127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “safety”

22,398 results

Safety

Dexterity from Supervised Play

DGX agent

arXiv:2610.22340v1 Announce Type: cross Abstract: How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation? We present DSP: Dexterity from supervised play

safetyarxiv-cs-ai

16 Oct 2026

Safety

Diffeomorphic Hidden-State Steering: Improving Imitation Learning Policy Robustness through Expert Hidden-State Geometry

DGX agent

Search: “safety”

Dexterity from Supervised Play

Diffeomorphic Hidden-State Steering: Improving Imitation Learning Policy Robustness through Expert Hidden-State Geometry

Do As I Do, Not As I Say: On-Policy Distillation Inherits the Teacher in Vision-Language Models

Does On-Policy Distillation Need to Complete Every Rollout?

Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL

Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems

Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory Confidence

EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric Alignment

Failure Is the Mother of Success: Recovering Supervision with Grounding Hindsight

Feasibility Ceilings Before Learning: Sizing and Timing Bounds for Drone-Mesh Interception

From Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Coding

GeoState: Learning View-Decoupled Geometry States for 3D World Modeling

GraphCompliance: Structure-Aware Regulatory Compliance through Policy-Context Graph Alignment

GRID-Planner: Graph-Structured Relational Reward Shaping for Diffusion Planning

Honesty is the Best Policy ... or is it? Demand Management for Probabilistic Service Options

How Do LLM-Generated Texts Impact Term-Based Retrieval Models?

Identification and Inference for Algorithmic Frontiers with Selective Labels

KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents

KODA: Kinematics--Observation Data Alignment for Humanoid Learning from Human Egocentric Demonstration

Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning

Learning from Unverified Peers via Shared Residual Distillation

Learning Intrinsic Dynamics in Latent World Models

Learning Rewards in Strategic Games

Learning to Forecast on Multiple Spatiotemporal Hierarchies

Learning to Reason with Selective Internal Feedback

Learning to Steer LLM Agents and Multi-Agent Systems

Learning Topology-Aware Representations for Mechanics-Relevant TPMS Metamaterials

Learning Warm Starts for the Simplex Method from Measured Solver Cost

Line-Augmented cuVSLAM: Robust Visual Odometry in Low-Texture Environments

MAIA: Anticipating Interaction Anomalies in Contact-Rich Manipulation via Multimodal World Models

MARS: A Momentum-Aware Adaptive Rating System for Personalized Assessment

Matoi: Selective Revalidation of Consequence Evidence for Agent Authorization

MedPAO-VL: Interpretable and Protocol-Compliant Agent for Structured Radiology Report Generation

Mem4Act: Learning Effective Latent Memory for Long-Horizon Robotic Manipulation

MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning

Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models

Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models

MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering

MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents

MoCaP: Mobile Code-as-Policies for Zero-Shot Mobile Manipulation from Passive Human Videos

Monotone Piecewise-Linear Harmonization of Multitemporal Multispectral Surface Reflectance With Unsupervised Deep Multiview Pseudoinvariant Features Learning

MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data

Multi-Teacher On-Policy Distillation for Flow-Based Vision-Language-Action Models

Neither True nor False: Do LLMs Represent Truth-Value Gaps in Plural Predication?

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Noise-Space Reward Alignment for Few-Step Generative Models

not the first time Dwarkesh comes as off to me as working as an undisclosed press secretary for the tech industry.

OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling