Zili Wang

Zili Wang on Hugging Face Daily Papers: 10 papers, 2 in the top 3 of their day, 237 upvotes.

1. Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training 35 upvotes, #16 of 2026-09-09
2. Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration 6 upvotes, #43 of 2026-05-28
3. Taming Modality Entanglement in Continual Audio-Visual Segmentation 3 upvotes, #20 of 2025-10-27
4. Continuous Speculative Decoding for Autoregressive Image Generation 14 upvotes, #4 of 2024-11-20
5. Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis 14 upvotes, #5 of 2024-09-11
6. Layerwise Recurrent Router for Mixture-of-Experts 30 upvotes, #4 of 2024-08-14
7. AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation 2 upvotes, #12 of 2024-08-07
8. A Closer Look into Mixture-of-Experts in Large Language Models 12 upvotes, #5 of 2024-06-27
9. Beyond Language Models: Byte Models are Digital World Simulators 52 upvotes, #3 of 2024-03-01
10. ChatMusician: Understanding and Generating Music Intrinsically with LLM 57 upvotes, #1 of 2024-02-27

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.