141 papers
This paper analyzes a decade-long dataset of 2 million YouTube videos to reveal that while affiliate marketing is widespread, disclosure compliance with FTC guidelines remains critically low, suggesting that platform-standardized features are essential for improving transparency and trust in the influencer economy.
This paper introduces GR4AD, a production-oriented generative recommendation system for large-scale advertising that integrates novel tokenization, a lazy autoregressive decoder, and value-aware reinforcement learning to achieve significant revenue gains and high-throughput real-time serving in Kuaishou's 400-million-user ecosystem.
This paper introduces PinRec, a novel outcome-conditioned, multi-token generative retrieval model developed for Pinterest that successfully balances performance, diversity, and efficiency to meet industrial-scale recommendation needs and multiple business metrics.
This paper introduces -Knowledge, a new benchmark featuring the -Banking domain to evaluate conversational agents' ability to coordinate unstructured knowledge retrieval with tool use in complex, policy-driven workflows, revealing that even frontier models struggle with low success rates and reliability in such realistic, long-horizon interactions.
This paper introduces LabelBuddy, an open-source collaborative tool that bridges the gap between human intent and machine understanding in Music Information Retrieval by decoupling the annotation interface from containerized AI backends to enable flexible, AI-assisted pre-tagging and multi-user consensus.
This paper proposes DisenReason, a novel two-stage sequential recommendation framework for shared accounts that overcomes the limitation of fixed user assumptions by disentangling collective account behaviors in the frequency domain to serve as a pivot for latent reasoning, thereby dynamically inferring the number of latent users and significantly improving recommendation accuracy.
This paper introduces HAP, a heterogeneity-aware pre-ranking framework that resolves gradient conflicts and optimizes computational efficiency by disentangling easy and hard samples for tailored model allocation, achieving significant user engagement improvements in the Toutiao production system without extra costs.
The paper introduces AgentSelect, a comprehensive benchmark that addresses the lack of principled agent selection methods by reframing the task as narrative query-to-agent recommendation, providing a unified dataset of over 111,000 queries and 107,000 agents to enable content-aware capability matching and demonstrate superior performance in recommending end-to-end agent configurations across diverse ecosystems.
This paper introduces SafeCRS, a safety-aware training framework and the SafeRec benchmark designed to mitigate personalized safety violations in LLM-based conversational recommender systems by integrating Safe-SFT and Safe-GDPO to align recommendations with individual user constraints while maintaining high recommendation quality.
This paper introduces Graph Hopfield Networks, an energy-based framework that unifies associative memory retrieval with graph Laplacian smoothing to achieve state-of-the-art node classification performance and enhanced robustness across diverse graph benchmarks.
MemSifter is an efficient framework that offloads memory retrieval to a small-scale proxy model trained via outcome-driven reinforcement learning, achieving state-of-the-art performance in long-term LLM memory tasks while minimizing computational overhead.
This paper proposes a multi-agent Retrieval-Augmented Generation framework that integrates open-weight large language models and vision-language models to enhance knowledge management and workforce training in state Departments of Transportation by enabling context-aware, evidence-grounded responses from both textual and visual technical documentation.
The paper introduces PlugMem, a task-agnostic plugin memory module that structures episodic memories into a compact, knowledge-centric graph to enable efficient retrieval and reasoning for LLM agents, demonstrating superior performance across diverse benchmarks compared to both task-specific and existing task-agnostic baselines.
The paper proposes MA-RAG, a multi-round agentic RAG framework that iteratively refines medical reasoning by transforming semantic conflicts into targeted evidence retrieval and optimizing reasoning traces, thereby achieving substantial accuracy improvements over existing baselines across seven medical benchmarks.
AriadneMem is a structured memory system for long-horizon LLM agents that employs a decoupled two-phase pipeline of entropy-aware filtering, conflict-aware coarsening, and algorithmic bridge discovery to significantly improve multi-hop reasoning accuracy and efficiency while drastically reducing context usage and runtime.
This paper introduces DevRev-Search, an automated benchmark for technical support retrieval, and proposes an Index-Preserving Adaptation strategy that fine-tunes only the query encoder to achieve scalable, high-performance multi-tenant search without the prohibitive cost of re-indexing.
The paper proposes REVISION, a novel framework that integrates offline large-model reasoning to mine implicit user intents from no-click requests with online adaptive decision-making to optimize Taobao's visual search system and significantly reduce no-click rates.
This paper introduces PDR-Bench, the first benchmark for evaluating personalization in Deep Research Agents, along with the PQR Evaluation Framework to assess performance across personalized, open-ended research tasks.
This paper proposes the Co-Evolutionary Alignment (CoEA) method, which integrates a Dual-Stable Interest Exploration module to model both group identity and individual interests and a Periodic Collaborative Optimization mechanism to establish a dynamic closed-loop feedback system, thereby overcoming the limitations of static optimization and biased interest modeling in LLM-enhanced serendipitous recommendation.
OSCAR is a novel online soft compression and reranking method that dynamically reduces computational overhead in Retrieval-Augmented Generation pipelines at inference time, achieving significant speed-ups with minimal accuracy loss across various large language model sizes.