全部收录论文
论文 · 第 48 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 48 / 141 页
查找论文请用站内搜索。
- Reducing Technician Search Burden: A Multimodal RAG for Cessna 172 Maintenance Manual
- GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval
- StocksTalk: A Voice-Enabled Conversational Agent for Structured Query Generation over Web Data
- PLASMA: A Layout-Aware Benchmark Reveals Memory Layout Matters for Graph-based ANNS on GPU
- SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents
- SPADE: Self-Play in Adaptive Synthetic Executable Environments
- Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents
- FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents
- SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
- SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation
- Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
- RAG 系统深度实战:从朴素检索到 Agentic RAG 的完整演进
- Developing NVIDIA Holoscan Applications with CLI, Skills, and AI Coding Agents
- Persona-Guided LLM Agents for Task-Oriented Dialogue
- MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing
- Redakto - The Incognito Tab for LLMs
- Fractional Decay KV-Cache: Ownership-Aware Memory Management for Improved Inference Relevancy in Dialog Systems
- 混合搜索(RRF 融合排序)
- SuTRA : Structurally-Unified Tokenization with Root Awareness
- NE-BERT: A Multilingual Language Model for Nine Northeast Indian Languages
- Evaluating Structured Information Extraction with Open Models in a High Risk Public Sector Application
- Compiler-Guided Adaptive Proof Search with Cross-Model Synergy on Context-Dependent Theorem Proving
- Post-Train NVIDIA Cosmos 3 Edge for On-Device Robot Control
- Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
- Once Generated, Ranked: End-to-End Generative Slate Recommendation with Unified Semantic-Collaborative IDs
- DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval
- ChatGPT Ads expands across Europe
- STAR: Structured Tokenization and Target-Aware Interest Representation for PCVR Prediction
- Empowering Compact LLMs with Fusion of Layer-wise Exits for Recommendation
- The Prosocial Ranking Challenge: Reducing Polarization on Social Media without Sacrificing Engagement
- On Mitigating Data Sparsity in Conversational Recommender Systems
- CARA: Cognitive Adaptive Recommendation Agent
- Towards welfare-oriented recommendations in activity-travel behavior
- Overview of the TREC 2025 Product Search and Recommendation Track
- Preference Is Not Intervention: The Structure and Stability Boundaries of Reader-Specific Evidence Utility
- Polaris: Learning to Generate Table Descriptions from Retrieval Feedback
- Sparse Coverage: Semantic Center Representations for Patent Prior-Art Retrieval
- CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method
- VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval
- There is No Theoretical Curse of Multilinguality For Embedding Space Structure
- Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents
- MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering model
- Agent Lightning v1.0: Towards Harnessed Agentic RL
- How NVIDIA scales expertise with ChatGPT Work
- Evaluating AI Agent Skill Performance with NVIDIA SkillEvaluator
- Write, Execute, Refine: From Skill Followers to Skill Optimizers via Reinforcement Learning from Execution Feedback
- Token Optimization and Context Window Management in Multi-Agent AI Workflows
- Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
- HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
- LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents