Submitted by akhaliq 58 TokenFlow: Consistent Diffusion Features for Consistent Video Editing · 4 authors 1.71k 5
Submitted by akhaliq 45 Meta-Transformer: A Unified Framework for Multimodal Learning · 7 authors 1.65k 3
Submitted by akhaliq 14 FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets · 9 authors 217 2
Submitted by akhaliq 9 SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models · 10 authors 131
Submitted by akhaliq 8 The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning · 8 authors 30