wangshuai

wangsssssss's activity

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

upvoted a paper 5 days ago

GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling

Paper • 2608.29335 • Published 9 days ago • 66

upvoted a paper 18 days ago

Energy-Guided Flow Matching

Paper • 2608.05811 • Published about 1 month ago • 12

upvoted a paper 26 days ago

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published 28 days ago • 117

upvoted a paper 27 days ago

Motif 3: Technical Report

Paper • 2608.09119 • Published 28 days ago • 47

upvoted 7 papers about 1 month ago

Poplar: A Scalable Pipeline for Human-Centric Image Dataset Synthesis

Paper • 2608.00440 • Published Aug 1 • 10

DiffusionGemma Technical Report

Paper • 2608.00146 • Published Jul 31 • 40

PhiZero: A World Model Built Around Physical Language

Paper • 2607.28624 • Published Jul 30 • 172

dRAE: Representation Autoencoder with Hyper-Spherical Codes

Paper • 2607.22148 • Published Jul 24 • 12

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 514

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation

Paper • 2607.21553 • Published Jul 23 • 39

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

Paper • 2607.21653 • Published Jul 22 • 32

upvoted a paper about 2 months ago

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published Jul 16 • 172

upvoted 7 papers 2 months ago

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Paper • 2607.05373 • Published Jul 6 • 66

Wan-Streamer v0.2: Higher Resolution, Same Latency

Paper • 2607.04443 • Published Jul 5 • 44

From SRA to Self-Flow: Data Augmentation or Self-Supervision?

Paper • 2607.02508 • Published Jul 2 • 15

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published Jun 26 • 117

MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

Paper • 2606.26016 • Published Jun 24 • 10

DanceOPD: On-Policy Generative Field Distillation

Paper • 2606.27377 • Published Jun 25 • 84

DiffusionBench: On Holistic Evaluation of Diffusion Transformers

Paper • 2606.24888 • Published Jun 23 • 12

upvoted a paper 3 months ago

UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer

Paper • 2606.16255 • Published Jun 15 • 16