全部收录论文
论文 · 第 30 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 30 / 141 页
查找论文请用站内搜索。
- Tracing Agent Harness Behavior with NVIDIA NeMo Relay
- From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework
- When Successful Memories Mislead Embodied Agents:Memory Adaption For Task-Conditioned Execution
- Can Agents Design Libraries for Agents?
- EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?
- Add Runtime Controls to AI Agents with NVIDIA OpenShell
- Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
- SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving
- Telescopic Language Models
- AutoLoCo: Communication Efficient Distributed LLM Training via Adaptive Synchronization
- Lower the Cost of Building and Running Visual AI Agents with NVIDIA VSS Blueprint 3.3
- Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving
- Scheduling Recursive Reasoning in Looped Transformers
- Expanding AI Storage Access with NVIDIA cuObject and the NVIDIA SCADA Server SDK
- Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention
- What Makes Recurrence Effective in Looped Language Models?
- GRP v0.1 Technical Report
- Learning Better Reasoning for Generative Recommendation with Semantic IDs
- Do Evidence-Reading Diagnostics Improve Interface Selection in Small LLM Recommenders?
- HELIX: Purified and Unified - Rethinking Feature Interaction and Sequence Modeling for Large-Scale Recommendation
- A Unified Generative Re-ranking Framework with Adaptive Multi-objective Fusion
- Bridge the Unseen Gap: Enhancing Non-overlapping Cross-domain CTR Prediction via Profile Retrieval
- Generated Query Expansion Still Helps Strong Sparse Retrieval: A Controlled Study with SPLADE-v3
- MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment
- Financial Evidence Crowding: Diagnosing and Mitigating Constraint-Induced Displacement in Retrieval-Augmented Generation
- AI-based semantic search improves e-commerce product search more consistently when augmenting keyword matching than when replacing it
- Retrieval Sensitivity to Identity Signals in Queries
- Effective Dense Retrieval using Only In-Context Examples
- TSG Suggester: Tree-Structured Knowledge-Graph Retrieval for Troubleshooting Guide Recommendation in Cloud Incident Management
- The Training Infrastructure Behind AI-Powered Job Search: 8X Faster Multi-Teacher Distillation
- Why content extraction still matters in the GenAI era
- Post-Generation Verification Dominates Retrieval Optimization: A 2^4 Factorial Ablation of RAG Pipeline Features
- Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG
- Follow the Entities: A Corpus Map for Agentic Search
- Socrates-RAG: Premise-Directed Inquiry against Coordinated Evidence Poisoning
- BITEM at the NTCIR-19 R2C2 Task: Predicting Confidence from Agentic RAG Pipeline Signals
- Structured Interaction, Visual Localization, and Robust Execution for Complex Web Tasks: A Technical Report on the WebRetriever Challenge
- Backdoor in the Loop: Compromising Agentic Search via Malicious Retrievers
- Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
- 《AgentScope 2.0实战指南》09 - RAG 检索增强生成
- EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory
- Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing
- Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning
- TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models
- TabFM: A Zero-Shot Foundation Model for Tabular Data
- How NVIDIA DSX MaxLPS Maximizes AI Factory Throughput and Efficiency
- FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution
- Chinese-Jev: Bringing System One Model to Chinese-Language Tasks
- 搜推一体架构设计:搜索与推荐怎么融合?四层架构与四阶段落地
- AI Native by Design: Lessons Learned from Building NVIDIA TensorRT Model Connect