0

Yehui Tang

Papers
18

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
18papers

Authored papers

18

MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling

arXiv 2026

2026

DualTHOR: A Dual-Arm Humanoid Simulation Platform for Contingency-Aware Planning

arXiv 2025

2025

Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts

arXiv 2025

2025

Rethinking Video Tokenization: A Conditioned Diffusion-based Approach

arXiv 2025

2025

EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization

arXiv 2025

2025

SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution

arXiv 2024

2024

No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding

arXiv 2024

2024

SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization

arXiv 2024

2024

Rethinking Optimization and Architecture for Tiny Language Models

arXiv 2024

2024

Data-efficient Large Vision Models through Sequential Autoregression

arXiv 2024

2024

Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs

arXiv 2024

2024

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

arXiv 2024

2024

Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning

arXiv 2024

2024

EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models

arXiv 2024

2024

Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning

arXiv 2024

2024

GPT4Image: Can Large Pre-trained Models Help Vision Models on Perception Tasks?

arXiv 2023

2023

TinySAM: Pushing the Envelope for Efficient Segment Anything Model

arXiv 2023

2023

Augmented Shortcuts for Vision Transformers

NeurIPS 2021 12

2021

Affiliations

No known affiliations.

Frequent co-authors

10

from 18 papers