8 citations · 28 across the 29 of their papers we have counts for
32 papers
Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry
Qi Yu, Ruizhong Qiu, Zhichen Zeng +6
Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse reasoning tasks. However, gr…
One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles
Zhichen Zeng, Huiyuan Chen, Jingru Cheng +7
Specializing Large Language Models (LLMs) toward distinct abilities underpins successes ranging from personalized assistants to multi-agent systems (MAS). Single-agent paradigms re…
From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model
Qi Yu, Zhichen Zeng, Katherine Tieu +8
Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference. Although significant effo…
SETA: Scaling Environments for Terminal Agents
Qijia Shen, Zhiqi Huang, Vamsidhar Kamanuru +19
Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interfaces (GUIs). Among these, the te…
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineerin…
AvAtar: Learning to Align via Active Optimal Transport
Qi Yu, Ruizhong Qiu, Zhichen Zeng +3
Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration. Recent works increasingly l…
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Ruizhong Qiu, Hanqing Zeng, Yinglong Xia +15
Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRA…
Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation
Xiao Lin, Zhicheng Tang, Weilin Cong +14
Sequential recommendation has rapidly advanced in click-through rate prediction due to its ability to model dynamic user interests. A key challenge, however, lies in modeling long…
A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
Tianxin Wei, Ting-Wei Li, Zhining Liu +26
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilitie…
ALERT: Zero-shot LLM Jailbreak Detection via Internal Discrepancy Amplification
Xiao Lin, Philip Li, Zhichen Zeng +6
Despite rich safety alignment strategies, large language models (LLMs) remain highly susceptible to jailbreak attacks, which compromise safety guardrails and pose serious security…
TSAQA: Time Series Analysis Question And Answering Benchmark
Baoyu Jing, Sanhorn Chen, Lecheng Zheng +13
Time series data are integral to critical applications across domains such as finance, healthcare, transportation, and environmental science. While recent work has begun to explore…
Subspace Alignment for Vision-Language Model Test-time Adaptation
Zhichen Zeng, Wenxuan Bao, Xiao Lin +8
Vision-language models (VLMs), despite their extraordinary zero-shot capabilities, are vulnerable to distribution shifts. Test-time adaptation (TTA) emerges as a predominant strate…
AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
Chengming Cui, Tianxin Wei, Ziyi Chen +6
Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling pr…
Hierarchical LoRA MoE for Efficient CTR Model Scaling
Zhichen Zeng, Mengyue Hang, Xiaolong Liu +11
Deep models have driven significant advances in click-through rate (CTR) prediction. While vertical scaling via layer stacking improves model expressiveness, the layer-by-layer seq…
Harnessing Consistency for Robust Test-Time LLM Ensemble
Zhichen Zeng, Qi Yu, Xiao Lin +6
Different large language models (LLMs) exhibit diverse strengths and weaknesses, and LLM ensemble serves as a promising approach to integrate their complementary capabilities. Desp…
PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment
Qi Yu, Zhichen Zeng, Yuchen Yan +5
Network alignment (NA) aims to identify node correspondence across different networks and serves as a critical cornerstone behind various downstream multi-network learning tasks. D…
Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics
Zhichen Zeng, Ruizhong Qiu, Wenxuan Bao +6
Graph neural networks, despite their impressive performance, are highly vulnerable to distribution shifts on graphs. Existing graph domain adaptation (graph DA) methods often impli…
CATS: Mitigating Correlation Shift for Multivariate Time Series Classification
Xiao Lin, Zhichen Zeng, Tianxin Wei +3
Unsupervised Domain Adaptation (UDA) leverages labeled source data to train models for unlabeled target data. Given the prevalence of multivariate time series (MTS) data across var…
ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration
Mengting Ai, Tianxin Wei, Yifan Chen +7
Mixture-of-Experts (MoE) Transformer, the backbone architecture of multiple phenomenal language models, leverages sparsity by activating only a fraction of model parameters for eac…
Joint Optimal Transport and Embedding for Network Alignment
Qi Yu, Zhichen Zeng, Yuchen Yan +3
Network alignment, which aims to find node correspondence across different networks, is the cornerstone of various downstream multi-network and Web mining tasks. Most of the embedd…
Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
Yuheng Zhang, Dian Yu, Tao Ge +5
Reinforcement learning from human feedback (RLHF) has demonstrated remarkable effectiveness in aligning large language models (LLMs) with human preferences. Many existing alignment…
THeGCN: Temporal Heterophilic Graph Convolutional Network
Yuchen Yan, Yuzhong Chen, Huiyuan Chen +6
Graph Neural Networks (GNNs) have exhibited remarkable efficacy in diverse graph learning tasks, particularly on static homophilic graphs. Recent attention has pivoted towards more…
PyG-SSL: A Graph Self-Supervised Learning Toolkit
Lecheng Zheng, Baoyu Jing, Zihao Li +9
Graph Self-Supervised Learning (SSL) has emerged as a pivotal area of research in recent years. By engaging in pretext tasks to learn the intricate topological structures and prope…
A Collaborative Ensemble Framework for CTR Prediction
Xiaolong Liu, Zhichen Zeng, Xiaoyi Liu +13
Recent advances in foundation models have established scaling laws that enable the development of larger models to achieve enhanced performance, motivating extensive research into…