全部收录论文
论文 · 第 128 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 128 / 141 页
查找论文请用站内搜索。
- CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems
- Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memory
- RaDAR: Relation-aware Diffusion-Asymmetric Graph Contrastive Learning for Recommendation
- SIA: A Synthesize-Inject-Align Framework for Knowledge-Grounded and Secure E-commerce Search LLMs with Industrial Deployment
- ReFORM: Review-aggregated Profile Generation via LLM with Multi-Factor Attention for Restaurant Recommendation
- Personalized Ranking on Cascading Behavior Graphs for Accurate Multi-Behavior Recommendation
- RecBundle: A Next-Generation Geometric Paradigm for Explainable Recommender Systems
- BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
- 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
- IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time
- LANCER: LLM Reranking for Nugget Coverage
- Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech
- CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering
- Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents
- Open-Source Reproduction and Explainability Analysis of Corrective Retrieval Augmented Generation
- Finder: A Multimodal AI-Powered Search Framework for Pharmaceutical Data Retrieval
- NextMem: Towards Latent Factual Memory for LLM-based Agents
- AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs
- Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users
- DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search
- SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering
- MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
- Compiled Memory: Not More Information, but More Precise Instructions for Language Agents
- Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective
- ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning
- Internalizing Agency from Reflective Experience
- Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models
- VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization
- FlashSampling: Fast and Memory-Efficient Exact Sampling
- Filtered Approximate Nearest Neighbor Search in Vector Databases: System Design and Performance Analysis
- Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space
- SQuat: Subspace-orthogonal KV Cache Quantization
- Cracking Vector Search Indexes: CrackIVF Adaptive Index
- Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization
- CacheSolidarity: Preventing Prefix Caching Side Channels in Multi-tenant LLM Serving Systems
- Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries
- Not All Queries Need Rewriting: When Prompt-Only LLM Refinement Helps and Hurts Dense Retrieval
- Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion
- Learning Retrieval Models with Sparse Autoencoders
- FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference
- AMES: Approximate Multi-modal Enterprise Search via Late Interaction Retrieval
- Location Aware Embedding for Geotargeting in Sponsored Search Advertising
- A Survey of Model Architectures in Information Retrieval
- Learning Image-Text Matching with Optimal Partial Transport
- Compute Allocation for Reasoning-Intensive Retrieval Agents
- Towards Foundation Models for Consensus Rank Aggregation
- MBD: A Model-Based Debiasing Framework Across User, Content, and Model Dimensions
- R3-REC: Reasoning-Driven Recommendation via Retrieval-Augmented LLMs over Multi-Granular Interest Signals
- Post-hoc Popularity Bias Correction in GNN-based Collaborative Filtering
- Iterative Semantic Reasoning from Individual to Group Interests for Generative Recommendation with LLMs