全部收录论文
论文 · 第 76 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 76 / 141 页
查找论文请用站内搜索。
- Self-Evolving Deep Research via Joint Generation and Evaluation
- 2026 年开源 Agent 工具包选型指南:延迟、审计、可移植性与语言栈
- Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving
- FlexNPU: Transparent NPU Virtualization for Dynamic LLM Prefill-Decode Co-location
- Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference
- CacheFlow: Efficient LLM Serving with 3D-Parallel KV Cache Restoration
- Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression
- dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats
- EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms
- Three trends from MLSys 2026
- Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory
- STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation
- When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems
- ICML 2026 | 美团技术团队学术论文精选
- Program-as-Weights: A Programming Paradigm for Fuzzy Functions
- ACL 2026 精选论文分享:美团履约团队前沿技术专场
- GR2 Technical Report
- MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders
- IntentTune: Using user demand and personalization to resolve "unknown" query intents for e-commerce search
- AI Innovations in Meta Ads Ranking Driving Advertiser Performance
- Planning over Matrix-Factorization MDPs for Candidate Generation
- CoPersona: Collaborative Persona Graphs for Robust LLM Personalization
- 美团技术团队顶会论文分享:搜索推荐ASX专场
- Bi-NAS: Towards Effective and Personalized Explanation for Recommender Systems via Bi-Level Neural Architecture Search
- 快手向左,阿里向右|2025大模型融入推荐系统的两条路线深度解读
- Monosemanticity in Recommender Systems
- Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale
- Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-turn RAG
- Deep Learning to Rank in Industrial Search Engines, Recommender Systems, and Online Advertising - An Overview and New Perspectives
- HNSW with Accuracy Guarantees Using Graph Spanners -- A Technical Report
- Hybrid Search: BM25, Vector & Reranking Reference 2026
- Learned Sparse Retrieval and Dense-Sparse Hybrid: Why Agents Need Both Vocabularies
- Embedding Inference Attack
- mamabench and mamaretrieval: Benchmarks for Evaluating Medical Retrieval-Augmented Generation in Maternal, Neonatal, and Reproductive Health
- Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts
- 美团 LongCat-2.0 正式发布:在国产算力集群上完成全流程训练与推理的万亿参数模型
- Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG
- Bringing Agentic Search to Earth Observation Data Discovery
- BaRA: Budget-constrained and Reliable Web Data Collection Agent
- SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use
- LongCat 开源 VitaBench 2.0:长期动态智能体基准新标杆
- 用 EdgeOne Makers 构建与托管 Agent:从 RAG 检索到智能助手
- Safeguarding LLM Agents from Misalignment through Provenance Analysis
- PACE: A Proxy for Agentic Capability Evaluation
- Mastering Agentic Techniques: AI Agent Reinforcement Learning
- AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
- HBM Is Not All You Need: Efficient Disaggregated LLM Serving across Memory-heterogeneous Accelerators
- Kara: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression
- Meta’s AI Storage Blueprint at Scale
- ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill