From the 1 of 7 linked papers with an AI index.
7 papers
LMEB: Long-horizon Memory Embedding Benchmark
Xinping Zhao, Xinshuo Hu, Jiaxin Xu +9
The paper presents LMEB, a benchmark suite of 22 datasets and 193 zero-shot retrieval tasks designed to evaluate how well text embedding models handle long-horizon, context‑depende…
Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
Xinping Zhao, Shouzheng Huang, Yan Zhong +4
Retrieval-Augmented Generation (RAG) effectively improves the accuracy of Large Language Models (LLMs). However, retrieval noises significantly undermine the quality of LLMs' gener…
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
Yuanxin Liu, Kun Ouyang, Haoning Wu +7
Recent studies have shown that long chain-of-thought (CoT) reasoning can significantly enhance the performance of large language models (LLMs) on complex tasks. However, this benef…
Fine-Grained Instruction-Guided Graph Reasoning for Vision-and-Language Navigation
Yaohua Liu, Xinyuan Song, Yunfu Deng +3
Vision-and-Language Navigation (VLN) requires an embodied agent to traverse complex environments by following natural language instructions, demanding accurate alignment between vi…
FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
Xinping Zhao, Yan Zhong, Zetian Sun +5
Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful…
RaSeRec: Retrieval-Augmented Sequential Recommendation
Xinping Zhao, Baotian Hu, Yan Zhong +5
Although prevailing supervised and self-supervised learning augmented sequential recommendation (SeRec) models have achieved improved performance with powerful neural network archi…