全部收录论文
论文 · 第 2 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 2 / 141 页
查找论文请用站内搜索。
- VecDBLens: An Evaluatology-Based Framework for Vector Database Diagnosis
- Snoopie: A Multi-GPU Communication Profiler and Visualizer
- SubGPU Pipelining: Intra-GPU Fine-Grained Spatial Parallelism for LLM Inference
- GC-MoE on SM120: Overlapping Expert-Parallel Token Dispatch with Warp-Level FP8xFP4 Block-Scaled MMA on Consumer Blackwell
- Towards Green Text Generation: Memory-Based Speculative Decoding
- When One GPU Isn’t Enough: Serving GLM-5.3 Across Two NVIDIA DGX Stations with vLLM
- 如何在“不能出错”的系统里使用 AI Coding?分布式存储实践与边界
- What Makes a VLA Reactive? A Study of Execution Strategies for Dynamic Manipulation
- Scaling VLA Serving Under Robotic Execution Constraints
- Learning Low-Latency Action Verification for Frozen Vision-Language-Action Models
- ILA: A Transferable Interface-Level Adapter for Compliant Humanoid Motion Tracking
- SALA: Semantically Aligned Latent Actions Enable Dual-Axis Scaling of Embodied Foundation Models
- FORGE: Force-Aware Multi-Granularity Control for Efficient Humanoid Loco-Manipulation
- I See What You Want: Decoding Hierarchical Operator Intent from Visual Teleoperation History
- Adapt Human Motion for Robots with NVIDIA SOMA Retargeter
- Build a Robot Pick-and-Place Simulation with SimReady Assets
- Six AGIBOT G2 Robots Complete 1,730 Tasks in 24-Hour Shanghai Convenience Store Trial
- Request-Only Optimization for Recommendation Systems
- From Counterfactual Edits to Human Narratives: LLM-Driven Interpretations for Recommender System Explanations
- ShopMind: A Mental World Model for Personalized and Realistic E-commerce User Simulation
- Clinical Evidence-Guided Residual Learning for Medication Recommendation with Dynamic DDI Regularization
- Severity-Controlled Prediction Sets for Medication Recommendation
- Do Feature Interactions Break Explainability? Provable Explanations for Any-Order Neural Additive Models
- Can the Remaining Answers Change the Prediction? Worst-Case Stability Checks for Personalized Rating Models
- Beyond Query-Item Matching: Personalized Behavioral Relevance Modeling for E-commerce Search via Rubric-Guided Reinforcement Learning
- PCG-RAG: Progressive Compositional Grounding for Retrieval-Augmented Generation in Complex Web Question Answering
- HiddenPathQA: A Benchmark for Knowledge Graph Question Answering When Questions Hide Their Paths
- SNAPRAG: Cost-Efficient Knowledge Extraction Attack on RAG Systems via Adversarial Perturbations
- MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs
- DeepResearch RewardBench: Evaluating Reward Models for Deep Research Report
- Dhara: Evidence-Oriented Retrieval for Indian Knowledge Systems
- Cascading Circle Loss: Order-Preserving Contrastive Learning for Graded Legal Retrieval
- VisProve: Learning Typed Visual Provenance for Scientific Document Question Answering
- ARMOR: Adaptive Curriculum Meta-Learning for Noise-Robust RAG Reasoning
- Dynamic Graph Indexing for Label-Filtered Approximate Nearest Neighbor Search
- Multi-Future Drafting: Mixture Block Drafters for Tree-Verified Speculative Decoding
- SinkState: On-the-Fly SVD of Recurrent States for Efficient Hybrid LLM Serving
- Evolving Infra: Agent-Adaptive LLM Serving at Scale
- Verify Before You Fetch: Reliable KV Cache Compression for LLM Inference
- OOM: Offload-Optimized Full-Parameter MoE Training via Memory-Execution Co-Design
- Ostinato: Fast CPU-GPU MoE Inference for Local Agents via Resident Experts in Every Forward Pass
- Why Kubernetes Cannot Contain a Full Lazy-Pulling Cache: Two Impossibility Results and a Bounded, Honest Design for Model Serving
- OverlapAdvisor: Modeling and Adapting Computation-Communication Overlap for Distributed MoE Serving
- TRANSIT: Transparent Scale-in for Multi-Node LLM Training
- Real-Time Robot Execution with Masked Action Chunking
- Runway’s Praxis-1 world action model for robotics is now available
- Zero-Shot VLA Adaptation with Retrieved Guidance
- Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models
- Thermo-VLA: A Thermal-Aware Vision-Language-Action Model with Gated Residual Modulation for Robotic Manipulation
- Streaming Failure Forecasting: VLA Failure Monitors That Keep Learning After Deployment