全部收录论文

论文 · 第 104 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 104 / 141 页

查找论文请用站内搜索。

  1. LAER-MoE: Load-Adaptive Expert Re-layout for Efficient Mixture-of-Experts Training2026-05-04 · 系统与索引
  2. Efficient Listwise Reranking with Compressed Document Representations2026-05-01 · 生成式推荐
  3. Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction2026-05-01 · 生成式推荐
  4. When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models2026-05-01 · 生成式推荐
  5. Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding2026-05-01 · 生成式推荐
  6. CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation2026-05-01 · 生成式推荐
  7. AgentSim: A Platform for Verifiable Agent-Trace Simulation2026-05-01 · 生成式推荐
  8. Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models2026-05-01 · 生成式推荐
  9. SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding2026-05-01 · 生成式推荐
  10. Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG2026-05-01 · 生成式推荐
  11. GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents2026-05-01 · 生成式推荐
  12. ProMax: Exploring the Potential of LLM-derived Profiles with Distribution Shaping for Recommender Systems2026-05-01 · 个性化推荐
  13. Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective2026-05-01 · 个性化推荐
  14. Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent2026-05-01 · 个性化推荐
  15. Explaining the "Why": A Unified Framework for the Additive Attribution of Changes in Arbitrary Measures2026-05-01 · 个性化推荐
  16. CARD: Non-Uniform Quantization of Visual Semantic Unit for Generative Recommendation2026-05-01 · 个性化推荐
  17. The Bandit's Blind Spot: The Critical Role of User State Representation in Recommender Systems2026-05-01 · 个性化推荐
  18. Factorized Latent Reasoning for LLM-based Recommendation2026-05-01 · 个性化推荐
  19. TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation2026-05-01 · 个性化推荐
  20. PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems2026-05-01 · 个性化推荐
  21. Meta-Learning and Targeted Differential Privacy to Improve the Accuracy-Privacy Trade-off in Recommendations2026-05-01 · 个性化推荐
  22. Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI2026-05-01 · AI 搜索
  23. CogRAG+: Cognitive-Level Guided Diagnosis and Remediation of Memory and Reasoning Deficiencies in Professional Exam QA2026-05-01 · AI 搜索
  24. Retrieval-Augmented LLMs for Evidence Localization in Clinical Trial Recruitment from Longitudinal EHR Narratives2026-05-01 · AI 搜索
  25. Auto-ARGUE: LLM-Based Report Generation Evaluation2026-05-01 · AI 搜索
  26. Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval2026-05-01 · AI 搜索
  27. HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models2026-05-01 · AI 搜索
  28. BioGraphletQA: Knowledge-Anchored Generation of Complex QA Datasets2026-05-01 · AI 搜索
  29. Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An Evaluation Study for Bachelor Projects2026-05-01 · AI 搜索
  30. Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge Graphs2026-05-01 · AI 搜索
  31. Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence2026-05-01 · AI 搜索
  32. SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support2026-05-01 · 智能体搜索
  33. ClawGym: A Scalable Framework for Building Effective Claw Agents2026-05-01 · 智能体搜索
  34. How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R12026-05-01 · 智能体搜索
  35. ReD-RAG: Rewritable Decomposition-Guided Iterative Retrieval-Augmented Generation for Open-Domain Multi-hop Reasoning2026-05-01 · 智能体搜索
  36. TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents2026-05-01 · 智能体搜索
  37. Training Computer Use Agents to Assess the Usability of Graphical User Interfaces2026-05-01 · 智能体搜索
  38. RAG-Enhanced Kernel-Based Heuristic Synthesis (RKHS): A Structured Methodology Using Large Language Models for Hardware Design2026-05-01 · 智能体搜索
  39. EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation2026-05-01 · 智能体搜索
  40. Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising2026-05-01 · 智能体搜索
  41. PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference2026-05-01 · 系统与索引
  42. Scheduling the Unschedulable: Taming Black-Box LLM Inference at Scale2026-05-01 · 系统与索引
  43. DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing2026-05-01 · 系统与索引
  44. Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter2026-05-01 · 系统与索引
  45. Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU2026-05-01 · 系统与索引
  46. K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance2026-04-30 · 生成式推荐
  47. From Citation Selection to Citation Absorption: A Measurement Framework for Generative Engine Optimization Across AI Search Platforms2026-04-30 · 生成式推荐
  48. Health System Scale Semantic Search Across Unstructured Clinical Notes2026-04-30 · 生成式推荐
  49. BridgeRAG: Training-Free Bridge-Conditioned Retrieval for Multi-Hop Question Answering2026-04-30 · 生成式推荐
  50. Don't Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination2026-04-30 · 生成式推荐