Crowded in B-Space: Calibrating Shared Directions for LoRA Merging Paper • 2604.16826 • Published 13 days ago • 18
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time Paper • 2604.11626 • Published 18 days ago • 100
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning Paper • 2604.03231 • Published 28 days ago • 7
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published 28 days ago • 375
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation Paper • 2604.03922 • Published 26 days ago • 53
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration Paper • 2603.29557 • Published about 1 month ago • 17
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 340
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers Paper • 2603.24414 • Published Mar 25 • 183
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization Paper • 2603.19835 • Published Mar 20 • 349
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models Paper • 2603.25716 • Published Mar 26 • 156
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning Paper • 2603.04597 • Published Mar 4 • 210
Does Your Reasoning Model Implicitly Know When to Stop Thinking? Paper • 2602.08354 • Published Feb 9 • 264