Pengxiang Li

pengxiang's activity

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

upvoted a paper 4 days ago

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

Paper • 2504.14239 • Published 7 days ago • 12

upvoted a paper 17 days ago

Rethinking Reflection in Pre-Training

Paper • 2504.04022 • Published 21 days ago • 77

upvoted 2 papers 18 days ago

Multi-Token Attention

Paper • 2504.00927 • Published 25 days ago • 46

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 19 days ago • 98

upvoted a paper 19 days ago

Understanding R1-Zero-Like Training: A Critical Perspective

Paper • 2503.20783 • Published about 1 month ago • 45

upvoted 2 papers about 1 month ago

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Paper • 2503.09573 • Published Mar 12 • 71

Frac-Connections: Fractional Extension of Hyper-Connections

Paper • 2503.14125 • Published Mar 18 • 21

upvoted 2 papers about 2 months ago

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

Paper • 2503.04598 • Published Mar 6 • 20

Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Paper • 2503.01307 • Published Mar 3 • 38

upvoted 2 papers 2 months ago

Large Language Diffusion Models

Paper • 2502.09992 • Published Feb 14 • 113

The Curse of Depth in Large Language Models

Paper • 2502.05795 • Published Feb 9 • 39

upvoted 3 papers 3 months ago

UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Paper • 2501.12326 • Published Jan 21 • 57

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Paper • 2501.09732 • Published Jan 16 • 72

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training

Paper • 2501.06842 • Published Jan 12 • 16

upvoted 6 papers 4 months ago

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Paper • 2501.04519 • Published Jan 8 • 277

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

Paper • 2501.04575 • Published Jan 8 • 24

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though

Paper • 2501.04682 • Published Jan 8 • 98

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Paper • 2412.19723 • Published Dec 27, 2024 • 89

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

Paper • 2412.13795 • Published Dec 18, 2024 • 20

Training Large Language Models to Reason in a Continuous Latent Space

Paper • 2412.06769 • Published Dec 9, 2024 • 84