全部收录论文

论文 · 第 32 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 32 / 141 页

查找论文请用站内搜索。

  1. Knowledge-as-Skill: A Structural Design for Autonomous Knowledge-Base Use by LLM Agents2026-09-24 · 智能体搜索
  2. MoM: Memory of Memory2026-09-24 · 智能体搜索
  3. FinFIRST: Benchmarking Search Agents for Financial Information Retrieval, Sourcing and Traceability2026-09-24 · 智能体搜索
  4. The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks2026-09-24 · 智能体搜索
  5. Self-Cleaning and Captured Anyway: One Measured Primitive for Error in a Store an Agent Writes to Itself, and What a Falling Score Actually Measures2026-09-24 · 智能体搜索
  6. Recursive self-improvement of AI research agents2026-09-24 · 智能体搜索
  7. Agensh: Scaling Organizational Intelligence to 1,024 Agents2026-09-24 · 智能体搜索
  8. Ringg’s AI agents resolve up to 65% of customer calls with OpenAI2026-09-24 · 智能体搜索
  9. How SWE-Serve Exposes the Gap Between Local Tests and Live Serving2026-09-24 · 系统与索引
  10. Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs2026-09-24 · 系统与索引
  11. Global AI routing with <1% overhead on multi-cluster GKE Inference Gateway2026-09-24 · 系统与索引
  12. ChainDoRA: Tensor-Train Factorized Weight-Decomposed Low-Rank Adaptation for Parameter-Efficient LLM Fine-Tuning2026-09-24 · 系统与索引
  13. Manage Kubernetes Node Fleets with NodeWright2026-09-24 · 系统与索引
  14. Enabling Private High-Performance Production AI Inference with NVIDIA Confidential Computing2026-09-24 · 系统与索引
  15. 技术更新 - 中国科学技术大学大模型公共服务平台用户指南2026-09-24 · 系统与索引
  16. Validate GPU Cluster Readiness Before AI Workloads Land2026-09-24 · 系统与索引
  17. Training a Language Model End-to-End in Rust: An Experience Report2026-09-24 · 系统与索引
  18. LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay2026-09-24 · 系统与索引
  19. Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel Decoding2026-09-22 · 生成式推荐
  20. Contexts, Conversations & Connections: Spotify Research at RecSys 20262026-09-22 · 生成式推荐
  21. Dual stream adaptive sequential recommendation2026-09-22 · 个性化推荐
  22. Auto-Bidding with Disentangled Advertiser Profiles and Train-Free Adaptation2026-09-22 · 个性化推荐
  23. Do We Care About Personalization and Explainability? An Interview Study with News Recommendation Engineers2026-09-22 · 个性化推荐
  24. Adaptive Preference Modeling via Explicit Indirect Relational Learning for Personalized Fashion Matching2026-09-22 · 个性化推荐
  25. MAGIC: Marginal-Guided Compression with Optimal Transport for Efficient Visual Document Retrieval2026-09-22 · AI 搜索
  26. Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention2026-09-22 · AI 搜索
  27. Candidate Recall in Large-Scale Code-to-Code Retrieval: A Comprehensive Benchmark2026-09-22 · AI 搜索
  28. Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale2026-09-22 · 智能体搜索
  29. Adaptive Instructed-Retriever: Frontier-Quality Search at 2x Lower Latency2026-09-22 · 智能体搜索
  30. Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency2026-09-22 · 智能体搜索
  31. When Better Turns Do Not Make Better Agents: Diagnosing the Gap Between Next-Turn Metrics and Workflow Success2026-09-22 · 智能体搜索
  32. How to Evaluate AI Agents From Tool Calls to Task Completion2026-09-22 · 智能体搜索
  33. Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces2026-09-22 · 智能体搜索
  34. AutoRecLab: Describe the Experiment, Get the Code!2026-09-22 · 智能体搜索
  35. How V7 gives AI agents institutional memory2026-09-22 · 智能体搜索
  36. Rewarding Efficient Reasoning Improves Abstention on Underspecified Tasks in Reasoning Models2026-09-22 · 智能体搜索
  37. From Task Success to Productive Success: Evaluating Human-AI Collaboration by Quality and Cost2026-09-22 · 智能体搜索
  38. Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale2026-09-22 · 系统与索引
  39. Open-Sourcing Rebalancer: A Generic, High-Performance Library for Solving Assignment Problems2026-09-22 · 系统与索引
  40. Scaling Forced Alignment to End-User Devices2026-09-22 · 系统与索引
  41. Simplifying Model Serving Across Multiple GPUs with NVIDIA TensorRT Multi-Device Integration in NVIDIA Dynamo-Triton2026-09-22 · 系统与索引
  42. Reading Less While Writing: A Closed-Form Bandwidth Dial for Streaming Multimodal Decoders2026-09-22 · 系统与索引
  43. Do small language models know what they don't know?2026-09-22 · 系统与索引
  44. mnemosyne systems: orangu 1.3.02026-09-22 · 系统与索引
  45. UniPolicy: Unified Objective-Specific Policies for Generative Search Advertising2026-09-21 · 生成式推荐
  46. TATK: Triple-Aware Top-K Learning with Knowledge-Grounded Verification for LLM-based Sequential Recommendation2026-09-21 · 生成式推荐
  47. Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignment2026-09-21 · 生成式推荐
  48. Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles2026-09-21 · 生成式推荐
  49. Safety as a Constraint: Fine-Tuning a LLM Recommender to Explain Itself2026-09-21 · 生成式推荐
  50. Following the Preference, Missing the Optimum: Compliance Without Optimization in AI Housing Recommendation2026-09-21 · 生成式推荐