全部收录论文

论文 · 第 36 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 36 / 141 页

查找论文请用站内搜索。

  1. Rapidly scaling online storage to serve over 1 billion ChatGPT users2026-09-14 · 系统与索引
  2. PATTON: Enabling Commodity PIM for Production LLM Serving2026-09-14 · 系统与索引
  3. FlexPosit: Tunable Fractional Precision for LLM Inference Accelerators2026-09-14 · 系统与索引
  4. A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware2026-09-14 · 系统与索引
  5. Spatial LLM Workload Shifting Needs Foresight: Model Commitment for AI Data Center Operation under Power Grid Constraints2026-09-14 · 系统与索引
  6. PDMR: Passage-Driven Multi-ID Document Retrieval2026-09-11 · 生成式推荐
  7. Purchase Advice and Observable Buyer Responses in Real AI Conversations2026-09-11 · 生成式推荐
  8. HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization2026-09-11 · 个性化推荐
  9. From Retrieval to Weights: Parametric Individualization of Small Language Models with Individual Text Corpora2026-09-11 · 个性化推荐
  10. REDSI: Addressing the Reproducibility and Evaluation Consistency of Differentiable Search Indexing for Document Retrieval2026-09-10 · 生成式推荐
  11. Exploring Bottom-Up Clustering for Creating Semantic IDs2026-09-10 · 生成式推荐
  12. Task-Blind No MORE: Multi-Task Information Flow in Unified Ranking Backbones2026-09-10 · 个性化推荐
  13. SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching2026-09-10 · 个性化推荐
  14. OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation2026-09-10 · 个性化推荐
  15. Closing the Long-Short View Gap in Sequential Recommendation without Cached History2026-09-10 · 个性化推荐
  16. FunnelAudit: Responsibility Auditing in Multi-Route Recommender Systems2026-09-10 · 个性化推荐
  17. Do All Nodes Benefit Equally from Knowledge Graphs? Adaptive Node-Aware KG Fusion for Recommendation2026-09-10 · 个性化推荐
  18. What Price Fairness? Evaluating Energy - Fairness - Accuracy Trade-off in Recommender Systems2026-09-10 · 个性化推荐
  19. Individual Text Corpora Predict User-Specific Knowledge: Benchmarks of Individualized Knowledge Simulation2026-09-10 · 个性化推荐
  20. Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval2026-09-10 · AI 搜索
  21. Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems2026-09-10 · AI 搜索
  22. Tracing Query Expansion Effects through Sparse Autoencoder Features2026-09-10 · AI 搜索
  23. EigenLI: Spectral Approximations to Late Interaction2026-09-10 · AI 搜索
  24. Tool Retrievers Are Underestimated: Annotation Expansion Reveals True Capability2026-09-10 · AI 搜索
  25. Better Together: Complementary Query Rewriting Under a Strong RAG Baseline2026-09-10 · AI 搜索
  26. Same Problem, Different Field: Cross-Domain Solution Import via Domain-Stripped Computational Fingerprints2026-09-10 · AI 搜索
  27. Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval2026-09-10 · AI 搜索
  28. Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment2026-09-10 · AI 搜索
  29. Cassette: Case-to-Case Structural Distillation for Efficient Legal Case Retrieval2026-09-10 · AI 搜索
  30. Procedural Graphs: Self-Evolving Execution Structures for LLM Agents2026-09-10 · 智能体搜索
  31. Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks2026-09-10 · 智能体搜索
  32. Explore Before Committing: Hypothesis-Guided Search for Deep Research Agents2026-09-10 · 智能体搜索
  33. Audit Without Verification: When LLM Accountability Layers Relay Rather Than Check2026-09-10 · 智能体搜索
  34. RuleMem: Active Rule Memory for Long-Term Conversational Agents2026-09-10 · 智能体搜索
  35. EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph2026-09-10 · 智能体搜索
  36. NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness2026-09-10 · 智能体搜索
  37. Beyond Agent Harnesses: Cross-Substrate Authority for Multi-Agent Systems2026-09-10 · 智能体搜索
  38. CAPMAS: Capability-Based Delegation of Privileges in Multi-Agent Systems2026-09-10 · 智能体搜索
  39. Omni Interaction Agent Technical Report2026-09-10 · 智能体搜索
  40. Sample-Guided Exact Top-K Selection for Long-Context Sparse Attention2026-09-10 · 系统与索引
  41. Miles v0.1: Production-Level Post-Training2026-09-10 · 系统与索引
  42. Elasticsearch Vector Database: Ship in minutes, scale affordably to hundreds of billions2026-09-10 · 系统与索引
  43. Analytical Resource Management for Fine-grained MoE Computation-Communication Overlap2026-09-10 · 系统与索引
  44. When to Use Encode-Prefill-Decode Disaggregation to Accelerate Multimodal Model Serving2026-09-10 · 系统与索引
  45. CUDA Toolkit 13.4 Adds Windows on Arm Support and Greater Control over Shared GPUs2026-09-10 · 系统与索引
  46. SemBridge: Compiling Consumer Observations into Cross-Stack Communication Plans2026-09-10 · 系统与索引
  47. Sharing a Fabric with Collective Communication: Two Storage Penalties in Deep Learning Training2026-09-10 · 系统与索引
  48. Poseidon: DAG-Guided Parallelism Search for LLM Pre-Training on Heterogeneous Clusters2026-09-10 · 系统与索引
  49. A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware2026-09-10 · 系统与索引
  50. WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval2026-09-09 · 生成式推荐