Haokun Lin's picture

Haokun Lin

Felix1023

·

https://felixmessi.github.io/

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

Trust Region On-Policy Distillation

upvoted a paper 25 days ago

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both

liked a dataset 25 days ago

erinxia/MedVersa

View all activity

Organizations

submitted a paper to Daily Papers 3 months ago

QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models

Paper • 2602.20309 • Published Feb 23 • 16

authored a paper 7 months ago

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation

Paper • 2508.03485 • Published Aug 5, 2025 • 2

authored a paper 10 months ago

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

Paper • 2508.14896 • Published Aug 20, 2025 • 23

authored 2 papers about 1 year ago

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric

Paper • 2403.07839 • Published Mar 12, 2024

TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation

Paper • 2505.05422 • Published May 8, 2025 • 9