2 citations · 5 across the 15 of their papers we have counts for
9 papers · 1 filter
See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning
Shuoshuo Zhang, Yizhen Zhang, Jingjing Fu +4
Large vision-language models (VLMs) often benefit from intermediate visual cues, either injected via external tools or generated as latent visual tokens during reasoning, but these…
Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
Sijia Li, Yuchen Huang, Zifan Liu +6
As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing appro…
Rethinking Reward Models for Multi-Domain Test-Time Scaling
Dong Bok Lee, Seanie Lee, Sangwoo Park +12
The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning…
PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured Images
Shuoshuo Zhang, Zijian Li, Yizhen Zhang +6
Structured images (e.g., charts and geometric diagrams) remain challenging for multimodal large language models (MLLMs), as perceptual slips can cascade into erroneous conclusions.…
In-Context Compositional Q-Learning for Offline Reinforcement Learning
Qiushui Xu, Yuhao Huang, Yushu Jiang +4
Accurate estimation of the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a shared global Q-function, which is inad…
Learning to Select In-Context Demonstration Preferred by Large Language Model
Zheng Zhang, Shaocheng Lan, Lei Song +3
In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks during inference using only a few demonstrations. However, ICL performance is highly dependent…
OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval
Wei Yang, Jingjing Fu, Rui Wang +3
Vision-language retrieval-augmented generation (RAG) has become an effective approach for tackling Knowledge-Based Visual Question Answering (KB-VQA), which requires external knowl…
Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data
Zijian Li, Jingjing Fu, Lei Song +3
Visual reasoning is crucial for multimodal large language models (MLLMs) to address complex chart queries, yet high-quality rationale data remains scarce. Existing methods leverage…
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
Jinyu Wang, Jingjing Fu, Rui Wang +2
Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often str…