3 citations · 10 across the 14 of their papers we have counts for
14 papers
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Dong Chen, Fangyun Wei, Ziyu Wan +18
We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters acro…
MMViR: A Multi-Modal and Multi-Granularity Representation for Long-range Video Understanding
Zizhong Li, Haopeng Zhang, Jiawei Zhang
Long videos, ranging from minutes to hours, present significant challenges for current Multi-modal Large Language Models (MLLMs) due to their complex events, diverse scenes, and lo…
Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation
Zizhong Li, Haopeng Zhang, Jiawei Zhang
While large language models (LLMs) have achieved remarkable success in providing trustworthy responses for knowledge-intensive tasks, they still face critical limitations such as h…
Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval
Zizhong Li, Haopeng Zhang, Jiawei Zhang
Recent research has explored distilling knowledge from large language models (LLMs) to optimize retriever models, especially within the retrieval-augmented generation (RAG) framewo…
GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs
Xiao Liu, Jiawei Zhang
This study introduces GPTA, a Large Language Model assistance training framework, that enhances the training of downstream task models via prefix prompt. By minimizing data exposur…
Unveiling the Magic: Investigating Attention Distillation in Retrieval-augmented Generation
Zizhong Li, Haopeng Zhang, Jiawei Zhang
Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in…
A Revisit of Fake News Dataset with Augmented Fact-checking by ChatGPT
Zizhong Li, Haopeng Zhang, Jiawei Zhang
The proliferation of fake news has emerged as a critical issue in recent years, requiring significant efforts to detect it. However, the existing fake news detection datasets are s…
Beyond Text: Unveiling Multimodal Proficiency of Large Language Models with MultiAPI Benchmark
Xiao Liu, Jianfeng Lin, Jiawei Zhang
The proliferation of Large Language Models like ChatGPT has significantly advanced language understanding and generation, impacting a broad spectrum of applications. However, these…
Generic Attention-model Explainability by Weighted Relevance Accumulation
Yiming Huang, Aozhe Jia, Xiaodan Zhang +1
Attention-based transformer models have achieved remarkable progress in multi-modal tasks, such as visual question answering. The explainability of attention-based methods has rece…
Contrastive Hierarchical Discourse Graph for Scientific Document Summarization
Haopeng Zhang, Xiao Liu, Jiawei Zhang
The extended structural context has made scientific paper summarization a challenging task. This paper proposes CHANGES, a contrastive hierarchical graph neural network for extract…
DiffuSum: Generation Enhanced Extractive Summarization with Diffusion
Haopeng Zhang, Xiao Liu, Jiawei Zhang
Extractive summarization aims to form a summary by directly extracting sentences from the source document. Existing works mostly formulate it as a sequence labeling problem by maki…
SummIt: Iterative Text Summarization via ChatGPT
Haopeng Zhang, Xiao Liu, Jiawei Zhang
Text summarization systems have made significant progress in recent years, but typically generate summaries in one single step. However, the one-shot summarization setting is somet…
Extractive Summarization via ChatGPT for Faithful Summary Generation
Haopeng Zhang, Xiao Liu, Jiawei Zhang
Extractive summarization is a crucial task in natural language processing that aims to condense long documents into shorter versions by directly extracting sentences. The recent in…
HEGEL: Hypergraph Transformer for Long Document Summarization
Haopeng Zhang, Xiao Liu, Jiawei Zhang
Extractive summarization for long documents is challenging due to the extended structured input context. The long-distance sentence dependency hinders cross-sentence relations mode…