Maohua Li

Met4physics's activity

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

upvoted a paper 4 days ago

SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolation

Paper • 2610.25844 • Published 6 days ago • 35

upvoted a paper 10 days ago

Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate

Paper • 2610.04781 • Published 17 days ago • 25

upvoted 2 papers 3 months ago

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

Paper • 2607.19747 • Published Jul 22 • 29

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers

Paper • 2607.19139 • Published Jul 21 • 76

upvoted a paper 4 months ago

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published May 7 • 93

upvoted 4 papers 5 months ago

Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications

Paper • 2409.03368 • Published Mar 5, 2025 • 2

RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models

Paper • 2605.26632 • Published May 26 • 8

Rethinking Cross-Layer Information Routing in Diffusion Transformers

Paper • 2605.20708 • Published May 20 • 113

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Paper • 2605.16928 • Published May 16 • 92

upvoted 2 papers 6 months ago

EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation

Paper • 2605.04062 • Published Apr 10 • 32

Demystifing Video Reasoning

Paper • 2603.16870 • Published Mar 17 • 116

upvoted a paper 9 months ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published Jan 6 • 202