全部收录论文

论文 · 第 130 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 130 / 141 页

查找论文请用站内搜索。

  1. Aligning Language Models from User Interactions2026-03-17 · AI 搜索
  2. Asynchronous Verified Semantic Caching for Tiered LLM Architectures2026-03-17 · AI 搜索
  3. NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval2026-03-17 · AI 搜索
  4. Task-Specific Knowledge Distillation via Intermediate Probes2026-03-17 · AI 搜索
  5. Test-Time Strategies for More Efficient and Accurate Agentic RAG2026-03-17 · AI 搜索
  6. Towards AI Search Paradigm2026-03-17 · AI 搜索
  7. LMEB: Long-horizon Memory Embedding Benchmark2026-03-17 · AI 搜索
  8. InterDeepResearch: Enabling Human-Agent Collaborative Information Seeking through Interactive Deep Research2026-03-17 · AI 搜索
  9. Diagnosing Retrieval Bias Under Multiple In-Context Knowledge Updates in Large Language Models2026-03-17 · AI 搜索
  10. ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning2026-03-17 · 智能体搜索
  11. Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation2026-03-17 · 智能体搜索
  12. Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents2026-03-17 · 智能体搜索
  13. Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization2026-03-17 · 智能体搜索
  14. AI Planning Framework for LLM-Based Web Agents2026-03-17 · 智能体搜索
  15. Prompt Injection as Role Confusion2026-03-17 · 智能体搜索
  16. XSkill: Continual Learning from Experience and Skills in Multimodal Agents2026-03-17 · 智能体搜索
  17. OpenSage: Self-programming Agent Generation Engine2026-03-17 · 智能体搜索
  18. Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned2026-03-17 · 智能体搜索
  19. ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning2026-03-17 · 智能体搜索
  20. 98× Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router2026-03-17 · 系统与索引
  21. Serving Hybrid LLM Loads with SLO Guarantees Using CPU-GPU Attention Piggybacking2026-03-17 · 系统与索引
  22. Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study2026-03-17 · 系统与索引
  23. TaxBreak: Unmasking the Hidden Costs of LLM Inference Through Overhead Decomposition2026-03-17 · 系统与索引
  24. CMoE: Converting Mixture-of-Experts from Dense to Accelerate LLM Inference2026-03-17 · 系统与索引
  25. Cost-Efficient Multimodal LLM Inference via Cross-Tier GPU Heterogeneity2026-03-17 · 系统与索引
  26. EWSJF: An Adaptive Scheduler with Hybrid Partitioning for Mixed-Workload LLM Inference2026-03-17 · 系统与索引
  27. LLM Query Scheduling with Prefix Reuse and Latency Constraints2026-03-17 · 系统与索引
  28. KernelFoundry: Hardware-Aware Evolutionary GPU Kernel Optimization2026-03-17 · 系统与索引
  29. Google Cloud AI infrastructure at NVIDIA GTC 20262026-03-17 · 系统与索引
  30. Beyond Interleaving: Causal Attention Reformulations for Generative Recommender Systems2026-03-14 · 生成式推荐
  31. Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation2026-03-14 · 生成式推荐
  32. UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Optimization2026-03-14 · 生成式推荐
  33. LASER: An Efficient Target-Aware Segmented Attention Framework for End-to-End Long Sequence Modeling2026-03-14 · 个性化推荐
  34. CAMMSR: Category-Guided Attentive Mixture of Experts for Multimodal Sequential Recommendation2026-03-14 · 个性化推荐
  35. FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning2026-03-14 · 个性化推荐
  36. Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation2026-03-14 · 个性化推荐
  37. Social Knowledge for Cross-Domain User Preference Modeling2026-03-14 · 个性化推荐
  38. Sharpness-Aware Minimization for Generalized Embedding Learning in Federated Recommendation2026-03-14 · 个性化推荐
  39. BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs2026-03-14 · AI 搜索
  40. LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum2026-03-14 · AI 搜索
  41. Rank1: Test-Time Compute for Reranking in Information Retrieval2026-03-14 · AI 搜索
  42. A Systematic Study of Pseudo-Relevance Feedback with LLMs2026-03-14 · AI 搜索
  43. Constraint-Aware Generative Re-ranking for Multi-Objective Optimization in Advertising Feeds2026-03-14 · AI 搜索
  44. Differentiable Geometric Indexing for End-to-End Generative Retrieval2026-03-14 · AI 搜索
  45. TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation2026-03-14 · AI 搜索
  46. Seq vs Seq: An Open Suite of Paired Encoders and Decoders2026-03-14 · AI 搜索
  47. Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval2026-03-14 · AI 搜索
  48. Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankers2026-03-14 · AI 搜索
  49. Meta-Reinforcement Learning with Self-Reflection for Agentic Search2026-03-14 · 智能体搜索
  50. Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents2026-03-14 · 智能体搜索