全部收录论文
论文 · 第 53 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 53 / 141 页
查找论文请用站内搜索。
- Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback
- LLM Agents Factory: Retrieval of Domain-Specific LLM Agents
- Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents
- InSight-doc: Agentic Visual Perception for Long-Document Understanding
- CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
- ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering
- SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information
- VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?
- Role of Personality in Conversational Information Seeking
- DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?
- Power-aware Deep Learning Model Serving with μ-Serve
- Compiler Optimization via LLM Reasoning for Efficient Model Serving
- Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension
- The Multilingual Quantization Tax: Structural Collapse and Typological Fragility in Edge SLMs
- How to Choose Full-Stack Observability for NVIDIA AI Factories
- SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
- Locally Deployable Small Language Models for Emergency Department Decision Support: A Systematic Benchmark of Fine-Tuning Strategies
- Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation
- Proceedings of the 1st Workshop on Small and Efficient Large Language Models for Knowledge Extraction (SmaLLEXT 2025) co-located with CIKM 2025, Seoul, Korea, November 14, 2025.
- Daybreak models are now available on AWS
- Preserving Item Semantics for Free: Rethinking Token Initialization in LLM-Based Generative Recommendation
- Fine-grained Semantics Integration for Large Language Model-based Recommendation
- SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems
- What Would Fix This RAG Failure? Auditing Counterfactual Response with Paired Evidence Interventions
- BOUND: Brief-Guided Corrective Preference Distillation at Search-Control Boundaries
- Guardian Crawler: Retrieval-First Knowledge Discovery with Bounded LLM Augmentation for Noisy Web Intelligence
- Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents
- BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
- Evo-Bench: Can Language Models Improve Agent Harness?
- Route AI Agent Workloads Across Models with NVIDIA NeMo Switchyard
- MetaStrategy: Generative Ranking with Executable LLM Strategies
- PushDualGen: Enabling LLMs to Generate Semantic IDs with Interpretable Copy for Industrial Push Recommendation
- IntHQ: Task-Interactive Hierarchical Query on Dual-Stream Representations for Generative Recommendation
- DREAM Technical Report
- TSPORec: Token Selection via Preference Optimization for LLM-Based Sequential Recommendation
- Give the Long-tail More SPACE: Promoting Provider Fairness in Next POI Recommendation
- Structure-Preserving Projection for Mitigating Modality Bias in LLM-Based Sequential Recommendation
- Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization
- Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation
- Testing ads in ChatGPT
- Listwise Cross-Encoder Fine-Tuning vs. Agentic Instruction Tuning for LLM Rerankers: A Systematic Study in Medical Procedure Reranking
- RVANNS: Mixed-Precision Indexing and Locality-Aware Graph Traversal on RISC-V
- Difficulty-Gated Fusion of Reasoning Views for Temporal Retrieval
- AnchorFold: A Focus-Then-Fold Framework via Recursive Attention Propagation for Efficient Multi-Vector Visual Document Retrieval
- DUTIR at SemEval-2026 Task 8: Hybrid Retrieval and Reranking for Multi-Turn RAG
- Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law
- Production RAG Evaluation: Keyword, Vector, SQL, or Hybrid Search?
- omni-macos: On-Device Omni-Modal Search on Apple Silicon
- Search over the Visual World: Persistent Visual Memory, Layered Indexes, and Source-Grounded Evidence
- How we Decide Between Keyword and Hybrid Search: 5 Enterprise Evaluation Criteria