全部收录论文
论文 · 第 17 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 17 / 141 页
查找论文请用站内搜索。
- An Explicit Feedback Contract for Iterative ML-Agent Harnesses
- How to Read Data into GPU Memory in Python with NVIDIA GPUDirect Storage
- The science behind TorchNeuron, Amazon’s new PyTorch backend for AWS Trainium chips
- Running Frontier-Class AI Models Across 8 NVIDIA DGX Spark Nodes
- PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States
- FrontierCS 2: A Benchmark for Computer Science R&D
- MemoryTax: The Bitter Lesson of Agent Memory
- Let Agents Design How They Search: Automatic Interface Optimization for Agentic Search
- MAPS: Macro-Adaptive Parallel Reasoning for Regulating Search Momentum in Retrieval-Augmented Generation
- Signals and Queries: Token-Efficient Agentic Context Discovery
- A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation
- Uni-Mem: Learning a Long-Horizon Agentic Memory Manager with Unified Online Policy Optimization
- How AI agents search
- BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments
- Harness Scaling for Generalizable Agentic Reinforcement Learning
- Flint-interactive: A language for creating interactive data visualizations
- Inside NVIDIA Sentry: Secure AI Agents at Runtime
- Is 2:4 Sparsity Still Worth It? Semi-Structured Sparsity versus Quantization in LLM Inference
- SGLang Low-Latency Mode: Kernels and Runtime
- RCSD: Reinforcement and Continual Learning for Domain-Specific Speculative Decoding
- UlaCache: Unified Logical Addressing for Sparse LLM Serving
- SPARE: Sparsity Allocation via Routing Entropy for Efficient MoEs
- NormTune: Norm-Guided Parameter-Efficient Fine-Tuning for Reasoning-Intensive Tasks
- FlashNext-RL: A System Optimization Study for Long-Horizon Agentic RL of Qwen3.8-Flash-Next
- TrainBridge: Agentic NPU Training Optimization Guided by GPU Compilation Evidence
- Looped Uniform Diffusion Language Models
- Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers
- Evolving Semantic Indexes for Generative Retrieval
- LightCRS: Lightweight Multi-Domain Conversational Recommendation System
- Factual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and Retrieval
- Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling
- Which Model for Which Role? Cost-Efficient Pareto Recommendation for LLM Agentic Workflows
- DiffuPlan: Editable Planning State for Diffusion Language Model Agents
- How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
- BERT Is Already a Denoiser: Cheaply Unlocking Iterative Generation in Masked Language Models
- Training the Whole Agent, Not Just the Model
- DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
- ECHO: Efficient Cascade with Homogeneous Operators for Distillation-Guided 100K-Sequence Modeling
- KuaFu: Compressing Long User Behavior into Understanding at Billion Scale
- EASformer: Environment-Action-State Alignment for Industrial Generative Ranking
- SPAR: Stepwise Personalized Autoregressive Recommendation with Prefix-Balanced Semantic IDs
- Robustness Analysis of Pareto-based Joint Evaluation of Fairness and Relevance in Recommender Systems
- Do Sequential Recommendation Benchmarks Require Higher-Order Sequence Modelling?
- MOSS: A Production Framework for Monitoring and Diagnosing Semantic Failures in Search and Recommendation Systems
- Neighborhood-Aware Unlearning for Generative Recommendation
- Multimodal Reranking Is a System One Decision
- How we built ChatGPT’s novel ad stack for user trust and relevance
- UIBK-Embedding: Effective Text Retrieval by Unifying Dense and Late-Interaction Retrieval
- FLINT: Fixed-budget Late Interaction
- GARRET: Generative Feedback for Region Retrieval in Visual Documents