Zengzhi Wang

SinclairWang's activity

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

upvoted 2 papers 10 days ago

LLaDA2.0: Scaling Up Diffusion Language Models to 100B

Paper • 2512.15745 • Published 19 days ago • 77

Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

Paper • 2512.16912 • Published 10 days ago • 10

upvoted a paper about 1 month ago

GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization

Paper • 2511.15705 • Published Nov 19 • 92

upvoted 2 papers about 2 months ago

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Paper • 2510.25726 • Published Oct 29 • 45

Context Engineering 2.0: The Context of Context Engineering

Paper • 2510.26493 • Published Oct 30 • 8

upvoted 3 papers 2 months ago

DeepSeek-OCR: Contexts Optical Compression

Paper • 2510.18234 • Published Oct 21 • 84

olmOCR 2: Unit Test Rewards for Document OCR

Paper • 2510.19817 • Published Oct 22 • 15

FineVision: Open Data Is All You Need

Paper • 2510.17269 • Published Oct 20 • 72

upvoted an article 2 months ago

view article

Article

SmolLM3: smol, multilingual, long-context reasoner

• 
• 
• +21

Jul 8

•

740

upvoted a paper 3 months ago

LIMI: Less is More for Agency

Paper • 2509.17567 • Published Sep 22 • 102

upvoted a paper 5 months ago

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

Paper • 2508.10433 • Published Aug 14 • 144

upvoted 4 collections 5 months ago

ProX General Models

Collection

base models trained on ProX curated data. • 16 items • Updated Oct 10, 2024 • 1

ProX Math Models

Collection

base models trained on ProX curated openwebmath-pro. • 5 items • Updated Oct 10, 2024 • 1

ProX Refining Models

Collection

Adapted small language models used to generate data refining programs • 5 items • Updated Oct 10, 2024 • 5

Qwen3

Collection

84 items • Updated Aug 6 • 1.52k

upvoted 2 papers 5 months ago

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

Paper • 2507.16812 • Published Jul 22 • 63

Scaling Laws for Optimal Data Mixtures

Paper • 2507.09404 • Published Jul 12 • 36

upvoted a paper 6 months ago

ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention

Paper • 2507.01004 • Published Jul 1 • 10

upvoted 2 collections 6 months 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 Jul 6 • 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 Jul 6 • 2