11 papers
A Multi-Task Embedder For Retrieval Augmented LLMs
Peitian Zhang, Shitao Xiao, Zheng Liu +2
LLMs confront inherent limitations in terms of its knowledge, memory, and action. The retrieval augmentation stands as a vital mechanism to address these limitations, which brings…
M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
Jianlv Chen, Shitao Xiao, Peitian Zhang +3
In this paper, we introduce a new embedding model called M3-Embedding, which is distinguished for its versatility in \textit{Multi-Linguality}, \textit{Multi-Functionality}, and \t…
Task-Aware KV Compression For Cost-Effective Long Video Understanding
Minghao Qin, Yan Shu, Peitian Zhang +6
Long-video understanding (LVU) remains a severe challenge for existing multimodal large language models (MLLMs), primarily due to the prohibitive computational cost. Recent approac…
Boosting Long-Context Management via Query-Guided Activation Refilling
Hongjin Qian, Zheng Liu, Peitian Zhang +2
Processing long contexts poses a significant challenge for large language models (LLMs) due to their inherent context-window limitations and the computational burden of extensive k…
MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
Hongjin Qian, Zheng Liu, Peitian Zhang +4
Processing long contexts presents a significant challenge for large language models (LLMs). While recent advancements allow LLMs to handle much longer contexts than before (e.g., 3…
From Matching to Generation: A Survey on Generative Information Retrieval
Xiaoxi Li, Jiajie Jin, Yujia Zhou +4
Information Retrieval (IR) systems are crucial tools for users to access information, which have long been dominated by traditional methods relying on similarity matching. With the…