Knowledge catalogue
arXiv:2605.12741v1 Announce Type: new Abstract: Enabling Large Language Models (LLMs) to continuously improve from environmental interactions is a central challenge in post-training. While on-policy s
arXiv:2605.13822v1 Announce Type: new Abstract: This paper considers fixed-wing unmanned aerial vehicle (UAV) corridors comprising a main lane, a circular loiter lane for managing traffic congestion,
arXiv:2605.12655v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing beh
arXiv:2506.12876v2 Announce Type: replace Abstract: The rapid scaling of large language models~(LLMs) has made inference efficiency a primary bottleneck in the practical deployment. To address this, s
arXiv:2605.13779v1 Announce Type: cross Abstract: We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a set
arXiv:2605.13125v1 Announce Type: new Abstract: In automated driving, crash mitigation is crucial to ensure passenger safety. Accurate avoidance requires precise knowledge of the object's position and
arXiv:2605.13058v1 Announce Type: new Abstract: Wheeled-legged robots hold promise for traversing complex terrains and offer superior mobility compared to legged robots. However, wheeled-legged robots
arXiv:2605.13641v1 Announce Type: new Abstract: Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distribu
arXiv:2605.12652v1 Announce Type: cross Abstract: Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited gu
arXiv:2605.12862v1 Announce Type: cross Abstract: In production Wide-Area Networks (WANs), correlated failures dominate availability losses, forcing operators to reserve large safety margins that leav
arXiv:2605.13044v1 Announce Type: cross Abstract: LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, b
arXiv:2605.12991v1 Announce Type: cross Abstract: LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widel
arXiv:2605.12667v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) utilizes Reinforcement Learning from AI Feedback (RLAIF) for non-verifiable domains such as long-form qu
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:2602.10032v2 Announce Type: replace Abstract: Agents in cyber-physical systems are increasingly entrusted with safety-critical tasks. Ensuring safety of these agents often requires localizing th
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:2605.12869v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that ci
arXiv:2605.13830v1 Announce Type: new Abstract: Decision tree ensembles (DTE) are a popular model for a wide range of AI classification tasks, used in multiple safety critical domains, and hence verif
arXiv:2510.03992v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in agentic systems, where a fundamental task is mapping user intents to relevant extern
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:2605.12674v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly used in safety-critical applications because of their broad reasoning capabilities and ability to general
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:2506.00982v3 Announce Type: replace Abstract: Deep multi-agent reinforcement learning (MARL) has been demonstrated effectively in simulations for multi-robot problems. For autonomous vehicles, t
arXiv:2605.12651v1 Announce Type: new Abstract: Runtime monitoring of autonomous systems traditionally relies on mapping continuous sensor observations to discrete logical propositions defined over lo
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:2602.00616v3 Announce Type: replace Abstract: Text-to-Image (T2I) diffusion models enable high quality open ended synthesis, but practical use requires suppressing unsafe generations while prese
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:2605.12963v1 Announce Type: new Abstract: As AI systems become increasingly capable, safety strategies must be evaluated not only by how much they reduce present risk, but by whether they could
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