Knowledge catalogue
arXiv:2605.13143v1 Announce Type: cross Abstract: Knowledge distillation is widely used to improve generalization in practice, yet its theoretical understanding remains elusive. In the standard distil
arXiv:2510.21060v3 Announce Type: replace-cross Abstract: Policy optimization (PO) is a cornerstone of modern reinforcement learning (RL), with diverse applications spanning robotics, healthcare, and
This post likely discusses a topic of broad bipartisan agreement among Americans, with Gary Marcus commenting on its significance on social media. The specific topic of agreement is not determinable f
arXiv:2512.07775v2 Announce Type: replace Abstract: Autonomous robots rely on geometric maps to inform a diverse set of perception and decision-making algorithms. As autonomy requires reasoning and pl
arXiv:2605.13155v1 Announce Type: new Abstract: Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward model
arXiv:2605.12541v1 Announce Type: cross Abstract: Electrocardiography (ECG) is the clinical standard for cardiac assessment but requires dedicated hardware that does not scale to daily-life monitoring
arXiv:2605.13579v1 Announce Type: new Abstract: Assistive agents for Blind and Visually Impaired (BVI) users require accessibility alignment as a first-class design objective. Despite rapid progress i
arXiv:2605.13081v1 Announce Type: new Abstract: Missing modalities are prevalent in real-world Alzheimer's disease (AD) assessment and pose a significant challenge to multimodal learning, particularly
arXiv:2605.12505v1 Announce Type: cross Abstract: Autonomous AI systems generate responsibility gaps: consequential actions that cannot be satisfactorily attributed to developers, operators, or users
arXiv:2605.13436v1 Announce Type: cross Abstract: Subword regularization methods such as BPE dropout are typically applied only during fine-tuning, while pretraining is usually done with deterministic
arXiv:2605.12981v1 Announce Type: cross Abstract: Automated program synthesis has reduced the cost of producing candidate implementations, but it introduces a harder governance problem: determining wh
arXiv:2602.06239v2 Announce Type: replace Abstract: We introduce PEPO (Pessimistic Ensemble based Preference Optimization), a single-step Direct Preference Optimization (DPO)-like algorithm to mitigat
arXiv:2605.13278v1 Announce Type: cross Abstract: Score-based diffusion models demonstrate superior performance in generative tasks but encounter fundamental bottlenecks in inverse problems due to the
arXiv:2605.13111v1 Announce Type: new Abstract: Autoregressive video generation enables streaming and open-ended long video synthesis, but still suffers from long-term degradation caused by accumulate
arXiv:2605.13435v1 Announce Type: cross Abstract: There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity.
arXiv:2605.13838v1 Announce Type: new Abstract: Video-guided 3D animation holds immense potential for content creation, offering intuitive and precise control over dynamic assets. However, practical d
arXiv:2602.00586v2 Announce Type: replace-cross Abstract: Network topology excels at structural predictions but fails to capture functional semantics encoded in biomedical literature. We present RAG-G
arXiv:2605.13591v1 Announce Type: new Abstract: Reliable autonomous driving relies on large-scale, well-labeled data and robust models. However, manual data collection is resource-intensive, and tradi
arXiv:2605.13255v1 Announce Type: new Abstract: On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provid
arXiv:2605.13047v1 Announce Type: cross Abstract: Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge. Tr
arXiv:2605.12913v1 Announce Type: new Abstract: Long-horizon LM agents learn from multi-turn interaction, where a single early mistake can alter the subsequent state distribution and derail the whole
arXiv:2605.13501v1 Announce Type: cross Abstract: LLM-based generation of SystemVerilog Assertions (SVA) is often reported as nearing saturation, with the strongest specialized model reaching {sim}76%
arXiv:2605.13775v1 Announce Type: cross Abstract: The scalability of robotic manipulation is fundamentally bottlenecked by the scarcity of task-aligned physical interaction data. While vision-language
arXiv:2605.13665v1 Announce Type: new Abstract: Quadruped robots demonstrate exceptional potential for navigating complex terrain in critical applications such as search and rescue missions and infras
arXiv:2605.13725v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent simulation offers a powerful testbed for studying social opinion dynamics. Yet current approaches often ado
arXiv:2605.13117v1 Announce Type: cross Abstract: Achieving reliable robotic manipulation, such as dexterous grasping, requires a synergy between physically stable interactions and semantic task guida
arXiv:2605.11505v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards helps reasoning, but GRPO-style methods stall on hard prompts where all sampled rollouts fail. SORT a
arXiv:2605.13554v1 Announce Type: cross Abstract: Contrastive reinforcement learning (CRL) learns goal-conditioned Q-values through a contrastive objective over state-action and goal representations,
arXiv:2511.00066v4 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a practical route to improve large language model reasoning, and Group Relative Pol
arXiv:2605.13428v1 Announce Type: new Abstract: Generalizing robotic manipulation across object poses, viewpoints, and dynamic disturbances is difficult, especially with only a few demonstrations. End
arXiv:2605.12513v1 Announce Type: cross Abstract: Influence maximization (IM) in real platforms is challenged by incomplete, noisy social graphs and non-stationary diffusion dynamics. We propose SP-GC
arXiv:2605.13566v1 Announce Type: new Abstract: Land Surface Temperature (LST) is a key variable for various applications, such as urban climate and ecology studies. Yet, existing satellite-derived LS
arXiv:2605.12709v1 Announce Type: new Abstract: Implicit Neural Representations (INRs) model continuous signals using multilayer perceptrons (MLPs), enabling compact, differentiable, and high-fidelity
arXiv:2605.13202v1 Announce Type: cross Abstract: Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress
arXiv:2605.12514v1 Announce Type: cross Abstract: Scientific innovation increasingly depends on collaboration, yet the organizational structure that fosters breakthrough ideas remains poorly understoo
arXiv:2605.13207v1 Announce Type: new Abstract: Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing a
arXiv:2605.13230v1 Announce Type: cross Abstract: The convergence of reinforcement learning and imitation learning has positioned Reverse KL (RKL) as a promising paradigm for on-policy LLM distillatio
arXiv:2602.09628v2 Announce Type: replace Abstract: Real-time whole-body teleoperation is a critical method for humanoid robots to perform complex tasks in unstructured environments. However, developi
arXiv:2605.13537v1 Announce Type: cross Abstract: Inference-time alignment techniques offer a lightweight alternative or complement to costly reinforcement learning, while enabling continual adaptatio
arXiv:2507.18809v2 Announce Type: replace Abstract: Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There ar
arXiv:2605.13316v1 Announce Type: new Abstract: Action diffusion excels at high-fidelity action generation but incurs heavy computational costs owing to its iterative denoising nature. Despite current
arXiv:2605.12717v1 Announce Type: cross Abstract: AI alignment and participatory design motivate a new democratic design problem: how to collectively choose a decision rule to use repeatedly. We study
arXiv:2602.01453v3 Announce Type: replace Abstract: We study cooperative multi-agent reinforcement learning in the setting of reward-free exploration, where multiple agents jointly explore an unknown
arXiv:2605.12620v1 Announce Type: new Abstract: Building generalist embodied agents capable of solving complex real-world tasks remains a fundamental challenge in AI. Multimodal Large Language Models
arXiv:2605.13717v1 Announce Type: new Abstract: We study best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure. Recent work established a
arXiv:2605.13834v1 Announce Type: cross Abstract: In this paper, we study solution operators of physical field equations on geometric meshes from a function-space perspective. We reveal that Hodge ort
arXiv:2605.13430v1 Announce Type: cross Abstract: Selection bias is pervasive in observational studies. For example, large scale biobanks data can exhibit ``healthy volunteer bias'' when respondents a
arXiv:2602.06475v2 Announce Type: replace Abstract: Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coup
arXiv:2605.12587v1 Announce Type: new Abstract: Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geome
arXiv:2605.13401v1 Announce Type: new Abstract: We propose a data augmentation method for offline reinforcement learning, motivated by active positioning problems. Particularly, our approach enables t
arXiv:2605.13049v1 Announce Type: new Abstract: Infrared and Visible Image Fusion (IVIF) has shown promise in visual tasks under challenging environments, but fusion under unregistered conditions face
arXiv:2512.06109v3 Announce Type: replace-cross Abstract: This paper develops a unified perspective on several optimal control formulations through the lens of Kullback-Leibler (KL) regularization. We
arXiv:2510.10642v3 Announce Type: replace-cross Abstract: Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage kn
arXiv:2605.13601v1 Announce Type: new Abstract: As intelligent systems are increasingly implemented in our society to make autonomous decisions, their commitment to human values raises serious concern
arXiv:2605.12571v1 Announce Type: cross Abstract: Long video question answering requires locating sparse, time-scattered visual evidence within highly redundant content. Although current MLLMs perform
Gary Marcus expresses frustration about the increasing prevalence of bot-generated and LLM-written responses on social media platforms, noting that filtering through such content has become increasing
arXiv:2605.13621v1 Announce Type: new Abstract: Infrared-visible object detection improves detection performance by combining complementary features from multispectral images. Existing backbone-specif
“we are working harder to manage our tools than we are to solve the actual problems they were meant to fix.” Harvard Business Review research reveals that excessive interaction with AI is causing a sp
arXiv:2605.13290v1 Announce Type: new Abstract: Validating training data for reasoning models typically requires expensive trial-and-error fine-tuning cycles. In this work, we investigate whether the
arXiv:2605.13105v1 Announce Type: new Abstract: Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual sh