6 citations · 8 across the 27 of their papers we have counts for
32 papers
Geospatial Vector Geometry as a Native Spatial Modality for Vision-Language Models
Huang Fei, Boyi Chen, Hao Xue +3
Geospatial reasoning links VLMs to real-world action and decision making. Reliable reasoning requires accurate spatial information and effective spatial representations. However, c…
You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue
Junle Chen, Wei Chen, Zhengjun Huang +5
When a large language model handles a multi-turn task and a user proposes a change but ultimately rejects it, the model should continue as if nothing changed. We find a surprising…
Flash-OPD: Fast On-Policy Distillation
Wei Chen, Junle Chen, Yitong Yang +6
On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but generating and evaluating long rollouts incurs substantial training cost. Exi…
Beyond Retrieval: Analytic Memory for Multimodal Agents
Zhoujin Tian, Hao Zhang, Yao Tian +4
Long-term multimodal memory must support not only retrieving relevant information but also computing over observations accumulated across interactions. Existing systems largely emp…
Unified Dominance Graph for Interval-Predicate Approximate Nearest Neighbor Search
Kwun Hang Lau, Ruiyuan Zhang, Elton Chun-Chai Li +3
Approximate Nearest Neighbor Search (ANNS) is a core primitive for unstructured data retrieval. Real-world applications--such as temporal databases, financial data analysis, and re…
From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction
Shuhao Li, Weidong Yang, Yue Cui +4
Efficient acquisition, storage, and utilization of traffic data are critical challenges in spatio-temporal data management. Most traffic data systems collect and store observations…
MExam: Benchmarking Multimodal Memory for Realistic User-Agent Interactions
Zhengjun Huang, Wenxuan Liu, Zhoujin Tian +6
Language agents are increasingly deployed over accumulating multimodal information, yet existing benchmarks assume a human-human form with sparse visuals and straightforward conten…
SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs
Jiawei Li, Ziyi Liu, Weijie Shi +3
3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together with dialog, QA, and captioning…
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
Weijie Shi, Qiang Xu, Fan Deng +9
Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters fall into two camps with oppo…
VisualNeo: Bridging the Gap between Visual Query Interfaces and Graph Query Engines
Kai Huang, Houdong Liang, Chongchong Yao +5
Visual Graph Query Interfaces (VQIs) empower non-programmers to query graph data by constructing visual queries intuitively. Devising efficient technologies in Graph Query Engines…
Cardinality Estimation for High Dimensional Similarity Queries with Adaptive Bucket Probing
Zhonghan Chen, Qintian Guo, Ruiyuan Zhang +1
In this work, we address the problem of cardinality estimation for similarity search in high-dimensional spaces. Our goal is to design a framework that is lightweight, easy to cons…
Adaptive Stopping for Multi-Turn LLM Reasoning
Xiaofan Zhou, Huy Nguyen, Bo Yu +2
Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer diff…
GEM: A Native Graph-based Index for Multi-Vector Retrieval
Yao Tian, Zhoujin Tian, Xi Zhao +2
In multi-vector retrieval, both queries and data are represented as sets of high-dimensional vectors, enabling finer-grained semantic matching and improving retrieval quality over…
Locatability-Guided Adaptive Reasoning for Image Geo-Localization with Vision-Language Models
Bo Yu, Fengze Yang, Yiming Liu +6
The emergence of Vision-Language Models (VLMs) has introduced new paradigms for global image geo-localization through retrieval-augmented generation (RAG) and reasoning-driven infe…
Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation
Kwun Hang Lau, Fangyuan Zhang, Boyu Ruan +4
Recent advances in Retrieval-Augmented Generation (RAG) have shifted from simple vector similarity to structure-aware approaches like HippoRAG, which leverage Knowledge Graphs (KGs…
Toward Temporal Attribution Analytics in Dataflows
Chrysanthi Kosyfaki, Ruiyuan Zhang, Nikos Mamoulis +1
Data provenance (the process of determining the origin and derivation of data outputs) has applications across multiple domains including explaining database query results and audi…
RL: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification
Weijie Shi, Yanxi Chen, Zexi Li +5
Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers…
LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning
Zhengjun Huang, Zhoujin Tian, Qintian Guo +5
Large Language Model (LLM) agents exhibit remarkable conversational and reasoning capabilities but remain constrained by limited context windows and the lack of persistent memory.…
Data-Aware Socratic Query Refinement in Database Systems
Ruiyuan Zhang, Chrysanthi Kosyfaki, Xiaofang Zhou
In this paper, we propose Data-Aware Socratic Guidance (DASG), a dialogue-based query enhancement framework that embeds \linebreak interactive clarification as a first-class operat…
Reading Between the Timelines: RAG for Answering Diachronic Questions
Kwun Hang Lau, Ruiyuan Zhang, Weijie Shi +2
While Retrieval-Augmented Generation (RAG) excels at injecting static, factual knowledge into Large Language Models (LLMs), it exhibits a critical deficit in handling longitudinal…
EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora
Fangyuan Zhang, Zhengjun Huang, Yingli Zhou +6
Graph-based Retrieval-Augmented Generation (Graph-RAG) enhances large language models (LLMs) by structuring retrieval over an external corpus. However, existing approaches typicall…
Semantic-guided Diverse Decoding for Large Language Model
Weijie Shi, Yue Cui, Yaguang Wu +7
Diverse decoding of large language models is crucial for applications requiring multiple semantically distinct responses, yet existing methods primarily achieve lexical rather than…
Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists
Yue Cui, Liuyi Yao, Shuchang Tao +4
Large language models (LLMs) have significantly advanced natural language processing, particularly through the integration of external tools and APIs. However, their effectiveness…
Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection
Yue Cui, Liuyi Yao, Zitao Li +3
Multi-agent systems based on large language models (LLMs) advance automatic task completion in various fields, where debate is a common cooperation form for agents to solve complic…