全部收录论文

论文 · 第 14 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 14 / 141 页

查找论文请用站内搜索。

  1. Separating Thinking from Spelling for Efficient Generative Recommendation2026-10-27 · 生成式推荐
  2. SAGE: Sequence-level Adaptive Gradient Evolution for Generative Recommendation2026-10-27 · 生成式推荐
  3. TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent2026-10-27 · 生成式推荐
  4. GUIDER: Generative User Interest Discovery via Explicit Reasoning with Large Language Models2026-10-27 · 生成式推荐
  5. Hierarchical GTV Estimation: Bridging the Gap between Container-Level Ranking and Item-Level Conversion2026-10-27 · 个性化推荐
  6. iFusion: Integrating Dynamic Interest Streams via Diffusion Model for Click-Through Rate Prediction2026-10-27 · 个性化推荐
  7. MARS: Multi-resolution Adaptive Routing for Sequential Recommendation2026-10-27 · 个性化推荐
  8. Adaptive Diffusion-based Augmentation for Recommendation2026-10-27 · 个性化推荐
  9. GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation2026-10-27 · 个性化推荐
  10. Beyond Single Embedding: Modeling User Preferences as Distribution in Federated Recommendation2026-10-27 · 个性化推荐
  11. Bayesian Ensemble for Sequential Decision-Making2026-10-27 · 个性化推荐
  12. Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization2026-10-27 · 个性化推荐
  13. System One models Are Not Better Rerankers2026-10-27 · AI 搜索
  14. LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference2026-10-27 · AI 搜索
  15. Closing the Modality Gap via Simplex-Constrained Representations2026-10-27 · AI 搜索
  16. Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings2026-10-27 · AI 搜索
  17. 56 scanned pages to a cited answer in 5 minutes: RAG pipeline for the documents search cannot read2026-10-27 · AI 搜索
  18. Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model2026-10-27 · AI 搜索
  19. Scalable PDF Retrieval with Cohere Embed 5 and Qdrant Asymmetric Quantization2026-10-27 · AI 搜索
  20. Mitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text Alignment2026-10-27 · AI 搜索
  21. UAE GovTrust Scope Filtering Gains and Routing Failures in Bilingual Public Service Retrieval2026-10-27 · AI 搜索
  22. Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images2026-10-27 · AI 搜索
  23. Where Rounding Happens Matters: Rounding-Location Alignment Stabilizes LLM Reinforcement Learning2026-10-27 · 系统与索引
  24. C 2 KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference2026-10-27 · 系统与索引
  25. Qdrant 1.20 - Full-Text Search Improvements2026-10-27 · 系统与索引
  26. NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding2026-10-27 · 系统与索引
  27. KnitTrans: Coordinated Trajectory Transfer for Effective and Efficient LLM Reinforcement Learning2026-10-27 · 系统与索引
  28. How NVIDIA Mission Control 2.5 Brings Autonomous Recovery to Kubernetes2026-10-27 · 系统与索引
  29. Aquavit: Ascending Quantization for Communication-Efficient Vast-Scale Distributed Training2026-10-27 · 系统与索引
  30. Accordion: Elastic-Depth Inference via Fixed-Prefix Layer Looping2026-10-27 · 系统与索引
  31. Beyond Hotness: High-Resolution Memory Characterization of Cloud and LLM Workloads for Tiered Memory with ARM SPE2026-10-27 · 系统与索引
  32. Tile-Based Decompression in Compiled GPU Engines2026-10-27 · 系统与索引
  33. Coupling Execution Horizon and Sampling Depth in Flow-Matching VLA Policies2026-10-27 · 具身智能
  34. OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning2026-10-27 · 具身智能
  35. FLORA: An Open Model Suite for Scaling Robotics Data Engines2026-10-27 · 具身智能
  36. DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning2026-10-27 · 具身智能
  37. BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation2026-10-27 · 具身智能
  38. No Eyes, No Problem: What Does Touch Contribute to Blind Baoding Ball Manipulation?2026-10-27 · 具身智能
  39. RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning2026-10-27 · 具身智能
  40. Training in Deployment: Human-in-the-loop Online Post-Training for Robot Manipulation2026-10-27 · 具身智能
  41. Regularised RL improves sim-to-real transfer2026-10-27 · 具身智能
  42. Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning2026-10-27 · 具身智能
  43. From Item Scores to Semantic Tokens: Test-Time Collaborative Adaptation for Generative Recommendation2026-10-26 · 生成式推荐
  44. MPQ: A Message-Passing View of Post-Training Quantization2026-10-26 · 生成式推荐
  45. SynRec: Synergistic multi-domain recommendation with frequency-guided expert specialization2026-10-26 · 个性化推荐
  46. Semantically Rich, Metrically Affect-Blind: A Geometric Blind Spot in Modern Text Embedders2026-10-26 · AI 搜索
  47. What the Query Remembers: Query Abstraction Governs Lexical and Dense Retrieval of Classical Arabic Poetry2026-10-26 · AI 搜索
  48. PersonalQuery-Benchmark:Evaluating Retrieval Robustness to Personalized User Expression Differences2026-10-26 · AI 搜索
  49. MICE to Meet You: From Re-ranking Only to End-to-End Retrieval2026-10-26 · AI 搜索
  50. Collection-Date Assignment Redirects Answers in Temporal QA2026-10-26 · AI 搜索