most citedDP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass

48 citations · 69 across the 3 of their papers we have counts for

collaborators

8 papers

cs.CL2024

MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

Xiang Yue, Tianyu Zheng, Yuansheng Ni +10

This paper introduces MMMU-Pro, a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark. MMMU-Pro rigorously assesses multimodal mo…

cs.CL2024

Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

Boshi Wang, Xiang Yue, Yu Su +1

We study whether transformers can learn to implicitly reason over parametric knowledge, a skill that even the most capable language models struggle with. Focusing on two representa…

cs.CV2024

Towards Artwork Explanation in Large-scale Vision Language Models

Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito +2

Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating capabilities in text generation and comprehension. However, it has not been clari…

cs.CL2024

AttributionBench: How Hard is Automatic Attribution Evaluation?

Yifei Li, Xiang Yue, Zeyi Liao +1

Modern generative search engines enhance the reliability of large language model (LLM) responses by providing cited evidence. However, evaluating the answer's attribution, i.e., wh…

cs.CL2023

MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI

Xiang Yue, Yuansheng Ni, Kai Zhang +19

We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU…

cs.CL2023

TableLlama: Towards Open Large Generalist Models for Tables

Tianshu Zhang, Xiang Yue, Yifei Li +1

Semi-structured tables are ubiquitous. There has been a variety of tasks that aim to automatically interpret, augment, and query tables. Current methods often require pretraining o…