Submitted by akhaliq 46 MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark · 17 authors 3
Submitted by akhaliq 33 Show, Don't Tell: Aligning Language Models with Demonstrated Feedback · 6 authors 1
Submitted by akhaliq 21 Learning Temporally Consistent Video Depth from Video Diffusion Priors · 7 authors 2
Submitted by akhaliq 14 Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning · 5 authors 1
Submitted by akhaliq 12 ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation · 5 authors 1