Zengzhi Wang

SinclairWang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 6 days ago

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning

Paper • 2507.16812 • Published 6 days ago • 45

upvoted a paper 12 days ago

Scaling Laws for Optimal Data Mixtures

Paper • 2507.09404 • Published 16 days ago • 32

upvoted a paper 21 days ago

ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention

Paper • 2507.01004 • Published 27 days ago • 10

upvoted 4 collections 22 days ago

OctoThinker-Llama-1B Family

Collection

What makes a base language model suitable for RL? Through controlled experiments, we identify key factors then leverage them to scale up mid-training. • 6 items • Updated 23 days ago • 2

OctoThinker-Llama-3B Family

Collection

What makes a base language model suitable for RL? Through controlled experiments, we identify key factors then leverage them to scale up mid-training. • 6 items • Updated 23 days ago • 2

OctoThinker-Llama-8B Family

Collection

What makes a base language model suitable for RL? Through controlled experiments, we identify key factors then leverage them to scale up mid-training. • 3 items • Updated 23 days ago • 3

Mid-training Analysis Checkpoints (Llama-3.2-3B)

Collection

What makes a base language model suitable for RL? Through controlled experiments, we identify key factors then leverage them to scale up mid-training. • 10 items • Updated 22 days ago • 1

upvoted 2 papers about 1 month ago

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling

Paper • 2506.20512 • Published Jun 25 • 46

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Paper • 2506.14965 • Published Jun 17 • 49

upvoted a paper 2 months ago

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

Paper • 2505.15612 • Published May 21 • 34

upvoted a collection 3 months ago

DeepSeek-R1

Collection

10 items • Updated May 29 • 765

upvoted a paper 3 months ago

NEMOTRON-CROSSTHINK: Scaling Self-Learning beyond Math Reasoning

Paper • 2504.13941 • Published Apr 15 • 11

upvoted an article 4 months ago

view article

Article

SmolVLM2: Bringing Video Understanding to Every Device

By and 6 others •

Feb 20

• 286

upvoted 4 papers 4 months ago

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values

Paper • 2504.05535 • Published Apr 7 • 44

MegaMath: Pushing the Limits of Open Math Corpora

Paper • 2504.02807 • Published Apr 3 • 34

Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme

Paper • 2504.02587 • Published Apr 3 • 32

Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

Paper • 2503.12605 • Published Mar 16 • 36

upvoted an article 5 months ago

view article

Article

Open R1: Update #3

By and 9 others •

Mar 11

• 295

upvoted a collection 5 months ago

ProX Dataset

Collection

a collection of pre-training corpora refined by ProX • 6 items • Updated Feb 14 • 7

upvoted a paper 5 months ago

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published Feb 20 • 105