Publications (245)
Phonon heat transport with squeezing-based symmetry breaking
Yan Cao, Cheng Yang, Xintong Gu +3
The controllability of phonon thermal transport is fundamental for numerous technologies, from cooling high-performance chips to managing heat in quantum computing. Despite extensi…
Incorporating Vision Bias into Click Models for Image-oriented Search Engine
Ningxin Xu, Cheng Yang, Yixin Zhu +2
Most typical click models assume that the probability of a document to be examined by users only depends on position, such as PBM and UBM. It works well in various kinds of search…
Scaling Large Language Model-based Multi-Agent Collaboration
Chen Qian, Zihao Xie, YiFei Wang +9
Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning. Ins…
KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
Jie Zhou, Shengding Hu, Xin Lv +6
A comprehensive knowledge graph (KG) contains an instance-level entity graph and an ontology-level concept graph. The two-view KG provides a testbed for models to "simulate" human'…
Small Lesions-aware Bidirectional Multimodal Multiscale Fusion Network for Lung Disease Classification
Jianxun Yu, Ruiquan Ge, Zhipeng Wang +6
The diagnosis of medical diseases faces challenges such as the misdiagnosis of small lesions. Deep learning, particularly multimodal approaches, has shown great potential in the fi…
Neural Diffusion Model for Microscopic Cascade Prediction
Cheng Yang, Maosong Sun, Haoran Liu +3
The prediction of information diffusion or cascade has attracted much attention over the last decade. Most cascade prediction works target on predicting cascade-level macroscopic p…
Ultra-high-density local structure of liquid water
Cheng Yang, Chuanbiao Zhang, Fangfu Ye +1
The local structure of liquid water plays a key role in determining the anomalous properties of water. We run all-atom simulations for three microscopic water models, and use multi…
A Neural Network Approach to Joint Modeling Social Networks and Mobile Trajectories
Cheng Yang, Maosong Sun, Wayne Xin Zhao +2
The accelerated growth of mobile trajectories in location-based services brings valuable data resources to understand users' moving behaviors. Apart from recording the trajectory d…
First-principles study of electronic structure, optical and phonon properties of α-ZrW2O8
Jinping Li, Songhe Meng, Cheng Yang +1
ZrW2O8 exhibits isotropic negative thermal expansions over its entire temperature range of stability, yet so far its physical properties and mechanism have not been fully addressed…
Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs
Xin Gao, Cheng Yang, Chufan Shi +1
Unified multimodal models (UMMs) have emerged as a promising paradigm for general-purpose multimodal intelligence. As they are deployed in real-world applications, effectively upda…
Graph Foundation Models for Recommendation: A Comprehensive Survey
Bin Wu, Yihang Wang, Yuanhao Zeng +7
Recommender systems (RS) serve as a fundamental tool for navigating the vast expanse of online information, with deep learning advancements playing an increasingly important role i…
MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
Xiaoyuan Yi, Ruoyu Li, Cheng Yang +2
As an essential step towards computer creativity, automatic poetry generation has gained increasing attention these years. Though recent neural models make prominent progress in so…
Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning
Jiaxuan Lu, Ziyu Kong, Yemin Wang +10
The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on…
Effective Rank Analysis and Optimization of Flexible Antenna-Enabled Wireless Systems: Movable Antennas or Pinching Antennas?
Cheng Yang, Dong Li
Flexible antenna technology has recently emerged as a key enabler for next-generation wireless communications, which can effectively exploit the spatial degrees of freedom (DoF). H…
SAS: Self-Augmentation Strategy for Language Model Pre-training
Yifei Xu, Jingqiao Zhang, Ru He +4
The core of self-supervised learning for pre-training language models includes pre-training task design as well as appropriate data augmentation. Most data augmentations in languag…
Graph Foundation Models: Concepts, Opportunities and Challenges
Jiawei Liu, Cheng Yang, Zhiyuan Lu +8
Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and seve…
Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization
Tianrui Jia, Haoyang Li, Cheng Yang +2
Graph neural networks (GNNs) have been demonstrated to perform well in graph representation learning, but always lacking in generalization capability when tackling out-of-distribut…
Filter-then-Generate: Large Language Models with Structure-Text Adapter for Knowledge Graph Completion
Ben Liu, Jihai Zhang, Fangquan Lin +2
Large Language Models (LLMs) present massive inherent knowledge and superior semantic comprehension capability, which have revolutionized various tasks in natural language processi…
LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules
Cheng Yang, Hui Jin, Xinlei Yu +7
Diagnosing lung cancer typically involves physicians identifying lung nodules in Computed tomography (CT) scans and generating diagnostic reports based on their morphological featu…
Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
Tianyu Zhao, Cheng Yang, Yibo Li +7
Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due…
An Efficient Virtual Data Generation Method for Reducing Communication in Federated Learning
Cheng Yang, Xue Yang, Dongxian Wu +1
Communication overhead is one of the major challenges in Federated Learning(FL). A few classical schemes assume the server can extract the auxiliary information about training data…
Markdowns in E-Commerce Fresh Retail: A Counterfactual Prediction and Multi-Period Optimization Approach
Junhao Hua, Ling Yan, Huan Xu +1
In this paper, by leveraging abundant observational transaction data, we propose a novel data-driven and interpretable pricing approach for markdowns, consisting of counterfactual…
Masked Language Models are Good Heterogeneous Graph Generalizers
Jinyu Yang, Cheng Yang, Shanyuan Cui +5
Heterogeneous graph neural networks (HGNNs) excel at capturing structural and semantic information in heterogeneous graphs (HGs), while struggling to generalize across domains and…
Optimizing Personalized Federated Learning through Adaptive Layer-Wise Learning
Weihang Chen, Cheng Yang, Jie Ren +2
Real-life deployment of federated Learning (FL) often faces non-IID data, which leads to poor accuracy and slow convergence. Personalized FL (pFL) tackles these issues by tailoring…
Endowing Pre-trained Graph Models with Provable Fairness
Zhongjian Zhang, Mengmei Zhang, Yue Yu +3
Pre-trained graph models (PGMs) aim to capture transferable inherent structural properties and apply them to different downstream tasks. Similar to pre-trained language models, PGM…
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Xinlei Yu, Zhangquan Chen, Yongbo He +36
Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an inc…
BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences
Ao Sun, Weilin Zhao, Xu Han +4
Effective attention modules have played a crucial role in the success of Transformer-based large language models (LLMs), but the quadratic time and memory complexities of these att…
Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation
Zheng Wu, Yibo Luo, Pu Zhang +2
The paper introduces ESPP, a three-stage evaluation framework that uses a panel of diverse, evidence‑grounded personas to rate generative UI screenshots, improving alignment with h…
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Weize Chen, Yusheng Su, Jingwei Zuo +13
Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements, enabling them to generalize across a broad spectrum of tasks. However, in real-…
Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning
Ju He, Adam Kortylewski, Shaokang Yang +4
Semi-Supervised Learning (SSL) has shown its strong ability in utilizing unlabeled data when labeled data is scarce. However, most SSL algorithms work under the assumption that the…
Giant negative thermal expansion covering room temperature in nanocrystalline GaNxMn3
Jianchao Lin, Peng Tong, Xiaojuan Zhou +11
Materials with negative thermal expansion (NTE), which contract upon heating, are of great interest both technically and fundamentally. Here, we report giant NTE covering room temp…
AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework
Xubin Luo, Cheng Yang
AI inference is becoming a persistent and geographically distributed source of electricity demand. Unlike many traditional electrical loads, inference workloads can sometimes be ex…
GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
Hongtai Zeng, Chao Yang, Yanzhen Zhou +2
Ensuring that the outputs of neural networks satisfy specific constraints is crucial for applying neural networks to real-life decision-making problems. In this paper, we consider…
ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
Cheng Yang, Chufan Shi, Yaxin Liu +11
We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-i…
Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrieval
Mingyan Wu, Zhenghao Liu, Xinze Li +7
Retrieval-Augmented Generation (RAG) has become a dominant paradigm for mitigating hallucinations in Large Language Models (LLMs) by incorporating external knowledge. However, exis…
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
Zhiqing Cui, Haotong Xie, Jiahao Yuan +11
Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so decom…
InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation
Jinqi Xiao, Qing Yan, Liming Jiang +8
Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when using monolithic adapters like LoRA.…
GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration
Xin Li, Qizhi Chu, Yubin Chen +7
Graphs are widely used for modeling relational data in real-world scenarios, such as social networks and urban computing. Existing LLM-based graph analysis approaches either integr…
HiSkill: Empowering LLM Agents with Hierarchical Skill Graphs
Yu Hao, Jinxuan Cai, Qi Zhang +4
Skills have become an important abstraction for enabling large language model (LLM) agents to reuse past experience in long-horizon interactive tasks. However, existing trajectory-…
Multi-Agent Collaboration via Cross-Team Orchestration
Zhuoyun Du, Chen Qian, Wei Liu +9
Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents. A representative scenario is in software develo…
FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization
Cheng Yang, Jixi Liu, Yunhe Yan +1
Despite the remarkable success of graph neural networks (GNNs) in modeling graph-structured data, like other machine learning models, GNNs are also susceptible to making biased pre…
Abnormal Event Detection via Hypergraph Contrastive Learning
Bo Yan, Cheng Yang, Chuan Shi +2
Abnormal event detection, which refers to mining unusual interactions among involved entities, plays an important role in many real applications. Previous works mostly over-simplif…
ParaTool: Shifting Tool Representations from Context to Parameters
Zekai Yu, Qi Meng, Qizhi Chu +3
Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby supporting environment-coupled problem solving. Howe…
Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
Xinrong Chen, Xu Chu, Yingmin Qiu +8
Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and…
LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis
Chengfu Liu, Dongyang Hou, Junwu Xiang +5
Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientif…
LLM2: Let Large Language Models Harness System 2 Reasoning
Cheng Yang, Chufan Shi, Siheng Li +3
Large language models (LLMs) have exhibited impressive capabilities across a myriad of tasks, yet they occasionally yield undesirable outputs. We posit that these limitations are r…
Improved "Position Squared" Readout of a Mechanical Resonator in an Optical Cavity Using Degenerate Optical Modes
Jack C. Sankey, Andrew M. Jayich, Benjamin M. Zwickl +2
Optomechanical devices in which a flexible SiN membrane is placed inside an optical cavity allow for very high finesse and mechanical quality factor in a single device. They also p…
Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection
Zhuoyang Wu, Xinze Li, Zhenghao Liu +7
Large Language Models (LLMs) have exhibited strong reasoning capabilities and achieved remarkable performance in mathematical problem-solving tasks. Recently, distilling reasoning…
Latent Action Reparameterization for Efficient Agent Inference
Wenhao Huang, Qingwen Zeng, Qiyue Chen +11
Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior wor…
A Pairwise DomMix Attentive Adversarial Network for Unsupervised Domain Adaptive Object Detection
Jie Shao, Jiacheng Wu, Wenzhong Shen +1
Unsupervised Domain Adaptive Object Detection (DAOD) could adapt a model trained on a source domain to an unlabeled target domain for object detection. Existing unsupervised DAOD m…
Unfolding Projection-free SDP Relaxation of Binary Graph Classifier via GDPA Linearization
Cheng Yang, Gene Cheung, Wai-tian Tan +1
Algorithm unfolding creates an interpretable and parsimonious neural network architecture by implementing each iteration of a model-based algorithm as a neural layer. However, unfo…
TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model
Cheng Yang, Yang Sui, Jinqi Xiao +8
Vision-Language Models (VLMs) demand substantial computational resources during inference, largely due to the extensive visual input tokens for representing visual information. Pre…
Critical-Set-Aided Simplified Blind SCL Recognition of Polar Codes
Changwei Tu, Cheng Yang, Xianzhao Feng +1
Blind recognition of polar codes from noisy observations is a key problem in non-cooperative signal processing. Although existing blind successive cancellation list (BSCL) recognit…
GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks
Mengmei Zhang, Mingwei Sun, Peng Wang +6
Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, e…
AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning
Jiayi Zhang, Yiran Peng, Fanqi Kong +12
Humans naturally adapt to diverse environments by learning underlying rules across worlds with different dynamics, observations, and reward structures. In contrast, existing agents…
Adaptive Graph Encoder for Attributed Graph Embedding
Ganqu Cui, Jie Zhou, Cheng Yang +1
Attributed graph embedding, which learns vector representations from graph topology and node features, is a challenging task for graph analysis. Recently, methods based on graph co…
3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model
Jin Zeng, Gene Cheung, Michael Ng +2
3D point cloud - a new signal representation of volumetric objects - is a discrete collection of triples marking exterior object surface locations in 3D space. Conventional imperfe…
Self-organized synchronization of phonon lasers
Jiteng Sheng, Xinrui Wei, Cheng Yang +1
Self-organized synchronization is a ubiquitous collective phenomenon, in which each unit adjusts their rhythms to achieve synchrony through mutual interactions. The optomechanical…
ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web
Zhiyuan Yao, Zishan Xu, Yifu Guo +6
With the rise of the Agent Web and Model Context Protocol (MCP), the agent ecosystem is evolving into an open collaborative network, exponentially increasing accessible tools. Howe…
Large Language Models Can Self-Improve in Long-context Reasoning
Siheng Li, Cheng Yang, Zesen Cheng +4
Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fi…
GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents
Lingxiao Diao, Xinyue Xu, Wanxuan Sun +2
Large language models (LLMs) have been widely deployed as autonomous agents capable of following user instructions and making decisions in real-world applications. Previous studies…
Averaging, symplectic reduction, and central extensions
Cheng Yang, Boris Khesin
We show that the averaged equation for a one-frequency fast-oscillating Hamiltonian system is the result of symplectic reduction of a certain natural system on the corresponding $S…
Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast
Chufan Shi, Cheng Yang, Xinyu Zhu +6
Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activat…
Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
Weize Chen, Ziming You, Ran Li +7
The rapid advancement of large language models (LLMs) has paved the way for the development of highly capable autonomous agents. However, existing multi-agent frameworks often stru…
Learning and Transferring IDs Representation in E-commerce
Kui Zhao, Yuechuan Li, Zhaoqian Shuai +1
Many machine intelligence techniques are developed in E-commerce and one of the most essential components is the representation of IDs, including user ID, item ID, product ID, stor…
GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis
Bo Yu, Cheng Yang, Dongyang Hou +6
The integration of Large Language Models (LLMs) into Geographic Information Systems (GIS) marks a paradigm shift toward autonomous spatial analysis. However, evaluating these LLM-b…
Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models
Yuanzhao Zhai, Tingkai Yang, Kele Xu +4
Agents significantly enhance the capabilities of standalone Large Language Models (LLMs) by perceiving environments, making decisions, and executing actions. However, LLM agents st…
Vortex motion of the Euler and Lake equations
Cheng Yang
We start by surveying the planar point vortex motion of the Euler equations in the whole plane, half-plane and quadrant. Then we go on to prove non-collision property of 2-vortex s…
GNNVerifier: Graph-based Verifier for LLM Task Planning
Yu Hao, Qiuyu Wang, Cheng Yang +3
Large language models (LLMs) facilitate the development of autonomous agents. As a core component of such agents, task planning aims to decompose complex natural language requests…
GUIM -- General User and Item Embedding with Mixture of Representation in E-commerce
Chao Yang, Ru He, Fangquan Lin +3
Our goal is to build general representation (embedding) for each user and each product item across Alibaba's businesses, including Taobao and Tmall which are among the world's bigg…
A basis of Casimirs in 3D magnetohydrodynamics
Boris Khesin, Daniel Peralta-Salas, Cheng Yang
We prove that any regular Casimir in 3D magnetohydrodynamics is a function of the magnetic helicity and cross-helicity. In other words, these two helicities are the only independen…
Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?
Zhongjian Zhang, Xiao Wang, Huichi Zhou +4
Graph neural networks (GNNs) are vulnerable to adversarial attacks, especially for topology perturbations, and many methods that improve the robustness of GNNs have received consid…
TransFG: A Transformer Architecture for Fine-grained Recognition
Ju He, Jie-Neng Chen, Shuai Liu +4
Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most…
Optical Context Compression Is Just (Bad) Autoencoding
Ivan Yee Lee, Cheng Yang, Taylor Berg-Kirkpatrick
DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual con…
Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agents
Zeyuan Wang, Dongyang Hou, Cheng Yang +10
Large language model (LLM)-based agents provide a novel paradigm for the automated processing of remote sensing(RS) data. Their success in complex RS tasks rely on extensive specia…
Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty
Xu Wan, Chao Yang, Cheng Yang +2
Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty…
Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication
Weize Chen, Chenfei Yuan, Jiarui Yuan +6
Natural language (NL) has long been the predominant format for human cognition and communication, and by extension, has been similarly pivotal in the development and application of…
Coarse-to-Fine Long-term Interest Modeling for Generative Recommendation
Shiteng Cao, Junda She, Ji Liu +9
Leveraging long-term user behavioral patterns is a key trajectory for enhancing the accuracy of modern recommender systems. While generative recommender systems have emerged as a t…
Does Correction Remain A Problem For Large Language Models?
Xiaowu Zhang, Xiaotian Zhang, Cheng Yang +2
As large language models, such as GPT, continue to advance the capabilities of natural language processing (NLP), the question arises: does the problem of correction still persist?…
MoE-I: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition
Cheng Yang, Yang Sui, Jinqi Xiao +7
The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by…
Pulsar and Magnetar Navigation with Fermi/GBM and GECAM
Xi-Hong Luo, Shuo Xiao, Shi-Jie Zheng +29
The determination of the absolute and relative position of a spacecraft is critical for its operation, observations, data analysis, scientific studies, as well as deep space explor…
On the Ergodic theory of the Generalized incompressible flow
Cheng Yang, Xiaoping Yuan
To study the variation problem related to the incompressible fluid mechanics, Brenier brings the concept of generalized flow and shows that the generalized incompressible flow (GIF…
Real-World Denoising via Diffusion Model
Cheng Yang, Lijing Liang, Zhixun Su
Real-world image denoising is an extremely important image processing problem, which aims to recover clean images from noisy images captured in natural environments. In recent year…
Federated Graph Condensation with Information Bottleneck Principles
Bo Yan, Sihao He, Cheng Yang +3
Graph condensation (GC), which reduces the size of a large-scale graph by synthesizing a small-scale condensed graph as its substitution, has benefited various graph learning tasks…
From Reasoning to Pixels: Benchmarking the Alignment Gap in Unified Multimodal Models
Cheng Yang, Chufan Shi, Bo Shui +7
Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent their representations…
Brain-HGCN: A Hyperbolic Graph Convolutional Network for Brain Functional Network Analysis
Junhao Jia, Yunyou Liu, Cheng Yang +4
Functional magnetic resonance imaging (fMRI) reveals complex brain functional networks with hierarchical topologies crucial for cognitive processing. Standard Euclidean Graph Neura…
ControlMambaIR: Conditional Controls with State-Space Model for Image Restoration
Cheng Yang, Lijing Liang, Zhixun Su
This paper proposes ControlMambaIR, a novel image restoration method designed to address perceptual challenges in image deraining, deblurring, and denoising tasks. By integrating t…
An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation
Cheng Yang, Guoping Huang, Mo Yu +6
Word-level AutoCompletion(WLAC) is a rewarding yet challenging task in Computer-aided Translation. Existing work addresses this task through a classification model based on a neura…
Information Diffusion Prediction with Latent Factor Disentanglement
Haoran Wang, Cheng Yang
Information diffusion prediction is a fundamental task which forecasts how an information item will spread among users. In recent years, deep learning based methods, especially tho…
Tool Learning with Foundation Models
Yujia Qin, Shengding Hu, Yankai Lin +38
Humans possess an extraordinary ability to create and utilize tools, allowing them to overcome physical limitations and explore new frontiers. With the advent of foundation models,…
Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts
Riyang Bao, Cheng Yang, Dazhou Yu +3
Geospatial reasoning is essential for real-world applications such as urban analytics, transportation planning, and disaster response. However, existing LLM-based agents often fail…
xTrimoABFold: De novo Antibody Structure Prediction without MSA
Yining Wang, Xumeng Gong, Shaochuan Li +7
In the field of antibody engineering, an essential task is to design a novel antibody whose paratopes bind to a specific antigen with correct epitopes. Understanding antibody struc…
Blend the Separated: Mixture of Synergistic Experts for Data-Scarcity Drug-Target Interaction Prediction
Xinlong Zhai, Chunchen Wang, Ruijia Wang +7
Drug-target interaction prediction (DTI) is essential in various applications including drug discovery and clinical application. There are two perspectives of input data widely use…
Few-shot Knowledge Transfer for Fine-grained Cartoon Face Generation
Nan Zhuang, Cheng Yang
In this paper, we are interested in generating fine-grained cartoon faces for various groups. We assume that one of these groups consists of sufficient training data while the othe…
IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?
Yang Chen, Minghao Liu, Yufan Shen +18
The webpage-to-code task requires models to understand visual representations of webpages and generate corresponding code. However, existing benchmarks primarily focus on static sc…
Dynamic Point-Formation in Dielectric Fluids
Cheng Yang
We use boundary-integral methods to compute the time-dependent deformation of a drop of dielectric fluid immersed in another dielectric fluid in a uniform electric field E. Steady…
PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths
Boyu Chen, Zirui Guo, Zidan Yang +5
Retrieval-augmented generation (RAG) improves the response quality of large language models (LLMs) by retrieving knowledge from external databases. Typical RAG approaches split the…
Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling
Xinlei Yu, Chengming Xu, Zhangquan Chen +6
The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles w…
Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development
Rennai Qiu, Chen Qian, Ran Li +9
Recent advancements in Large Language Models (LLMs) and autonomous agents have demonstrated remarkable capabilities across various domains. However, standalone agents frequently en…
Realization of a coupled-mode heat engine with cavity-mediated nanoresonators
Jiteng Sheng, Cheng Yang, Haibin Wu
We report an experimental demonstration of a coupled-mode heat engine in a two-membrane-in-the-middle cavity optomechanical system. The normal mode of the cavity-mediated strongly…