T-DIG: Text-Conditioned Diversity for Image Generation Paper • 2610.29003 • Published 28 days ago • 4
VIEWCRAFT: Evolving What Multimodal Agents See and How They Read It Paper • 2610.15915 • Published Oct 11 • 20
Into the Unknown: Benchmarking AI agents on open scientific research problems Paper • 2610.19159 • Published Oct 13 • 57
Into the Unknown: Benchmarking AI agents on open scientific research problems Paper • 2610.19159 • Published Oct 13 • 57
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research Paper • 2610.02202 • Published Oct 1 • 12
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published Aug 19 • 48
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL Paper • 2607.04412 • Published Jul 5 • 37
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks Paper • 2606.29082 • Published Jun 27 • 42
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration Paper • 2609.16204 • Published Sep 14 • 4
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks Paper • 2609.15029 • Published Sep 14 • 8
Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language Paper • 2510.23828 • Published Oct 27, 2025 • 2
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models Paper • 2510.10390 • Published Oct 12, 2025 • 5
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration Paper • 2609.16204 • Published Sep 14 • 4
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks Paper • 2609.15029 • Published Sep 14 • 8
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published Aug 17 • 68
Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models Paper • 2608.13760 • Published Aug 13 • 4