Knowledge catalogue
arXiv:2601.00728v5 Announce Type: replace Abstract: We propose a reinforcement learning (RL) framework for xy{responsive} precision tuning for linear solvers, which can be extended to general algorith
arXiv:2602.04620v3 Announce Type: replace Abstract: GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approxima
arXiv:2609.19729v1 Announce Type: new Abstract: Autoregressive (AR) video generation degrades over long horizons due to an overlooked train-inference discrepancy we term KV eviction mismatch: models t
arXiv:2609.20538v1 Announce Type: new Abstract: An AI evaluation can be perfectly reproducible and still support the wrong claim. This risk is acute in closed-loop systems: policy determines visited s
arXiv:2609.19170v1 Announce Type: new Abstract: Emphatic temporal-difference learning (ETD) stabilizes the expected off-policy TD update and changes its projection geometry, but neither property deter
arXiv:2609.19866v1 Announce Type: new Abstract: High annotation reproducibility does not necessarily imply that an LLM-inferred measure captures the construct it is intended to measure. We test this d
arXiv:2609.19661v1 Announce Type: new Abstract: Imitation-learned robot policies are frequently overfit to the visual conditions present in their training demonstrations. Consequently, variations in o
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
arXiv:2609.20264v1 Announce Type: cross Abstract: In staggered treatment-adoption designs, later-treated units are valid controls for an earlier-treated cohort only until their own treatment begins, s
arXiv:2601.07823v2 Announce Type: replace-cross Abstract: Video world models have emerged as promising candidates for high-fidelity world models, offering the potential to synthesize high-quality vide
arXiv:2609.20063v1 Announce Type: cross Abstract: The rapid advancement of speech synthesis and voice conversion technologies has made audio deepfakes increasingly realistic, posing serious security r
arXiv:2609.19817v1 Announce Type: new Abstract: Robotic garment unfolding is essential for downstream tasks, yet quasi-static methods require repeated actions, while existing dynamic approaches predom
arXiv:2609.20629v1 Announce Type: new Abstract: Autonomous recovery of a micro unmanned aerial vehicle (UAV) onto a moving airborne carrier enables reusable deploy-mission-recover operation, but coupl
arXiv:2609.19665v1 Announce Type: new Abstract: Runtime safety filters for learned manipulation policies typically define unsafe states as unions of object-wise keep-out regions. This representation c
arXiv:2609.20103v1 Announce Type: new Abstract: Safety-critical driving scenario generation has largely focused on manipulating the behavior of surrounding agents while starting from an initial scene
arXiv:2609.20398v1 Announce Type: new Abstract: Semantic parsing (SP)-based knowledge base question answering aims to answer natural language questions by generating executable logical forms (LFs) ove
arXiv:2609.20807v1 Announce Type: new Abstract: Reinforcement learning (RL) of large language models is notoriously sensitive to small differences between training and inference engines, often referre
arXiv:2609.19444v1 Announce Type: new Abstract: Fine-grained evaluation of glomerular pathology must distinguish normal glomeruli from abnormalities such as global and segmental glomerulosclerosis, ob
arXiv:2609.19330v1 Announce Type: new Abstract: Autonomous robots operating in partially observed environments must navigate safely while acquiring observations that improve future planning. Existing
arXiv:2510.10232v2 Announce Type: replace-cross Abstract: Recursive self-modification is increasingly central in AutoML, neural architecture search, and adaptive optimization, yet no existing framewor
arXiv:2609.20648v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are a class of generalist robot policies that map camera images and language instructions directly to robot actions.
New York Times: Sources: Anthropic expects to generate 100B+ in annualized revenue this year, up from 65B as of July, as it moves ahead with its IPO amid the AI safety debate — The company is expected
arXiv:2609.19418v1 Announce Type: cross Abstract: In evidence-based policymaking, typically one experimental sample is observed, then a learned policy recommendation is implemented at scale. Policies
arXiv:2609.20791v1 Announce Type: new Abstract: Hierarchical planning frameworks combine skills from multiple robot control policies for long-horizon task execution, where determining when to terminat
arXiv:2510.12904v2 Announce Type: replace Abstract: Surgical future prediction, driven by real-time AI analysis of surgical video, is critical for operating room safety and efficiency. It provides act
arXiv:2609.19820v1 Announce Type: new Abstract: Regularized self-play -- the family behind DeepNash's Stratego play -- drives a two-player zero-sum policy to a Nash equilibrium by best-responding to a
arXiv:2609.20347v1 Announce Type: cross Abstract: LEO satellite networks feature dynamic topologies, time-varying links, and diverse service requirements, which make conventional routing schemes diffi
arXiv:2609.20712v1 Announce Type: new Abstract: This paper introduces and operationalizes summarization bias: a proposed systematic tendency of large language models (LLMs) to represent narrative mean
arXiv:2609.19613v1 Announce Type: cross Abstract: Dexterous food manipulation requires control under deformation, occlusion, and uncertain contact. We present TacSushi, a tactile-grounded, Cosmos3-bas
arXiv:2609.19577v1 Announce Type: new Abstract: Teleoperation, a human-in-the-loop control scheme, allows a human operator to remotely command and guide a mobile robot to navigate in off-road environm
arXiv:2609.19234v1 Announce Type: cross Abstract: This paper presents the AR fairness metamodel, a framework designed to represent, analyze, and compare different fairness scenarios. The metamodel con
arXiv:2609.20409v1 Announce Type: new Abstract: Two-timescale stochastic approximation (TTSA) is a fundamental tool for analyzing coupled iterative algorithms in reinforcement learning, optimization,
arXiv:2609.19366v1 Announce Type: new Abstract: Prior work has shown that internal harmfulness representations in large language models vary across risk categories, while sharing a common general harm
These are precisely the scenarios that I spend a significant time actually being concerned with. The adoption of unreliable, brittle, and inaccurate LLMs within safety-critical fields (e.g., defense a
arXiv:2609.20131v1 Announce Type: cross Abstract: Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly r
this this this The focus on AI causing extinction is going to get people killed. AI lab employees talk about how hard security is, not to point to some new solution, but to say security won’t work. On
This was a super fun podcast, went far further afield than most of them do. Give it a listen! Episode 432 w/ Connor Leahy (@NPCollapse) is available now. Connor is an AI researcher & co-founder of Ele
arXiv:2609.20435v1 Announce Type: new Abstract: Autonomous mobile robots require timeefficient planning and safety-critical dynamic obstacle avoidance under constrained onboard computation. While Iter
arXiv:2609.19666v1 Announce Type: new Abstract: Imitation-learned vision--language--action (VLA) foundation models acquire broad manipulation capabilities by scaling robot data across tasks and embodi
arXiv:2609.20646v1 Announce Type: new Abstract: A vision-language-action (VLA) policy with a flow-matching action expert generates each action chunk (a short command sequence) by integrating a learned
arXiv:2609.19200v1 Announce Type: new Abstract: Underwater visuomotor policy learning has focused primarily on single manipulators, while bimanual imitation learning has been studied largely in air. W
arXiv:2609.19690v1 Announce Type: cross Abstract: Daily locomotion encompasses diverse activities and frequent transitions between them, yet most exoskeleton controllers are designed for a single acti
arXiv:2609.19628v1 Announce Type: new Abstract: We present VGGT-GS SLAM, a monocular 3D Gaussian Splatting SLAM system designed for uncalibrated videos. Starting from feed-forward VGGT pose and depth
arXiv:2609.20744v1 Announce Type: new Abstract: Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major computational bottleneck. Linea
arXiv:2609.19340v1 Announce Type: new Abstract: Humanoid loco-manipulation requires adaptive whole-body coordination to seamlessly integrate locomotion and physical interaction. Despite recent advance
arXiv:2609.20477v1 Announce Type: new Abstract: Rebar insertion is among the most repetitive and physically demanding tasks on construction sites, and a contact-rich problem at 1.4 mm clearance. The p
arXiv:2609.20191v1 Announce Type: cross Abstract: Running vision-language navigation fully onboard an aerial robot is hard, since grounding, planning, and control must share limited compute and a sing
As the tech sector sounds alarms about AI's potential to destroy humanity, entertainment labor groups are urging the public to stay focused on what's already happening. The Verge reached out to Disney
arXiv:2609.20261v1 Announce Type: new Abstract: Autonomous agents derive concrete mutations from database reads, retrieved evidence, policy, beliefs, and delegated authority. Those inputs may change w
arXiv:2603.24651v2 Announce Type: replace-cross Abstract: Automatic depression detection from doctor-patient conversations has gained momentum thanks to the availability of public corpora and advances
arXiv:2405.09360v3 Announce Type: replace Abstract: Fairness in decision-making processes is often quantified using probabilistic metrics. However, these metrics need not reflect the consequences of d
Wild woah. Court just unsealed Summary Judgment motions in New York Times v OpenAI / Microsoft. Easy to see why the AI companies had so many redactions (pink). Their own people wrote the lede for NYT,
arXiv:2609.19449v1 Announce Type: new Abstract: Robots must complete their tasks and maintain the achieved outcomes while avoiding safety failures at all times. Strict reach-avoid-stay (sRAS) formaliz
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 policie
arXiv:2609.19600v1 Announce Type: new Abstract: Adapting robots to new objects and tasks requires interaction experience that can be costly to obtain. We present WorldContact, a contact-centric world
arXiv:2609.20408v1 Announce Type: cross Abstract: Large language models are usually interpreted through concepts that humans already possess: truthfulness, refusal, deception, personality, harmfulness
arXiv:2609.18122v1 Announce Type: cross Abstract: Learning-enabled robotic manipulation increasingly relies on robot simulators for policy training and evaluation before real-world deployment. Inside
arXiv:2609.18111v1 Announce Type: cross Abstract: The integration of large-scale foundation models with physical embodiments has led to significant advancements in robotics known as Generative Physica
arXiv:2609.18782v1 Announce Type: new Abstract: We establish convergence bounds for deep V-learning with horizon H. The algorithm fits a scalar value function to targets from executed transitions and
New York Times: A former US State Department envoy says the US-China AI safety talks will not yield a breakthrough treaty as Beijing is prioritizing its strategic advantage — The United States is prep