Fangyun Wei

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

VideoVLA: Video Generators Can Be Generalizable Robot Manipulators

The Devil is in the Word: Video-Conditioned Text Representation Refinement for Text-to-Video Retrieval

Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models

Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%

RAIN: Your Language Models Can Align Themselves without Finetuning