Xiaozhi Wang

Xiaozhi Wang on Hugging Face Daily Papers: 9 papers, 1 in the top 3 of their day, 148 upvotes.

1. Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders 15 upvotes, #24 of 2026-05-28
2. WildReward: Learning Reward Models from In-the-Wild Human Interactions 3 upvotes, #36 of 2026-02-10
3. VerIF: Verification Engineering for Reinforcement Learning in Instruction Following 6 upvotes, #27 of 2025-06-13
4. AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios 8 upvotes, #30 of 2025-05-23
5. Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems 21 upvotes, #9 of 2025-02-27
6. LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks 31 upvotes, #5 of 2024-12-20
7. Constraint Back-translation Improves Complex Instruction Following of Large Language Models 15 upvotes, #6 of 2024-11-01
8. Configurable Foundation Models: Building LLMs from a Modular Perspective 26 upvotes, #2 of 2024-09-09
9. KoLA: Carefully Benchmarking World Knowledge of Large Language Models 20 upvotes, #6 of 2023-06-16

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.