Pengxiang Li

Diffusion Language Model Knows the Answer Before It Decodes

Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes

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

DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking

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

Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback

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

Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking

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

The Curse of Depth in Large Language Models

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

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

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