全部收录论文

论文 · 第 57 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 57 / 141 页

查找论文请用站内搜索。

  1. SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation2026-08-06 · 个性化推荐
  2. From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking2026-08-06 · 个性化推荐
  3. LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation2026-08-06 · 个性化推荐
  4. ATLAS: Learning to Recommend Across Unseen Domains2026-08-06 · 个性化推荐
  5. Position Bias Undermines Preference Consistency in Listwise LLM-Based Reranking2026-08-06 · 个性化推荐
  6. The Value of Personalized Recommendations: Evidence from Netflix2026-08-06 · 个性化推荐
  7. Conditionally Identifiable Latent-Environment Modeling for Out-of-Distribution Recommendation2026-08-06 · 个性化推荐
  8. Circles powers telco personalization with OpenAI technology2026-08-06 · 个性化推荐
  9. Coverage Matters: MarginMerge for Compressing Multi-Vector Visual Document Retrievers2026-08-06 · AI 搜索
  10. Skill Is Not Document: Query-Conditioned Compatibility for LLM Agent Skill Routing2026-08-06 · AI 搜索
  11. Field Aware Agent Skill Retrieval2026-08-06 · AI 搜索
  12. Diagnosing and Mitigating Context Rot in Long-horizon Search2026-08-06 · AI 搜索
  13. MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale2026-08-06 · AI 搜索
  14. LegalPincite: Multi-level Legal Information Retrieval Dataset2026-08-06 · AI 搜索
  15. ISEE: Interactive Semantic Enrichment for Database Fields2026-08-06 · AI 搜索
  16. MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning2026-08-06 · AI 搜索
  17. 搜索核心算法:从召回到排序2026-08-06 · AI 搜索
  18. TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning2026-08-06 · 智能体搜索
  19. AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG2026-08-06 · 智能体搜索
  20. ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?2026-08-06 · 智能体搜索
  21. FLARE: Few-shot Learning-based Adaptive Reflective Engine2026-08-06 · 智能体搜索
  22. Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking2026-08-06 · 智能体搜索
  23. ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning2026-08-06 · 智能体搜索
  24. SkillJack: Persistent Skill Backdoors in Self-Evolving Agents2026-08-06 · 智能体搜索
  25. PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents2026-08-06 · 智能体搜索
  26. 腾讯云智能体开发平台 Agentic RAG2026-08-06 · 智能体搜索
  27. JudgeArena: A Unified Framework for Reproducible LLM-Judge Evaluation2026-08-06 · 智能体搜索
  28. ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads2026-08-06 · 系统与索引
  29. 智能开放搜索 OpenSearch:一站式智能搜索业务开发平台2026-08-06 · 系统与索引
  30. LLM Serving in the Wild: An Empirical Study of Frameworks, Methods, and System Designs2026-08-06 · 系统与索引
  31. VIBE: Vector Index Benchmark for Embeddings2026-08-06 · 系统与索引
  32. Speculative Correction: Draft-then-Refine Decoding for Diffusion Language Models2026-08-06 · 系统与索引
  33. OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models2026-08-06 · 系统与索引
  34. LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models2026-08-06 · 系统与索引
  35. When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings2026-08-06 · 系统与索引
  36. 腾讯云大模型训推平台 TI-ONE 产品概述2026-08-06 · 系统与索引
  37. Building Open Source Inference Serving Systems2026-08-06 · 系统与索引
  38. SPEAR: Selection-aware Personalized End-to-end Adaptive Rewriting and Retrieval for Community Search2026-08-05 · AI 搜索
  39. Douyin Multimodal Embedding Model Technical Report2026-08-05 · AI 搜索
  40. CeQe: Grounding Lexical Retrieval in Semantic Evidence2026-08-05 · AI 搜索
  41. Advancing Relevance Measurement with Vision-Language Models for Web-Scale Search2026-08-05 · AI 搜索
  42. Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget2026-08-05 · AI 搜索
  43. Index-Time Prefix Injection for Multi-Tenant Retrieval: Improving Search Relevance Without Model Fine-Tuning2026-08-05 · AI 搜索
  44. SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams2026-08-05 · AI 搜索
  45. Hierarchical BM25: Lexical Search at Billion-Document Scale2026-08-05 · AI 搜索
  46. UEmbed: Unified Sparse and Dense Multimodal Embeddings2026-08-05 · AI 搜索
  47. From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines2026-08-05 · AI 搜索
  48. Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents2026-08-05 · 智能体搜索
  49. Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents2026-08-05 · 智能体搜索
  50. Verification Without Sufficiency: Per-Chunk Filtering Fails on Multi-Hop RAG, and Decomposition Repairs It2026-08-05 · 智能体搜索