11 papers
REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation
Yang Sun, Lichao Ma, Houyuan Qin +5
On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher. Reward-extrapolation methods such as ExOPD amplify the tea…
EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval
Hongwei Zhang, Xiaoman Wang, Zehui Ling +7
Retrieving evidence pages from visually rich long documents is a key challenge in document question answering. Existing page-level visual retrievers operate under an independent ma…
IA-RAG: Interval-Algebra-Driven Temporal Reasoning for Dynamic Knowledge Retrieval
Xiaoman Wang, Yaoze Zhang, Wenzhuo Fan +7
Retrieval-Augmented Generation (RAG) has shown strong effectiveness in grounding Large Language Models (LLMs) with external knowledge. However, existing RAG and Graph RAG framework…
Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders
Yizhou Wang, Song Mao, Yang Chen +8
Recent multimodal large language models (MLLMs) increasingly integrate multiple vision encoders to improve performance on various benchmarks, assuming that diverse pretraining obje…
Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning
Junming Liu, Siyuan Meng, Yanting Gao +7
Multimodal reasoning in Large Language Models (LLMs) struggles with incomplete knowledge and hallucination artifacts, challenges that textual Knowledge Graphs (KGs) only partially…
LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval
Yaoze Zhang, Rong Wu, Pinlong Cai +5
Retrieval-Augmented Generation (RAG) plays a crucial role in grounding Large Language Models by leveraging external knowledge, whereas the effectiveness is often compromised by the…