WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents Paper • 2611.17955 • Published 8 days ago • 14
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published Sep 2 • 149
DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation Paper • 2610.04596 • Published Oct 3 • 20
Fair-GPTQ: Bias-Aware Quantization for Large Language Models Paper • 2509.15206 • Published Sep 18, 2025 • 6
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity Paper • 2608.13430 • Published Aug 13 • 5
The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data Paper • 2608.04268 • Published Aug 4 • 1
Debias-SparseGPT: Bias-Aware Pruning for Large Language Models Paper • 2609.02496 • Published Sep 2 • 3
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World Paper • 2608.13546 • Published Aug 13 • 72
HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection Paper • 2511.06391 • Published Apr 5 • 1
Histoires Morales: A French Dataset for Assessing Moral Alignment Paper • 2501.17117 • Published Jan 28, 2025 • 5