Knowledge catalogue
arXiv:2506.13456v2 Announce Type: replace Abstract: Diffusion Policy has demonstrated strong visuomotor modeling capabilities, but its high computational cost renders it impractical for real-time robo
arXiv:2605.13054v1 Announce Type: cross Abstract: Cross-domain offline reinforcement learning aims to adapt a policy from a source domain to a target domain using only pre-collected datasets, where en
arXiv:2605.13544v1 Announce Type: new Abstract: Fine-grained Vision-Language Pre-training (FVLP) demonstrates significant potential in 3D medical image understanding by aligning anatomy-level visual r
arXiv:2410.14375v3 Announce Type: replace Abstract: Adapting to latent confounded shift remains a core challenge in modern AI. This setting is driven by hidden variables that induce spurious correlati
arXiv:2605.13646v1 Announce Type: cross Abstract: End-to-end autonomous driving, which bypasses traditional modular pipelines by directly predicting future trajectories from sensor inputs, has recentl
arXiv:2508.01049v2 Announce Type: replace Abstract: Independent on-policy policy gradient algorithms are widely used for multi-agent reinforcement learning (MARL) in cooperative and no-conflict games,
arXiv:2605.12876v1 Announce Type: new Abstract: Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continu
arXiv:2605.13675v1 Announce Type: new Abstract: Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. Ho
arXiv:2406.05410v3 Announce Type: replace Abstract: Current multimodal large language models (MLLMs) are mainly focused on the understanding and processing of perceptual modalities such as images and
arXiv:2605.13638v1 Announce Type: cross Abstract: A quantum compiler is a critical piece in the quantum computing pipeline since it allows an abstract quantum circuit to be run on a physical quantum c
arXiv:2510.08992v3 Announce Type: replace Abstract: While researchers have made significant progress in enabling large language models (LLMs) to perform multi-step planning, LLMs struggle to ensure th
arXiv:2605.13113v1 Announce Type: cross Abstract: Text-to-image (T2I) generative models are increasingly used to produce content for education, media, and public-facing communication, and are starting
In this post, you will configure Chrome enterprise policies to restrict a browser agent to a specific website, observe the policy enforcement through session recording, and demonstrate custom root CA
arXiv:2605.12654v1 Announce Type: new Abstract: Replicating and surpassing the autonomy of natural organisms remains a long-standing goal in robotics. Yet most robotic systems have their structure, ma
arXiv:2605.13077v1 Announce Type: cross Abstract: Responsibility allocation -- determining the extent to which agents are accountable for outcomes -- is a fundamental challenge in the design and analy
arXiv:2605.12650v1 Announce Type: new Abstract: Foundation diffusion models can generate photorealistic natural images, but adapting them to medical imaging remains challenging. In medical adaptation,
arXiv:2605.12545v1 Announce Type: cross Abstract: Aesthetic image cropping aims to enhance the aesthetic quality of an image by improving its composition through spatial cropping. Previous methods oft
arXiv:2603.07433v2 Announce Type: replace-cross Abstract: Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typic
arXiv:2605.12840v1 Announce Type: cross Abstract: Marketplace platforms routinely evaluate pricing and allocation policies using logged observational data, yet strong offline performance does not impl
arXiv:2603.22273v4 Announce Type: replace Abstract: The process of discovery requires active exploration -- the act of collecting new and informative data. However, efficient autonomous exploration re
arXiv:2603.20521v2 Announce Type: replace-cross Abstract: Distributed reinforcement learning trains on data from stale, buggy, or mismatched actors, producing actions with high surprisal (negative log
arXiv:2512.13399v2 Announce Type: replace Abstract: Crafting effective reward signals remains a central challenge in Reinforcement Learning (RL), especially for complex reasoning tasks. Existing autom
arXiv:2602.06021v2 Announce Type: replace-cross Abstract: We study a data-dependent notion of diffusion-model generalization: when a model does not memorize the training set, where do its generated sa
arXiv:2605.13115v1 Announce Type: cross Abstract: Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor atta
arXiv:2605.12832v1 Announce Type: cross Abstract: Single-arm trials are an important study design for evaluating drug efficacy and safety without enrolling patients into a control arm. Although they d
arXiv:2605.12702v1 Announce Type: new Abstract: General-purpose safety benchmarks for large language models do not adequately evaluate disability-related harms. We introduce DisaBench: a taxonomy of t
arXiv:2605.12974v1 Announce Type: new Abstract: In this work, we study how to ensure probabilistic safety for nonlinear systems under distributional ambiguity. Our approach builds on a backup-based sa
arXiv:2605.12701v1 Announce Type: cross Abstract: Machine learning algorithms in socially sensitive domains (e.g., credit decisions) often focus on equalizing predictive outcomes. However, satisfying
arXiv:2605.12994v1 Announce Type: new Abstract: We study differentially private (DP) training with Muon, a matrix-valued optimizer that updates hidden-layer weights using momentum followed by Newton--
arXiv:2605.12625v1 Announce Type: cross Abstract: Continuous-action policies trained on a single demonstrated trajectory per scene suffer from mode collapse: samples cluster around the demonstrated ma
arXiv:2605.12798v1 Announce Type: cross Abstract: Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning
arXiv:2605.13063v1 Announce Type: new Abstract: Designing continuous trajectories whose time-averaged occupancy provably matches a prescribed spatial density (the ergodic coverage problem) is central
arXiv:2605.13131v1 Announce Type: new Abstract: Multi-Agent Proximal Policy Optimization (MAPPO) is a variant of the Proximal Policy Optimization (PPO) algorithm, specifically tailored for multi-agent
arXiv:2605.12995v1 Announce Type: new Abstract: Traditional retrieval pipelines optimize utility through stages of candidate retrieval and reranking, where ranking operates over a predefined candidate
arXiv:2602.06138v2 Announce Type: replace Abstract: Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applica
arXiv:2605.13757v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies are commonly trained from dense robot demonstration trajectories, often collected through teleoperation, by sampli
arXiv:2605.12997v1 Announce Type: new Abstract: Neural operators learn to map initial conditions to the terminal solution of partial differential equations (PDEs), providing a surrogate for the full o
arXiv:2605.13217v1 Announce Type: cross Abstract: Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments
arXiv:2605.13755v1 Announce Type: new Abstract: In recent years, autonomous driving has significantly in creased the demand for high-quality data to train 2D and 3D perception models for safety-critic
arXiv:2605.13130v1 Announce Type: new Abstract: Existing reasoning data curation pipelines score whole samples, treating every intermediate step as equally valuable. In reality, steps within a trace c
arXiv:2605.12782v1 Announce Type: new Abstract: Financial transaction fraud prevention faces challenges such as complex relationship structures, concealed behavioral patterns, and dynamically changing
OpenAI implemented improvements to help ChatGPT better understand and respond appropriately to context in sensitive conversations, such as those involving mental health, abuse, or other delicate topic
arXiv:2605.13581v1 Announce Type: new Abstract: Hyperspectral image (HSI) restoration is crucial for reliable analysis, as real HSIs suffer from degradations like noise, blur, and resolution loss. How
arXiv:2605.13825v1 Announce Type: new Abstract: Frontier LLMs are increasingly deployed as agents that pick the next action after a long log of prior tool calls produced by the same or a different mod
arXiv:2605.13723v1 Announce Type: cross Abstract: The phrase 'human in the loop' is increasingly used to imply a sense of safety in relation to AI decision systems. It shouldn't. There are contexts wh
arXiv:2601.21892v2 Announce Type: replace-cross Abstract: Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirica
arXiv:2605.13229v1 Announce Type: new Abstract: LLMs have shown immense potential for code translation, yet they often struggle to ensure both syntactic correctness and semantic consistency. While pre
arXiv:2605.12573v1 Announce Type: cross Abstract: Diffusion-based posterior sampling (PS) is a leading framework for imaging inverse problems, combining learned priors with measurement constraints. Ye
arXiv:2605.13801v1 Announce Type: cross Abstract: As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of th
Anthropic: In a policy paper, Anthropic urges the US and allies to enforce export controls, curb distillation attacks, and export US AI to hold the lead over China by 2028 — We're releasing a new pape
arXiv:2605.12530v1 Announce Type: cross Abstract: LLM fairness should be evaluated through in-situ conversational behavior rather than standardized-test Q&A benchmarks. We show that the standardized-t
In the @nytimes, Media Lab Prof. @kesvelt and other scientists call for stronger oversight and regulation of AI technologies, including chatbots that can provide information on producing lethal biolog
arXiv:2605.13539v1 Announce Type: new Abstract: Simulative and scenario-based testing are crucial methods in the safety assurance for automated driving systems. To ensure that simulation results are r
Interesting position paper on agentic AI as a foreseeable pathway to AGI. (bookmark it) There has been strong debate on whether a larger single model get us there or a multi-agent system. The authors
arXiv:2602.11202v3 Announce Type: replace-cross Abstract: Reasoning models produce long traces of intermediate decisions and tool calls, making test-time verification important for ensuring correctnes
arXiv:2605.12725v1 Announce Type: new Abstract: Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scen
arXiv:2605.12729v1 Announce Type: cross Abstract: Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), includ
arXiv:2605.12646v1 Announce Type: cross Abstract: It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate th
arXiv:2605.12682v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as reasoning modules in many applications. While they are efficient in certain tasks, LLMs often stru
arXiv:2605.12561v1 Announce Type: new Abstract: Safe reinforcement learning (RL) typically asks extit{what} an agent should do. We ask extit{when} it needs to act, and show that a single policy can jo