Pengxiang Li

pengxiang's activity

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

upvoted a paper about 20 hours ago

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training

Paper • 2605.09608 • Published 4 days ago • 43

upvoted a paper 2 days ago

Model Merging Scaling Laws in Large Language Models

Paper • 2509.24244 • Published 3 days ago • 39

authored 3 papers 4 days ago

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

Paper • 2507.20879 • Published Jul 28, 2025

Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?

Paper • 2602.23225 • Published Feb 26

ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving

Paper • 2605.04647 • Published 8 days ago • 9

upvoted a paper 6 days ago

ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving

Paper • 2605.04647 • Published 8 days ago • 9

submitted a paper to Daily Papers 6 days ago

ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving

Paper • 2605.04647 • Published 8 days ago • 9

upvoted a paper 13 days ago

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

Paper • 2604.26752 • Published 15 days ago • 106

liked a dataset 16 days ago

YefanZhou98/DLM-Decoding-Analysis

Updated 16 days ago • 277 • 2

upvoted a paper about 1 month ago

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Paper • 2604.08995 • Published Apr 10 • 50

updated a dataset about 1 month ago

pengxiang/nap-parallel-packing-demo

Updated Apr 8 • 24 • 1

published a dataset about 1 month ago

pengxiang/nap-parallel-packing-demo

Updated Apr 8 • 24 • 1

upvoted a paper about 2 months ago

Voxtral TTS

Paper • 2603.25551 • Published Mar 26 • 61

liked 2 datasets 2 months ago

allenai/Dolci-Think-SFT-7B

Viewer • Updated Jan 5 • 2.27M • 3.79k • 15

allenai/Dolci-Think-RL-7B-Completions-SFT

Viewer • Updated Jan 5 • 636k • 207 • 8

upvoted a paper 3 months ago

SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs

Paper • 2602.06040 • Published Feb 5 • 10

commented a paper 3 months ago

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

Paper • 2601.19895 • Published Jan 27 • 27 •

4

upvoted a paper 4 months ago

Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning

Paper • 2601.14750 • Published Jan 21 • 18

upvoted 2 papers 5 months ago

Bolmo: Byteifying the Next Generation of Language Models

Paper • 2512.15586 • Published Dec 17, 2025 • 17

PretrainZero: Reinforcement Active Pretraining

Paper • 2512.03442 • Published Dec 3, 2025 • 50