Knowledge catalogue
arXiv:2605.19461v1 Announce Type: new Abstract: On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on
arXiv:2605.19532v1 Announce Type: new Abstract: Text-to-image diffusion models can synthesize high-quality images, yet the outcome is notoriously sensitive to the random seed: different initial seeds
arXiv:2605.19352v1 Announce Type: cross Abstract: Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challenge at the
⚠️👇 🚨Breaking ⚠️ If we can’t make AI agents follow rules, we are screwed. New study from METR reports that “when the agents were faced with hard tasks, they routinely violated constraints” This—routin
arXiv:2605.19837v1 Announce Type: cross Abstract: Adverse weather (rain, fog, sand, and snow) degrades camera-based object detection in autonomous vehicles. Existing enhancement-then-detect approaches
arXiv:2605.19229v1 Announce Type: new Abstract: Survey research faces mounting structural challenges: declining response rates, sample bias, block-wise missingness among at-risk respondents, and AI-as
arXiv:2605.19981v1 Announce Type: new Abstract: Humanoid robots have achieved impressive locomotion performance, yet contact-rich and long-horizon manipulation remains a major bottleneck. Manipulation
arXiv:2605.19436v1 Announce Type: cross Abstract: When a model produces a correct solution under reinforcement learning with verifiable rewards (RLVR), every token receives the same reward signal rega
arXiv:2512.20931v2 Announce Type: replace Abstract: Estimating the absolute orientation of a local system relative to a global navigation satellite system (GNSS) reference often suffers from local min
arXiv:2605.19091v1 Announce Type: new Abstract: Chess has long served as a canonical testbed for artificial intelligence, but modeling approaches for its central tasks have diverged. Maximizing playin
arXiv:2507.15698v2 Announce Type: replace-cross Abstract: Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially fo
arXiv:2504.09188v2 Announce Type: replace Abstract: This paper introduces the Compliant Explicit Reference Governor (CERG), a modular reference management system that enables robots to interact physic
arXiv:2605.19374v1 Announce Type: cross Abstract: Vision-language alignment using chest X-rays and radiology reports has emerged as an advanced paradigm for zero-shot classification and grounding of c
arXiv:2603.11673v2 Announce Type: replace Abstract: Many physical systems exhibit a low-dimensional structure that varies with external parameters: link lengths in a robot, forcing constants in a flui
arXiv:2605.19314v1 Announce Type: cross Abstract: Long-horizon embodied agents increasingly delegate navigation, search, approach, and manipulation to specialist executors. As these executors become s
arXiv:2605.20075v1 Announce Type: cross Abstract: Chain-of-thought (CoT) is a standard approach for eliciting reasoning capabilities from large language models (LLMs). However, the common CoT paradigm
‼️ Could large language models turn out to be the tech industry’s Vietnam? All In’s @jason notes below that today’s students are speaking out against AI, just as students in the 60s and 70s spoke out
arXiv:2605.19665v1 Announce Type: cross Abstract: Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond
arXiv:2510.13293v3 Announce Type: replace Abstract: While Text-to-Speech (TTS) systems enable emotional control via natural-language instructions, expressiveness, naturalness, and speech quality degra
arXiv:2605.19690v1 Announce Type: new Abstract: Navigation Foundation Models (NFMs) trained on large cross-embodied datasets have demonstrated powerful generalizability in various scenarios. Adopting
arXiv:2511.13588v2 Announce Type: replace-cross Abstract: Model Predictive Control (MPC) is a powerful framework for optimal control but can be too slow for low-latency applications. We present a data
arXiv:2605.19294v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically deployed with asynchronous inference: the robot executes a previously predicted action chunk while
arXiv:2605.18793v1 Announce Type: cross Abstract: Accurate spatiotemporal pattern analysis is critical in fields such as urban traffic, meteorology, and public health monitoring. However, existing met
arXiv:2506.12218v2 Announce Type: replace-cross Abstract: Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architec
arXiv:2512.16856v2 Announce Type: replace Abstract: AI safety and alignment research has predominantly been focused on methods for safeguarding individual AI systems, resting on the assumption of an e
arXiv:2605.19293v1 Announce Type: cross Abstract: Wireless extended reality (XR) teleoperation provides embodied interaction capability for collecting humanoid robot demonstrations, but the large-scal
arXiv:2605.18899v1 Announce Type: cross Abstract: Generative LLM-based recommenders (LLM-Rec) require continual post-deployment updates, yet deployment logs provide only policy-shaped contextual bandi
arXiv:2603.23722v2 Announce Type: replace-cross Abstract: While Multi-Agent Reinforcement Learning (MARL) algorithms achieve unprecedented successes across complex continuous domains, their standard d
arXiv:2601.05391v2 Announce Type: replace Abstract: Accurate multistep forecasting of node-level attributes on dynamic graphs is critical for applications ranging from financial trust networks to biol
arXiv:2605.19322v1 Announce Type: new Abstract: Recent advances in Video Large Language Models (Video-LLMs) have greatly expanded multimodal reasoning capabilities. However, the massive number of visu
arXiv:2511.19741v3 Announce Type: replace Abstract: Optimal Transport (OT) offers a powerful framework for finding correspondences between distributions and addressing matching and alignment problems
arXiv:2605.18918v1 Announce Type: cross Abstract: Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web s
arXiv:2605.18848v1 Announce Type: cross Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by leveraging
arXiv:2605.19321v1 Announce Type: cross Abstract: Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards.
arXiv:2509.26464v2 Announce Type: replace Abstract: Self-preference is a fundamental feature of biological organisms. Since large language models (LLMs) lack sentience, they might be expected to avoid
arXiv:2410.15362v2 Announce Type: replace-cross Abstract: Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks t
arXiv:2601.16200v3 Announce Type: replace-cross Abstract: Modern deep learning models exhibit strong capabilities across diverse applications, yet remain vulnerable to malicious inputs that induce err
arXiv:2605.19739v1 Announce Type: new Abstract: Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the
arXiv:2605.19604v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable act
arXiv:2605.18841v1 Announce Type: new Abstract: Safety in reinforcement learning is often specified through cumulative cost constraints, but these trajectory-level guarantees do not directly prevent u
arXiv:2510.13727v2 Announce Type: replace Abstract: Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-g
arXiv:2605.19235v1 Announce Type: new Abstract: Competitive multi-agent reinforcement learning in imperfect-information games requires agents to act under partial observability and against adversarial
arXiv:2605.19457v1 Announce Type: new Abstract: Automated bidding is central to modern digital advertising. Early rule-based methods lacked adaptability, while subsequent Reinforcement Learning approa
arXiv:2605.19529v1 Announce Type: new Abstract: When the same LLM generates assessment items, simulates student responses, and scores them, the validation loop is self-referential. We introduce Genera
arXiv:2603.11768v2 Announce Type: replace Abstract: Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong m
arXiv:2605.19209v1 Announce Type: new Abstract: The multi-robot unlabeled motion planning problem of concurrently assigning robots to goals and generating safe trajectories is central in many collabor
arXiv:2605.19038v1 Announce Type: cross Abstract: The rapid advancement of autonomous driving (AD) technologies has outpaced the development of robust safety evaluation methods. Conventional testing r
arXiv:2605.20138v1 Announce Type: new Abstract: This article presents a Hamilton--Jacobi (HJ) reachability framework for a two--satellite collision avoidance problem operating in the same circular orb
arXiv:2412.00404v2 Announce Type: replace Abstract: With the maturity of depth sensors in various 3D safety-critical applications, 3D point cloud models have been shown to be vulnerable to adversarial
arXiv:2604.17237v2 Announce Type: replace-cross Abstract: Decoding-free reranking methods that read relevance signals directly from LLM attention weights offer significant latency advantages over auto
arXiv:2510.00054v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tasks. However, their performance on high-resol
arXiv:2506.07209v2 Announce Type: replace-cross Abstract: We present HOI-PAGE, a new approach that prioritizes part-level affordance reasoning to generate high-fidelity 4D human-object interactions (H
arXiv:2605.19309v1 Announce Type: new Abstract: Document Layout Analysis (DLA) pipelines provide structured page representations for retrieval-augmented generation, long-document question answering, a
arXiv:2602.07570v2 Announce Type: replace-cross Abstract: Understanding how humans and artificial intelligence systems process complex narrative videos is a fundamental challenge at the intersection o
arXiv:2503.08633v2 Announce Type: replace Abstract: Machine unlearning is the task of updating a trained model to forget specific training data without retraining from scratch. In this paper, we inves
arXiv:2605.19592v1 Announce Type: cross Abstract: Reinforcement learning often produces high-frequency oscillatory control signals that undermine the safety and stability required for physical deploym
arXiv:2605.19458v1 Announce Type: new Abstract: We study the max-margin solutions reached by mirror flow in deep neural networks with homogeneous activation functions. Extending classical results on g
arXiv:2504.03758v4 Announce Type: replace-cross Abstract: Crowd movement simulation is crucial for pedestrian safety management and facility design. Data-driven models offer the potential to improve r
arXiv:2605.19641v1 Announce Type: cross Abstract: Stochastic gradient methods are central to modern large-scale learning, but their use with incomplete covariates remains delicate since imputation sch
arXiv:2605.18759v1 Announce Type: cross Abstract: Artificial intelligence (AI), exemplified by large language models (LLMs), is rapidly approaching and in some cases surpassing human performance acros