RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation Paper • 2609.16900 • Published 10 days ago • 48
HyQuant: Hybrid-Precision Quantization for LLM Attention Paper • 2608.27875 • Published 28 days ago • 30
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 23 days ago • 402
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published Aug 19 • 54
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination Paper • 2608.14391 • Published Aug 14 • 285
DarwinX: Evolving Agent Harnesses Through Natural Selection Paper • 2608.07545 • Published Jul 31 • 116
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 265
AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss Paper • 2608.11205 • Published Aug 11 • 27