Pengxiang Li

pengxiang's activity

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

commented a paper 2 months ago

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published Jan 27 • 26 •

4

commented a paper 5 months ago

From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model

Paper • 2510.19871 • Published Oct 22, 2025 • 30 •

2

commented 2 papers 6 months ago

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training

Paper • 2510.15859 • Published Oct 17, 2025 • 13 •

2

Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling

Paper • 2510.01329 • Published Oct 1, 2025 • 6 •

3

commented 2 papers 7 months ago

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

Paper • 2509.20109 • Published Sep 24, 2025 • 4 •

2

Diffusion Language Models Know the Answer Before Decoding

Paper • 2508.19982 • Published Aug 27, 2025 • 27 •

2

commented a paper 8 months ago

Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

Paper • 2508.02193 • Published Aug 4, 2025 • 138 •

17

commented a paper 9 months ago

GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling

Paper • 2506.22049 • Published Jun 27, 2025 • 2 •

1

commented a paper 10 months ago

Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking

Paper • 2505.20199 • Published May 26, 2025 • 1 •

2

commented a paper 12 months ago

InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners

Paper • 2504.14239 • Published Apr 19, 2025 • 14 •

2

commented 3 papers about 1 year ago

Frac-Connections: Fractional Extension of Hyper-Connections

Paper • 2503.14125 • Published Mar 18, 2025 • 22 •

5

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

Paper • 2503.04598 • Published Mar 6, 2025 • 22 •

8

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

Paper • 2503.04598 • Published Mar 6, 2025 • 22 •

8

New activity in pengxiang/LNS_1B about 1 year ago

Create README.md

1

#2 opened about 1 year ago by

lmsdss

commented a paper about 1 year ago

The Curse of Depth in Large Language Models

Paper • 2502.05795 • Published Feb 9, 2025 • 40 •

5

commented 3 papers over 1 year ago

InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection

Paper • 2501.04575 • Published Jan 8, 2025 • 25 •

2

Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN

Paper • 2412.13795 • Published Dec 18, 2024 • 20 •

2

DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting

Paper • 2411.17223 • Published Nov 26, 2024 • 7 •

3

New activity in diffusers/controlnet-canny-sdxl-1.0 over 2 years ago

Dynamically adjust the guidance scale for ControlNet XL

#8 opened over 2 years ago by

pengxiang

New activity in fusing/fill50k over 2 years ago

How to load it from local?

9

#1 opened almost 3 years ago by

hrimsky