全部收录论文
论文 · 第 35 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 35 / 141 页
查找论文请用站内搜索。
- Cost Characterization of Vertically Partitioned Federated Knowledge Graphs
- How NVIDIA NVLink 6 Delivers Multi-Layer Resiliency for AI Factories
- Scaling Federated Learning Across Docker, Kubernetes, and Slurm with NVIDIA FLARE
- Token Merging for Multilingual Speech Recognition: A Systematic Study Across Model Scale and Fine-Tuning
- How NVIDIA Groq 3 LPX Deterministic Execution Drives Power-Efficient High-Interactivity Inference on NVIDIA Vera Rubin
- InitGen: Candidate Generation for Interaction Initiation in Intelligent Assistants
- Preference-Drift-Aware Subsequence Learning and Hierarchical Context Fusion for Long-Sequence Generative Recommendation
- Recommendation Retrievers Need Verifiers: Universal Generative Reranking for Sequential Recommendations
- OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation
- ChronicleRec: Pre-training Temporally Anchored Tokens for Lifelong User Modeling
- PinDCO: Whole-Page Aware Dynamic Creative Optimization at Scale
- MIMA: Multi-Interest Recommendation via Multi-Positive Exclusive Assignment
- A Historical Corpus Is Not a Historical System: Auditing Hindsight Leakage in Stateful Data Discovery
- CueMem: Cue-Guided Context Reconstruction for Long-Term Conversational Memory
- Learning the Lake: Reliable Experience for Adaptive Data Product Discovery
- EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development
- Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy
- MemRetriever: Learning to Search, Reflect, and Retrieve from Long-Term Memory
- Iris: Climbing to the Search Frontier
- GAUGE: When Not to Trust LLM-as-a-Judge in User-Simulated Evaluation of Task-Oriented Agents
- ToolGrad: Efficient tool-use dataset generation with textual "gradients"
- Autonomous Research for Open-Ended Problems: A Case Study on Telecom Ticket Retrieval
- Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis
- Persistent Teacher Anchoring for Tool-Using Agents
- R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration
- Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering
- AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization
- Argus: Orchestrating Cross-Layer GPU Performance Measurements around Semantic Regions
- ForgeMegakernel: A General Framework for Efficient Auto-Regressive Model Decode Megakernels
- SGLang and Miles Add Day-0 Support for DeepSeek-V4.1
- Unleashing the Power of Equality Saturation for Tensor Program Superoptimization
- Accelerating Dropless MoE Training in JAX with NVIDIA Transformer Engine
- Dissecting GPU Utilization for LLM Inference on Nvidia Hopper
- Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models
- HoliBench: A Cross-Platform Benchmarking and Deployment Toolkit for Foundation Models in CPS-IoT Applications
- Infer-forge: Harness, Loop, and Graph Engineering Around SGLang
- EAGER: Enrich-and-Align Generative Query Recommendation from Clicked Items in E-commerce Search
- UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems
- FedHUR: Learning Hierarchical Utility-Guided Client Relations for Personalized Federated Recommendation
- A Multi-Source Ensemble Approach to Candidate Generation for Alternative Vacation Rental Property Recommendations
- Depth-Selective Residual Routing for Dense Retrieval: Block Attention Residual Adapters under Cross-Domain and Quantization Controls
- VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents
- AREX: Towards a Recursively Self-Improving Agent for Deep Research
- CIVI: A Framework for Diagnosing Search Agent Failures in Civic Information
- 《Agent 评测白皮书》系列01:Agent 评测全览
- REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
- Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs
- Deadline-Aware Adaptive Prefill Chunking for Efficient Large Language Model Serving
- Phase-Decoupled, Model-Calibrated Power Control for Disaggregated LLM Serving
- Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Serving-Time Weight Compression