全部收录论文

论文 · 第 127 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 127 / 141 页

查找论文请用站内搜索。

  1. A Family of LLMs Liberated from Static Vocabularies2026-03-20 · 生成式推荐
  2. Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models2026-03-20 · 生成式推荐
  3. Role-Augmented Intent-Driven Generative Search Engine Optimization2026-03-20 · 生成式推荐
  4. Deploying Semantic ID-based Generative Retrieval for Large-Scale Podcast Discovery at Spotify2026-03-20 · 个性化推荐
  5. A Unified Language Model for Large Scale Search, Recommendation, and Reasoning2026-03-20 · 个性化推荐
  6. HierarchicalKV: A GPU Hash Table with Cache Semantics for Continuous Online Embedding Storage2026-03-20 · 个性化推荐
  7. Learning Evolving Preferences: A Federated Continual Framework for User-Centric Recommendation2026-03-20 · 个性化推荐
  8. VLM2Rec: Resolving Modality Collapse in Vision-Language Model Embedders for Multimodal Sequential Recommendation2026-03-20 · 个性化推荐
  9. Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)2026-03-20 · 个性化推荐
  10. Embedding World Knowledge into Tabular Models: Towards Best Practices for Embedding Pipeline Design2026-03-20 · 个性化推荐
  11. ListK: Semantic ORDER BY and LIMIT K with Listwise Prompting2026-03-20 · 个性化推荐
  12. MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment2026-03-20 · 个性化推荐
  13. OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation2026-03-20 · AI 搜索
  14. Negation is Not Semantic: Diagnosing Dense Retrieval Failure Modes for Trade-offs in Contradiction-Aware Biomedical QA2026-03-20 · AI 搜索
  15. Training-Induced Bias Toward LLM-Generated Content in Dense Retrieval2026-03-20 · AI 搜索
  16. Visual Product Search Benchmark2026-03-20 · AI 搜索
  17. The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA2026-03-20 · AI 搜索
  18. Public Profile Matters: A Scalable Integrated Approach to Recommend Citations in the Wild2026-03-20 · AI 搜索
  19. From Isolated Scoring to Collaborative Ranking: A Comparison-Native Framework for LLM-Based Paper Evaluation2026-03-20 · AI 搜索
  20. Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search2026-03-20 · AI 搜索
  21. How often do Answers Change? Estimating Recency Requirements in Question Answering2026-03-20 · AI 搜索
  22. PJB: A Reasoning-Aware Benchmark for Person-Job Retrieval2026-03-20 · AI 搜索
  23. TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas2026-03-20 · 智能体搜索
  24. PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization2026-03-20 · 智能体搜索
  25. CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents2026-03-20 · 智能体搜索
  26. InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning2026-03-20 · 智能体搜索
  27. RAGXplain: From Explainable Evaluation to Actionable Guidance of RAG Pipelines2026-03-20 · 智能体搜索
  28. Tree Search for LLM Agent Reinforcement Learning2026-03-20 · 智能体搜索
  29. Generalizable End-to-End Tool-Use RL with Synthetic CodeGym2026-03-20 · 智能体搜索
  30. Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context2026-03-20 · 智能体搜索
  31. Facts as First Class Objects: Knowledge Objects for Persistent LLM Memory2026-03-20 · 智能体搜索
  32. Alternating Reinforcement Learning with Contextual Rubric Rewards2026-03-20 · 智能体搜索
  33. FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling2026-03-20 · 系统与索引
  34. ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression2026-03-20 · 系统与索引
  35. The 1/W Law: An Analytical Study of Context-Length Routing Topology and GPU Generation Gains for LLM Inference Energy Efficiency2026-03-20 · 系统与索引
  36. BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization2026-03-20 · 系统与索引
  37. RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference2026-03-20 · 系统与索引
  38. Efficient Reasoning on the Edge2026-03-20 · 系统与索引
  39. Speculative Decoding: Performance or Illusion?2026-03-20 · 系统与索引
  40. MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios2026-03-20 · 系统与索引
  41. Learning When to Attend: Conditional Memory Access for Long-Context LLMs2026-03-20 · 系统与索引
  42. PRISM: Demystifying Retention and Interaction in Mid-Training2026-03-20 · 系统与索引
  43. Quantized Inference for OneRec-V22026-03-19 · 生成式推荐
  44. SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation2026-03-19 · 生成式推荐
  45. UserSimCRS v2: Simulation-Based Evaluation for Conversational Recommender Systems2026-03-19 · 生成式推荐
  46. RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments2026-03-19 · 生成式推荐
  47. Answer Bubbles: Information Exposure in AI-Mediated Search2026-03-19 · 生成式推荐
  48. MemX: A Local-First Long-Term Memory System for AI Assistants2026-03-19 · 生成式推荐
  49. AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents2026-03-19 · 生成式推荐
  50. PREFINE: Personalized Story Generation via Simulated User Critics and User-Specific Rubric Generation2026-03-19 · 生成式推荐