Pengxiang Li

pengxiang's activity

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

authored 5 papers about 1 month ago

Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking

Paper • 2505.20199 • Published May 26 • 1

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

Paper • 2506.22049 • Published Jun 27 • 2

Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning

Paper • 2506.21285 • Published Jun 26

InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

Paper • 2508.05731 • Published Aug 7 • 25

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

Paper • 2509.20109 • Published Sep 24 • 3

authored a paper 2 months ago

Diffusion Language Models Know the Answer Before Decoding

Paper • 2508.19982 • Published Aug 27 • 23

authored a paper 6 months ago

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

Paper • 2504.14239 • Published Apr 19 • 13

authored a paper 9 months ago

The Curse of Depth in Large Language Models

Paper • 2502.05795 • Published Feb 9 • 40

authored 5 papers 10 months ago

TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models

Paper • 2312.00651 • Published Dec 1, 2023 • 1

Automated Evaluation of Large Vision-Language Models on Self-driving Corner Cases

Paper • 2404.10595 • Published Apr 16, 2024 • 1

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

Paper • 2411.17223 • Published Nov 26, 2024 • 7

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

Paper • 2501.04575 • Published Jan 8 • 25

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

Paper • 2412.13795 • Published Dec 18, 2024 • 20

authored a paper over 1 year ago

OwLore: Outlier-weighed Layerwise Sampled Low-Rank Projection for Memory-Efficient LLM Fine-tuning

Paper • 2405.18380 • Published May 28, 2024 • 1