9 papers · 1 filter
Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation
Jinfeng Xu, Zheyu Chen, Ziyue Peng +5
Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the succe…
Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents
Wenhao Yuan, Chenchen Lin, Jian Chen +3
Long-horizon multimodal agents rely on specialized capabilities for perception, retrieval, reasoning, verification, and execution. Existing designs typically activate a fixed capab…
Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration
Chenchen Lin, Wenhao Yuan, Xuehe Wang +1
Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent evidence…
When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation
Wenhao Yuan, Chenchen Lin, Wentao Hu +4
\textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients. However, under client heterogeneity, the convention…
Neural Tree Collaborative Filtering: Rethinking Graph Collaborative Filtering as Tree Collaborative Filtering with Curvature-Aware Propagation Depth
Jinfeng Xu, Zheyu Chen, Ziyue Peng +5
Graph Collaborative Filtering (GCF) has become the dominant paradigm in modern recommender systems by modeling user-item interactions as a bipartite graph and propagating embedding…
Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning
Wenhao Yuan, Chenchen Lin, Jian Chen +3
Federated Learning (FL) emerged as a promising distributed machine learning paradigm. However, extending FL to the class incremental learning scenarios introduces unique challenges…
Belief-Guided Inference Control for Large Language Model Services via Verifiable Observations
Wenhao Yuan, Chenchen Lin, Jian Chen +3
In black-box large language model (LLM) services, response reliability is often only partially observable at decision time, while stronger inference pathways incur substantial comp…
DBGL: Decay-aware Bipartite Graph Learning for Irregular Medical Time Series Classification
Jian Chen, Yuzhu Hu, Xiaoyan Yuan +6
Irregular Medical Time Series play a critical role in the clinical domain to better understand the patient's condition. However, inherent irregularity arising from heterogeneous sa…
Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
Wenhao Yuan, Chenchen Lin, Jian Chen +3
In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still…