Weigao Sun's picture

Weigao Sun

weigao266

·

https://weigao266.github.io/

AI & ML interests

Algo & MLSys

Recent Activity

upvoted a paper 1 day ago

Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations

upvoted a paper 2 days ago

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

upvoted a paper 2 days ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

View all activity

Organizations

weigao266's activity

upvoted a paper 1 day ago

Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations

Paper • 2506.04633 • Published 2 days ago • 16

upvoted 2 papers 2 days ago

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

Paper • 2506.04207 • Published 3 days ago • 41

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Paper • 2506.01844 • Published 5 days ago • 74

upvoted a paper 9 days ago

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Paper • 2505.22617 • Published 10 days ago • 116

upvoted a paper 16 days ago

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

Paper • 2505.15612 • Published 17 days ago • 32

upvoted a paper 18 days ago

Accelerate TarFlow Sampling with GS-Jacobi Iteration

Paper • 2505.12849 • Published 19 days ago • 7

upvoted a collection about 1 month ago

Liger

6 items • Updated Mar 20 • 2

upvoted a paper 2 months ago

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond

Paper • 2503.21614 • Published Mar 27 • 39

upvoted a collection 3 months ago

MoM

9 items • Updated Mar 18 • 2

upvoted 2 papers 3 months ago

Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts

Paper • 2503.05447 • Published Mar 7 • 8

Liger: Linearizing Large Language Models to Gated Recurrent Structures

Paper • 2503.01496 • Published Mar 3 • 18

upvoted 3 papers 4 months ago

MoM: Linear Sequence Modeling with Mixture-of-Memories

Paper • 2502.13685 • Published Feb 19 • 36

LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid

Paper • 2502.07563 • Published Feb 11 • 24

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

Paper • 2501.12895 • Published Jan 22 • 63

upvoted a collection 11 months ago

Qwen2

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated Apr 28 • 364

upvoted a collection 12 months ago

SSMs

A collection of Mamba-2-based research models with 8B parameters trained on 3.5T tokens for comparison with Transformers. • 5 items • Updated about 16 hours ago • 27

upvoted 3 papers about 1 year ago

CO2: Efficient Distributed Training with Full Communication-Computation Overlap

Paper • 2401.16265 • Published Jan 29, 2024 • 1

Linear Attention Sequence Parallelism

Paper • 2404.02882 • Published Apr 3, 2024 • 3

Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models

Paper • 2401.04658 • Published Jan 9, 2024 • 28