Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling Paper • 2609.19499 • Published 10 days ago • 37
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments Paper • 2609.19134 • Published 10 days ago • 100
Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise Paper • 2609.07139 • Published 19 days ago • 17
DriveZero: End-to-End Driving Beyond Human Demonstrations Paper • 2609.06055 • Published 21 days ago • 57
Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance Paper • 2609.02373 • Published 24 days ago • 14
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published 23 days ago • 186
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation Paper • 2608.17426 • Published Aug 18 • 160
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
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published Aug 1 • 265