139 citations · 336 across the 52 of their papers we have counts for
59 papers
Rethinking Latent Reasoning for Generative Recommendation: Beyond Teacher-Generated CoT and Recurrent Hidden-State Feedback
Yiwen Chen, Fuwei Zhang, Zehao Chen +8
Latent reasoning in generative recommendation faces two practical barriers: constructing teacher-generated chain-of-thought (CoT) supervision is costly, and recurrent hidden-state…
Residual Trajectory Distillation for Generative Retrieval
Weihao Shen, Wei Chen, Fuwei Zhang +4
Generative retrieval has emerged as a general retrieval paradigm, representing items with discrete Semantic IDs (SIDs) and retrieving them through autoregressive identifier generat…
Learning Multiresolution Relevance for Hierarchical Generative Retrieval
Weihao Shen, Wei Chen, Fuwei Zhang +4
Generative retrieval with semantic identifiers (SIDs) makes successive decisions over a document hierarchy. Relevant documents for the same query may share coarse prefixes and dive…
Dual-Channel Robust Group-Relative Policy Optimization via Advantage and Sequence-Weight Estimation
Zhongyi Li, Wan Tian, Xiang Xu +4
Group-relative policy optimization relies on reward-derived advantages and sequence-level likelihood weights, both of which can be sensitive to localized outliers. Extreme rewards…
STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking
Wan Tian, Zhongyi Li, Xiang Xu +3
Reward hacking occurs when policy optimization exploits a brittle reward interface or an overly permissive proxy objective, improving the training score without improving the under…
HiTS-CL: A Continual Learning Framework for Long-Horizon Temporal Knowledge Graph Extrapolation
Yansong Liu, Rui Liu, Yuan Zuo +6
Extrapolative temporal knowledge graph reasoning (TKGR) predicts future facts from historical snapshots. Most existing methods train once on an early prefix of the timeline and the…
NaviScale: Generating Large-Scale Semantic Map Datasets for Object Navigation
Chuanlin Lan, Yanwei Zheng, Yuxi Jing +6
Embodied navigation requires spatial representations that generalize across unseen environments, yet collecting large amounts of annotated data from real 3D environments is difficu…
WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training
Zehao Chen, Gongxun Li, Tianxiang Ai +9
On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline distillation. The sa…
D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection
Xin Chen, Fuwei Zhang, Yiqi Tong +3
AI-generated text detection is commonly framed as a binary document-level judgment about whether a text is human-written or machine-generated. This framing breaks down for mixed-or…
Requirement--Evidence Alignment for Compositional E-Commerce Queries
Weihao Shen, Wei Chen, Fuwei Zhang +6
Compositional e-commerce queries express multiple requirements that must hold jointly, yet existing rerankers collapse these constraints into aggregate relevance and often promote…
Unpaired Modality-Agnostic Generative Recommendation
Weihao Shen, Wei Chen, Fuwei Zhang +6
Generative Recommendation (GR) formulates recommendation as autoregressive generation over discrete semantic identifiers (IDs). Although recent multimodal GR methods improve semant…
Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce
Fuwei Zhang, Xiaoyu Liu, Jiajie Jin +8
Generative retrieval offers a new paradigm for e-commerce search by mapping user queries directly to product Semantic Identifiers (SIDs). However, e-commerce queries are often shor…
Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection
Yiwen Chen, Kuan Li, Fuzhen Zhuang +6
Recent advances in large language models (LLMs) have expanded the context window to beyond 128K tokens, enabling long-document understanding and multi-source reasoning. A key chall…
SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
Wei Chen, Xingyu Guo, Shuang Li +6
Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over item identifiers. Recent studie…
LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation
Yiwen Chen, Fuwei Zhang, Zehao Chen +7
Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hi…
Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
Wei Chen, Xingyu Guo, Shuang Li +4
Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs but is challenged by complex, multi-faceted distributional shifts. Existing…
Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
Zhongyi Li, Wan Tian, Jinju Chen +4
Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assi…
Heterogeneous Agent Collaborative Reinforcement Learning
Zhixia Zhang, Zixuan Huang, Gongxun Li +10
We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new Reinforcement Learning from Verifiable Reward (RLVR) problem that addresses the inefficiencies…
Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation
Wei Chen, Xingyu Guo, Shuang Li +7
Graph Domain Adaptation (GDA) aims to bridge distribution shifts between domains by transferring knowledge from well-labeled source graphs to given unlabeled target graphs. One pro…
UniFAR: A Unified Facet-Aware Retrieval Framework for Scientific Documents
Zheng Dou, Zhao Zhang, Deqing Wang +2
Scientific document retrieval (SDR) plays a critical role in modern scientific research, supporting knowledge discovery and evidence-based reasoning. It has evolved along two parad…
Does Your Reasoning Model Implicitly Know When to Stop Thinking?
Zixuan Huang, Xin Xia, Yuxi Ren +11
Recent advancements in large reasoning models (LRMs) have greatly improved their capabilities on complex reasoning tasks through Long Chains of Thought (CoTs). However, this approa…
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger
Zehao Chen, Gongxun Li, Tianxiang Ai +9
As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training…
You Only Anonymize What Is Not Intent-Relevant: Suppressing Non-Intent Privacy Evidence
Weihao Shen, Yaxin Xu, Shuang Li +4
Anonymizing sensitive information in user text is essential for privacy, yet existing methods often apply uniform treatment across attributes, which can conflict with communicative…
Real-Time Aligned Reward Model beyond Semantics
Zixuan Huang, Xin Xia, Yuxi Ren +10
Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptim…