全部收录论文

论文 · 第 27 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 27 / 141 页

查找论文请用站内搜索。

  1. LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search2026-10-07 · 智能体搜索
  2. Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction2026-10-07 · 智能体搜索
  3. WHALE: A Simple Recipe for Joint Harness-Weight Optimization2026-10-07 · 智能体搜索
  4. Control How Your GPU Shares Work with Green Contexts2026-10-07 · 系统与索引
  5. StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs2026-10-07 · 系统与索引
  6. Tailoring the Quantization Space for 1-Bit KV Cache Compression2026-10-07 · 系统与索引
  7. Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving2026-10-07 · 系统与索引
  8. Closing the Context Gap: Activation Alignment for Tabular In-Context Learning2026-10-07 · 系统与索引
  9. How DOCA GPUNetIO Unifies GPU-Initiated Networking Across the NVIDIA Software Stack2026-10-07 · 系统与索引
  10. Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression2026-10-07 · 系统与索引
  11. Capability Scaling-Down Laws for LLM Compression2026-10-07 · 系统与索引
  12. AICR v1.0: Open, stable, and verifiable GPU cluster configuration2026-10-07 · 系统与索引
  13. MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Model Serving2026-10-07 · 系统与索引
  14. When History Misleads: Asymmetric Margin Supervision for Instruction-Guided LLM Generative Recommendation2026-10-06 · 生成式推荐
  15. Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation2026-10-06 · 生成式推荐
  16. Beyond One Epoch: Uncertainty-Weighted Sensitivity Regularization for Recommendation Models2026-10-06 · 个性化推荐
  17. MuSeR: Scalable Long-sequence Recommendation with Multi-interest Modeling2026-10-06 · 个性化推荐
  18. Adaptive Sparsity Optimization with Learnable Soft Top-K and Per-Term Thresholding for Efficient Retrieval2026-10-06 · AI 搜索
  19. Learning Query Encoders Can Be Hard Even When Vector Retrieval Is Geometrically Easy2026-10-06 · AI 搜索
  20. Benchmarking Literature Retrieval for a Model Organism: A Dictyostelium Case Study2026-10-06 · AI 搜索
  21. Query-aware routing for Cross-lingual performance gains in Encoders2026-10-06 · AI 搜索
  22. Page-Aware Retrieval-Augmented Generation for EvalLLM 2026: A Five-Variant Study on French PDFs2026-10-06 · AI 搜索
  23. The Memory Server in the Lab: 21 Studies, 125 Test Questions, +20.8 Percentage Points2026-10-06 · AI 搜索
  24. APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory2026-10-06 · 智能体搜索
  25. CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking2026-10-06 · 智能体搜索
  26. Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL2026-10-06 · 智能体搜索
  27. When History Fails to Become Experience: Action Calibration in Language Agents2026-10-06 · 智能体搜索
  28. LongCat-DeepResearch Technical Report2026-10-06 · 智能体搜索
  29. Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents2026-10-06 · 智能体搜索
  30. Counterexample Generation via Per-Theorem Symbolic Verifiers: When Imitation Hurts and Reinforcement Repairs2026-10-06 · 智能体搜索
  31. Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories2026-10-06 · 智能体搜索
  32. Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents2026-10-06 · 智能体搜索
  33. Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle2026-10-06 · 智能体搜索
  34. SOLO: Certified-Recall Metric Similarity Search with Scan-Only Sampled Inverted Lists2026-10-06 · 系统与索引
  35. MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search2026-10-06 · 系统与索引
  36. WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds2026-10-06 · 系统与索引
  37. How Full-Stack NIM Optimizations Deliver 2.5x More Users on Nemotron 3 Ultra2026-10-06 · 系统与索引
  38. vLLM x Novita AI: Chord, Faster INT4 MoE for Kimi K2.x. Up to 1.3x on H200, 2.15x on Untuned B3002026-10-06 · 系统与索引
  39. Text-Centric Post-Training for Omni-Modal Reasoning2026-10-06 · 系统与索引
  40. Large Language Continuous Diffusion Models2026-10-06 · 系统与索引
  41. How we trained the fastest DSpark for Kimi-K3 using GB300 NVL722026-10-06 · 系统与索引
  42. Watermarking in vLLM2026-10-06 · 系统与索引
  43. On-Premises Multi-Course RAG Tutoring for Business Education: Hardware-Software Trade-offs in a Campus AI Tutor2026-10-06 · 系统与索引
  44. OneTrans-V2: Unifying Retrieval, Pre-rank, and Fine-rank with One Transformer in Industrial Recommender2026-10-05 · 生成式推荐
  45. SPRINT: Single-Step Generative Recommendation via Average Probability Velocity2026-10-05 · 生成式推荐
  46. Neither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS)2026-10-05 · 生成式推荐
  47. Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops2026-10-05 · 生成式推荐
  48. Do Multilingual Encoders Produce Language-Consistent Semantic IDs?2026-10-05 · 生成式推荐
  49. Beyond the Beam: Constructive Repair and Candidate Completion for Generative Recommendation2026-10-05 · 生成式推荐
  50. X-Rec Technical Report2026-10-05 · 生成式推荐