A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks Paper • 2605.28556 • Published May 27 • 73
Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips Paper • 2502.07408 • Published Apr 16 • 59
view article Article Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding nvidia • Mar 19 • 47