全部收录论文

论文 · 第 38 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 38 / 141 页

查找论文请用站内搜索。

  1. Evidence Integration in Large Language Models2026-09-08 · 智能体搜索
  2. Search2Skill: Skill Distillation Beyond Knowledge Boundaries Via Rubric-Based Reinforcement Learning2026-09-08 · 智能体搜索
  3. PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent2026-09-08 · 智能体搜索
  4. Cross-Domain Hybrid OPD for Generalizable Search Agents2026-09-08 · 智能体搜索
  5. GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion2026-09-08 · 智能体搜索
  6. Advanced CUDA Graph Techniques in SGLang2026-09-08 · 系统与索引
  7. Fast Engine Recovery: Sub-Second Engine Restart for SGLang via Weight Cache Daemon2026-09-08 · 系统与索引
  8. HPC-Ops × SGLang: High-Performance Attention, Router GEMM, and MoE Kernels from Tencent Hunyuan2026-09-08 · 系统与索引
  9. Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters2026-09-08 · 系统与索引
  10. Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving2026-09-08 · 系统与索引
  11. Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs2026-09-08 · 系统与索引
  12. Unified Radix Cache: One Tree for Hybrid Model Prefix Caching2026-09-08 · 系统与索引
  13. CIERA: Cross-Iteration Exponent Reuse for Lossless Allgather in Sharded MoE Training2026-09-08 · 系统与索引
  14. Tuning Collective Patterns to Alleviate Congestion in Shared AI Clusters2026-09-08 · 系统与索引
  15. What Attention Recalls and Recurrence Controls in Hybrid Language Models2026-09-08 · 系统与索引
  16. LLM4AIGQ: LLM-based AI Guidance Query Generation Framework for Multi Interest Mining2026-09-07 · 生成式推荐
  17. EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation2026-09-07 · 生成式推荐
  18. SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendation2026-09-07 · 生成式推荐
  19. HypRQ-VAE: Hyperbolic Item Indexing for Long-Tail-Aware Generative Recommender Systems2026-09-07 · 生成式推荐
  20. The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations2026-09-07 · 生成式推荐
  21. UniCon: A Unified Context-Centric Modeling Paradigm for CTR Prediction2026-09-07 · 个性化推荐
  22. One Size Does Not Fit All: Adaptive Interest Representation Learning for Multi-interest Recommendation2026-09-07 · 个性化推荐
  23. DISR: Distributional Item Representations for Sequential Recommendation2026-09-07 · 个性化推荐
  24. Comparative Analysis and Unified Evaluation Framework of User Simulators for Realistic Behaviour Modelling2026-09-07 · 个性化推荐
  25. DoPR: Reusable Compressed Document Prefixes for Efficient LLM Reranking2026-09-07 · AI 搜索
  26. From Topical Relevance to Answerability: Entailment Distillation for Conversational Retrieval2026-09-07 · AI 搜索
  27. CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation2026-09-07 · AI 搜索
  28. Retrieval Grounding Latent Reasoning for Dense Retrieval2026-09-07 · AI 搜索
  29. Comparing Retrieval Methods for Academic Advisor Discovery: A Six-Method Study of 768 CS Faculty Profiles Across 9 US Universities2026-09-07 · AI 搜索
  30. CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAG2026-09-07 · AI 搜索
  31. Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models2026-09-07 · 智能体搜索
  32. When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents2026-09-07 · 智能体搜索
  33. DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training2026-09-07 · 智能体搜索
  34. Agentic Search. More accurate and efficient results from your AI systems.2026-09-07 · 智能体搜索
  35. Building a Memory-Driven Agent with NVIDIA NemoClaw2026-09-07 · 智能体搜索
  36. Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory2026-09-07 · 智能体搜索
  37. KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents2026-09-07 · 智能体搜索
  38. Speculative Macro Commit for Faster Tool-Using Agents2026-09-07 · 智能体搜索
  39. Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments2026-09-07 · 智能体搜索
  40. Research acceleration: The view inside OpenAI2026-09-07 · 智能体搜索
  41. Fast Embeddings on GPUs2026-09-07 · 系统与索引
  42. AInfer-PD: Communication-Safe In-Place Prefill-Decode Multiplexing for Distributed MoE Rollouts2026-09-07 · 系统与索引
  43. FlowTT: Exploiting Computation Flow Reuse in Irregular Tensor-Train Embedding2026-09-07 · 系统与索引
  44. MeanField Surrogate Modeling for Scalable Runtime Scheduling of Concurrent Heterogeneous AI Inference on Shared GPUs2026-09-07 · 系统与索引
  45. RT-HiSS: Ray Tracing Accelerated High Dimensional Vector Similarity Searches2026-09-07 · 系统与索引
  46. Latency-Aware Orchestration for Multi-Agent LLM Workflows on Heterogeneous GPUs2026-09-07 · 系统与索引
  47. Every Kernel Is a Join: Automatic Multi-GPU Parallelism for AI Computations in Einsummable2026-09-07 · 系统与索引
  48. mzCache: On-Device LLM Memory Management under Multitasking2026-09-07 · 系统与索引
  49. CREDIT: Cost-guided Reduction-reuse with Efficient DSMEM Inter-CTA Tiling2026-09-07 · 系统与索引
  50. Frontier Reasoning Reaches the Edge: How to Deploy and Optimize Models on NVIDIA Jetson2026-09-07 · 系统与索引