Zhongzhi Yu

Researcher@NVIDIA·美国·OpenReview

研究方向

Large Language Models · Foundation Models · Automatic Speech Recognition · Deep Learning · Dynamic Network · Network Quantization · Neural Architecture Search

5.0

ZoomVLM: A Tuning-Free Framework for Efficient Video Understanding via Adaptive Zooming in Vision-Language Models

ICLR 2025Rejected

一作

4.9

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models

ICML 2025Poster

4.3

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks

ICLR 2025Rejected

5.5

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment

NeurIPS 2024Poster

二作

4.0

S$^6$-DAMON: Unlocking Structured Sparsity in Self-Supervised Speech Models via Data-Model Co-Compression

合作者 (20)