Xin Dong

Xin Dong on Hugging Face Daily Papers: 11 papers, 5 in the top 3 of their day, 933 upvotes.

  1. GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization 191 upvotes, #1 of 2026-01-09
  2. Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed 12 upvotes, #17 of 2025-12-17
  3. ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration 100 upvotes, #2 of 2025-12-03
  4. Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models 29 upvotes, #7 of 2025-12-01
  5. TiDAR: Think in Diffusion, Talk in Autoregression 95 upvotes, #2 of 2025-11-13
  6. DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning 15 upvotes, #15 of 2025-10-20
  7. NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model 31 upvotes, #7 of 2025-08-21
  8. Small Language Models are the Future of Agentic AI 3 upvotes, #36 of 2025-06-05
  9. ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models 118 upvotes, #1 of 2025-06-02
  10. CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training 87 upvotes, #1 of 2025-04-18
  11. Hymba: A Hybrid-head Architecture for Small Language Models 37 upvotes, #4 of 2024-11-22

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.