全部收录论文
论文 · 第 33 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 33 / 141 页
查找论文请用站内搜索。
- Who You Are Adds Nothing Detectable to Where You Go Next: Sociodemographic Conditioning in LLM Next-Location Prediction
- Position: Recommender Systems Should Move Beyond Platform-Centric Ranking toward Personal Agent-Mediated Recommendation
- BanglaShop-CRS: A User-Centric Bangla Dataset for Conversational Recommendation
- Dense Feature Representation over Sequence Modeling: A Solution to the KDD Cup 2026 UniRec Challenge
- DiSAM4Rec: distilled and sparsity adaptive Mamba for sequential recommendation
- Reasoning Quality Matters: Combating Reasoning Collapse in LLM-based Embedding Learning
- Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking
- TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives
- Characterizing Web Search by Conversational LLM Agents: From Search Decisions and Strategies to Results and Responses
- FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA
- MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards
- Closed-World Resolution Against Tool Hallucination in LLM Agents
- RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
- APEx: Distillation of Agent Procedural Experience for Adaptive Deep Research Question Answering
- When Failures Propagate: Causal Failure Attribution in Agentic Retrieval-Augmented Generation
- Agentic ML Exploration (A-MLE) for Ads Ranking
- Shared Selective Persistent Memory for Agentic LLM Systems
- 4-bit Rotational Quantization
- Benchmarking LLM Inference at Scale with AIPerf
- Elastic Introduces Serverless Vector Database: Ship in Minutes, Scale Affordably to Hundreds of Billions of Vectors
- One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations
- LIGE-GR: A Smooth Leap from Ranking to Generative Recommendation in the LLM Era
- Single-Token Expected-Value Scoring for Cold-Start Candidate Ranking
- SURF: Subtractive Updates for Recommender Forgetting
- How Calibration Content Shapes Attention-Based Reranking
- DUPAR: Dual-Path Conversational Retrieval via Speech Retriever with Cross-Turn Evidence Caching
- PageRecall: Measuring Page Selection in Literature-Grounded Question Answering
- One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG
- Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
- Agora: Git as Shared Memory for Collective AutoResearch
- CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
- ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
- ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks
- BOA: Beamwidth Online Adaptation for Filtered-ANNS on a GPU
- Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It
- RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation
- Quanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphs
- Zero-I/O Fault Recovery for Sharded Deep Learning via Dynamic Framework Dependency Rebinding
- PipeSwift: Revisiting Pipeline Parallelism for Large-Scale Completion-Oriented Agentic LLM Serving
- The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
- Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches
- GeoMesh: Workload-Balanced and Sign-Compressed Geo-Distributed LLM Training
- Beyond Static RAG: An Adaptive, Tri-Metric Routing Framework for Efficient Long-Context Inference on Commodity GPUs
- ReliGRec: Reliability-Oriented LLM-Based Generative Recommendation via User-Risk-Aware Prompt Routing
- Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning
- Evaluating Brand Retrieval and Ranking in Large Language Model Recommendations
- Balancing Trial and Reorder: A Hybrid Sequential Transformer-GBDT Ranker for On-Demand Delivery
- PCap: Personalized Retrieval-Stage Diversity Capping in Facebook Marketplace
- RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models
- Efficient Swing Computation for Retrieval in Large-Scale Recommender Systems