全部收录论文

论文 · 第 25 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 25 / 141 页

查找论文请用站内搜索。

  1. RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees2026-10-12 · 智能体搜索
  2. Programmatic Search Agents: Extending Agentic Search Beyond Query Reformulation2026-10-12 · 智能体搜索
  3. Asana cuts model costs 76x in browser tests with GPT-6.1 Sol2026-10-12 · 智能体搜索
  4. Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads2026-10-12 · 智能体搜索
  5. ATLAS: Evaluating Agents on Search-Intensive Tasks2026-10-12 · 智能体搜索
  6. PhantomEnvironments: Training LLM Agents in Fictional Worlds2026-10-12 · 智能体搜索
  7. Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning2026-10-12 · 智能体搜索
  8. MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents2026-10-12 · 智能体搜索
  9. Mechanism-centric cross-domain retrieval for scientific discovery: LLM agents for structural isomorphism beyond semantic similarity2026-10-12 · 智能体搜索
  10. Sophos cuts threat investigation time by 96% with OpenAI Daybreak2026-10-12 · 智能体搜索
  11. AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation2026-10-12 · 系统与索引
  12. BARQ: Balanced Codebook Refinement for Low-Bit LLM Quantization2026-10-12 · 系统与索引
  13. FailBench: Evaluating Fault Tolerance Across Distributed Training Architectures2026-10-12 · 系统与索引
  14. ML Drift: Next-Gen GPU AI/ML Inference at the Edge2026-10-12 · 系统与索引
  15. XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization2026-10-12 · 系统与索引
  16. SpecForge v0.3.0: a Unified Disaggregated and Colocated Speculative Decoding Stack, and New Open SpecBundle Draft Models2026-10-12 · 系统与索引
  17. SGLang and Miles on NVIDIA Vera Rubin2026-10-12 · 系统与索引
  18. Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis2026-10-12 · 系统与索引
  19. Cross-Facility LLM Pre-training on HPC: Elastic Aggregation, Data Leasing, and Queue-Aware Placement2026-10-12 · 系统与索引
  20. QuantaSpike: Short-Window Spike-Driven Quantization for Large Language Models2026-10-12 · 系统与索引
  21. Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition2026-10-09 · 生成式推荐
  22. Generate What You Can Trust: Content Credibility in Generative Recommenders2026-10-09 · 生成式推荐
  23. LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation2026-10-09 · 个性化推荐
  24. ScalarLens: Numerical Embeddings with Stable Coordinates and Contextual Responses for CTR Prediction2026-10-09 · 个性化推荐
  25. Reading Position Is the Baseline to Beat: A Time-Ordered Evaluation of Personalised Highlight Prediction2026-10-09 · 个性化推荐
  26. Behavior-Evidence-Based Dynamic User Feature Calibration for Unified-Token Click-Through Rate Prediction2026-10-09 · 个性化推荐
  27. Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion2026-10-09 · 个性化推荐
  28. Finding the Right Balance: Relevance and Diversity in LLM Retrieval2026-10-09 · AI 搜索
  29. The Impact of Backbone Evolution on LLM-Based Relevance Assessments2026-10-09 · AI 搜索
  30. Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora2026-10-09 · AI 搜索
  31. What Transfers from a VLM Teacher? Comparing Supervision Signals for Visual Document Retrieval2026-10-09 · AI 搜索
  32. Towards Explaining Query Expansion Performance in Information Retrieval2026-10-09 · AI 搜索
  33. Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives2026-10-09 · AI 搜索
  34. From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA2026-10-09 · AI 搜索
  35. Inverting Multi-Vector Visual Document Indices2026-10-09 · AI 搜索
  36. From High Recall to High Utility: Dataset-Adaptive Post-Processing of LLM-Generated Customer Intents2026-10-09 · AI 搜索
  37. ExperienceIndex: Artifact-Grounded Memory2026-10-09 · 智能体搜索
  38. SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles2026-10-09 · 智能体搜索
  39. MIMESIS: Learning User Simulators as Training Environments for Interactive Agents2026-10-09 · 智能体搜索
  40. UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy2026-10-09 · 智能体搜索
  41. RunningTab: Direct Workspace Interaction with Environment-Side Tabs2026-10-09 · 智能体搜索
  42. Building Reliable Data Analytics Agents: Lessons from the KDD Cup2026-10-09 · 智能体搜索
  43. ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation2026-10-09 · 智能体搜索
  44. From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery2026-10-09 · 智能体搜索
  45. System Switch: When Should a Fast Decision Model Stop and Think?2026-10-09 · 智能体搜索
  46. BEACON-SP: Ontology-Grounded GraphRAG Framework for Clinical Suicide Risk Assessment2026-10-09 · 智能体搜索
  47. Quantize by Drift: Label-Free Mixed-Precision Post-Training Quantization for Text Embedders2026-10-09 · 系统与索引
  48. Building Navigable Graphs Without Search in Three Composable Stages2026-10-09 · 系统与索引
  49. Same Text, Different Prediction: Serving-Context Nondeterminism in Text Classifiers2026-10-09 · 系统与索引
  50. LRCC: Generalizing Low-Rank Compression with Conditional Computation2026-10-09 · 系统与索引