DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents Paper • 2608.18524 • Published Aug 19 • 72
FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory Paper • 2608.04530 • Published Aug 5 • 14
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model Paper • 2607.17977 • Published Jul 20 • 63
Video Generation Models are General-Purpose Vision Learners Paper • 2607.09024 • Published Jul 10 • 83
Representation Distribution Matching for One-Step Visual Generation Paper • 2607.02375 • Published Jul 2 • 11
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Paper • 2606.08063 • Published Jun 6 • 33
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks Paper • 2606.12344 • Published Jun 10 • 41
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval Paper • 2605.29271 • Published May 28 • 4
From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors Paper • 2605.31042 • Published May 29 • 17
Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality? Paper • 2605.22109 • Published May 21 • 50