arXiv:2602.01346v2 Announce Type: replace Abstract: While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often…
arXiv:2512.13142v5 Announce Type: replace Abstract: People use LLMs for reproductive-health questions, including abortion-related support. A response can sound supportive while answers reinforce harmful assumptions: judgment is likely, secrecy is…
arXiv:2510.09011v4 Announce Type: replace Abstract: In our deployed travel-planning service, most users give minimal inputs or free-form requests rather than the structured constraint checklists assumed by existing benchmarks. We therefore present…
arXiv:2510.07731v4 Announce Type: replace Abstract: Organic reaction mechanisms describe the step-wise elementary processes by which reactants transform into intermediates and products, and are fundamental to understanding chemical reactivity and…
arXiv:2609.20822v1 Announce Type: cross Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots without…
arXiv:2609.20820v1 Announce Type: cross Abstract: Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to spurious correlations and degrades…
arXiv:2609.20817v1 Announce Type: cross Abstract: Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer articulation from…
arXiv:2609.20816v1 Announce Type: cross Abstract: Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation…
arXiv:2609.20815v1 Announce Type: cross Abstract: Hereditary polyposis syndromes can be precursor lesions to colorectal cancer and are associated with a broad spectrum of extracolonic tumors. Early identification and accurate classification of…
arXiv:2609.20812v1 Announce Type: cross Abstract: Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response is often the only account of that work a user sees. We quantify the propensity of…
arXiv:2609.20784v1 Announce Type: cross Abstract: Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision…
arXiv:2609.20779v1 Announce Type: cross Abstract: Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores across model generations. We provide evidence that this methodology is systematically…
arXiv:2609.20776v1 Announce Type: cross Abstract: Action chunking is widely used for action generation and execution in Vision-Language-Action (VLA) policies, yet existing approaches commonly use a fixed action horizon. During a rollout, different…
arXiv:2609.20768v1 Announce Type: cross Abstract: Generative agents are increasingly used to select and narrate video highlights, but they typically operate over unstructured or frame-level representations. Their output is consequently difficult…
arXiv:2609.20758v1 Announce Type: cross Abstract: Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exhaustive testing is…
arXiv:2609.20752v1 Announce Type: cross Abstract: Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Logic (STL), falsification can be formulated as a…
arXiv:2609.20715v1 Announce Type: cross Abstract: Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using environment observations as…
arXiv:2609.20659v1 Announce Type: cross Abstract: Large-scale vision-language-action (VLA) models provide powerful priors for robot manipulation, yet adapting them to a specific deployment remains challenging. Supervised fine-tuning (SFT) on…
arXiv:2609.20625v1 Announce Type: cross Abstract: Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitwise reproducible, on tools that read changing…
arXiv:2609.20620v1 Announce Type: cross Abstract: Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate an architecture in which conventional…
arXiv:2609.20614v1 Announce Type: cross Abstract: Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes performed by frontier…
arXiv:2609.20575v1 Announce Type: cross Abstract: Learning visual policies for locomotion and manipulation requires coordinating contact with the environment and can incur substantial computation and GPU memory costs. First-order policy gradients…
arXiv:2609.20548v1 Announce Type: cross Abstract: Reinforcement learning agents trained to maximize their own reward in repeated interactions can converge to supra-competitive outcomes resembling explicit collusion, without communication or shared…
arXiv:2609.20504v1 Announce Type: cross Abstract: FarmerChat is Digital Green's AI-powered agricultural advisory assistant for smallholder farmers, who access it in their own language through text, voice, or photographs. Voice is a critical channel…
Pick what should wake you up. We only push stories the AI rates as genuinely urgent.