LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published 9 days ago • 204
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published May 13 • 274
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling Paper • 2605.12411 • Published May 12 • 49
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 237
Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips Paper • 2502.07408 • Published Apr 16 • 59