7 papers
CARA: Concept-Aware Risk Attention for Interpretable Collision Anticipation
Zhishan Tao, Ruoyu Wang, Yucheng Wu +6
Collision anticipation in autonomous driving requires not only accurate early warnings but also interpretable reasoning about what risk factors are being tracked and how risk evolv…
EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking
Enjun Du, Siyi Liu, Zirong Chen +8
Real-world image search queries are multimodal and compositional: ``find this shirt in pink'' specifies an entity to retain, an attribute to modify, and context to ignore. Yet exis…
LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger
Enjun Du, Hange Zhou, Chenxu Du +4
Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely r…
Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning
Enjun Du, Siyi Liu, Yongqi Zhang
Knowledge Graph (KG) reasoning, which aims to infer new facts from structured knowledge repositories, plays a vital role in Natural Language Processing (NLP) systems. Its effective…
GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments
Enjun Du, Xunkai Li, Tian Jin +3
The era of foundation models has revolutionized AI research, yet Graph Foundation Models (GFMs) remain constrained by the scarcity of large-scale graph corpora. Traditional graph d…
GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs
Enjun Du, Siyi Liu, Yongqi Zhang
Knowledge graph reasoning in the fully-inductive setting, where both entities and relations at test time are unseen during training, remains an open challenge. In this work, we int…
S2A: A Unified Framework for Parameter and Memory Efficient Transfer Learning
Tian Jin, Enjun Du, Changwei Wang +2
Parameter-efficient transfer learning (PETL) aims to reduce the scales of pretrained models for multiple downstream tasks. However, as the models keep scaling up, the memory footpr…