We have 11 of 50 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the successor consolidates the update, although pre- and post-update models may retain complementary ranking decisions. We term this \emph{distribute...
Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose heterogeneous capability units, including Tools, MCP servers, and Skills, the carriers of injection multiply, and defenses built to recognize attack patterns fall behind th...
UA-TWM is introduced, a utility-anchored world-model interface that constructs nearby slate actions, estimates their target-relevant consequences, and selects an alternative subject to utility constraints, and enables target-aware selection around a trained sequential ranker.
While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive memory requirements. Extracting a compact subset of experts presents a promising solution. However, existing expert selection heuristics predominantly rely on Top-k ran...
Learning What to Skip is introduced, which learns action-specific safety models from these interventions and combines held-out calibration with domain-native guards to select skips and reduces recorded token cost while matching or improving aggregate full-workflow accuracy in the evaluated settings.
This work proposes AgentMMRec, an agent-based multimodal recommendation framework with two coordinated roles that consistently improves Recall and NDCG over recent multimodal baselines, remains effective under sparsity and item cold-start settings, and can transfer its constructed knowledge to existing backbones.
This paper introduces CoCA, an on-policy learning framework that recovers a deployable capability-subset policy from sparse conditional comparisons, and introduces dual-level on-policy distillation to address distribution mismatch both across environment states and within the partial subsets encountered during set cons...
Recent studies in multimodal recommendation, which leverage diverse modal information to address data sparsity and enhance recommendation accuracy, have garnered significant interest. Two critical processes in this domain are modality fusion and representation learning. In representation learning, existing studies ofte...
This paper proposes Neural Tree Collaborative Filtering (NTCF), a framework that re-interprets each node's local neighborhood as a rooted tree and assigns a node-specific propagation depth based on a closed-form local-degree-imbalance score that serves as a discrete Ricci-curvature proxy.
This paper proposes Dude, the first Dual-Detection Multi-Agent System for paper-code discrepancy detection, with a granularity-aligned negotiation and a two-stage salience-filtering mechanism in Dude that effectively prevents agents from falsely reporting discrepancies.
A client-specific adaptation channel based on private prompt tokens, which tracks local adaptation dynamics separately from the shared backbone and provides a lightweight signal for detecting whether client adaptation remains active, and a shallow sufficiency estimator that combines cross-client semantic alignment, tem...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
