Huiqiang Jiang

Huiqiang Jiang on Hugging Face Daily Papers: 9 papers, 3 in the top 3 of their day, 394 upvotes.

1. Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling 21 upvotes, #13 of 2026-06-11
2. Stabilizing Reinforcement Learning with LLMs: Formulation and Practices 83 upvotes, #4 of 2025-12-02
3. Chain-of-Model Learning for Language Model 107 upvotes, #1 of 2025-05-20
4. RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference 23 upvotes, #5 of 2025-05-07
5. MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention 8 upvotes, #8 of 2025-04-29
6. SCBench: A KV Cache-Centric Analysis of Long-Context Methods 8 upvotes, #13 of 2024-12-16
7. RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval 28 upvotes, #3 of 2024-09-17
8. MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention 22 upvotes, #4 of 2024-07-03
9. LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression 20 upvotes, #2 of 2024-03-20

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.