全部收录论文

论文 · 第 31 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 31 / 141 页

查找论文请用站内搜索。

  1. The Recall Ceiling of LLM Recommendation Reranking2026-09-25 · 生成式推荐
  2. Explainable Recommendations at Scale: LLM Rationales for YouTube Music Artist Discovery2026-09-25 · 生成式推荐
  3. MTFM:美团统一推荐基座大模型在外卖多业务场景的落地实践2026-09-25 · 个性化推荐
  4. When LLM-Based User Profiling Adds Value in Production Streaming Recommendation2026-09-25 · 个性化推荐
  5. Tie Handling Is Part of the Evaluation Protocol: An Order-Invariance Audit for Tie-Heavy Recommender Scores2026-09-25 · 个性化推荐
  6. Beyond a Scalar: Distributional Serving Interfaces for Watch-Time Prediction2026-09-25 · 个性化推荐
  7. Calibrating Reproduced Claims in Recommender Systems2026-09-25 · 个性化推荐
  8. BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval2026-09-25 · AI 搜索
  9. ItColBERT: An Italian-Specialised Late-Interaction Retriever2026-09-25 · AI 搜索
  10. Test-Time Adaptation with Query-Dependent Residuals for Visual Document Retrieval2026-09-25 · AI 搜索
  11. WARP: Wasserstein-Aligned RAG for Population Opinions2026-09-25 · AI 搜索
  12. When Learned Context Planning Fails to Beat Strong Retrieval: A Controlled Study of Planning, Routing, and Reranking for Long-Context QA2026-09-25 · AI 搜索
  13. MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos2026-09-25 · AI 搜索
  14. Distilling Lexical Product Associations into Deep Transformers: An Extreme Multi-Label Approach for Natural Language E-Commerce Search2026-09-25 · AI 搜索
  15. EidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QA2026-09-25 · AI 搜索
  16. Realize What Matters: Principled Context Representation for Large-Scale Reasoning2026-09-25 · 智能体搜索
  17. Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents2026-09-25 · 智能体搜索
  18. Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms2026-09-25 · 智能体搜索
  19. Meet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge Lattices2026-09-25 · 智能体搜索
  20. COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference2026-09-25 · 智能体搜索
  21. Dual-Hypergraph Indexing: Bridging Knowledge Islands for Multi-Hop Reasoning in Retrieval-Augmented Generation2026-09-25 · 智能体搜索
  22. Large Knowledge Model: From Papers to a Scientific Reasoning Landscape2026-09-25 · 智能体搜索
  23. UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation2026-09-25 · 智能体搜索
  24. Parallel cut research time and cost in half with GPT‑6 Astra2026-09-25 · 智能体搜索
  25. LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning2026-09-25 · 智能体搜索
  26. MLCommons Sets Participation Record with New MLPerf Inference v6.1 Benchmark Results2026-09-25 · 系统与索引
  27. FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation2026-09-25 · 系统与索引
  28. Better prompt caching for GPT-62026-09-25 · 系统与索引
  29. Hunyuan-A13B Technical Report2026-09-25 · 系统与索引
  30. Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs2026-09-25 · 系统与索引
  31. Distilling Sequential Computation in Transformer Language Models2026-09-25 · 系统与索引
  32. Topology-Aware Workload Scheduling with NVIDIA Topograph2026-09-25 · 系统与索引
  33. Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery2026-09-25 · 系统与索引
  34. Efficient MoE Training for Biological Foundation Models2026-09-25 · 系统与索引
  35. Seal, Then Sample: Sampled Layerwise Proofs for Verifiable LLM Inference from GPT-2 to 70B2026-09-25 · 系统与索引
  36. What Makes a Good Semantic ID for Generative Recommendation? A Reproducibility Study2026-09-24 · 生成式推荐
  37. Robust Fusion of Semantic and Behavioural Signals for LLM Reranking in Personalised Search2026-09-24 · 个性化推荐
  38. TailSpec-EASE: Knowledge-Graph-Regularized Linear Recommendation for Web Long-Tail Discovery2026-09-24 · 个性化推荐
  39. From Ranked Documents to Reliable Contexts: An Answer-Oriented Context Construct Framework for AI Search2026-09-24 · AI 搜索
  40. Parameterized Dense-Sparse Fusion for Hybrid Retrieval: Tuning a Rank-Score Mix on BEIR SciFact with Qdrant2026-09-24 · AI 搜索
  41. GroundedGEO: Auditing the Evidence Gap in Generative Search Rankings2026-09-24 · AI 搜索
  42. ReFilter: Bridging Embeddings and LLM Filtering for Similar Mobile App Retrieval2026-09-24 · AI 搜索
  43. Which Reranking Conclusions Survive the Answer Interface? A Prospective Finite-Orbit Audit2026-09-24 · AI 搜索
  44. Semantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval2026-09-24 · AI 搜索
  45. Scoring With the Engine: Retrieval Exposure, Cross-Engine Divergence, and the Limits of Engine-Agnostic GEO Scores2026-09-24 · AI 搜索
  46. ABAI at COLIEE 2026 Task 1: Multi-Stage Retrieval with GraphRAG-Enhanced Meta-Learning, and a Post-Hoc Study of the Cross-Validation-to-Test Gap2026-09-24 · AI 搜索
  47. Algebraic Retrieval: Composable Search for Agents2026-09-24 · AI 搜索
  48. Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation2026-09-24 · AI 搜索
  49. CoVeR: Coverage-Based Routing of Verifier Calls in Agentic Retrieval2026-09-24 · 智能体搜索
  50. SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue2026-09-24 · 智能体搜索