeneous datasets while minimizing computational overhead. By combining open-source accessibility with robust methodologies, PVAL establishes an automated and reproducible pipeline for solar panel detection, paving the way for large-scale renewable energy integration and optimized grid management.
Authors: Michael Amir, Guang Yang, Zhan Gao, Keisuke Okumura, Heedo Woo, Amanda Prorok
Abstract: Constraint-based optimization is a cornerstone of robotics, enabling the design of controllers that reliably encode task and safety requirements such as collision avoidance or formation adherence. However, handcrafted constraints can fail in multi-agent settings that demand complex coordination. We introduce ReCoDe--Reinforcement-based Constraint Design--a decentralized, hybrid framework that merges the reliability of optimization-based controllers with the adaptability of multi-agent reinforcement learning. Rather than discarding expert controllers, ReCoDe improves them by learning additional, dynamic constraints that capture subtler behaviors, for example, by constraining agent movements to prevent congestion in cluttered scenarios. Through local communication, agents collectively constrain their allowed actions to coordinate more effectively under changing conditions. In this work, we focus on applications of ReCoDe to multi-agent navigation tasks requiring intricate, context-based movements and consensus, where we show that it outperforms purely handcrafted controllers, other hybrid approaches, and standard MARL baselines. We give empirical (real robot) and theoretical evidence that retaining a user-defined controller, even when it is imperfect, is more efficient than learning from scratch, especially because ReCoDe can dynamically change the degree to which it relies on this controller.
Authors: Gioele Giachino, Marco Rondina, Antonio Vetr\`o, Riccardo Coppola, Juan Carlos De Martin
Abstract: The increasing use of Large Language Models (LLMs) in a large variety of domains has sparked worries about how easily they can perpetuate stereotypes and contribute to the generation of biased content. With a focus on gender and professional bias, this work examines in which manner LLMs shape responses to ungendered prompts, contributing to biased outputs. This analysis uses a structured experimental method, giving different prompts involving three different professional job combinations, which are also characterized by a hierarchical relationship. This study uses Italian, a language with extensive grammatical gender differences, to highlight potential limitations in current LLMs' ability to generate objective text in non-English languages. Two popular LLM-based chatbots are examined, namely OpenAI ChatGPT (gpt-4o-mini) and Google Gemini (gemini-1.5-flash). Through APIs, we collected a range of 3600 responses. The results highlight how content generated by LLMs can perpetuate stereotypes. For example, Gemini associated 100% (ChatGPT 97%) of 'she' pronouns to the 'assistant' rather than the 'manager'. The presence of bias in AI-generated text can have significant implications in many fields, such as in the workplaces or in job selections, raising ethical concerns about its use. Understanding these risks is pivotal to developing mitigation strategies and assuring that AI-based systems do not increase social inequalities, but rather contribute to more equitable outcomes. Future research directions include expanding the study to additional chatbots or languages, refining prompt engineering methods or further exploiting a larger experimental base.
Authors: Tarek Gasmi, Ramzi Guesmi, Mootez Aloui, Jihene Bennaceur
Abstract: Static benchmarks fail to capture LLM vulnerabilities emerging through community experimentation in online forums. We present PrompTrend, a system that collects vulnerability data across platforms and evaluates them using multidimensional scoring, with an architecture designed for scalable monitoring. Cross-sectional analysis of 198 vulnerabilities collected from online communities over a five-month period (January-May 2025) and tested on nine commercial models reveals that advanced capabilities correlate with increased vulnerability in some architectures, psychological attacks significantly outperform technical exploits, and platform dynamics shape attack effectiveness with measurable model-specific patterns. The PrompTrend Vulnerability Assessment Framework achieves 78% classification accuracy while revealing limited cross-model transferability, demonstrating that effective LLM security requires comprehensive socio-technical monitoring beyond traditional periodic assessment. Our findings challenge the assumption that capability advancement improves security and establish community-driven psychological manipulation as the dominant threat vector for current language models.
Authors: Chaymaa Abbas, Mariette Awad, Razane Tajeddine
Abstract: Despite the ongoing improvements in the design of large language models (LLMs) to foster inclusion and balanced responses, these systems remain susceptible to encoding and amplifying social biases. This study examines how dialectal variation, specifically African American Vernacular English (AAVE) versus Standard American English (SAE), interacts with data poisoning to influence toxicity in outputs. Using both small- and medium-scale LLaMA models, we show that even minimal exposure to poisoned data significantly increases toxicity for AAVE inputs, while it remains comparatively unaffected for SAE. Larger models exhibit a more significant amplification effect which suggests heightened susceptibility with scale. To further assess these disparities, we employed GPT-4o as a fairness auditor, which identified harmful stereotypical patterns disproportionately tied to AAVE inputs, including portrayals of aggression, criminality, and intellectual inferiority. These findings underscore the compounding impact of data poisoning and dialectal bias and emphasize the need for dialect-aware evaluation, targeted debiasing interventions, and socially responsible training protocols during development.
Authors: Youngmin Seo, Yunhyeong Kwon, Younghun Park, HwiRyong Kim, Seungho Eum, Jinha Kim, Taigon Song, Juho Kim, Unsang Park
Abstract: Accurate spatial prediction of power integrity issues, such as IR drop, is critical for reliable VLSI design. However, traditional simulation-based solvers are computationally expensive and difficult to scale. We address this challenge by reformulating IR drop estimation as a pixel-wise regression task on heterogeneous multi-channel physical maps derived from circuit layouts. Prior learning-based methods treat all input layers (e.g., metal, via, and current maps) equally, ignoring their varying importance to prediction accuracy. To tackle this, we propose a novel Weakness-Aware Channel Attention (WACA) mechanism, which recursively enhances weak feature channels while suppressing over-dominant ones through a two-stage gating strategy. Integrated into a ConvNeXtV2-based attention U-Net, our approach enables adaptive and balanced feature representation. On the public ICCAD-2023 benchmark, our method outperforms the ICCAD-2023 contest winner by reducing mean absolute error by 61.1% and improving F1-score by 71.0%. These results demonstrate that channel-wise heterogeneity is a key inductive bias in physical layout analysis for VLSI.
Authors: Abdul Hannan, Zahid Mahmood, Rizwan Qureshi, Hazrat Ali
Abstract: Automatic classification of Diabetic Retinopathy (DR) can assist ophthalmologists in devising personalized treatment plans, making it a critical component of clinical practice. However, imbalanced data distribution in the dataset becomes a bottleneck in the generalization of deep learning models trained for DR classification. In this work, we combine global attention block (GAB) and category attention block (CAB) into the deep learning model, thus effectively overcoming the imbalanced data distribution problem in DR classification. Our proposed approach is based on an attention mechanism-based deep learning model that employs three pre-trained networks, namely, MobileNetV3-small, Efficientnet-b0, and DenseNet-169 as the backbone architecture. We evaluate the proposed method on two publicly available datasets of retinal fundoscopy images for DR. Experimental results show that on the APTOS dataset, the DenseNet-169 yielded 83.20% mean accuracy, followed by the MobileNetV3-small and EfficientNet-b0, which yielded 82% and 80% accuracies, respectively. On the EYEPACS dataset, the EfficientNet-b0 yielded a mean accuracy of 80%, while the DenseNet-169 and MobileNetV3-small yielded 75.43% and 76.68% accuracies, respectively. In addition, we also compute the F1-score of 82.0%, precision of 82.1%, sensitivity of 83.0%, specificity of 95.5%, and a kappa score of 88.2% for the experiments. Moreover, in our work, the MobileNetV3-small has 1.6 million parameters on the APTOS dataset and 0.90 million parameters on the EYEPACS dataset, which is comparatively less than other methods. The proposed approach achieves competitive performance that is at par with recently reported works on DR classification.
Authors: Xin Li, Kaixiang Yang, Qiang Li, Zhiwei Wang
Abstract: Mammography is the most commonly used imaging modality for breast cancer screening, driving an increasing demand for deep-learning techniques to support large-scale analysis. However, the development of accurate and robust methods is often limited by insufficient data availability and a lack of diversity in lesion characteristics. While generative models offer a promising solution for data synthesis, current approaches often fail to adequately emphasize lesion-specific features and their relationships with surrounding tissues. In this paper, we propose Gated Conditional Diffusion Model (GCDM), a novel framework designed to jointly synthesize holistic mammogram images and localized lesions. GCDM is built upon a latent denoising diffusion framework, where the noised latent image is concatenated with a soft mask embedding that represents breast, lesion, and their transitional regions, ensuring anatomical coherence between them during the denoising process. To further emphasize lesion-specific features, GCDM incorporates a gated conditioning branch that guides the denoising process by dynamically selecting and fusing the most relevant radiomic and geometric properties of lesions, effectively capturing their interplay. Experimental results demonstrate that GCDM achieves precise control over small lesion areas while enhancing the realism and diversity of synthesized mammograms. These advancements position GCDM as a promising tool for clinical applications in mammogram synthesis. Our code is available at https://github.com/lixinHUST/Gated-Conditional-Diffusion-Model/
URLs: https://github.com/lixinHUST/Gated-Conditional-Diffusion-Model/
Authors: Tianfu Wang, Liwei Deng, Xi Chen, Junyang Wang, Huiguo He, Leilei Ding, Wei Wu, Qilin Fan, Hui Xiong
Abstract: Resource allocation (RA) is critical to efficient service deployment in Network Function Virtualization (NFV), a transformative networking paradigm. Recently, deep Reinforcement Learning (RL)-based methods have been showing promising potential to address this complexity. However, the lack of a systematic benchmarking framework and thorough analysis hinders the exploration of emerging networks and the development of more robust algorithms while causing inconsistent evaluation. In this paper, we introduce Virne, a comprehensive benchmarking framework for the NFV-RA problem, with a focus on supporting deep RL-based methods. Virne provides customizable simulations for diverse network scenarios, including cloud, edge, and 5G environments. It also features a modular and extensible implementation pipeline that supports over 30 methods of various types, and includes practical evaluation perspectives beyond effectiveness, such as scalability, generalization, and scalability. Furthermore, we conduct in-depth analysis through extensive experiments to provide valuable insights into performance trade-offs for efficient implementation and offer actionable guidance for future research directions. Overall, with its diverse simulations, rich implementations, and extensive evaluation capabilities, Virne could serve as a comprehensive benchmark for advancing NFV-RA methods and deep RL applications. The code is publicly available at https://github.com/GeminiLight/virne.
Authors: Faruk Alpay, Bugra Kilictas, Taylan Alpay
Abstract: This paper contributes to the Alpay Algebra by demonstrating that the stable outcome of a self referential process, obtained by iterating a transformation through all ordinal stages, is identical to the unique equilibrium of an unbounded revision dialogue between a system and its environment. The analysis initially elucidates how classical fixed point theorems guarantee such convergence in finite settings and subsequently extends the argument to the transfinite domain, relying upon well founded induction and principles of order theoretic continuity. Furthermore, the resulting transordinal fixed point operator is embedded into dependent type theory, a formalization which permits every step of the transfinite iteration and its limit to be verified within a modern proof assistant. This procedure yields a machine checked proof that the iterative dialogue necessarily stabilizes and that its limit is unique. The result provides a foundation for Alpay's philosophical claim of semantic convergence within the framework of constructive logic. By unifying concepts from fixed point theory, game semantics, ordinal analysis, and type theory, this research establishes a broadly accessible yet formally rigorous foundation for reasoning about infinite self referential systems and offers practical tools for certifying their convergence within computational environments.
Authors: Yifan Zhang
Abstract: Auto-regressive language models factorize sequence probabilities and are trained by minimizing the negative log-likelihood (NLL) objective. While empirically powerful, a deep theoretical understanding of why this simple objective yields such versatile representations remains elusive. This work introduces a unifying analytical framework using Markov Categories (MCs) to deconstruct the AR generation process and the NLL objective. We model the single-step generation map as a composition of Markov kernels in the category Stoch. This compositional view, when enriched with statistical divergences, allows us to dissect information flow and learned geometry. Our framework makes three main contributions. First, we provide a formal, information-theoretic rationale for the success of modern speculative decoding methods like EAGLE, quantifying the information surplus in hidden states that these methods exploit. Second, we formalize how NLL minimization forces the model to learn not just the next token, but the data's intrinsic conditional stochasticity, a process we analyze using categorical entropy. Third, and most centrally, we prove that NLL training acts as an implicit form of spectral contrastive learning. By analyzing the information geometry of the model's prediction head, we show that NLL implicitly forces the learned representation space to align with the eigenspectrum of a predictive similarity operator, thereby learning a geometrically structured space without explicit contrastive pairs. This compositional and information-geometric perspective reveals the deep structural principles underlying the effectiveness of modern LMs. Project Page: https://github.com/asiresearch/lm-theory
Authors: Igli Begolli, Meltem Aksoy, Daniel Neider
Abstract: Code review is essential for maintaining software quality but often time-consuming and cognitively demanding, especially in industrial environments. Recent advancements in language models (LMs) have opened new avenues for automating core review tasks. This study presents the empirical evaluation of monolingual fine-tuning on the performance of open-source LMs across three key automated code review tasks: Code Change Quality Estimation, Review Comment Generation, and Code Refinement. We fine-tuned three distinct models, CodeReviewer, CodeLlama-7B, and DeepSeek-R1-Distill, on a C\# specific dataset combining public benchmarks with industrial repositories. Our study investigates how different configurations of programming languages and natural languages in the training data affect LM performance, particularly in comment generation. Additionally, we benchmark the fine-tuned models against an automated software analysis tool (ASAT) and human reviewers to evaluate their practical utility in real-world settings. Our results show that monolingual fine-tuning improves model accuracy and relevance compared to multilingual baselines. While LMs can effectively support code review workflows, especially for routine or repetitive tasks, human reviewers remain superior in handling semantically complex or context-sensitive changes. Our findings highlight the importance of language alignment and task-specific adaptation in optimizing LMs for automated code review.
Authors: Sebastian Lubos, Alexander Felfernig, Thi Ngoc Trang Tran, Viet-Man Le, Damian Garber, Manuel Henrich, Reinhard Willfort, Jeremias Fuchs
Abstract: In contrast to single-user recommender systems, group recommender systems are designed to generate and explain recommendations for groups. This group-oriented setting introduces additional complexities, as several factors - absent in individual contexts - must be addressed. These include understanding group dynamics (e.g., social dependencies within the group), defining effective decision-making processes, ensuring that recommendations are suitable for all group members, and providing group-level explanations as well as explanations for individual users. In this paper, we analyze in which way large language models (LLMs) can support these aspects and help to increase the overall decision support quality and applicability of group recommender systems.
Authors: Abhinav Singh, Petros Koumoutsakos
Abstract: Topological defects in active polar fluids exhibit complex dynamics driven by internally generated stresses, reflecting the deep interplay between topology, flow, and non-equilibrium hydrodynamics. Feedback control offers a powerful means to guide such systems, enabling transitions between dynamic states. We investigated closed-loop steering of integer-charged defects in a confined active fluid by modulating the spatial profile of activity. Using a continuum hydrodynamic model, we show that localized control of active stress induces flow fields that can reposition and direct defects along prescribed trajectories by exploiting non-linear couplings in the system. A reinforcement learning framework is used to discover effective control strategies that produce robust defect transport across both trained and novel trajectories. The results highlight how AI agents can learn the underlying dynamics and spatially structure activity to manipulate topological excitations, offering insights into the controllability of active matter and the design of adaptive, self-organized materials.
Authors: Muhammad Ibrahim, Naveed Akhtar, Haitian Wang, Saeed Anwar, Ajmal Mian
Abstract: Fusion of LiDAR and RGB data has the potential to enhance outdoor 3D object detection accuracy. To address real-world challenges in outdoor 3D object detection, fusion of LiDAR and RGB input has started gaining traction. However, effective integration of these modalities for precise object detection task still remains a largely open problem. To address that, we propose a MultiStream Detection (MuStD) network, that meticulously extracts task-relevant information from both data modalities. The network follows a three-stream structure. Its LiDAR-PillarNet stream extracts sparse 2D pillar features from the LiDAR input while the LiDAR-Height Compression stream computes Bird's-Eye View features. An additional 3D Multimodal stream combines RGB and LiDAR features using UV mapping and polar coordinate indexing. Eventually, the features containing comprehensive spatial, textural and geometric information are carefully fused and fed to a detection head for 3D object detection. Our extensive evaluation on the challenging KITTI Object Detection Benchmark using public testing server at https://www.cvlibs.net/datasets/kitti/eval_object_detail.php?&result=d162ec699d6992040e34314d19ab7f5c217075e0 establishes the efficacy of our method by achieving new state-of-the-art or highly competitive results in different categories while remaining among the most efficient methods. Our code will be released through MuStD GitHub repository at https://github.com/IbrahimUWA/MuStD.git
URLs: https://www.cvlibs.net/datasets/kitti/eval_object_detail.php?&result=d162ec699d6992040e34314d19ab7f5c217075e0, https://github.com/IbrahimUWA/MuStD.git
Authors: Viktar Dubovik, {\L}ukasz Struski, Jacek Tabor, Dawid Rymarczyk
Abstract: Understanding the decisions made by deep neural networks is essential in high-stakes domains such as medical imaging and autonomous driving. Yet, these models often lack transparency, particularly in computer vision. Prototypical-parts-based neural networks have emerged as a promising solution by offering concept-level explanations. However, most are limited to fine-grained classification tasks, with few exceptions such as InfoDisent. InfoDisent extends prototypical models to large-scale datasets like ImageNet, but produces complex explanations. We introduce Sparse Information Disentanglement for Explainability (SIDE), a novel method that improves the interpretability of prototypical parts through a dedicated training and pruning scheme that enforces sparsity. Combined with sigmoid activations in place of softmax, this approach allows SIDE to associate each class with only a small set of relevant prototypes. Extensive experiments show that SIDE matches the accuracy of existing methods while reducing explanation size by over $90\%$, substantially enhancing the understandability of prototype-based explanations.
Authors: Shuo Yang, Zheyu Zhang, Bardh Prenkaj, Gjergji Kasneci
Abstract: Tabular data is critical across diverse domains, yet high-quality datasets remain scarce due to privacy concerns and the cost of collection. Contemporary approaches adopt large language models (LLMs) for tabular augmentation, but exhibit two major limitations: (1) dense dependency modeling among tabular features that can introduce bias, and (2) high computational overhead in sampling. To address these issues, we propose SPADA for SPArse Dependency-driven Augmentation, a lightweight generative framework that explicitly captures sparse dependencies via an LLM-induced graph. We treat each feature as a node and synthesize values by traversing the graph, conditioning each feature solely on its parent nodes. We explore two synthesis strategies: a non-parametric method using Gaussian kernel density estimation, and a conditional normalizing flow model that learns invertible mappings for conditional density estimation. Experiments on four datasets show that SPADA reduces constraint violations by 4% compared to diffusion-based methods and accelerates generation by nearly 9,500 times over LLM-based baselines.
Authors: Kai Liu, Zhan Su, Peijie Dong, Fengran Mo, Jianfei Gao, ShaoTing Zhang, Kai Chen
Abstract: Recently, recurrent large language models (Recurrent LLMs) with linear computational complexity have re-emerged as efficient alternatives to self-attention-based LLMs (Self-Attention LLMs), which have quadratic complexity. However, Recurrent LLMs often underperform on long-context tasks due to their limited fixed-size memory. Previous research has primarily focused on enhancing the memory capacity of Recurrent LLMs through architectural innovations, but these approaches have not yet enabled Recurrent LLMs to match the performance of Self-Attention LLMs on long-context tasks. We argue that this limitation arises because processing the entire context at once is not well-suited for Recurrent LLMs. In this paper, we propose Smooth Reading, a chunk-wise inference method inspired by human reading strategies. Smooth Reading processes context in chunks and iteratively summarizes the contextual information, thereby reducing memory demands and making the approach more compatible with Recurrent LLMs. Our experimental results show that this method substantially narrows the performance gap between Recurrent and Self-Attention LLMs on long-context tasks, while preserving the efficiency advantages of Recurrent LLMs. Our Smooth Reading boosts SWA-3B-4k (a Recurrent LLM) from 5.68% lower to 3.61% higher performance than Self-Attention LLMs on LongBench. Besides, our method maintains the high efficiency, training 3x faster and inferring 2x faster at 64k context compared to Self-Attention LLMs. To our knowledge, this is the first work to achieve comparable performance using Recurrent LLMs compared with Self-Attention LLMs on long-context tasks. We hope our method will inspire future research in this area. To facilitate further progress, we will release code and dataset.
Authors: Zhen Wan, Chao-Han Huck Yang, Yahan Yu, Jinchuan Tian, Sheng Li, Ke Hu, Zhehuai Chen, Shinji Watanabe, Fei Cheng, Chenhui Chu, Sadao Kurohashi
Abstract: We introduce Speech-based Intelligence Quotient (SIQ) as a new form of human cognition-inspired evaluation pipeline for voice understanding large language models, LLM Voice, designed to assess their voice understanding ability. Moving beyond popular voice understanding metrics such as word error rate (WER), SIQ examines LLM Voice across three cognitive levels motivated by Bloom's Taxonomy: (1) Remembering (i.e., WER for verbatim accuracy); (2) Understanding (i.e., similarity of LLM's interpretations); and (3) Application (i.e., QA accuracy for simulating downstream tasks). We demonstrate that SIQ not only quantifies voice understanding abilities but also provides unified comparisons between cascaded methods (e.g., ASR LLM) and end-to-end models, identifies annotation errors in existing benchmarks, and detects hallucinations in LLM Voice. Our framework represents a first-of-its-kind intelligence examination that bridges cognitive principles with voice-oriented benchmarks, while exposing overlooked challenges in multi-modal training.
Authors: Yusuke Hirota, Boyi Li, Ryo Hachiuma, Yueh-Hua Wu, Boris Ivanovic, Yuta Nakashima, Marco Pavone, Yejin Choi, Yu-Chiang Frank Wang, Chao-Han Huck Yang
Abstract: Large Vision-Language Models (LVLMs) have transformed image captioning, shifting from concise captions to detailed descriptions. We introduce LOTUS, a leaderboard for evaluating detailed captions, addressing three main gaps in existing evaluations: lack of standardized criteria, bias-aware assessments, and user preference considerations. LOTUS comprehensively evaluates various aspects, including caption quality (e.g., alignment, descriptiveness), risks (\eg, hallucination), and societal biases (e.g., gender bias) while enabling preference-oriented evaluations by tailoring criteria to diverse user preferences. Our analysis of recent LVLMs reveals no single model excels across all criteria, while correlations emerge between caption detail and bias risks. Preference-oriented evaluations demonstrate that optimal model selection depends on user priorities.
Authors: Julia Siekiera, Stefan Kramer
Abstract: Artificial intelligence is increasingly leveraged across various domains to automate decision-making processes that significantly impact human lives. In medical image analysis, deep learning models have demonstrated remarkable performance. However, their inherent complexity makes them black box systems, raising concerns about reliability and interpretability. Counterfactual explanations provide comprehensible insights into decision processes by presenting hypothetical "what-if" scenarios that alter model classifications. By examining input alterations, counterfactual explanations provide patterns that influence the decision-making process. Despite their potential, generating plausible counterfactuals that adhere to similarity constraints providing human-interpretable explanations remains a challenge. In this paper, we investigate this challenge by a model-specific optimization approach. While deep generative models such as variational autoencoders (VAEs) exhibit significant generative power, probabilistic models like sum-product networks (SPNs) efficiently represent complex joint probability distributions. By modeling the likelihood of a semi-supervised VAE's latent space with an SPN, we leverage its dual role as both a latent space descriptor and a classifier for a given discrimination task. This formulation enables the optimization of latent space counterfactuals that are both close to the original data distribution and aligned with the target class distribution. We conduct experimental evaluation on the cheXpert dataset. To evaluate the effectiveness of the integration of SPNs, our SPN-guided latent space manipulation is compared against a neural network baseline. Additionally, the trade-off between latent variable regularization and counterfactual quality is analyzed.
Authors: Penny Karanasou, Mengjie Qian, Stefano Bann\`o, Mark J. F. Gales, Kate M. Knill
Abstract: While there exist strong benchmark datasets for grammatical error correction (GEC), high-quality annotated spoken datasets for Spoken GEC (SGEC) are still under-resourced. In this paper, we propose a fully automated method to generate audio-text pairs with grammatical errors and disfluencies. Moreover, we propose a series of objective metrics that can be used to evaluate the generated data and choose the more suitable dataset for SGEC. The goal is to generate an augmented dataset that maintains the textual and acoustic characteristics of the original data while providing new types of errors. This augmented dataset should augment and enrich the original corpus without altering the language assessment scores of the second language (L2) learners. We evaluate the use of the augmented corpus both for written GEC (the text part) and for SGEC (the audio-text pairs). Our experiments are conducted on the S\&I Corpus, the first publicly available speech dataset with grammar error annotations.
Authors: Altaf Allah Abbassi, Leuson Da Silva, Amin Nikanjam, Foutse Khomh
Abstract: Large Language Models (LLMs) for code generation evolve rapidly through fine-tuning, merging, or new model releases. However, such updates can introduce regressions, not only in correctness but also in code quality and performance. To address this, we present ReCatcher, a regression testing framework for Python code generation. ReCatcher systematically compares two LLMs, typically a current model and a candidate update, across three dimensions: logical correctness, static code quality, and execution performance. We apply ReCatcher to assess regressions across three update scenarios, fine-tuning, merging, and model release, using CodeLlama, DeepSeek-Coder, and GPT-4o. Our evaluation shows that fine-tuning with cross-language datasets increases syntax errors by up to 12%. Merging with general-purpose models like Llama2 leads to regressions in correctness by up to 18%. GPT-4o introduces regressions of up to 50% in handling missing imports compared to GPT-3.5-turbo, while GPT-4o-mini suffers up to 80% performance degradation in execution time versus GPT-4o. Overall, logical correctness, performance, and error handling (e.g., syntax errors and missing imports) are the most regression-prone areas. Comparing ReCatcher with baseline solutions, it presents better and consistent accuracy across logical and performance aspects. ReCatcher highlights the importance of systematic regression evaluation before adopting new models, while assisting researchers and practitioners in making more informed update decisions.
Authors: Rajesh Madhipati, Sheethal Bhat, Lukas Buess, Andreas Maier
Abstract: Chest radiography (CXR) plays a crucial role in the diagnosis of various diseases. However, the inherent class imbalance in the distribution of clinical findings presents a significant challenge for current self-supervised deep learning models. These models often fail to accurately classify long-tailed classes. Current Vision-Language models such as Contrastive Language Image Pre-training (CLIP) models effectively model the manifold distribution of the latent space, enabling high zero-shot classification accuracies. Although CLIP performs well on most of the primary classes in the dataset, our work reveals that its effectiveness decreases significantly for classes with a long-tailed distribution. Our approach employs a class-weighting mechanism that directly aligns with the distribution of classes within the latent space. This method ensures a substantial improvement in overall classification performance, with particular emphasis on enhancing the recognition and accuracy of rarely observed classes. We accomplish this by applying Gaussian Mixture Model (GMM) clustering to the latent space. The subsequent clusters are further refined by Student t-distribution, followed by a metric loss that utilizes the altered embeddings. Our approach facilitates stable and adaptive clustering of the features. This results in a notable average improvement of 7\% points in zero-shot AUC scores across 40 classes in the MIMIC-CXR-JPG dataset from previous SOTA models.
Authors: Gabriel Chua
Abstract: As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level cybersecurity threats, fundamentally different from prompt-based vulnerabilities. To systematically evaluate these interpreter-specific risks, we propose CIRCLE (Code-Interpreter Resilience Check for LLM Exploits), a simple benchmark comprising 1,260 prompts targeting CPU, memory, and disk resource exhaustion. Each risk category includes explicitly malicious ("direct") and plausibly benign ("indirect") prompt variants. Our automated evaluation framework assesses not only whether LLMs refuse or generates risky code, but also executes the generated code within the interpreter environment to evaluate code correctness, simplifications made by the LLM to make the code safe, or execution timeouts. Evaluating 7 commercially available models from OpenAI and Google, we uncover significant and inconsistent vulnerabilities. For instance, evaluations show substantial disparities even within providers - OpenAI's o4-mini correctly refuses risky requests at 7.1%, notably higher rates compared to GPT-4.1 at 0.5%. Results particularly underscore that indirect, socially-engineered prompts substantially weaken model defenses. This highlights an urgent need for interpreter-specific cybersecurity benchmarks, dedicated mitigation tools (e.g., guardrails), and clear industry standards to guide safe and responsible deployment of LLM interpreter integrations. The benchmark dataset and evaluation code are publicly released to foster further research.
Authors: Matthias Wei{\ss}, Falk Dettinger, Michael Weyrich
Abstract: Connected and software-defined vehicles promise to offer a broad range of services and advanced functions to customers, aiming to increase passenger comfort and support autonomous driving capabilities. Due to the high reliability and availability requirements of connected vehicles, it is crucial to resolve any occurring failures quickly. To achieve this however, a complex cloud/edge architecture with a mesh of dependencies must be navigated to diagnose the responsible root cause. As such, manual analyses become unfeasible since they would significantly delay the troubleshooting. To address this challenge, this paper presents SDVDiag, an extensible platform for the automated diagnosis of connected vehicle functions. The platform enables the creation of pipelines that cover all steps from initial data collection to the tracing of potential root causes. In addition, SDVDiag supports self-adaptive behavior by the ability to exchange modules at runtime. Dependencies between functions are detected and continuously updated, resulting in a dynamic graph view of the system. In addition, vital system metrics are monitored for anomalies. Whenever an incident is investigated, a snapshot of the graph is taken and augmented by relevant anomalies. Finally, the analysis is performed by traversing the graph and creating a ranking of the most likely causes. To evaluate the platform, it is deployed inside an 5G test fleet environment for connected vehicle functions. The results show that injected faults can be detected reliably. As such, the platform offers the potential to gain new insights and reduce downtime by identifying problems and their causes at an early stage.
Authors: Sarah Lockfisch, Kristian Schwethelm, Martin Menten, Rickmer Braren, Daniel Rueckert, Alexander Ziller, Georgios Kaissis
Abstract: Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In medicine, these models can admit conflicting predictions for the same patient -- a risk that is poorly understood and insufficiently addressed. In this study, we empirically analyze the extent, drivers, and ramifications of predictive multiplicity across diverse medical tasks and model architectures, and show that even small ensembles can mitigate/eliminate predictive multiplicity in practice. Our analysis reveals that (1) standard validation metrics fail to identify a uniquely optimal model and (2) a substantial amount of predictions hinges on arbitrary choices made during model development. Using multiple models instead of a single model reveals instances where predictions differ across equally plausible models -- highlighting patients that would receive arbitrary diagnoses if any single model were used. In contrast, (3) a small ensemble paired with an abstention strategy can effectively mitigate measurable predictive multiplicity in practice; predictions with high inter-model consensus may thus be amenable to automated classification. While accuracy is not a principled antidote to predictive multiplicity, we find that (4) higher accuracy achieved through increased model capacity reduces predictive multiplicity. Our findings underscore the clinical importance of accounting for model multiplicity and advocate for ensemble-based strategies to improve diagnostic reliability. In cases where models fail to reach sufficient consensus, we recommend deferring decisions to expert review.
Authors: StepFun, :, Bin Wang, Bojun Wang, Changyi Wan, Guanzhe Huang, Hanpeng Hu, Haonan Jia, Hao Nie, Mingliang Li, Nuo Chen, Siyu Chen, Song Yuan, Wuxun Xie, Xiaoniu Song, Xing Chen, Xingping Yang, Xuelin Zhang, Yanbo Yu, Yaoyu Wang, Yibo Zhu, Yimin Jiang, Yu Zhou, Yuanwei Lu, Houyi Li, Jingcheng Hu, Ka Man Lo, Ailin Huang, Binxing Jiao, Bo Li, Boyu Chen, Changxin Miao, Chang Lou, Chen Hu, Chen Xu, Chenfeng Yu, Chengyuan Yao, Daokuan Lv, Dapeng Shi, Deshan Sun, Ding Huang, Dingyuan Hu, Dongqing Pang, Enle Liu, Fajie Zhang, Fanqi Wan, Gulin Yan, Han Zhang, Han Zhou, Hanghao Wu, Hangyu Guo, Hanqi Chen, Hanshan Zhang, Hao Wu, Haocheng Zhang, Haolong Yan, Haoran Lv, Haoran Wei, Hebin Zhou, Heng Wang, Heng Wang, Hongxin Li, Hongyu Zhou, Hongyuan Wang, Huiyong Guo, Jia Wang, Jiahao Gong, Jialing Xie, Jian Zhou, Jianjian Sun, Jiaoren Wu, Jiaran Zhang, Jiayu Liu, Jie Cheng, Jie Luo, Jie Yan, Jie Yang, Jieyi Hou, Jinguang Zhang, Jinlan Cao, Jisheng Yin, Junfeng Liu, Junhao Huang, Junzhe Lin, Kaijun Tan, Kaixiang Li, Kang An, Kangheng Lin, Kenkun Liu, Lei Yang, Liang Zhao, Liangyu Chen, Lieyu Shi, Liguo Tan, Lin Lin, Lin Zhang, Lina Chen, Liwen Huang, Liying Shi, Longlong Gu, Mei Chen, Mengqiang Ren, Ming Li, Mingzhe Chen, Na Wang, Nan Wu, Qi Han, Qian Zhao, Qiang Zhang, Qianni Liu, Qiaohui Chen, Qiling Wu, Qinglin He, Qinyuan Tan, Qiufeng Wang, Qiuping Wu, Qiuyan Liang, Quan Sun, Rui Li, Ruihang Miao, Ruosi Wan, Ruyan Guo, Shangwu Zhong, Shaoliang Pang, Shengjie Fan, Shijie Shang, Shilei Jiang, Shiliang Yang, Shiming Hao, Shuli Gao, Siming Huang, Siqi Liu, Tiancheng Cao, Tianhao Cheng, Tianhao Peng, Wang You, Wei Ji, Wen Sun, Wenjin Deng, Wenqing He, Wenzhen Zheng, Xi Chen, Xiangwen Kong, Xianzhen Luo, Xiaobo Yang, Xiaojia Liu, Xiaoxiao Ren, Xin Han, Xin Li, Xin Wu, Xu Zhao, Yanan Wei, Yang Li, Yangguang Li, Yangshijie Xu, Yanming Xu, Yaqiang Shi, Yeqing Shen, Yi Yang, Yifei Yang, Yifeng Gong, Yihan Chen, Yijing Yang, Yinmin Zhang, Yizhuang Zhou, Yuanhao Ding, Yuantao Fan, Yuanzhen Yang, Yuchu Luo, Yue Peng, Yufan Lu, Yuhang Deng, Yuhe Yin, Yujie Liu, Yukun Chen, Yuling Zhao, Yun Mou, Yunlong Li, Yunzhou Ju, Yusheng Li, Yuxiang Yang, Yuxiang Zhang, Yuyang Chen, Zejia Weng, Zhe Xie, Zheng Ge, Zheng Gong, Zhenyi Lu, Zhewei Huang, Zhichao Chang, Zhiguo Huang, Zhirui Wang, Zidong Yang, Zili Wang, Ziqi Wang, Zixin Zhang, Binxing Jiao, Daxin Jiang, Heung-Yeung Shum, Xiangyu Zhang
Abstract: Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hardware-aware model-system co-design optimized for minimizing decoding costs. Step-3 innovates in two key dimensions: (1) A novel Multi-Matrix Factorization Attention (MFA) mechanism that significantly reduces both KV cache size and computation while maintaining high attention expressiveness, and (2) Attention-FFN Disaggregation (AFD), a distributed inference system that decouples attention and Feed-Forward Network (FFN) layers into specialized subsystems. This co-design achieves unprecedented cost efficiency: Step-3 significantly reduces theoretical decoding costs compared with models like DeepSeek-V3 and Qwen3 MoE 235B, with the gains widening at longer context. Step-3 achieves low cost while activating 38B parameters per token (more than DeepSeek-V3 and Qwen3 MoE 235B), demonstrating that hardware-aligned attention arithmetic intensity, MoE sparsity, and AFD are critical to cost-effectiveness. We perform a head-to-head comparison with DeepSeek-V3 in its favorable scenarios. Our implementation on Hopper GPUs achieves a decoding throughput of up to 4,039 tokens per second per GPU under 50ms TPOT SLA (4K context, FP8, no MTP). It is higher than DeepSeek-V3's 2,324 in the same setup and sets a new Pareto frontier for LLM decoding.
Authors: Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab
Abstract: Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language can often provide a much richer learning medium for LLMs, compared with policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples system-level trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across four tasks, GEPA outperforms GRPO by 10% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% across two LLMs, and demonstrates promising results as an inference-time search strategy for code optimization.
Authors: Anton Pembek, Artem Fatkulin, Anton Klenitskiy, Alexey Vasilev
Abstract: Many sequential recommender systems suffer from the cold start problem, where items with few or no interactions cannot be effectively used by the model due to the absence of a trained embedding. Content-based approaches, which leverage item metadata, are commonly used in such scenarios. One possible way is to use embeddings derived from content features such as textual descriptions as initialization for the model embeddings. However, directly using frozen content embeddings often results in suboptimal performance, as they may not fully adapt to the recommendation task. On the other hand, fine-tuning these embeddings can degrade performance for cold-start items, as item representations may drift far from their original structure after training. We propose a novel approach to address this limitation. Instead of entirely freezing the content embeddings or fine-tuning them extensively, we introduce a small trainable delta to frozen embeddings that enables the model to adapt item representations without letting them go too far from their original semantic structure. This approach demonstrates consistent improvements across multiple datasets and modalities, including e-commerce datasets with textual descriptions and a music dataset with audio-based representation.
Authors: Sang-Woo Lee, Sohee Yang, Donghyun Kwak, Noah Y. Siegel
Abstract: Many recent papers have studied the development of superforecaster-level event forecasting LLMs. While methodological problems with early studies cast doubt on the use of LLMs for event forecasting, recent studies with improved evaluation methods have shown that state-of-the-art LLMs are gradually reaching superforecaster-level performance, and reinforcement learning has also been reported to improve future forecasting. Additionally, the unprecedented success of recent reasoning models and Deep Research-style models suggests that technology capable of greatly improving forecasting performance has been developed. Therefore, based on these positive recent trends, we argue that the time is ripe for research on large-scale training of superforecaster-level event forecasting LLMs. We discuss two key research directions: training methods and data acquisition. For training, we first introduce three difficulties of LLM-based event forecasting training: noisiness-sparsity, knowledge cut-off, and simple reward structure problems. Then, we present related ideas to mitigate these problems: hypothetical event Bayesian networks, utilizing poorly-recalled and counterfactual events, and auxiliary reward signals. For data, we propose aggressive use of market, public, and crawling datasets to enable large-scale training and evaluation. Finally, we explain how these technical advances could enable AI to provide predictive intelligence to society in broader areas. This position paper presents promising specific paths and considerations for getting closer to superforecaster-level AI technology, aiming to call for researchers' interest in these directions.
Authors: Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip H. S. Torr, Lewis Hammond, Christian Schroeder de Witt
Abstract: Recent capability increases in large language models (LLMs) open up applications in which groups of communicating generative AI agents solve joint tasks. This poses privacy and security challenges concerning the unauthorised sharing of information, or other unwanted forms of agent coordination. Modern steganographic techniques could render such dynamics hard to detect. In this paper, we comprehensively formalise the problem of secret collusion in systems of generative AI agents by drawing on relevant concepts from both AI and security literature. We study incentives for the use of steganography, and propose a variety of mitigation measures. Our investigations result in a model evaluation framework that systematically tests capabilities required for various forms of secret collusion. We provide extensive empirical results across a range of contemporary LLMs. While the steganographic capabilities of current models remain limited, GPT-4 displays a capability jump suggesting the need for continuous monitoring of steganographic frontier model capabilities. We conclude by laying out a comprehensive research program to mitigate future risks of collusion between generative AI models.
Authors: Lixiang Xu, Xianwei Ding, Xin Yuan, Zhanlong Wang, Lu Bai, Enhong Chen, Philip S. Yu, Yuanyan Tang
Abstract: Designed to track changes in students' knowledge status and predict their future answers based on students' historical answer records. Current research on KT modeling focuses on predicting future student performance based on existing, unupdated records of student learning interactions. However, these methods ignore distractions in the response process (such as slipping and guessing) and ignore that static cognitive representations are temporary and limited. Most of them assume that there are no distractions during the answering process, and that the recorded representation fully represents the student's understanding and proficiency in knowledge. This can lead to many dissonant and uncoordinated issues in the original record. Therefore, we propose a knowledge-tracking cognitive representation optimization (CRO-KT) model that uses dynamic programming algorithms to optimize the structure of cognitive representation. This ensures that the structure matches the student's cognitive patterns in terms of practice difficulty. In addition, we use a synergistic optimization algorithm to optimize the cognitive representation of sub-target exercises based on the overall picture of exercise responses by considering all exercises with synergistic relationships as one goal. At the same time, the CRO-KT model integrates the relationship embedding learned in the dichotomous graph with the optimized record representation in a weighted manner, which enhances students' cognitive expression ability. Finally, experiments were conducted on three public datasets to verify the effectiveness of the proposed cognitive representation optimization model.
Authors: Yuhang Yao, Haixin Wang, Yibo Chen, Jiawen Wang, Min Chang Jordan Ren, Bosheng Ding, Salman Avestimehr, Chaoyang He
Abstract: AI Agents powered by Large Language Models are transforming the world through enormous applications. A super agent has the potential to fulfill diverse user needs, such as summarization, coding, and research, by accurately understanding user intent and leveraging the appropriate tools to solve tasks. However, to make such an agent viable for real-world deployment and accessible at scale, significant optimizations are required to ensure high efficiency and low cost. This position paper presents a design of the Super Agent System powered by the hybrid AI routers. Upon receiving a user prompt, the system first detects the intent of the user, then routes the request to specialized task agents with the necessary tools or automatically generates agentic workflows. In practice, most applications directly serve as AI assistants on edge devices such as phones and robots. As different language models vary in capability and cloud-based models often entail high computational costs, latency, and privacy concerns, we then explore the hybrid mode where the router dynamically selects between local and cloud models based on task complexity. Finally, we introduce the blueprint of an on-device super agent enhanced with cloud. With advances in multi-modality models and edge hardware, we envision that most computations can be handled locally, with cloud collaboration only as needed. Such architecture paves the way for super agents to be seamlessly integrated into everyday life in the near future.
Authors: Zuhong Lin, Daoyuan Ren, Kai Ran, Jing Sun, Songlin Yu, Xuefeng Bai, Xiaotiang Huang, Haiyang He, Pengxu Pan, Xiaohang Zhang, Ying Fang, Tianying Wang, Minli Wu, Zhanglin Li, Xiaochuan Zhang, Haipu Li, Jingjing Yao
Abstract: Accurately identifying synthesis conditions for metal-organic frameworks (MOFs) remains a critical bottleneck in materials research, as translating literature-derived knowledge into actionable insights is hindered by the unstructured and heterogeneous nature of scientific texts. Here we present MOFh6, a large language model (LLM)-based multi-agent system designed to extract, structure, and apply synthesis knowledge from diverse input formats, including raw literature and crystal codes. Built on gpt-4o-mini and fine-tuned with up to few-shot expert-annotated data, MOFh6 achieves 99% accuracy in synthesis data parsing and resolves 94.1% of complex co-reference abbreviations. It processes a single full-text document in 9.6 seconds and localizes structured synthesis descriptions within 36 seconds, with the cost per 100 papers reduced to USD 4.24, a 76% saving over existing systems. By addressing long-standing limitations in cross-paragraph semantic fusion and terminology standardization, MOFh6 reshapes the LLM-based paradigm for MOF synthesis research, transforming static retrieval into an integrated and dynamic knowledge acquisition process. This shift bridges the gap between scientific literature and actionable synthesis design, providing a scalable framework for accelerating materials discovery.
Authors: Alice Rueda, Mohammed S. Hassan, Argyrios Perivolaris, Bazen G. Teferra, Reza Samavi, Sirisha Rambhatla, Yuqi Wu, Yanbo Zhang, Bo Cao, Divya Sharma, Sridhar Krishnan, Venkat Bhat
Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and problem-solving across various domains. However, their ability to perform complex, multi-step reasoning task-essential for applications in science, medicine, and law-remains an area of active investigation. This paper examines the reasoning capabilities of contemporary LLMs, analyzing their strengths, limitations, and potential for improvement. The study uses prompt engineering techniques on the Graduate-Level GoogleProof Q&A (GPQA) dataset to assess the scientific reasoning of GPT-4o. Five popular prompt engineering techniques and two tailored promptings were tested: baseline direct answer (zero-shot), chain-of-thought (CoT), zero-shot CoT, self-ask, self-consistency, decomposition, and multipath promptings. Our findings indicate that while LLMs exhibit emergent reasoning abilities, they often rely on pattern recognition rather than true logical inference, leading to inconsistencies in complex problem-solving. The results indicated that self-consistency outperformed the other prompt engineering technique with an accuracy of 52.99%, followed by direct answer (52.23%). Zero-shot CoT (50%) outperformed multipath (48.44%), decomposition (47.77%), self-ask (46.88%), and CoT (43.75%). Self-consistency performed the second worst in explaining the answers. Simple techniques such as direct answer, CoT, and zero-shot CoT have the best scientific reasoning. We propose a research agenda aimed at bridging these gaps by integrating structured reasoning frameworks, hybrid AI approaches, and human-in-the-loop methodologies. By critically evaluating the reasoning mechanisms of LLMs, this paper contributes to the ongoing discourse on the future of artificial general intelligence and the development of more robust, trustworthy AI systems.
Authors: Praphul Singh, Charlotte Dzialo, Jangwon Kim, Sumana Srivatsa, Irfan Bulu, Sri Gadde, Krishnaram Kenthapadi
Abstract: Ensuring clinical data privacy while preserving utility is critical for AI-driven healthcare and data analytics. Existing de-identification (De-ID) methods, including rule-based techniques, deep learning models, and large language models (LLMs), often suffer from recall errors, limited generalization, and inefficiencies, limiting their real-world applicability. We propose a fully automated, multi-modal framework, RedactOR for de-identifying structured and unstructured electronic health records, including clinical audio records. Our framework employs cost-efficient De-ID strategies, including intelligent routing, hybrid rule and LLM based approaches, and a two-step audio redaction approach. We present a retrieval-based entity relexicalization approach to ensure consistent substitutions of protected entities, thereby enhancing data coherence for downstream applications. We discuss key design desiderata, de-identification and relexicalization methodology, and modular architecture of RedactOR and its integration with the Oracle Health Clinical AI system. Evaluated on the i2b2 2014 De-ID dataset using standard metrics with strict recall, our approach achieves competitive performance while optimizing token usage to reduce LLM costs. Finally, we discuss key lessons and insights from deployment in real-world AI- driven healthcare data pipelines.
Authors: Yigui Feng, Qinglin Wang, Ke Liu, Xinhai Chen, Bo Yang, Jie Liu
Abstract: Psychological counseling faces huge challenges due to the growing demand for mental health services and the shortage of trained professionals. Large language models (LLMs) have shown potential to assist psychological counseling, especially in empathy and emotional support. However, existing models lack a deep understanding of emotions and are unable to generate personalized treatment plans based on fine-grained emotions. To address these shortcomings, we present AI PsyRoom, a multi-agent simulation framework designed to enhance psychological counseling by generating empathetic and emotionally nuanced conversations. By leveraging fine-grained emotion classification and a multi-agent framework, we construct a multi-agent PsyRoom A for dialogue reconstruction, generating a high-quality dialogue dataset EmoPsy, which contains 35 sub-emotions, 423 specific emotion scenarios, and 12,350 dialogues. We also propose PsyRoom B for generating personalized treatment plans. Quantitative evaluations demonstrate that AI PsyRoom significantly outperforms state-of-the-art methods, achieving 18% improvement in problem orientation, 23% in expression, 24% in Empathy, and 16% in interactive communication quality. The datasets and models are publicly available, providing a foundation for advancing AI-assisted psychological counseling research.
Authors: Hongjun An, Wenhan Hu, Sida Huang, Siqi Huang, Ruanjun Li, Yuanzhi Liang, Jiawei Shao, Yiliang Song, Zihan Wang, Cheng Yuan, Chi Zhang, Hongyuan Zhang, Wenhao Zhuang, Xuelong Li
Abstract: Pioneered by the foundational information theory by Claude Shannon and the visionary framework of machine intelligence by Alan Turing, the convergent evolution of information and communication technologies (IT/CT) has created an unbroken wave of connectivity and computation. This synergy has sparked a technological revolution, now reaching its peak with large artificial intelligence (AI) models that are reshaping industries and redefining human-machine collaboration. However, the realization of ubiquitous intelligence faces considerable challenges due to substantial resource consumption in large models and high communication bandwidth demands. To address these challenges, AI Flow has been introduced as a multidisciplinary framework that integrates cutting-edge IT and CT advancements, with a particular emphasis on the following three key points. First, device-edge-cloud framework serves as the foundation, which integrates end devices, edge servers, and cloud clusters to optimize scalability and efficiency for low-latency model inference. Second, we introduce the concept of familial models, which refers to a series of different-sized models with aligned hidden features, enabling effective collaboration and the flexibility to adapt to varying resource constraints and dynamic scenarios. Third, connectivity- and interaction-based intelligence emergence is a novel paradigm of AI Flow. By leveraging communication networks to enhance connectivity, the collaboration among AI models across heterogeneous nodes achieves emergent intelligence that surpasses the capability of any single model. The innovations of AI Flow provide enhanced intelligence, timely responsiveness, and ubiquitous accessibility to AI services, paving the way for the tighter fusion of AI techniques and communication systems.
Authors: Joel Becker, Nate Rush, Elizabeth Barnes, David Rein
Abstract: Despite widespread adoption, the impact of AI tools on software development in the wild remains understudied. We conduct a randomized controlled trial (RCT) to understand how AI tools at the February-June 2025 frontier affect the productivity of experienced open-source developers. 16 developers with moderate AI experience complete 246 tasks in mature projects on which they have an average of 5 years of prior experience. Each task is randomly assigned to allow or disallow usage of early 2025 AI tools. When AI tools are allowed, developers primarily use Cursor Pro, a popular code editor, and Claude 3.5/3.7 Sonnet. Before starting tasks, developers forecast that allowing AI will reduce completion time by 24%. After completing the study, developers estimate that allowing AI reduced completion time by 20%. Surprisingly, we find that allowing AI actually increases completion time by 19%--AI tooling slowed developers down. This slowdown also contradicts predictions from experts in economics (39% shorter) and ML (38% shorter). To understand this result, we collect and evaluate evidence for 20 properties of our setting that a priori could contribute to the observed slowdown effect--for example, the size and quality standards of projects, or prior developer experience with AI tooling. Although the influence of experimental artifacts cannot be entirely ruled out, the robustness of the slowdown effect across our analyses suggests it is unlikely to primarily be a function of our experimental design.
Authors: David Poole
Abstract: AI seems to be taking over the world with systems that model pixels, words, and phonemes. The world is arguably made up, not of pixels, words, and phonemes but of entities (objects, things, including events) with properties and relations among them. Surely we should model these, not the perception or description of them. You might suspect that concentrating on modeling words and pixels is because all of the (valuable) data in the world is in terms of text and images. If you look into almost any company you will find their most valuable data is in spreadsheets, databases and other relational formats. These are not the form that are studied in introductory machine learning, but are full of product numbers, student numbers, transaction numbers and other identifiers that can't be interpreted naively as numbers. The field that studies this sort of data has various names including relational learning, statistical relational AI, and many others. This paper explains why relational learning is not taking over the world -- except in a few cases with restricted relations -- and what needs to be done to bring it to it's rightful prominence.
Authors: Yichen Huang, Lin F. Yang
Abstract: The International Mathematical Olympiad (IMO) poses uniquely challenging problems requiring deep insight, creativity, and formal reasoning. While Large Language Models (LLMs) perform well on mathematical benchmarks like AIME, they struggle with Olympiad-level tasks. We use Google's Gemini 2.5 Pro on the newly released IMO 2025 problems, avoiding data contamination. Using a self-verification pipeline with careful prompt design, 5 (out of 6) problems are solved correctly. This result underscores the importance of developing optimal strategies to harness the full potential of powerful LLMs for complex reasoning tasks.
Authors: Sho Takase, Shun Kiyono, Sosuke Kobayashi, Jun Suzuki
Abstract: Loss spikes often occur during pre-training of large language models. The spikes degrade the performance of large language models and sometimes ruin the pre-training. Since the pre-training needs a vast computational budget, we should avoid such spikes. Based on the assumption that the loss spike is caused by the sudden growth of the gradient norm, we explore factors to keep the gradient norm small through an analysis of the spectral norms of the Jacobian matrices for the sub-layers. Our findings suggest that stabilizing the pre-training process requires two conditions: small sub-layers and large shortcut. We conduct various experiments to empirically verify our theoretical analyses. Experimental results demonstrate that methods satisfying the conditions effectively prevent loss spikes during pre-training.
Authors: Tu Nguyen, Nedim \v{S}rndi\'c, Alexander Neth
Abstract: Tactics, Techniques and Procedures (TTPs) represent sophisticated attack patterns in the cybersecurity domain, described encyclopedically in textual knowledge bases. Identifying TTPs in cybersecurity writing, often called TTP mapping, is an important and challenging task. Conventional learning approaches often target the problem in the classical multi-class or multilabel classification setting. This setting hinders the learning ability of the model due to a large number of classes (i.e., TTPs), the inevitable skewness of the label distribution and the complex hierarchical structure of the label space. We formulate the problem in a different learning paradigm, where the assignment of a text to a TTP label is decided by the direct semantic similarity between the two, thus reducing the complexity of competing solely over the large labeling space. To that end, we propose a neural matching architecture with an effective sampling-based learn-to-compare mechanism, facilitating the learning process of the matching model despite constrained resources.
Authors: Fatemeh Nazary, Yashar Deldjoo, Tommaso Di Noia, Eugenio di Sciascio
Abstract: Clinical decision support systems require models that are not only highly accurate but also equitable and sensitive to the implications of missed diagnoses. In this study, we introduce a knowledge-guided in-context learning (ICL) framework designed to enable large language models (LLMs) to effectively process structured clinical data. Our approach integrates domain-specific feature groupings, carefully balanced few-shot examples, and task-specific prompting strategies. We systematically evaluate this method across seventy distinct ICL designs by various prompt variations and two different communication styles-natural-language narrative and numeric conversational-and compare its performance to robust classical machine learning (ML) benchmarks on tasks involving heart disease and diabetes prediction. Our findings indicate that while traditional ML models maintain superior performance in balanced precision-recall scenarios, LLMs employing narrative prompts with integrated domain knowledge achieve higher recall and significantly reduce gender bias, effectively narrowing fairness disparities by an order of magnitude. Despite the current limitation of increased inference latency, LLMs provide notable advantages, including the capacity for zero-shot deployment and enhanced equity. This research offers the first comprehensive analysis of ICL design considerations for applying LLMs to tabular clinical tasks and highlights distillation and multimodal extensions as promising directions for future research.
Authors: Yan Ru Pei, Olivier Coenen
Abstract: We introduce a class of neural networks named PLEIADES (PoLynomial Expansion In Adaptive Distributed Event-based Systems), which contains temporal convolution kernels generated from orthogonal polynomial basis functions. We focus on interfacing these networks with event-based data to perform online spatiotemporal classification and detection with low latency. By virtue of using structured temporal kernels and event-based data, we have the freedom to vary the sample rate of the data along with the discretization step-size of the network without additional finetuning. We experimented with three event-based benchmarks and obtained state-of-the-art results on all three by large margins with significantly smaller memory and compute costs. We achieved: 1) 99.59% accuracy with 192K parameters on the DVS128 hand gesture recognition dataset and 100% with a small additional output filter; 2) 99.58% test accuracy with 277K parameters on the AIS 2024 eye tracking challenge; and 3) 0.556 mAP with 576k parameters on the PROPHESEE 1 Megapixel Automotive Detection Dataset.
Authors: Ruiyuan Gao, Kai Chen, Zhihao Li, Lanqing Hong, Zhenguo Li, Qiang Xu
Abstract: Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains underdeveloped. Existing methods lack flexible controllability and often rely on dense view data collection in controlled environments, limiting their generalizability across common datasets (e.g., nuScenes). In this paper, we introduce MagicDrive3D, a novel framework for controllable 3D street scene generation that combines video-based view synthesis with 3D representation (3DGS) generation. It supports multi-condition control, including road maps, 3D objects, and text descriptions. Unlike previous approaches that require 3D representation before training, MagicDrive3D first trains a multi-view video generation model to synthesize diverse street views. This method utilizes routinely collected autonomous driving data, reducing data acquisition challenges and enriching 3D scene generation. In the 3DGS generation step, we introduce Fault-Tolerant Gaussian Splatting to address minor errors and use monocular depth for better initialization, alongside appearance modeling to manage exposure discrepancies across viewpoints. Experiments show that MagicDrive3D generates diverse, high-quality 3D driving scenes, supports any-view rendering, and enhances downstream tasks like BEV segmentation, demonstrating its potential for autonomous driving simulation and beyond.
Authors: Dominik Macko, Jakub Kopal, Robert Moro, Ivan Srba
Abstract: Recent LLMs are able to generate high-quality multilingual texts, indistinguishable for humans from authentic human-written ones. Research in machine-generated text detection is however mostly focused on the English language and longer texts, such as news articles, scientific papers or student essays. Social-media texts are usually much shorter and often feature informal language, grammatical errors, or distinct linguistic items (e.g., emoticons, hashtags). There is a gap in studying the ability of existing methods in detection of such texts, reflected also in the lack of existing multilingual benchmark datasets. To fill this gap we propose the first multilingual (22 languages) and multi-platform (5 social media platforms) dataset for benchmarking machine-generated text detection in the social-media domain, called MultiSocial. It contains 472,097 texts, of which about 58k are human-written and approximately the same amount is generated by each of 7 multilingual LLMs. We use this benchmark to compare existing detection methods in zero-shot as well as fine-tuned form. Our results indicate that the fine-tuned detectors have no problem to be trained on social-media texts and that the platform selection for training matters.
Authors: Veedant Jain, Gabriel Kreiman, Felipe dos Santos Alves Feitosa
Abstract: Despite significant advancements in image segmentation and object detection, understanding complex scenes remains a significant challenge. Here, we focus on graphical humor as a paradigmatic example of image interpretation that requires elucidating the interaction of different scene elements in the context of prior cognitive knowledge. This paper introduces \textbf{HumorDB}, a novel, controlled, and carefully curated dataset designed to evaluate and advance visual humor understanding by AI systems. The dataset comprises diverse images spanning photos, cartoons, sketches, and AI-generated content, including minimally contrastive pairs where subtle edits differentiate between humorous and non-humorous versions. We evaluate humans, state-of-the-art vision models, and large vision-language models on three tasks: binary humor classification, funniness rating prediction, and pairwise humor comparison. The results reveal a gap between current AI systems and human-level humor understanding. While pretrained vision-language models perform better than vision-only models, they still struggle with abstract sketches and subtle humor cues. Analysis of attention maps shows that even when models correctly classify humorous images, they often fail to focus on the precise regions that make the image funny. Preliminary mechanistic interpretability studies and evaluation of model explanations provide initial insights into how different architectures process humor. Our results identify promising trends and current limitations, suggesting that an effective understanding of visual humor requires sophisticated architectures capable of detecting subtle contextual features and bridging the gap between visual perception and abstract reasoning. All the code and data are available here: \href{https://github.com/kreimanlab/HumorDB}{https://github.com/kreimanlab/HumorDB}
URLs: https://github.com/kreimanlab/HumorDB, https://github.com/kreimanlab/HumorDB
Authors: Rhys Burchett-Vass, Arshdeep Singh, Gabriel Bibb\'o, Mark D. Plumbley
Abstract: The broadcasting industry has adopted IP technologies, revolutionising both live and pre-recorded content production, from news gathering to live music events. IP broadcasting allows for the transport of audio and video signals in an easily configurable way, aligning with modern networking techniques. This shift towards an IP workflow allows for much greater flexibility, not only in routing signals but with the integration of tools using standard web development techniques. One possible tool could include the use of live audio tagging, which has a number of uses in the production of content. These could include adding sound effects to automated closed captioning or identifying unwanted sound events within a scene. In this paper, we describe the process of containerising an audio tagging model into a microservice, a small segregated code module that can be integrated into a multitude of different network setups. The goal is to develop a modular, accessible, and flexible tool capable of seamless deployment into broadcasting workflows of all sizes, from small productions to large corporations. Challenges surrounding latency of the selected audio tagging model and its effect on the usefulness of the end product are discussed.
Authors: Xiang Gao, Jiaying Liu
Abstract: Large-scale text-to-image diffusion models have been a revolutionary milestone in the evolution of generative AI and multimodal technology, allowing wonderful image generation with natural-language text prompt. However, the issue of lacking controllability of such models restricts their practical applicability for real-life content creation. Thus, attention has been focused on leveraging a reference image to control text-to-image synthesis, which is also regarded as manipulating (or editing) a reference image as per a text prompt, namely, text-driven image-to-image translation. This paper contributes a novel, concise, and efficient approach that adapts pre-trained large-scale text-to-image (T2I) diffusion model to the image-to-image (I2I) paradigm in a plug-and-play manner, realizing high-quality and versatile text-driven I2I translation without any model training, model fine-tuning, or online optimization process. To guide T2I generation with a reference image, we propose to decompose diverse guiding factors with different frequency bands of diffusion features in the DCT spectral space, and accordingly devise a novel frequency band substitution layer which realizes dynamic control of the reference image to the T2I generation result in a plug-and-play manner. We demonstrate that our method allows flexible control over both guiding factor and guiding intensity of the reference image simply by tuning the type and bandwidth of the substituted frequency band, respectively. Extensive qualitative and quantitative experiments verify superiority of our approach over related methods in I2I translation visual quality, versatility, and controllability. The code is publicly available at: https://github.com/XiangGao1102/FBSDiff.
Authors: Weiwen Liu, Xu Huang, Xingshan Zeng, Xinlong Hao, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan, Zhengying Liu, Yuanqing Yu, Zezhong Wang, Yuxian Wang, Wu Ning, Yutai Hou, Bin Wang, Chuhan Wu, Xinzhi Wang, Yong Liu, Yasheng Wang, Duyu Tang, Dandan Tu, Lifeng Shang, Xin Jiang, Ruiming Tang, Defu Lian, Qun Liu, Enhong Chen
Abstract: Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability. However, real function-calling data is quite challenging to collect and annotate, while synthetic data generated by existing pipelines tends to lack coverage and accuracy. In this paper, we present ToolACE, an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data. ToolACE leverages a novel self-evolution synthesis process to curate a comprehensive API pool of 26,507 diverse APIs. Dialogs are further generated through the interplay among multiple agents, guided by a formalized thinking process. To ensure data accuracy, we implement a dual-layer verification system combining rule-based and model-based checks. We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard, rivaling the latest GPT-4 models. Our model and a subset of the data are publicly available at https://huggingface.co/Team-ACE.
Authors: Yuqian Fu, Runze Wang, Bin Ren, Guolei Sun, Biao Gong, Yanwei Fu, Danda Pani Paudel, Xuanjing Huang, Luc Van Gool
Abstract: Bridging the gap between ego-centric and exo-centric views has been a long-standing question in computer vision. In this paper, we focus on the emerging Ego-Exo object correspondence task, which aims to understand object relations across ego-exo perspectives through segmentation. While numerous segmentation models have been proposed, most operate on a single image (view), making them impractical for cross-view scenarios. PSALM, a recently proposed segmentation method, stands out as a notable exception with its demonstrated zero-shot ability on this task. However, due to the drastic viewpoint change between ego and exo, PSALM fails to accurately locate and segment objects, especially in complex backgrounds or when object appearances change significantly. To address these issues, we propose ObjectRelator, a novel approach featuring two key modules: Multimodal Condition Fusion (MCFuse) and SSL-based Cross-View Object Alignment (XObjAlign). MCFuse introduces language as an additional cue, integrating both visual masks and textual descriptions to improve object localization and prevent incorrect associations. XObjAlign enforces cross-view consistency through self-supervised alignment, enhancing robustness to object appearance variations. Extensive experiments demonstrate ObjectRelator's effectiveness on the large-scale Ego-Exo4D benchmark and HANDAL-X (an adapted dataset for cross-view segmentation) with state-of-the-art performance. Code is made available at: http://yuqianfu.com/ObjectRelator.
Authors: Wenjun Huang, Yang Ni, Hanning Chen, Yirui He, Ian Bryant, Yezi Liu, Mohsen Imani
Abstract: Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to localize an arbitrary number of targets based on a language expression and continuously track them in a video. This intricate task involves reasoning on multi-modal data and precise target localization with temporal association. However, prior studies overlook the imbalanced data distribution between newborn targets and existing targets due to the nature of the task. In addition, they only indirectly fuse multi-modal features, struggling to deliver clear guidance on newborn target detection. To solve the above issues, we conduct a collaborative matching strategy to alleviate the impact of the imbalance, boosting the ability to detect newborn targets while maintaining tracking performance. In the encoder, we integrate and enhance the cross-modal and multi-scale fusion, overcoming the bottlenecks in previous work, where limited multi-modal information is shared and interacted between feature maps. In the decoder, we also develop a referring-infused adaptation that provides explicit referring guidance through the query tokens. The experiments showcase the superior performance of our model (+3.42%) compared to prior works, demonstrating the effectiveness of our designs.
Authors: Aneta Zugecova, Dominik Macko, Ivan Srba, Robert Moro, Jakub Kopal, Katarina Marcincinova, Matus Mesarcik
Abstract: The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be effectively misused for generating disinformation news articles following predefined narratives. Their capabilities to generate personalized (in various aspects) content have also been evaluated and mostly found usable. However, a combination of personalization and disinformation abilities of LLMs has not been comprehensively studied yet. Such a dangerous combination should trigger integrated safety filters of the LLMs, if there are some. This study fills this gap by evaluating vulnerabilities of recent open and closed LLMs, and their willingness to generate personalized disinformation news articles in English. We further explore whether the LLMs can reliably meta-evaluate the personalization quality and whether the personalization affects the generated-texts detectability. Our results demonstrate the need for stronger safety-filters and disclaimers, as those are not properly functioning in most of the evaluated LLMs. Additionally, our study revealed that the personalization actually reduces the safety-filter activations; thus effectively functioning as a jailbreak. Such behavior must be urgently addressed by LLM developers and service providers.
Authors: Jacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin, Rahul V. Kulkarni
Abstract: In reinforcement learning, especially in sparse-reward domains, many environment steps are required to observe reward information. In order to increase the frequency of such observations, "potential-based reward shaping" (PBRS) has been proposed as a method of providing a more dense reward signal while leaving the optimal policy invariant. However, the required "potential function" must be carefully designed with task-dependent knowledge to not deter training performance. In this work, we propose a "bootstrapped" method of reward shaping, termed BSRS, in which the agent's current estimate of the state-value function acts as the potential function for PBRS. We provide convergence proofs for the tabular setting, give insights into training dynamics for deep RL, and show that the proposed method improves training speed in the Atari suite.
Authors: Tianyu Fu, Tengxuan Liu, Qinghao Han, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang
Abstract: The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily prune tokens based on importance metrics, such as cumulative attention scores. However, even important tokens may exhibit high redundancy caused by similarity among adjacent video frames and repetitive visual elements. To address this limitation, we propose FrameFusion, a novel token reduction approach integrating similarity-based merging with importance-based pruning. We conduct a thorough study on token similarity characteristics, revealing three key insights: (1) spatially corresponding visual tokens between adjacent frames have higher cosine similarities compared to other token pairs; (2) high token similarities prominently decrease in deeper model layers; and (3) token similarity rankings are highly consistent across different layers. Guided by these observations, FrameFusion computes token similarities exclusively between corresponding visual tokens from adjacent frames, applies token merging at initial successive layers followed by pruning in deeper layers, and adopts a cascaded merging strategy to further enhance efficiency. We evaluate FrameFusion comprehensively across six diverse LVLMs, ranging from 2B to 72B parameters, using five video benchmarks encompassing video retrieval, question-answering, and spatial-temporal understanding tasks. Experiments show that FrameFusion reduces visual tokens by 70%, achieving 1.6-3.6x end-to-end speedups, with an average performance impact of less than 3%. Our code is available at: https://github.com/thu-nics/FrameFusion.
Authors: Satvik Golechha, Maheep Chaudhary, Joan Velja, Alessandro Abate, Nandi Schoots
Abstract: An approach to improve neural network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We define a measure for clusterability and show that pre-trained models form highly enmeshed clusters via spectral graph clustering. We thus train models to be more modular using a "clusterability loss" function that encourages the formation of non-interacting clusters. We then investigate the emerging properties of these highly clustered models. We find our trained clustered models do not exhibit more task specialization, but do form smaller circuits. We investigate CNNs trained on MNIST and CIFAR, small transformers trained on modular addition, and GPT-2 and Pythia on the Wiki dataset, and Gemma on a Chemistry dataset. This investigation shows what to expect from clustered models.
Authors: Zora Che, Stephen Casper, Robert Kirk, Anirudh Satheesh, Stewart Slocum, Lev E McKinney, Rohit Gandikota, Aidan Ewart, Domenic Rosati, Zichu Wu, Zikui Cai, Bilal Chughtai, Yarin Gal, Furong Huang, Dylan Hadfield-Menell
Abstract: Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful behaviors from the system. However, this approach suffers from two limitations. First, input-output evaluations cannot fully evaluate realistic risks from open-weight models. Second, the behaviors identified during any particular input-output evaluation can only lower-bound the model's worst-possible-case input-output behavior. As a complementary method for eliciting harmful behaviors, we propose evaluating LLMs with model tampering attacks which allow for modifications to latent activations or weights. We pit state-of-the-art techniques for removing harmful LLM capabilities against a suite of 5 input-space and 6 model tampering attacks. In addition to benchmarking these methods against each other, we show that (1) model resilience to capability elicitation attacks lies on a low-dimensional robustness subspace; (2) the success rate of model tampering attacks can empirically predict and offer conservative estimates for the success of held-out input-space attacks; and (3) state-of-the-art unlearning methods can easily be undone within 16 steps of fine-tuning. Together, these results highlight the difficulty of suppressing harmful LLM capabilities and show that model tampering attacks enable substantially more rigorous evaluations than input-space attacks alone.
Authors: Junbo Li, Zhangyang Wang, Qiang Liu
Abstract: Offline preference alignment for language models such as Direct Preference Optimization (DPO) is favored for its effectiveness and simplicity, eliminating the need for costly reinforcement learning. Various offline algorithms have been developed for different data settings, yet they lack a unified understanding. In this study, we introduce Pior-Informed Preference Alignment (PIPA), a unified, RL-free probabilistic framework that formulates language model preference alignment as a Maximum Likelihood Estimation (MLE) problem with prior constraints. This method effectively accommodates both paired and unpaired data, as well as answer and step-level annotations. We illustrate that DPO and KTO are special cases with different prior constraints within our framework. By integrating different types of prior information, we developed two variations of PIPA: PIPA-M and PIPA-N. Both algorithms demonstrate a $3\sim10\%$ performance enhancement on the GSM8K and MATH benchmarks across all configurations, achieving these gains without additional training or computational costs compared to existing algorithms.
Authors: Dan Busbridge, Amitis Shidani, Floris Weers, Jason Ramapuram, Etai Littwin, Russ Webb
Abstract: We propose a distillation scaling law that estimates distilled model performance based on a compute budget and its allocation between the student and teacher. Our findings mitigate the risks associated with large-scale distillation by enabling compute-optimal allocation for both the teacher and student to maximize student performance. We provide compute-optimal distillation recipes for two key scenarios: when a teacher already exists, and when a teacher needs training. In settings involving many students or an existing teacher, distillation outperforms supervised learning up to a compute level that scales predictably with student size. Conversely, if only one student is to be distilled and a teacher also requires training, supervised learning is generally preferable. Additionally, our large-scale study of distillation increases our understanding of the process and helps inform experimental design.
Authors: Kefan Li, Yuan Yuan, Hongyue Yu, Tingyu Guo, Shijie Cao
Abstract: Large Language Models (LLMs) have shown remarkable performance in automated code generation. However, existing approaches often rely heavily on pre-defined test cases, which become impractical in scenarios where such cases are unavailable. While prior works explore filtering techniques between programs and test cases, they overlook the refinement of test cases. To address this limitation, we introduce CoCoEvo, a novel LLM-based co-evolution framework that simultaneously evolves programs and test cases. CoCoEvo eliminates the dependency on pre-defined test cases by generating both programs and test cases directly from natural language problem descriptions and function headers. The framework employs specialized evolutionary operators, including LLM-based crossover and mutation operators for program evolution, along with an additional test case generation operator for test case evolution. Additionally, we propose optimization strategies such as a crossover rate scheduler to balance exploration and convergence, and a multi-objective optimization method for test case selection. Experimental results on multiple state-of-the-art LLMs demonstrate that CoCoEvo surpasses existing methods, achieving state-of-the-art performance in automated code generation and testing. These results underscore the potential of co-evolutionary techniques in advancing the field of automated programming.
Authors: Cen-Jhih Li, Aditya Bhaskara
Abstract: Fine-tuning is an important step in adapting foundation models such as large language models to downstream tasks. To make this step more accessible to users with limited computational budgets, it is crucial to develop fine-tuning methods that are memory and computationally efficient. Sparse Fine-tuning (SpFT) and Low-rank adaptation (LoRA) are two frameworks that have emerged for addressing this problem and have been adopted widely in practice. In this work, we develop a new SpFT framework, based on ideas from neural network pruning. At a high level, we first identify ``important'' neurons/nodes using feature importance metrics from network pruning (specifically, we use the structural pruning method), and then perform fine-tuning by restricting to weights involving these neurons. Experiments on common language tasks show our method improves SpFT's memory efficiency by 20-50\% while matching the accuracy of state-of-the-art methods like LoRA's variants.
Authors: Yanbiao Ma, Bowei Liu, Andi Zhang
Abstract: Bias formation in deep neural networks (DNNs) remains a critical yet poorly understood challenge, influencing both fairness and reliability in artificial intelligence systems. Inspired by the human visual system, which decouples object manifolds through hierarchical processing to achieve object recognition, we propose a geometric analysis framework linking the geometric complexity of class-specific perceptual manifolds in DNNs to model bias. Our findings reveal that differences in geometric complexity can lead to varying recognition capabilities across categories, introducing biases. To support this analysis, we present the Perceptual-Manifold-Geometry library, designed for calculating the geometric properties of perceptual manifolds. The toolkit has been downloaded and installed over 4,500 times. This work provides a novel geometric perspective on bias formation in modern learning systems and lays a theoretical foundation for developing more equitable and robust artificial intelligence.
Authors: Davor Vukadin, Marin \v{S}ili\'c, Goran Dela\v{c}
Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains. However, effectively leveraging their vast knowledge for training smaller downstream models remains an open challenge, especially in domains like tabular data learning, where simpler models are often preferred due to interpretability and efficiency. In this paper, we introduce a novel yet straightforward method for incorporating LLM-generated global task feature attributions into the training process of smaller networks. Specifically, we propose an attribution-matching regularization term that aligns the training dynamics of the smaller model with the insights provided by the LLM. By doing so, our approach yields superior performance in few-shot learning scenarios. Notably, our method requires only black-box API access to the LLM, making it easy to integrate into existing training pipelines with minimal computational overhead. Furthermore, we demonstrate how this method can be used to address common issues in real-world datasets, such as skewness and bias. By integrating high-level knowledge from LLMs, our approach improves generalization, even when training data is limited or imbalanced. We validate its effectiveness through extensive experiments across multiple tasks, demonstrating improved learning efficiency and model robustness.
Authors: Guanglin Zhou, Sebastiano Barbieri
Abstract: Generating realistic synthetic electronic health records (EHRs) holds tremendous promise for accelerating healthcare research, facilitating AI model development and enhancing patient privacy. However, existing generative methods typically treat EHRs as flat sequences of discrete medical codes. This approach overlooks two critical aspects: the inherent hierarchical organization of clinical coding systems and the rich semantic context provided by code descriptions. Consequently, synthetic patient sequences often lack high clinical fidelity and have limited utility in downstream clinical tasks. In this paper, we propose the Hierarchy- and Semantics-Guided Transformer (HiSGT), a novel framework that leverages both hierarchical and semantic information for the generative process. HiSGT constructs a hierarchical graph to encode parent-child and sibling relationships among clinical codes and employs a graph neural network to derive hierarchy-aware embeddings. These are then fused with semantic embeddings extracted from a pre-trained clinical language model (e.g., ClinicalBERT), enabling the Transformer-based generator to more accurately model the nuanced clinical patterns inherent in real EHRs. Extensive experiments on the MIMIC-III and MIMIC-IV datasets demonstrate that HiSGT significantly improves the statistical alignment of synthetic data with real patient records, as well as supports robust downstream applications such as chronic disease classification. By addressing the limitations of conventional raw code-based generative models, HiSGT represents a significant step toward clinically high-fidelity synthetic data generation and a general paradigm suitable for interpretable medical code representation, offering valuable applications in data augmentation and privacy-preserving healthcare analytics.
Authors: Fakhraddin Alwajih, Abdellah El Mekki, Samar Mohamed Magdy, Abdelrahim A. Elmadany, Omer Nacar, El Moatez Billah Nagoudi, Reem Abdel-Salam, Hanin Atwany, Youssef Nafea, Abdulfattah Mohammed Yahya, Rahaf Alhamouri, Hamzah A. Alsayadi, Hiba Zayed, Sara Shatnawi, Serry Sibaee, Yasir Ech-Chammakhy, Walid Al-Dhabyani, Marwa Mohamed Ali, Imen Jarraya, Ahmed Oumar El-Shangiti, Aisha Alraeesi, Mohammed Anwar Al-Ghrawi, Abdulrahman S. Al-Batati, Elgizouli Mohamed, Noha Taha Elgindi, Muhammed Saeed, Houdaifa Atou, Issam Ait Yahia, Abdelhak Bouayad, Mohammed Machrouh, Amal Makouar, Dania Alkawi, Mukhtar Mohamed, Safaa Taher Abdelfadil, Amine Ziad Ounnoughene, Rouabhia Anfel, Rwaa Assi, Ahmed Sorkatti, Mohamedou Cheikh Tourad, Anis Koubaa, Ismail Berrada, Mustafa Jarrar, Shady Shehata, Muhammad Abdul-Mageed
Abstract: As large language models (LLMs) become increasingly integrated into daily life, ensuring their cultural sensitivity and inclusivity is paramount. We introduce our dataset, a year-long community-driven project covering all 22 Arab countries. The dataset includes instructions (input, response pairs) in both Modern Standard Arabic (MSA) and dialectal Arabic (DA), spanning 20 diverse topics. Built by a team of 44 researchers across the Arab world, all of whom are authors of this paper, our dataset offers a broad, inclusive perspective. We use our dataset to evaluate the cultural and dialectal capabilities of several frontier LLMs, revealing notable limitations. For instance, while closed-source LLMs generally exhibit strong performance, they are not without flaws, and smaller open-source models face greater challenges. Moreover, certain countries (e.g., Egypt, the UAE) appear better represented than others (e.g., Iraq, Mauritania, Yemen). Our annotation guidelines, code, and data for reproducibility are publicly available.
Authors: Calarina Muslimani, Kerrick Johnstonbaugh, Suyog Chandramouli, Serena Booth, W. Bradley Knox, Matthew E. Taylor
Abstract: Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from, yet reward design is often overlooked under the assumption that a well-defined reward is readily available. However, in practice, designing rewards is difficult, and even when specified, evaluating their correctness is equally problematic: how do we know if a reward function is correctly specified? In our work, we address these challenges by focusing on reward alignment -- assessing whether a reward function accurately encodes the preferences of a human stakeholder. As a concrete measure of reward alignment, we introduce the Trajectory Alignment Coefficient to quantify the similarity between a human stakeholder's ranking of trajectory distributions and those induced by a given reward function. We show that the Trajectory Alignment Coefficient exhibits desirable properties, such as not requiring access to a ground truth reward, invariance to potential-based reward shaping, and applicability to online RL. Additionally, in an 11 -- person user study of RL practitioners, we found that access to the Trajectory Alignment Coefficient during reward selection led to statistically significant improvements. Compared to relying only on reward functions, our metric reduced cognitive workload by 1.5x, was preferred by 82% of users and increased the success rate of selecting reward functions that produced performant policies by 41%.
Authors: Jiangran Lyu, Ziming Li, Xuesong Shi, Chaoyi Xu, Yizhou Wang, He Wang
Abstract: Nonprehensile manipulation is crucial for handling objects that are too thin, large, or otherwise ungraspable in unstructured environments. While conventional planning-based approaches struggle with complex contact modeling, learning-based methods have recently emerged as a promising alternative. However, existing learning-based approaches face two major limitations: they heavily rely on multi-view cameras and precise pose tracking, and they fail to generalize across varying physical conditions, such as changes in object mass and table friction. To address these challenges, we propose the Dynamics-Adaptive World Action Model (DyWA), a novel framework that enhances action learning by jointly predicting future states while adapting to dynamics variations based on historical trajectories. By unifying the modeling of geometry, state, physics, and robot actions, DyWA enables more robust policy learning under partial observability. Compared to baselines, our method improves the success rate by 31.5% using only single-view point cloud observations in the simulation. Furthermore, DyWA achieves an average success rate of 68% in real-world experiments, demonstrating its ability to generalize across diverse object geometries, adapt to varying table friction, and robustness in challenging scenarios such as half-filled water bottles and slippery surfaces.
Authors: Chang Gao, Kang Zhao, Runqi Wang, Jianfei Chen, Liping Jing
Abstract: Large language models (LLMs) have demonstrated impressive capabilities, but their enormous size poses significant challenges for deployment in real-world applications. To address this issue, researchers have sought to apply network pruning techniques to LLMs. A critical challenge in pruning is allocation the sparsity for each layer. Recent sparsity allocation methods is often based on heuristics or search that can easily lead to suboptimal performance. In this paper, we conducted an extensive investigation into various LLMs and revealed three significant discoveries: (1) the layerwise pruning sensitivity (LPS) of LLMs is highly non-uniform, (2) the choice of pruning metric affects LPS, and (3) the performance of a sparse model is related to the uniformity of its layerwise redundancy level. Based on these observations, we propose that the layerwise sparsity of LLMs should adhere to three principles: \emph{non-uniformity}, \emph{pruning metric dependency}, and \emph{uniform layerwise redundancy level} in the pruned model. To this end, we proposed Maximum Redundancy Pruning (MRP), an iterative pruning algorithm that prunes in the most redundant layers (\emph{i.e.}, those with the highest non-outlier ratio) at each iteration. The achieved layerwise sparsity aligns with the outlined principles. We conducted extensive experiments on publicly available LLMs, including the LLaMA2 and OPT, across various benchmarks. Experimental results validate the effectiveness of MRP, demonstrating its superiority over previous methods.
Authors: Aitor Gomez-Tejedor, Eneko Osaba, Esther Villar-Rodriguez
Abstract: This study addresses the minor-embedding problem, which involves mapping the variables of an Ising model onto a quantum annealing processor. The primary motivation stems from the observed performance disparity of quantum annealers when solving problems suited to the processor's architecture versus those with non-hardware-native topologies. Our research has two main objectives: i) to analyze the impact of embedding quality on the performance of D-Wave Systems quantum annealers, and ii) to evaluate the quality of the embeddings generated by Minorminer, the standard minor-embedding technique in the quantum annealing literature, provided by D-Wave. Regarding the first objective, our experiments reveal a clear correlation between the average chain length of embeddings and the relative errors of the solutions sampled. This underscores the critical influence of embedding quality on quantum annealing performance. For the second objective, we evaluate Minorminer's embedding capabilities, the quality and robustness of its embeddings, and its execution-time performance. We also compare its performance with Clique Embedding, another algorithm developed by D-Wave, which is deterministic and designed to embed fully connected Ising models into quantum annealing processors, serving as a worst-case scenario. The results demonstrate that there is significant room for improvement for Minorminer, suggesting that more effective embedding strategies could lead to meaningful gains in quantum annealing performance.
Authors: Qitao Tan, Sung-En Chang, Rui Xia, Huidong Ji, Chence Yang, Ci Zhang, Jun Liu, Zheng Zhan, Zhenman Fang, Zhou Zou, Yanzhi Wang, Jin Lu, Geng Yuan
Abstract: Zeroth-order (ZO) optimization is an emerging deep neural network (DNN) training paradigm that offers computational simplicity and memory savings. However, this seemingly promising approach faces a significant and long-ignored challenge. ZO requires generating a substantial number of Gaussian random numbers, which poses significant difficulties and even makes it infeasible for hardware platforms, such as FPGAs and ASICs. In this paper, we identify this critical issue, which arises from the mismatch between algorithm and hardware designers. To address this issue, we proposed PeZO, a perturbation-efficient ZO framework. Specifically, we design random number reuse strategies to significantly reduce the demand for random number generation and introduce a hardware-friendly adaptive scaling method to replace the costly Gaussian distribution with a uniform distribution. Our experiments show that PeZO reduces the required LUTs and FFs for random number generation by 48.6\% and 12.7\%, and saves at maximum 86\% power consumption, all without compromising training performance, making ZO optimization feasible for on-device training. To the best of our knowledge, we are the first to explore the potential of on-device ZO optimization, providing valuable insights for future research.
Authors: Yinghan Zhou, Juan Wen, Wanli Peng, Yiming Xue, Ziwei Zhang, Zhengxian Wu
Abstract: The growing popularity of large language models has raised concerns regarding the potential to misuse AI-generated text (AIGT). It becomes increasingly critical to establish an excellent AIGT detection method with high generalization and robustness. However, existing methods either focus on model generalization or concentrate on robustness. The unified mechanism, to simultaneously address the challenges of generalization and robustness, is less explored. In this paper, we argue that robustness can be view as a specific form of domain shift, and empirically reveal an intrinsic mechanism for model generalization of AIGT detection task. Then, we proposed a novel AIGT detection method (DP-Net) via dynamic perturbations introduced by a reinforcement learning with elaborated reward and action. Experimentally, extensive results show that the proposed DP-Net significantly outperforms some state-of-the-art AIGT detection methods for generalization capacity in three cross-domain scenarios. Meanwhile, the DP-Net achieves best robustness under two text adversarial attacks. The code is publicly available at https://github.com/CAU-ISS-Lab/AIGT-Detection-Evade-Detection/tree/main/DP-Net.
URLs: https://github.com/CAU-ISS-Lab/AIGT-Detection-Evade-Detection/tree/main/DP-Net.
Authors: Daniel Goldstein, Eric Alcaide, Janna Lu, Eugene Cheah
Abstract: We present Rapid Attention Distillation to Linear Attention Decoders at Scale (RADLADS), a protocol for rapidly converting softmax attention transformers into linear attention decoder models, along with two new RWKV-variant architectures, and models converted from popular Qwen2.5 open source models in 7B, 32B, and 72B sizes. Our conversion process requires only 350-700M tokens, less than 0.005% of the token count used to train the original teacher models. Converting to our 72B linear attention model costs less than \$2,000 USD at today's prices, yet quality at inference remains close to the original transformer. These models achieve state-of-the-art downstream performance across a set of standard benchmarks for linear attention models of their size. We release all our models on HuggingFace under the Apache 2.0 license, with the exception of our 72B models which are also governed by the Qwen License Agreement. Models at https://huggingface.co/collections/recursal/radlads-6818ee69e99e729ba8a87102 Training Code at https://github.com/recursal/RADLADS-paper
URLs: https://huggingface.co/collections/recursal/radlads-6818ee69e99e729ba8a87102, https://github.com/recursal/RADLADS-paper
Authors: Zihao Pan, Yu Tong, Weibin Wu, Jingyi Wang, Lifeng Chen, Zhe Zhao, Jiajia Wei, Yitong Qiao, Zibin Zheng
Abstract: Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\textit{What content in inputs make models more likely to fail?}'' However, this information is crucial for researchers to specifically improve model robustness. Recent research suggests that models may be particularly sensitive to certain semantics in visual inputs (such as ``wet,'' ``foggy''), making them prone to errors. Inspired by this, in this paper we conducted the first exploration on large vision-language models (LVLMs) and found that LVLMs indeed are susceptible to hallucinations and various errors when facing specific semantic concepts in images. To efficiently search for these sensitive concepts, we integrated large language models (LLMs) and text-to-image (T2I) models to propose a novel semantic evolution framework. Randomly initialized semantic concepts undergo LLM-based crossover and mutation operations to form image descriptions, which are then converted by T2I models into visual inputs for LVLMs. The task-specific performance of LVLMs on each input is quantified as fitness scores for the involved semantics and serves as reward signals to further guide LLMs in exploring concepts that induce LVLMs. Extensive experiments on seven mainstream LVLMs and two multimodal tasks demonstrate the effectiveness of our method. Additionally, we provide interesting findings about the sensitive semantics of LVLMs, aiming to inspire further in-depth research.
Authors: Jiawei Gu, Ziting Xian, Yuanzhen Xie, Ye Liu, Enjie Liu, Ruichao Zhong, Mochi Gao, Yunzhi Tan, Bo Hu, Zang Li
Abstract: Large language models (LLMs) achieve strong performance on plain text tasks but underperform on structured data like tables and databases. Potential challenges arise from their underexposure during pre-training and rigid text-to-structure transfer mechanisms. Unlike humans who seamlessly apply learned patterns across data modalities, LLMs struggle to infer implicit relationships embedded in tabular formats, especially in the absence of explicit structural guidance. To bridge this cognitive gap, we introduce Contrastive Retrieval-Augmented Generation on Experience (CoRE), a framework that builds experience memory representations and enhances generalization through contrastive In-Context Learning (ICL) to simulate human-like knowledge transfer. Experiments on Text-to-SQL and TableQA show CoRE significantly improves performance, achieving average gains of 3.44% and 4.24%, with up to 17.2% on challenging tasks. Our Monte Carlo Tree Search (MCTS)-generated Experience Memory expands training data 8-9x, enhancing diversity and domain coverage. This training-free and continual method propels LLMs toward structured knowledge expertise.
Authors: Andrew Smith, Erhan Guven
Abstract: Hybrid quantum-classical machine learning offers a path to leverage noisy intermediate-scale quantum (NISQ) devices for drug discovery, but optimal model architectures remain unclear. We systematically optimize the quantum-classical bridge architecture of generative adversarial networks (GANs) for molecule discovery using multi-objective Bayesian optimization. Our optimized model (BO-QGAN) significantly improves performance, achieving a 2.27-fold higher Drug Candidate Score (DCS) than prior quantum-hybrid benchmarks and 2.21-fold higher than the classical baseline, while reducing parameter count by more than 60%. Key findings favor layering multiple (3-4) shallow (4-8 qubit) quantum circuits sequentially, while classical architecture shows less sensitivity above a minimum capacity. This work provides the first empirically-grounded architectural guidelines for hybrid models, enabling more effective integration of current quantum computers into pharmaceutical research pipelines.
Authors: Guohang Zhuang, Weixi Song, Jinyang Huang, Chenwei Yang, Wanli OuYang, Yan Lu
Abstract: With the rapid development of space exploration, space debris has attracted more attention due to its potential extreme threat, leading to the need for real-time and accurate debris tracking. However, existing methods are mainly based on traditional signal processing, which cannot effectively process the complex background and dense space debris. In this paper, we propose a deep learning-based Space Debris Tracking Network~(SDT-Net) to achieve highly accurate debris tracking. SDT-Net effectively represents the feature of debris, enhancing the efficiency and stability of end-to-end model learning. To train and evaluate this model effectively, we also produce a large-scale dataset Space Debris Tracking Dataset (SDTD) by a novel observation-based data simulation scheme. SDTD contains 18,040 video sequences with a total of 62,562 frames and covers 250,000 synthetic space debris. Extensive experiments validate the effectiveness of our model and the challenging of our dataset. Furthermore, we test our model on real data from the Antarctic Station, achieving a MOTA score of 73.2%, which demonstrates its strong transferability to real-world scenarios. Our dataset and code will be released soon.
Authors: Tianyi Xu, Jiaxin Liu, Nicholas Mattei, Zizhan Zheng
Abstract: We propose a multi-agent multi-armed bandit (MA-MAB) framework aimed at ensuring fair outcomes across agents while maximizing overall system performance. A key challenge in this setting is decision-making under limited information about arm rewards. To address this, we introduce a novel probing framework that strategically gathers information about selected arms before allocation. In the offline setting, where reward distributions are known, we leverage submodular properties to design a greedy probing algorithm with a provable performance bound. For the more complex online setting, we develop an algorithm that achieves sublinear regret while maintaining fairness. Extensive experiments on synthetic and real-world datasets show that our approach outperforms baseline methods, achieving better fairness and efficiency.
Authors: Ciro Listone, Aniello Murano
Abstract: Melanoma represents a critical health risk due to its aggressive progression and high mortality, underscoring the need for early, interpretable diagnostic tools. While deep learning has advanced in skin lesion classification, most existing models provide only binary outputs, offering limited clinical insight. This work introduces a novel approach that extends beyond classification, enabling interpretable risk modelling through a Conditional Variational Autoencoder. The proposed method learns a structured latent space that captures semantic relationships among lesions, allowing for a nuanced, continuous assessment of morphological differences. An SVM is also trained on this representation effectively differentiating between benign nevi and melanomas, demonstrating strong and consistent performance. More importantly, the learned latent space supports visual and geometric interpretation of malignancy, with the spatial proximity of a lesion to known melanomas serving as a meaningful indicator of risk. This approach bridges predictive performance with clinical applicability, fostering early detection, highlighting ambiguous cases, and enhancing trust in AI-assisted diagnosis through transparent and interpretable decision-making.
Authors: Omer Luxembourg, Haim Permuter, Eliya Nachmani
Abstract: Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel and effectively reduce to slow, autoregressive behavior. We propose the Dilated Unmasking Scheduler (DUS), an inference-only, planner-model-free method that partitions sequence positions into non-adjacent dilated groups and unmasked them in parallel so as to minimize an upper bound on joint entropy gain at each denoising step. By explicitly trading off the number of network calls against generation quality, DUS recovers most of the performance lost under traditional parallel unmasking strategies. Across math (GSM8K, MATH500), code (HumanEval, MBPP) and general-knowledge benchmarks (BBH, MMLU-Pro), DUS outperforms confidence-based planners, without modifying the underlying denoiser, and reveals the true speed-quality frontier of MDLMs.
Authors: Boxuan Zhang, Zhen Xu, Kuan Tao
Abstract: Spiking Neural Networks (SNNs) have received widespread attention due to their event-driven and low-power characteristics, making them particularly effective for processing event-based neuromorphic data. Recent studies have shown that directly trained SNNs suffer from severe overfitting issues due to the limited scale of neuromorphic datasets and the gradient mismatching problem, which fundamentally constrain their generalization performance. In this paper, we propose a temporal regularization training (TRT) method by introducing a time-dependent regularization mechanism to enforce stronger constraints on early timesteps. We compare the performance of TRT with other state-of-the-art methods performance on datasets including CIFAR10/100, ImageNet100, DVS-CIFAR10, and N-Caltech101. To validate the effectiveness of TRT, we conducted ablation studies and analyses including loss landscape visualization and learning curve analysis, demonstrating that TRT can effectively mitigate overfitting and flatten the training loss landscape, thereby enhancing generalizability. Furthermore, we establish a theoretical interpretation of TRT's temporal regularization mechanism based on the results of Fisher information analysis. We analyze the temporal information dynamics inside SNNs by tracking Fisher information during the TRT training process, revealing the Temporal Information Concentration (TIC) phenomenon, where Fisher information progressively concentrates in early timesteps. The time-decaying regularization mechanism implemented in TRT effectively guides the network to learn robust features in early timesteps with rich information, thereby leading to significant improvements in model generalization. Code is available at https://anonymous.4open.science/r/TRT-7FBFUYT4E.
Authors: Tzu-Hsuan Yang, Yue-Yang He, Berlin Chen
Abstract: Effective pronunciation feedback is critical in second language (L2) learning, for which computer-assisted pronunciation training (CAPT) systems often encompass two key tasks: automatic pronunciation assessment (APA) and mispronunciation detection and diagnosis (MDD). Recent work has shown that joint modeling of these two tasks can yield mutual benefits. Our unified framework leverages Mamba, a selective state space model (SSM), while integrating phonological features and think token strategies to jointly enhance interpretability and fine-grained temporal reasoning in APA and MDD. To our knowledge, this is the first study to combine phonological attribution, SSM-based modeling, and prompting in CAPT. A series of experiments conducted on the speechocean762 benchmark demonstrate that our model consistently outperforms prior methods, particularly on the MDD task.
Authors: He-Yang Xu, Hongxiang Gao, Yuwen Li, Xiu-Shen Wei, Chengyu Liu
Abstract: The diagnostic value of electrocardiogram (ECG) lies in its dynamic characteristics, ranging from rhythm fluctuations to subtle waveform deformations that evolve across time and frequency domains. However, supervised ECG models tend to overfit dominant and repetitive patterns, overlooking fine-grained but clinically critical cues, a phenomenon known as Simplicity Bias (SB), where models favor easily learnable signals over subtle but informative ones. In this work, we first empirically demonstrate the presence of SB in ECG analyses and its negative impact on diagnostic performance, while simultaneously discovering that self-supervised learning (SSL) can alleviate it, providing a promising direction for tackling the bias. Following the SSL paradigm, we propose a novel method comprising two key components: 1) Temporal-Frequency aware Filters to capture temporal-frequency features reflecting the dynamic characteristics of ECG signals, and 2) building on this, Multi-Grained Prototype Reconstruction for coarse and fine representation learning across dual domains, further mitigating SB. To advance SSL in ECG analyses, we curate a large-scale multi-site ECG dataset with 1.53 million recordings from over 300 clinical centers. Experiments on three downstream tasks across six ECG datasets demonstrate that our method effectively reduces SB and achieves state-of-the-art performance. Code and dataset will be released publicly.
Authors: Jacob Adamczyk
Abstract: Exploration remains a fundamental challenge in reinforcement learning (RL), particularly in environments with sparse or adversarial reward structures. In this work, we study how the architecture of deep neural policies implicitly shapes exploration before training. We theoretically and empirically demonstrate strategies for generating ballistic or diffusive trajectories from untrained policies in a toy model. Using the theory of infinite-width networks and a continuous-time limit, we show that untrained policies return correlated actions and result in non-trivial state-visitation distributions. We discuss the distributions of the corresponding trajectories for a standard architecture, revealing insights into inductive biases for tackling exploration. Our results establish a theoretical and experimental framework for using policy initialization as a design tool to understand exploration behavior in early training.
Authors: Giwon Lee, Wooseong Jeong, Daehee Park, Jaewoo Jeong, Kuk-Jin Yoon
Abstract: Motion planning is a crucial component of autonomous robot driving. While various trajectory datasets exist, effectively utilizing them for a target domain remains challenging due to differences in agent interactions and environmental characteristics. Conventional approaches, such as domain adaptation or ensemble learning, leverage multiple source datasets but suffer from domain imbalance, catastrophic forgetting, and high computational costs. To address these challenges, we propose Interaction-Merged Motion Planning (IMMP), a novel approach that leverages parameter checkpoints trained on different domains during adaptation to the target domain. IMMP follows a two-step process: pre-merging to capture agent behaviors and interactions, sufficiently extracting diverse information from the source domain, followed by merging to construct an adaptable model that efficiently transfers diverse interactions to the target domain. Our method is evaluated on various planning benchmarks and models, demonstrating superior performance compared to conventional approaches.
Authors: Zongyan Han, Mohamed El Amine Boudjoghra, Jiahua Dong, Jinhong Wang, Rao Muhammad Anwer
Abstract: Unified segmentation of 3D point clouds is crucial for scene understanding, but is hindered by its sparse structure, limited annotations, and the challenge of distinguishing fine-grained object classes in complex environments. Existing methods often struggle to capture rich semantic and contextual information due to limited supervision and a lack of diverse multimodal cues, leading to suboptimal differentiation of classes and instances. To address these challenges, we propose VDG-Uni3DSeg, a novel framework that integrates pre-trained vision-language models (e.g., CLIP) and large language models (LLMs) to enhance 3D segmentation. By leveraging LLM-generated textual descriptions and reference images from the internet, our method incorporates rich multimodal cues, facilitating fine-grained class and instance separation. We further design a Semantic-Visual Contrastive Loss to align point features with multimodal queries and a Spatial Enhanced Module to model scene-wide relationships efficiently. Operating within a closed-set paradigm that utilizes multimodal knowledge generated offline, VDG-Uni3DSeg achieves state-of-the-art results in semantic, instance, and panoptic segmentation, offering a scalable and practical solution for 3D understanding. Our code is available at https://github.com/Hanzy1996/VDG-Uni3DSeg.
Authors: Prady Saligram, Tanvir Bhathal, Robby Manihani
Abstract: Delayed and sparse rewards present a fundamental obstacle for reinforcement-learning (RL) agents, which struggle to assign credit for actions whose benefits emerge many steps later. The sliding-tile game 2048 epitomizes this challenge: although frequent small score changes yield immediate feedback, they often mislead agents into locally optimal but globally suboptimal strategies. In this work, we introduce a unified, distributional multi-step RL framework designed to directly optimize long-horizon performance. Using the open source Gym-2048 environment we develop and compare four agent variants: standard DQN, PPO, QR-DQN (Quantile Regression DQN), and a novel Horizon-DQN (H-DQN) that integrates distributional learning, dueling architectures, noisy networks, prioritized replay, and more. Empirical evaluation reveals a clear hierarchy in effectiveness: max episode scores improve from 3.988K (DQN) to 5.756K (PPO), 8.66K (QR-DQN), and 18.21K (H-DQN), with H-DQN reaching the 2048 tile. Upon scaling H-DQN it reaches a max score 41.828K and a 4096 tile. These results demonstrate that distributional, multi-step targets substantially enhance performance in sparse-reward domains, and they suggest promising avenues for further gains through model-based planning and curriculum learning.
Authors: K. Sahit Reddy, N. Ragavenderan, Vasanth K., Ganesh N. Naik, Vishalakshi Prabhu, Nagaraja G. S
Abstract: Recent advances in natural language processing (NLP) have been driven bypretrained language models like BERT, RoBERTa, T5, and GPT. Thesemodels excel at understanding complex texts, but biomedical literature, withits domain-specific terminology, poses challenges that models likeWord2Vec and bidirectional long short-term memory (Bi-LSTM) can't fullyaddress. GPT and T5, despite capturing context, fall short in tasks needingbidirectional understanding, unlike BERT. Addressing this, we proposedMedicalBERT, a pretrained BERT model trained on a large biomedicaldataset and equipped with domain-specific vocabulary that enhances thecomprehension of biomedical terminology. MedicalBERT model is furtheroptimized and fine-tuned to address diverse tasks, including named entityrecognition, relation extraction, question answering, sentence similarity, anddocument classification. Performance metrics such as the F1-score,accuracy, and Pearson correlation are employed to showcase the efficiencyof our model in comparison to other BERT-based models such as BioBERT,SciBERT, and ClinicalBERT. MedicalBERT outperforms these models onmost of the benchmarks, and surpasses the general-purpose BERT model by5.67% on average across all the tasks evaluated respectively. This work alsounderscores the potential of leveraging pretrained BERT models for medicalNLP tasks, demonstrating the effectiveness of transfer learning techniques incapturing domain-specific information. (PDF) MedicalBERT: enhancing biomedical natural language processing using pretrained BERT-based model. Available from: https://www.researchgate.net/publication/392489050_MedicalBERT_enhancing_biomedical_natural_language_processing_using_pretrained_BERT-based_model [accessed Jul 06 2025].
Authors: Neel Rajani, Aryo Pradipta Gema, Seraphina Goldfarb-Tarrant, Ivan Titov
Abstract: Training large language models (LLMs) for reasoning via maths and code datasets has become a major new focus in LLM post-training. Two particularly popular approaches are reinforcement learning (RL) and supervised fine-tuning (SFT), but their training dynamics are poorly understood. We present a comparative analysis of RL and SFT on the same maths problems with the same model and similar hyperparameters. We find that RL yields minor in-domain gains on maths and slight degradation on knowledge-intensive benchmarks like MMLU, while both trends are more pronounced in SFT. We also analyse model parameters across checkpoints, observing that both algorithms modify query and key weights the most. Meanwhile, SFT exhibits greater updates and also affects mid-layer MLPs more, leading us to hypothesise that this may have caused the out-of-domain degradation. We therefore investigate whether freezing parts of the model during training can mitigate the reduced performance on knowledge-intensive benchmarks. However, our results are inconclusive, with benefits on GPQA:Diamond and degradation on other benchmarks. Taken together, our observations provide a preliminary indication for why RL amplifies existing capabilities, while SFT replaces old skills with new ones.
Authors: Yuchi Tang, I\~naki Esnaola, George Panoutsos
Abstract: Existing post-hoc model-agnostic methods generate external explanations for opaque models, primarily by locally attributing the model output to its input features. However, they often lack an explicit and systematic framework for quantifying the contribution of individual features. Building on the Taylor expansion framework introduced by Deng et al. (2024) to unify existing local attribution methods, we propose a rigorous set of postulates -- "precision", "federation", and "zero-discrepancy" -- to govern Taylor term-specific attribution. Guided by these postulates, we introduce TaylorPODA (Taylor expansion-derived imPortance-Order aDapted Attribution), which incorporates an additional "adaptation" property. This property enables alignment with task-specific goals, especially in post-hoc settings lacking ground-truth explanations. Empirical evaluations demonstrate that TaylorPODA achieves competitive results against baseline methods, providing principled and visualization-friendly explanations. This work represents a step toward the trustworthy deployment of opaque models by offering explanations with stronger theoretical grounding.
Authors: Xiangyu Dong, Haoran Zhao, Jiang Gao, Haozhou Li, Xiaoguang Ma, Yaoming Zhou, Fuhai Chen, Juan Liu
Abstract: Recent advances in vision-language navigation (VLN) were mainly attributed to emerging large language models (LLMs). These methods exhibited excellent generalization capabilities in instruction understanding and task reasoning. However, they were constrained by the fixed knowledge bases and reasoning abilities of LLMs, preventing fully incorporating experiential knowledge and thus resulting in a lack of efficient evolutionary capacity. To address this, we drew inspiration from the evolution capabilities of natural agents, and proposed a self-evolving VLN framework (SE-VLN) to endow VLN agents with the ability to continuously evolve during testing. To the best of our knowledge, it was the first time that an multimodal LLM-powered self-evolving VLN framework was proposed. Specifically, SE-VLN comprised three core modules, i.e., a hierarchical memory module to transfer successful and failure cases into reusable knowledge, a retrieval-augmented thought-based reasoning module to retrieve experience and enable multi-step decision-making, and a reflection module to realize continual evolution. Comprehensive tests illustrated that the SE-VLN achieved navigation success rates of 57% and 35.2% in unseen environments, representing absolute performance improvements of 23.9% and 15.0% over current state-of-the-art methods on R2R and REVERSE datasets, respectively. Moreover, the SE-VLN showed performance improvement with increasing experience repository, elucidating its great potential as a self-evolving agent framework for VLN.
Authors: Junhong Min, Youngpil Jeon, Jimin Kim, Minyong Choi
Abstract: The pursuit of a generalizable stereo matching model, capable of performing across varying resolutions and disparity ranges without dataset-specific fine-tuning, has revealed a fundamental trade-off. Iterative local search methods achieve high scores on constrained benchmarks, but their core mechanism inherently limits the global consistency required for true generalization. On the other hand, global matching architectures, while theoretically more robust, have been historically rendered infeasible by prohibitive computational and memory costs. We resolve this dilemma with $S^2M^2$: a global matching architecture that achieves both state-of-the-art accuracy and high efficiency without relying on cost volume filtering or deep refinement stacks. Our design integrates a multi-resolution transformer for robust long-range correspondence, trained with a novel loss function that concentrates probability on feasible matches. This approach enables a more robust joint estimation of disparity, occlusion, and confidence. $S^2M^2$ establishes a new state of the art on the Middlebury v3 and ETH3D benchmarks, significantly outperforming prior methods across most metrics while reconstructing high-quality details with competitive efficiency.
Authors: Shanbo Cheng, Yu Bao, Qian Cao, Luyang Huang, Liyan Kang, Zhicheng Liu, Yu Lu, Wenhao Zhu, Jingwen Chen, Zhichao Huang, Tao Li, Yifu Li, Huiying Lin, Sitong Liu, Ningxin Peng, Shuaijie She, Lu Xu, Nuo Xu, Sen Yang, Runsheng Yu, Yiming Yu, Liehao Zou, Hang Li, Lu Lu, Yuxuan Wang, Yonghui Wu
Abstract: Multilingual translation stands as a challenging task for large language models (LLMs) to handle intricate language patterns and stilted translations that arise in automated translations. In this paper, we introduce Seed-X, a family of open-source LLMs comprising instruct and reasoning models, pushing the limits of translation capability with 7B parameter size. The base model is pre-trained on a diverse, high-quality dataset encompassing both monolingual and bilingual content across 28 languages, harnessing the full potential of multilingual data. The instruct model is then finetuned to translate by Chain-of-Thought (CoT) reasoning and further enhanced through reinforcement learning (RL) to achieve better generalization across diverse language pairs. Seed-X achieves performance comparable to leading closed-source models, including Gemini-2.5 and GPT-4o, across 28 languages, and significantly outperforms larger open-source models in both automatic metrics and human evaluations. We share the best practices through our optimization process, and make the parameter public available for advancing translation research and applications.
Authors: Rithesh Murthy, Ming Zhu, Liangwei Yang, Jielin Qiu, Juntao Tan, Shelby Heinecke, Caiming Xiong, Silvio Savarese, Huan Wang
Abstract: Large Language Models (LLMs) perform best with well-crafted prompts, yet prompt engineering remains manual, inconsistent, and inaccessible to non-experts. We introduce Promptomatix, an automatic prompt optimization framework that transforms natural language task descriptions into high-quality prompts without requiring manual tuning or domain expertise. Promptomatix supports both a lightweight meta-prompt-based optimizer and a DSPy-powered compiler, with modular design enabling future extension to more advanced frameworks. The system analyzes user intent, generates synthetic training data, selects prompting strategies, and refines prompts using cost-aware objectives. Evaluated across 5 task categories, Promptomatix achieves competitive or superior performance compared to existing libraries, while reducing prompt length and computational overhead making prompt optimization scalable and efficient.
Authors: Tanjin Taher Toma, Tejas Sudharshan Mathai, Bikash Santra, Pritam Mukherjee, Jianfei Liu, Wesley Jong, Darwish Alabyad, Vivek Batheja, Abhishek Jha, Mayank Patel, Darko Pucar, Jayadira del Rivero, Karel Pacak, Ronald M. Summers
Abstract: Accurate segmentation of pheochromocytoma (PCC) in abdominal CT scans is essential for tumor burden estimation, prognosis, and treatment planning. It may also help infer genetic clusters, reducing reliance on expensive testing. This study systematically evaluates anatomical priors to identify configurations that improve deep learning-based PCC segmentation. We employed the nnU-Net framework to evaluate eleven annotation strategies for accurate 3D segmentation of pheochromocytoma, introducing a set of novel multi-class schemes based on organ-specific anatomical priors. These priors were derived from adjacent organs commonly surrounding adrenal tumors (e.g., liver, spleen, kidney, aorta, adrenal gland, and pancreas), and were compared against a broad body-region prior used in previous work. The framework was trained and tested on 105 contrast-enhanced CT scans from 91 patients at the NIH Clinical Center. Performance was measured using Dice Similarity Coefficient (DSC), Normalized Surface Distance (NSD), and instance-wise F1 score. Among all strategies, the Tumor + Kidney + Aorta (TKA) annotation achieved the highest segmentation accuracy, significantly outperforming the previously used Tumor + Body (TB) annotation across DSC (p = 0.0097), NSD (p = 0.0110), and F1 score (25.84% improvement at an IoU threshold of 0.5), measured on a 70-30 train-test split. The TKA model also showed superior tumor burden quantification (R^2 = 0.968) and strong segmentation across all genetic subtypes. In five-fold cross-validation, TKA consistently outperformed TB across IoU thresholds (0.1 to 0.5), reinforcing its robustness and generalizability. These findings highlight the value of incorporating relevant anatomical context into deep learning models to achieve precise PCC segmentation, offering a valuable tool to support clinical assessment and longitudinal disease monitoring in PCC patients.
Authors: Yuzhi Liu, Zixuan Chen, Zirui Zhang, Yufei Liu, Giulia Lanzillotta
Abstract: The Neural Tangent Kernel (NTK) offers a powerful tool to study the functional dynamics of neural networks. In the so-called lazy, or kernel regime, the NTK remains static during training and the network function is linear in the static neural tangents feature space. The evolution of the NTK during training is necessary for feature learning, a key driver of deep learning success. The study of the NTK dynamics has led to several critical discoveries in recent years, in generalization and scaling behaviours. However, this body of work has been limited to the single task setting, where the data distribution is assumed constant over time. In this work, we present a comprehensive empirical analysis of NTK dynamics in continual learning, where the data distribution shifts over time. Our findings highlight continual learning as a rich and underutilized testbed for probing the dynamics of neural training. At the same time, they challenge the validity of static-kernel approximations in theoretical treatments of continual learning, even at large scale.
Authors: Md Min-Ha-Zul Abedin, Tazqia Mehrub
Abstract: This study investigates the effectiveness of several machine learning algorithms for static malware detection using the EMBER dataset, which contains feature representations of Portable Executable (PE) files. We evaluate eight classification models: LightGBM, XGBoost, CatBoost, Random Forest, Extra Trees, HistGradientBoosting, k-Nearest Neighbors (KNN), and TabNet, under three preprocessing settings: original feature space, Principal Component Analysis (PCA), and Linear Discriminant Analysis (LDA). The models are assessed on accuracy, precision, recall, F1 score, and AUC to examine both predictive performance and robustness. Ensemble methods, especially LightGBM and XGBoost, show the best overall performance across all configurations, with minimal sensitivity to PCA and consistent generalization. LDA improves KNN performance but significantly reduces accuracy for boosting models. TabNet, while promising in theory, underperformed under feature reduction, likely due to architectural sensitivity to input structure. The analysis is supported by detailed exploratory data analysis (EDA), including mutual information ranking, PCA or t-SNE visualizations, and outlier detection using Isolation Forest and Local Outlier Factor (LOF), which confirm the discriminatory capacity of key features in the EMBER dataset. The results suggest that boosting models remain the most reliable choice for high-dimensional static malware detection, and that dimensionality reduction should be applied selectively based on model type. This work provides a benchmark for comparing classification models and preprocessing strategies in malware detection tasks and contributes insights that can guide future system development and real-world deployment.
Authors: Arindam Ghosh, Mark Fuhs, Bongjun Kim, Anurag Chowdhury, Monika Woszczyna
Abstract: From an application standpoint, speaker-role diarization (RD), such as doctor vs. patient, host vs. guest, etc. is often more useful than traditional speaker diarization (SD), which assigns generic labels like speaker-1, speaker-2 etc. In the context of joint automatic speech recognition (ASR) + SD (who spoke what?), recent end-to-end models employ an auxiliary SD transducer, synchronized with the ASR transducer, to predict speakers per word. In this paper, we extend this framework to RD with three key contributions: (1) we simplify the training via forced alignment and cross-entropy loss instead of RNNT loss, (2) we show that word prediction and role prediction require different amounts of predictor's context, leading to separate task-specific predictors, unlike existing shared-predictor models, and (3) we propose a way to leverage RD posterior activity to influence ASR decoding and reduce small-word deletion errors.
Authors: Daniel Carlstr\"om Schad, Shrey Dixit, Janis Keck, Viktor Studenyak, Aleksandr Shpilevoi, Andrej Bicanski
Abstract: We present VIBE, a two-stage Transformer that fuses multi-modal video, audio, and text features to predict fMRI activity. Representations from open-source models (Qwen2.5, BEATs, Whisper, SlowFast, V-JEPA) are merged by a modality-fusion transformer and temporally decoded by a prediction transformer with rotary embeddings. Trained on 65 hours of movie data from the CNeuroMod dataset and ensembled across 20 seeds, VIBE attains mean parcel-wise Pearson correlations of 0.3225 on in-distribution Friends S07 and 0.2125 on six out-of-distribution films. An earlier iteration of the same architecture obtained 0.3198 and 0.2096, respectively, winning Phase-1 and placing second overall in the Algonauts 2025 Challenge.
Authors: Fitsum Gaim, Jong C. Park
Abstract: Despite being spoken by millions of people, Tigrinya remains severely underrepresented in Natural Language Processing (NLP) research. This work presents a comprehensive survey of NLP research for Tigrinya, analyzing over 40 studies spanning more than a decade of work from 2011 to 2025. We systematically review the current state of computational resources, models, and applications across ten distinct downstream tasks, including morphological processing, machine translation, speech recognition, and question-answering. Our analysis reveals a clear trajectory from foundational, rule-based systems to modern neural architectures, with progress consistently unlocked by resource creation milestones. We identify key challenges rooted in Tigrinya's morphological complexity and resource scarcity, while highlighting promising research directions, including morphology-aware modeling, cross-lingual transfer, and community-centered resource development. This work serves as both a comprehensive reference for researchers and a roadmap for advancing Tigrinya NLP. A curated metadata of the surveyed studies and resources is made publicly available.
Authors: Hongjie Chen, Zehan Li, Yaodong Song, Wenming Deng, Yitong Yao, Yuxin Zhang, Hang Lv, Xuechao Zhu, Jian Kang, Jie Lian, Jie Li, Chao Wang, Shuangyong Song, Yongxiang Li, Zhongjiang He, Xuelong Li
Abstract: Recent advances in end-to-end spoken language models (SLMs) have significantly improved the ability of AI systems to engage in natural spoken interactions. However, most existing models treat speech merely as a vehicle for linguistic content, often overlooking the rich paralinguistic and speaker characteristic cues embedded in human speech, such as dialect, age, emotion, and non-speech vocalizations. In this work, we introduce GOAT-SLM, a novel spoken language model with paralinguistic and speaker characteristic awareness, designed to extend spoken language modeling beyond text semantics. GOAT-SLM adopts a dual-modality head architecture that decouples linguistic modeling from acoustic realization, enabling robust language understanding while supporting expressive and adaptive speech generation. To enhance model efficiency and versatility, we propose a modular, staged training strategy that progressively aligns linguistic, paralinguistic, and speaker characteristic information using large-scale speech-text corpora. Experimental results on TELEVAL, a multi-dimensional evaluation benchmark, demonstrate that GOAT-SLM achieves well-balanced performance across both semantic and non-semantic tasks, and outperforms existing open-source models in handling emotion, dialectal variation, and age-sensitive interactions. This work highlights the importance of modeling beyond linguistic content and advances the development of more natural, adaptive, and socially aware spoken language systems.
Authors: Gonzalo Cardenal-Antolin, Jacques Fellay, Bashkim Jaha, Roger Kouyos, Niko Beerenwinkel, Diane Duroux
Abstract: Large language models (LLMs) are emerging as valuable tools to support clinicians in routine decision-making. HIV management is a compelling use case due to its complexity, including diverse treatment options, comorbidities, and adherence challenges. However, integrating LLMs into clinical practice raises concerns about accuracy, potential harm, and clinician acceptance. Despite their promise, AI applications in HIV care remain underexplored, and LLM benchmarking studies are scarce. This study evaluates the current capabilities of LLMs in HIV management, highlighting their strengths and limitations. We introduce HIVMedQA, a benchmark designed to assess open-ended medical question answering in HIV care. The dataset consists of curated, clinically relevant questions developed with input from an infectious disease physician. We evaluated seven general-purpose and three medically specialized LLMs, applying prompt engineering to enhance performance. Our evaluation framework incorporates both lexical similarity and an LLM-as-a-judge approach, extended to better reflect clinical relevance. We assessed performance across key dimensions: question comprehension, reasoning, knowledge recall, bias, potential harm, and factual accuracy. Results show that Gemini 2.5 Pro consistently outperformed other models across most dimensions. Notably, two of the top three models were proprietary. Performance declined as question complexity increased. Medically fine-tuned models did not always outperform general-purpose ones, and larger model size was not a reliable predictor of performance. Reasoning and comprehension were more challenging than factual recall, and cognitive biases such as recency and status quo were observed. These findings underscore the need for targeted development and evaluation to ensure safe, effective LLM integration in clinical care.
Authors: Riting Xia, Rucong Wang, Yulin Liu, Anchen Li, Xueyan Liu, Yan Zhang
Abstract: Class-imbalanced graph node classification is a practical yet underexplored research problem. Although recent studies have attempted to address this issue, they typically assume clean and reliable labels when processing class-imbalanced graphs. This assumption often violates the nature of real-world graphs, where labels frequently contain noise. Given this gap, this paper systematically investigates robust node classification for class-imbalanced graphs with noisy labels. We propose GraphALP, a novel Graph Augmentation framework based on Large language models (LLMs) and Pseudo-labeling techniques. Specifically, we design an LLM-based oversampling method to generate synthetic minority nodes, producing label-accurate minority nodes to alleviate class imbalance. Based on the class-balanced graphs, we develop a dynamically weighted pseudo-labeling method to obtain high-confidence pseudo labels to reduce label noise ratio. Additionally, we implement a secondary LLM-guided oversampling mechanism to mitigate potential class distribution skew caused by pseudo labels. Experimental results show that GraphALP achieves superior performance over state-of-the-art methods on class-imbalanced graphs with noisy labels.
Authors: Chenyu Su, Weiwei Shang, Chen Qian, Fei Zhang, Shuang Cong
Abstract: Semantics-driven 3D spatial constraints align highlevel semantic representations with low-level action spaces, facilitating the unification of task understanding and execution in robotic manipulation. The synergistic reasoning of Multimodal Large Language Models (MLLMs) and Vision Foundation Models (VFMs) enables cross-modal 3D spatial constraint construction. Nevertheless, existing methods have three key limitations: (1) coarse semantic granularity in constraint modeling, (2) lack of real-time closed-loop planning, (3) compromised robustness in semantically diverse environments. To address these challenges, we propose ReSem3D, a unified manipulation framework for semantically diverse environments, leveraging the synergy between VFMs and MLLMs to achieve fine-grained visual grounding and dynamically constructs hierarchical 3D spatial constraints for real-time manipulation. Specifically, the framework is driven by hierarchical recursive reasoning in MLLMs, which interact with VFMs to automatically construct 3D spatial constraints from natural language instructions and RGB-D observations in two stages: part-level extraction and region-level refinement. Subsequently, these constraints are encoded as real-time optimization objectives in joint space, enabling reactive behavior to dynamic disturbances. Extensive simulation and real-world experiments are conducted in semantically rich household and sparse chemical lab environments. The results demonstrate that ReSem3D performs diverse manipulation tasks under zero-shot conditions, exhibiting strong adaptability and generalization. Code and videos are available at https://github.com/scy-v/ReSem3D and https://resem3d.github.io.
URLs: https://github.com/scy-v/ReSem3D, https://resem3d.github.io.