8 papers
CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring
Xuan Lu, Haohang Huang, Yingqi Fan +5
Large language model (LLM) rerankers have become an important component of modern retrieval and retrieval-augmented generation pipelines, but their high computational cost limits t…
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
Madhuri Shanbhogue, Zhe Li, Shanfeng Zhang +86
We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage t…
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
Rui Meng, Bhavana Dalvi Mishra, Jiefeng Chen +10
Autonomous research agents produce competitive solutions and professional-looking manuscripts, yet their outputs contain verifiability failures undetectable by surface-level evalua…
MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models
Haohang Huang, Xuan Lu, Mingyi Su +9
Multimodal embedding models aim to map heterogeneous inputs, such as text, images, videos, and audio, into a shared semantic space. However, existing methods and benchmarks remain…
Beyond Global Similarity: Towards Fine-Grained, Multi-Condition Multimodal Retrieval
Xuan Lu, Kangle Li, Haohang Huang +3
Recent advances in multimodal large language models (MLLMs) have substantially expanded the capabilities of multimodal retrieval, enabling systems to align and retrieve information…
Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval
Xuan Lu, Haohang Huang, Rui Meng +3
Large Language Models (LLMs) have recently demonstrated strong capabilities in tool use, yet progress in tool retrieval remains hindered by incomplete and heterogeneous tool docume…
Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Short
Xuan Lu, Haohang Huang, Rui Meng +3
Document reranking is a key component in information retrieval (IR), aimed at refining initial retrieval results to improve ranking quality for downstream tasks. Recent studies--mo…
Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models
Jianqun Zhou, Yuanlei Zheng, Wei Chen +5
Instruction-following capabilities in LLMs have progressed significantly, enabling more complex user interactions through detailed prompts. However, retrieval systems have not matc…