papers

Publications (29)

cs.MA2026

MetaForge: A Self-Evolving Multimodal Agent that Retrieves, Adapts, and Forges Tools On Demand

Shouang Wei, Houcheng Min, Xinpeng Dong +8

Multimodal agents have achieved notable progress on complex reasoning tasks through tool use, yet remain limited by two issues: statically predefined tool inventories fail to gener…

cs.LG2024

Balancing Similarity and Complementarity for Federated Learning

Kunda Yan, Sen Cui, Abudukelimu Wuerkaixi +5

In mobile and IoT systems, Federated Learning (FL) is increasingly important for effectively using data while maintaining user privacy. One key challenge in FL is managing statisti…

cs.CL2025

Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought

Zhikang Chen, Sen Cui, Deheng Ye +3

Large Language Models (LLMs) have demonstrated strong reasoning capabilities through \emph{Chain-of-Thought} (CoT) prompting, which enables step-by-step intermediate reasoning. How…

cs.LG2025

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment

Zhikang Chen, Sen Cui, Deheng Ye +5

Model merging has emerged as a practical paradigm for integrating multiple independently trained models into a single model without joint retraining. Previous studies have demonstr…

cs.LG2021

Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility

Sen Cui, Weishen Pan, Changshui Zhang +1

Bipartite ranking, which aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data, is widely adopted in various applications whe…

cs.CL2026

Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs

Xinyu Pang, Zhanke Zhou, Xuan Li +5

Symbolic regression (SR) discovers compact mathematical expressions from data, yet recent LLM-based evolutionary methods remain sample-inefficient because they rely mainly on scala…

cs.IR2021

Correcting the User Feedback-Loop Bias for Recommendation Systems

Weishen Pan, Sen Cui, Hongyi Wen +3

Selection bias is prevalent in the data for training and evaluating recommendation systems with explicit feedback. For example, users tend to rate items they like. However, when ra…

cs.CV2026

ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing

Yueyi Liu, Chi Zhang, Sen Cui +1

Test-Time Tuning (TTT) on pretrained diffusion models has emerged as a powerful paradigm for video editing. However, there exists a foundational mismatch between the distribution-m…

cs.LG2021

Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition

Weishen Pan, Sen Cui, Jiang Bian +2

Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the devel…

cs.CV2026

CoDoL: Conditional Domain Prompt Learning for Out-of-Distribution Generalization

Min Zhang, Yuyin Wang, Zhongxiang Dai +4

Recent advances in pre-training vision-language models (VLMs), e.g., contrastive language-image pre-training (CLIP) methods, have shown great potential in learning out-of-distribut…

cs.AI2026

Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling

Sen Cui, Jingheng Ma

World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning. However, current world…

cs.LG2021

Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning

Sen Cui, Weishen Pan, Jian Liang +2

Federated learning (FL) has gain growing interests for its capability of learning from distributed data sources collectively without the need of accessing the raw data samples acro…

physics.optics2016

Disentangling the role of laser coupling in directional breaking of molecules

Qiying Song, Zhichao Li, Sen Cui +12

The directional control of molecular dissociation with the laser electric field waveform is a paradigm and was demonstrated for a variety of molecules. In most cases, the direction…

cs.CL2026

Reversible Diffusion Decoding for Diffusion Language Models

Xinyun Wang, Min Zhang, Sen Cui +4

Diffusion language models enable parallel token generation through block-wise decoding, but their irreversible commitments can lead to stagnation, where the reverse diffusion proce…

cs.LG2022

Collaboration Equilibrium in Federated Learning

Sen Cui, Jian Liang, Weishen Pan +3

Federated learning (FL) refers to the paradigm of learning models over a collaborative research network involving multiple clients without sacrificing privacy. Recently, there have…

cs.LG2025

Accurate Forgetting for Heterogeneous Federated Continual Learning

Abudukelimu Wuerkaixi, Sen Cui, Jingfeng Zhang +6

Recent years have witnessed a burgeoning interest in federated learning (FL). However, the contexts in which clients engage in sequential learning remain under-explored. Bridging F…

cs.RO2026

Affordance-Graphed Task Worlds: Self-Evolving Task Generation for Scalable Embodied Learning

Xiang Liu, Sen Cui, Guocai Yao +4

Training robotic policies directly in the real world is expensive and unscalable. Although generative simulation enables large-scale data synthesis, current approaches often fail t…

cs.AI2026

verdi: retrieval is not transfer for continual world model optimization

Junyu Wu, Shiqin Nie, Youyi Kou +9

Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence. However, optimizing a pretrained world model toward a user-specified objec…

cs.CR2024

Beyond Similarity: Personalized Federated Recommendation with Composite Aggregation

Honglei Zhang, Haoxuan Li, Jundong Chen +6

Federated recommendation aims to collect global knowledge by aggregating local models from massive devices, to provide recommendations while ensuring privacy. Current methods mainl…

cs.CV2026

Orca: The World is in Your Mind

Yihao Wang, Yuheng Ji, Mingyu Cao +54

We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multi…

cs.LG2025

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport

Zecheng Pan, Zhikang Chen, Ding Li +9

Merging models fine-tuned for different tasks into a single unified model has become an increasingly important direction for building versatile, efficient multi-task systems. Exist…

cs.AI2026

Guideline-grounded retrieval-augmented generation for ophthalmic clinical decision support

Shuying Chen, Sen Cui, Zhong Cao

In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat each guideline page as an indepen…

cs.LG2025

CALM: Consensus-Aware Localized Merging for Multi-Task Learning

Kunda Yan, Min Zhang, Sen Cui +4

Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task…

cs.AI2026

ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation

Zhikang Chen, Yue Wang, Sen Cui +4

Electrocardiogram (ECG)-based models have achieved strong performance in diagnostic tasks, yet they remain limited in modeling how cardiac dynamics evolve under external interventi…

cs.LG2023

Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustment

Sen Cui, Weishen Pan, Changshui Zhang +1

Algorithmic fairness has been a serious concern and received lots of interest in machine learning community. In this paper, we focus on the bipartite ranking scenario, where the in…

cs.LG2025

Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning

Danni Yang, Zhikang Chen, Sen Cui +6

Federated continual learning (FCL) has garnered increasing attention for its ability to support distributed computation in environments with evolving data distributions. However, t…

cs.LG2025

Learning without Isolation: Pathway Protection for Continual Learning

Zhikang Chen, Abudukelimu Wuerkaixi, Sen Cui +10

Deep networks are prone to catastrophic forgetting during sequential task learning, i.e., losing the knowledge about old tasks upon learning new tasks. To this end, continual learn…

cs.RO2026

FATE: Closed-Loop Feasibility-Aware Task Generation with Active Repair for Physically Grounded Robotic Curricula

Bingchuan Wei, Bingqi Huang, Jingheng Ma +2

Recent breakthroughs in generative simulation have harnessed Large Language Models (LLMs) to generate diverse robotic task curricula, yet these open-loop paradigms frequently produ…

cs.CV2026

Gold Points Sniper: Self-guided Visual Reasoning in VLM for Fine-grained Action Understanding

Haodi Liu, Xinhang Yang, Kunda Yan +3

Robots operating in everyday environments must understand fine-grained human actions, intentions, and contextual cues from broad views where people occupy only small regions, a cap…