全部收录论文
论文 · 第 47 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 47 / 141 页
查找论文请用站内搜索。
- Generative LLMs for educational recommendation
- Research on CTR Prediction Based on Deep Learning
- Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments
- ColBERTSaR: Sparsified ColBERT Index via Product Quantization
- Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
- How mobility gives language models a deeper understanding of place
- Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Segmentation Strategies for Information Retrieval
- Before Reasoning Can Fail: Pre-Evidence Procedural Failures in Agentic RAG
- HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents
- SOP-Bench: A new benchmark for evaluating AI agents on real business procedures
- HyMem: Hierarchical Context Management for Long-Horizon Agents via Information Isolation
- NVIDIA AVO Reaches 100% on ARC-AGI-3, Demonstrating a Frontier-Level General-Purpose Architecture for Long-Horizon Autonomous Agents
- Where Security Fits in an AI Agent Stack
- Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents
- EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
- ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision
- ECHO: Efficient KV Cache Offloading with Lossless Prefetching for Serving Native Sparse Attention LLMs
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Tessera: A Holistic Pipeline Parallelism Framework for Trillion-Parameter Heterogeneous MoE Training (Operational Systems)
- Kairox: Adaptive GPU-CPU Hybrid LLM Inference via Online Neuron Balancing
- Revisiting Pipeline Parallelism for LLM Serving
- Pallas: A Proactive KV Cache Migration Framework for LLM Inference in AI-RAN
- Maximizing AI Factory Performance per Watt with NVIDIA DSX MaxLPS
- GPU-Accelerated Clustering for Financial Instruments at Scale
- SIDScope: A Diagnostic Resource for Semantic-ID Interfaces in Generative Recommendation
- Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation
- How Generative Recommenders Are Redefining RecSys at Scale
- ICICLE: Expanding Retrieval with In-Context Documents
- PILOT Technical Report
- AI in Search Reduces Publisher Referrals Without Improving User Experience: Experimental Evidence
- 推荐系统进入“大模型时刻”:昇腾NPU如何支撑千亿级生成式推荐落地
- More Context, Same Budget: Dual-Bounded Relational Recall Beyond Top-K Retrieval
- Tunable LLM-based Proactive Recommendation Agent
- CG-MAR: LLM-Based Multi-Agent Recommendation System via Community Graph
- OneModel: A Unified Foundation for Platform-Scale Multi-Scenario Ranking
- GateDiffInt: Gate-Mediated Controllable Diffusion and Multi-Intent LLM Distillation for User Behavior Modeling
- Multimedia Asset Personalization via Multimodal Embeddings at Netflix
- rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation
- Think-to-Personalize: Unifying Reasoning and Retrieval for User-Centric Personalized Dense Retrieval
- DEGR: Dual Exploration-Driven Generative Re-Ranking for Adaptive Recommendation
- Dual-Stream MLP is All You Need for CTR Prediction
- Constructing a Joint Prediction Model for Advertising Click-Through Rate and Conversion Rate Based on a Multi-Task Learning Framework
- 美团搜索3.0:LLM 语义表征在排序模型的探索与应用
- HyTiFRec: Hybrid Time-Frequency Dual-Branch Transformer for Sequential Recommendation
- FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems
- Predicting the Benefit of Retrieval Augmentation in Open-Domain Question Answering
- LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum
- How GPU acceleration builds billion-scale vector indexes on Amazon OpenSearch Service
- AMU at RAG4Reports 2026 Task B: A Practical Multilingual RAG Pipeline for Citation-Grounded Reports
- GenAIus at SemEval-2026 Task 8: Beyond Retrieval with Relevance-Aware RAG for Faithful Multi-Turn Generation