Yunyang Xiong

Researcher@Meta·美国·OpenReview

研究方向

Vision-Language LLMs · Efficient Self-Attention · Transformer · ViT · DETR · neural architecture search · efficient machine learning · computer vision · deep learning · machine learning

7.3

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization

NeurIPS 2025Poster

7.2

Agent-as-a-Judge: Evaluate Agents with Agents

ICML 2025Poster

6.6

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

ICML 2025Poster

二作

5.8

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

ICLR 2025Rejected

二作

5.7

Agent-as-a-Judge: Evaluating Agents with Agents

ICLR 2025Rejected

6.0

MiniGPT-v2: Large Language Model as a Unified Interface for Vision-Language Multi-task Learning

ICLR 2024Rejected

4.5

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts

ICLR 2024Rejected

三作

合作者 (20)

Raghuraman Krishnamoorthi