Publications (14)
Unified Language Representation for Question Answering over Text, Tables, and Images
Bowen Yu, Cheng Fu, Haiyang Yu +2
When trying to answer complex questions, people often rely on multiple sources of information, such as visual, textual, and tabular data. Previous approaches to this problem have f…
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
Minzheng Wang, Longze Chen, Cheng Fu +11
Long-context modeling capabilities have garnered widespread attention, leading to the emergence of Large Language Models (LLMs) with ultra-context windows. Meanwhile, benchmarks fo…
Bridging the Gap between Reality and Ideality of Entity Matching: A Revisiting and Benchmark Re-Construction
Tianshu Wang, Hongyu Lin, Cheng Fu +6
Entity matching (EM) is the most critical step for entity resolution (ER). While current deep learningbased methods achieve very impressive performance on standard EM benchmarks, t…
Hidden in-plane long-range order in an amorphized crystal
Yin Chen, Anthony E. Phillips, Cheng Fu +12
Solid materials are commonly classified as crystalline or amorphous based on the presence or absence of long-range order.Metal-organic frameworks (MOFs), like other solids,also dis…
Metropolitan Segment Traffic Speeds from Massive Floating Car Data in 10 Cities
Moritz Neun, Christian Eichenberger, Yanan Xin +7
Traffic analysis is crucial for urban operations and planning, while the availability of dense urban traffic data beyond loop detectors is still scarce. We present a large-scale fl…
SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
Huashan Sun, Shengyi Liao, Yansen Han +8
Despite advances in pretraining with extended context sizes, large language models (LLMs) still face challenges in effectively utilizing real-world long-context information, primar…
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
Xinghua Zhang, Haiyang Yu, Cheng Fu +2
In the realm of large language models (LLMs), the ability of models to accurately follow instructions is paramount as more agents and applications leverage LLMs for construction, w…
Towards Fast and Energy-Efficient Binarized Neural Network Inference on FPGA
Cheng Fu, Shilin Zhu, Hao Su +2
Binarized Neural Network (BNN) removes bitwidth redundancy in classical CNN by using a single bit (-1/+1) for network parameters and intermediate representations, which has greatly…
Beyond Quantity: Trajectory Diversity Scaling for Code Agents
Guhong Chen, Chenghao Sun, Cheng Fu +16
As code large language models (LLMs) evolve into tool-interactive agents via the Model Context Protocol (MCP), their generalization is increasingly limited by low-quality synthetic…
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
Qiaoyu Tang, Jiawei Chen, Zhuoqun Li +10
The rise of large language models (LLMs) has significantly transformed both the construction and application of information retrieval (IR) systems. However, current interactions be…
Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs
Yeqin Zhang, Haomin Fu, Cheng Fu +3
Multi-document grounded dialogue systems (DGDS) belong to a class of conversational agents that answer users' requests by finding supporting knowledge from a collection of document…
Towards Measuring Place Function Similarity at Fine Spatial Granularity with Trajectory Embedding
Cheng Fu, Robert Weibel
Modeling place functions from a computational perspective is a prevalent research topic. Trajectory embedding, as a neural-network-backed dimension reduction technology, allows the…
Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration
Zhenyu Zhang, Bowen Yu, Haiyang Yu +6
Building document-grounded dialogue systems have received growing interest as documents convey a wealth of human knowledge and commonly exist in enterprises. Wherein, how to compre…
A Neural-based Program Decompiler
Cheng Fu, Huili Chen, Haolan Liu +4
Reverse engineering of binary executables is a critical problem in the computer security domain. On the one hand, malicious parties may recover interpretable source codes from the…