全部收录论文
论文 · 第 46 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 46 / 141 页
查找论文请用站内搜索。
- Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation
- Beyond Raw Transcripts: Structured Persona Extraction for LLM-Based Digital Twins
- Recommendation Quality and the Concentration of Consumption: Experimental Evidence from Netflix
- MTIA 300: Meta’s First Training Chip with Built-in NICs and Communication-Offloading Engines
- TH-GNN: Heterogeneous Temporal Graph Neural Networks for LLM-Agent Shilling Attack Detection
- ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models
- Clarify-Then-Search: A Clarification Benchmark for Deep Search with End-to-End Nugget Restoration
- EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering
- RAG Deserves an Index: Why Ingest-Time Compilation Beats Query-Time Interpretation
- Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
- Edge-Based Agentic Retrieval-Augmented Generation for Autonomous FHWA Bridge Inspection Compliance
- PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval
- Making Large Language Models Efficient Dense Retrievers
- KoViDoRe: Korean Visual Document Retrieval
- MetaRoCE: A New RDMA Transport Built for AI-Scale Ethernet
- How NVIDIA Groq 3 LPX Unlocks Ultrafast Interactivity at Long Context on NVIDIA Vera Rubin
- AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
- Reinforcing Agentic Search Via Reward Density Optimization
- jXBW: A Compressed Index Enabling Structure-Aware JSONL Retrieval for Structured RAG
- MMSearch-R1: Incentivizing LMMs to Search
- How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel
- Auditable by Construction: An Ontology-Driven Framework for Trustworthy LLM Analytics in Enterprise Finance
- Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
- Structure for Reading, Prose for Writing: Asymmetric Structural Conditioning in Multi-Agent Document Authoring
- WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
- 手把手教你构建Agentic RAG:一种基于多文档RAG应用的AI Agent智能体
- DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs
- GRAFT: Adaptive DLM-Based Draft Tree Construction with Target-Distilled Edge Scoring
- Self-Speculation for Faster Reasoning Models
- Nemotron 3 Ultra: Open, Efficient Mixture
- NVIDIA BlueField-4 Powers New Scale-In Network Infrastructure for Agentic AI Factories
- Giga-Scale AI and the Ethernet Evolution: How Spectrum-X Ethernet Rewrites the Rules
- Scaling AI with 8 to 20x energy efficiency
- NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt
- TriPLU: Bypassing the Gate with Direct Trilinear Product FFNs in Tiny Language Models
- When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems
- Training-Free LLM-Based Recommendation with Post-LLM Item Refinement Using Collaborative Signals
- SSR-GRPO: Integrating Supervision and Semantic IDs into Reinforcement Learning for Dense Retrieval in E-commerce
- SmartGR: Hierarchy and Beam-Aware Knowledge Distillation for Generative Recommendation
- SCoRD: Semantic-Assisted Continual Retriever-Reranker Distillation for LLM-Based Recommendation
- CD-LLMCARS: Cross Domain Fine-Tuned Large Language Model for Context-Aware Recommender Systems
- Recommender Systems Meet Large Language Model Agents: A Survey
- Preference-Driven Online Adaptation for Personalized Interaction Initiation in Proactive AI Assistants
- PI-adaptDiv: an adaptive algorithm to prevent and escape online filter bubbles
- An adaptive scalarization framework for multi-objective recommender systems
- MR-Rec: Mutual-Representation-Enhanced Model for Sequential Recommendation
- A reward-informed semi-personalized bandit approach for enhancing accuracy and serendipity in online slate recommendations
- RecSys Weekly 2026-W34
- AI Recommendations: This Time It’s Personal
- Agentic Recommender Systems and Harness Engineering: Implementation Guide