Submitted by zongkey 72 Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models feyospace 1
Submitted by Jiafei1224 50 Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models National University of Singapore 24 1
Submitted by ktwu01 46 Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation Carnegie Mellon University 201 3
Submitted by taesiri 45 SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking Tencent Hunyuan 3
Submitted by Lpc206 26 COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization Chinese University of Hong Kong, Shenzhen 5 1
Submitted by VennTum 22 PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization KAIST AI 0 1
Submitted by taesiri 2 SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image · 5 authors 1 1
Submitted by Franck-Dernoncourt 2 Online Learning with LLM Experts from Limited Feedback · 7 authors 1
Submitted by Franck-Dernoncourt 1 Beyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents · 10 authors 1
zongkey 
