Yuxuan Hu
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8PUSA V1.0: Surpassing Wan-I2V with $500 Training Cost by Vectorized Timestep Adaptation
arXiv 2025
QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition
arXiv 2025
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning
arXiv 2025
LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interaction
arXiv 2025
SAM Decoding: Speculative Decoding via Suffix Automaton
arXiv 2024
SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training
arXiv 2024
Streamlining Redundant Layers to Compress Large Language Models
arXiv 2024
LMDrive: Closed-Loop End-to-End Driving with Large Language Models
CVPR 2024 1
Affiliations
Frequent co-authors
10from 8 papers