全部收录论文
论文 · 第 72 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 72 / 141 页
查找论文请用站内搜索。
- 知识库检索 Agent
- 用两行代码将 AgentRun 集成到你的应用
- Accelerating End-to-End Co-Folding Performance with NVIDIA BioNeMo Agent Toolkit
- How Deutsche Telekom is rewiring telecommunications with AI
- RTP-LLM: High-Performance Alibaba LLM Inference Engine
- Serving Models, Fast and Slow: Optimizing Heterogeneous LLM Inferencing Workloads at Scale
- Reducing High-Bandwidth Memory Bottlenecks in JAX-Based LLM Training with Host Offloading
- Kernel Fusion in NVIDIA CUDA: Optimizing Memory Traffic and Launch Overhead
- AI Model Co-Design: Hardware-Friendly LLM Design
- Cache-Resident LLM Inference in GB-Scale Last-Level Caches
- 对象存储向量检索:面向非结构化数据的全托管语义检索
- From Tokens to Energy Flexibility: Quantization-Enabled Demand Response for Data Centers with LLM Inference Workloads
- Interpretable Uncertainty for Adaptive Retrieval and Reasoning in Question Answering
- Evaluating RAG Metrics in Applied Contexts: An Experiment, Its Findings and Its Limitations
- TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models
- Co-LMLM: Continuous-Query Limited Memory Language Models
- When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning
- Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity
- Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?
- GPT-5.6: Frontier intelligence that scales with your ambition
- InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs
- Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
- Field Matters: A Lightweight LLM-enhanced Method for CTR Prediction
- When and How to Ask: Dynamic Preference Elicitation Strategies for Conversational Recommendation
- Seeing and Reflecting: Multimodal Memory-Enhanced Agent Collaboration for Recommendation
- 推荐系统走向新范式:快手技术沙龙聚焦生成式推荐技术落地
- Ad Headline Generation using Self-Critical Masked Language Model
- SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation
- R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement
- From Text to Parameters: Predicting Item Parameters from Embedding Regularization with Reliability and Design Ceilings
- Capturing token IDs during agentic interactions for better reinforcement learning
- Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning
- Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering
- 5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control
- MTEB-BR: A Text Embedding Benchmark for Brazilian Portuguese
- ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
- Human-in-the-Loop Nugget Annotation for Accountable LLM-as-a-Judge Evaluations
- Riemannian Geometry for Pre-trained Language Model Embeddings
- MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
- Future Confidence Distillation in Large Language Models
- Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
- The power of collaboration: How we can reduce traffic congestion
- From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization
- From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
- How Search Quality Shapes RL Outcomes
- A Roadmap for Agentic Recommender Systems
- Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation
- 阿里云百炼推出Agentic RAG服务,让AI的知识检索和回答更精准
- A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
- ChatGPT is now a partner for your most ambitious work