GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation
Research
Research News
New papers, breakthroughs and academic AI research
PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation
Research
Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data
Research
How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning
Research
When Can We Trust the Matching Principle? Robust Deployment Geometry Under Finite-Sample and Model Uncertainty
Research
Do ResNets Route? Sparse Interaction Experts in Residual Networks
Research
Dynamic Expert Pruning for Multi-Agent Systems
Research
AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents
Research
WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites
Research
EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents
Research
S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales
Research
SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention
Research