全部收录论文
论文 · 第 44 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 44 / 141 页
查找论文请用站内搜索。
- CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
- On-policy Distillation with Verifiable Reward
- On the Role of Citations in Preference Data
- When LLM judges agree, should we believe them?
- TAGR: Temporally Adaptive Generative Recommendation for Industrial Live-Streaming Advertising
- RetrievalFormer: A Dual-Encoder Transformer for Efficient Approximate Nearest Neighbor Retrieval and Cold-Item Recommendation
- RecGPT-Mobile-V2 Technical Report
- Rethinking Semantic Alignment in LLM-Enhanced Collaborative Filtering: A Spectral Decoupling Approach
- Native Multimodal Representation Learning for Click-Through Rate Prediction in E-Commerce Scenarios
- Tlow: Flow-based Item Tokenizer for Recommendation
- WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report
- Auditing Return Conditioning as a Control Knob: An Offline Diagnostic for Decision Transformer Recommendation
- Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation
- Category-aware dual graph disentanglement with multi-task learning for session-based recommendation
- AdaWidth: Query-Adaptive Embedding Width for Dense Retrieval
- Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation
- SQLite is Enough. Lexical, Semantic, and Hybrid Search with scrydb
- DPR-FL: A Dual-Path Retrieval Method with Fusion-Based Filtering and LLM Feedback
- Wontopos Tablet 2: Measuring Multilingual and Multimodal Memory Retrieval Without Lexical Matching
- Optimizing Efficiency in Multi-Stage Semantic Re-ranking Architectures
- Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution
- PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding
- PlaceSeek: Human-Centered Geospatial Retrieval of Urban Outdoor Places via Semantic Grounding and Affective Alignment
- 前沿重器:聊聊搜索系统5——召回、检索、粗排、多路召回
- Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch
- When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows
- Contextual Information Policy Optimization for Search Agents
- Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
- SearchMaster: Grounded and Regulated Self-Play for Search Agents
- Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing
- Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models
- Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
- Experiment with Qwen3.8-Flash-Next 176B Model on NVIDIA GB300 NVL72 for Agentic Coding
- Beyond Two Bytes per Letter: Tokenization Overhead in Cyrillic AI Systems
- jina-reranker-v3.5:基于混合注意力机制与自蒸馏的更高效列表式重排器
- ES 向量搜索介绍
- Best Practice Critic Optimization
- NVIDIA NVLink Fusion Brings NVHBM to Next-Generation AI Infrastructure
- MoTE: Mixture of Task Experts for Multi-Task Video Understanding
- TorchMorph: CUDA-accelerated Morphological Transforms
- LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
- Faithful Evaluation of Semantic-ID Tokenizers for Generative Recommendation
- GRAFT: Graph-Distilled Generative Retrieval for Facet-Aware Scientific Literature Exploration
- Rethinking Item Tokenization in Generative Recommenders: From Fixed Atoms to Semantic Subwords
- Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Generative Recommendation
- The Disconnect Between Better Descriptive Reasoning Trace Quality and Recommendation Effectiveness
- RAG Collapse: LLM Responses Collapse When Retrieved Documents Are Self-Authored
- The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search
- Restore LLM Inference Capacity in Seconds with Shadow Engine Recovery in NVIDIA Dynamo
- The full stack behind abundant intelligence