From the 10 of 155 papers with an AI index.
53 citations
- Tsinghua UniversityCN46 papers
- University of Science and Technology of ChinaCN46 papers
- Peking UniversityCN45 papers
- University of BristolGB42 papers
- Carnegie Mellon UniversityUS41 papers
- Institute of Modern PhysicsCN41 papers
- South China Normal UniversityCN41 papers
- University of TarapacáCL41 papers
- University of TurinIT41 papers
- Beihang UniversityCN40 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT40 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di PerugiaIT40 papers
5 papers · 1 filter
ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
Xinkui Zhao, Enbo Chen, Yifan Zhang +4
Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However,…
UniMM: A Unified Mixture Model Framework for Multi-Agent Simulation
Longzhong Lin, Xuewu Lin, Kechun Xu +4
Simulation plays a crucial role in assessing autonomous driving systems, where the generation of realistic multi-agent behaviors is a key aspect. In multi-agent simulation, the pri…
A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation
Haoyang Zhong, Yifei Sun, Antong Zhang +3
Retrieval-Augmented Generation (RAG) has emerged as a paradigm for enhancing large language models (LLMs) with external knowledge, yet existing graph-based methods face a fundament…
A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications
Wenyi Xiao, Zechuan Wang, Leilei Gan +9
With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical. Direct Preference Optimization (DPO) has…
TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Planning Agents
Weiyi Chen, Shuaixiong Wang, Ziyun Gao +5
The development of Large Language Models (LLMs) has significantly improved travel planning applications, yet evaluating such models is limited by existing benchmarks' limitations:…