ALL COLLECTED PAPERS

Papers · page 17

1040 papers · newest first · 50 per page · page 17 of 21

Looking for a title? Use site search.

  1. An Explicit Feedback Contract for Iterative ML-Agent Harnesses2026-10-23 · AI Search
  2. How to Read Data into GPU Memory in Python with NVIDIA GPUDirect Storage2026-10-23 · AI Search
  3. The science behind TorchNeuron, Amazon’s new PyTorch backend for AWS Trainium chips2026-10-23 · AI Search
  4. Running Frontier-Class AI Models Across 8 NVIDIA DGX Spark Nodes2026-10-23 · AI Search
  5. PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States2026-10-23 · AI Search
  6. FrontierCS 2: A Benchmark for Computer Science R&D2026-10-23 · AI Search
  7. MemoryTax: The Bitter Lesson of Agent Memory2026-10-23 · AI Search
  8. Let Agents Design How They Search: Automatic Interface Optimization for Agentic Search2026-10-23 · Agentic
  9. MAPS: Macro-Adaptive Parallel Reasoning for Regulating Search Momentum in Retrieval-Augmented Generation2026-10-23 · Agentic
  10. Signals and Queries: Token-Efficient Agentic Context Discovery2026-10-23 · Agentic
  11. A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation2026-10-23 · Agentic
  12. Uni-Mem: Learning a Long-Horizon Agentic Memory Manager with Unified Online Policy Optimization2026-10-23 · Agentic
  13. How AI agents search2026-10-23 · Agentic
  14. BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments2026-10-23 · Agentic
  15. Harness Scaling for Generalizable Agentic Reinforcement Learning2026-10-23 · Agentic
  16. Flint-interactive: A language for creating interactive data visualizations2026-10-23 · Agentic
  17. Inside NVIDIA Sentry: Secure AI Agents at Runtime2026-10-23 · Agentic
  18. Is 2:4 Sparsity Still Worth It? Semi-Structured Sparsity versus Quantization in LLM Inference2026-10-23 · Infra
  19. SGLang Low-Latency Mode: Kernels and Runtime2026-10-23 · Infra
  20. RCSD: Reinforcement and Continual Learning for Domain-Specific Speculative Decoding2026-10-23 · Infra
  21. UlaCache: Unified Logical Addressing for Sparse LLM Serving2026-10-23 · Infra
  22. SPARE: Sparsity Allocation via Routing Entropy for Efficient MoEs2026-10-23 · Infra
  23. NormTune: Norm-Guided Parameter-Efficient Fine-Tuning for Reasoning-Intensive Tasks2026-10-23 · Infra
  24. FlashNext-RL: A System Optimization Study for Long-Horizon Agentic RL of Qwen3.8-Flash-Next2026-10-23 · Infra
  25. TrainBridge: Agentic NPU Training Optimization Guided by GPU Compilation Evidence2026-10-23 · Infra
  26. Looped Uniform Diffusion Language Models2026-10-23 · Infra
  27. Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers2026-10-23 · Infra
  28. Evolving Semantic Indexes for Generative Retrieval2026-10-22 · Generative
  29. LightCRS: Lightweight Multi-Domain Conversational Recommendation System2026-10-22 · Generative
  30. Factual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and Retrieval2026-10-22 · Generative
  31. Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling2026-10-22 · Generative
  32. Which Model for Which Role? Cost-Efficient Pareto Recommendation for LLM Agentic Workflows2026-10-22 · Generative
  33. DiffuPlan: Editable Planning State for Diffusion Language Model Agents2026-10-22 · Generative
  34. How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies2026-10-22 · Generative
  35. BERT Is Already a Denoiser: Cheaply Unlocking Iterative Generation in Masked Language Models2026-10-22 · Generative
  36. Training the Whole Agent, Not Just the Model2026-10-22 · Generative
  37. DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems2026-10-22 · Generative
  38. ECHO: Efficient Cascade with Homogeneous Operators for Distillation-Guided 100K-Sequence Modeling2026-10-22 · Personalization
  39. KuaFu: Compressing Long User Behavior into Understanding at Billion Scale2026-10-22 · Personalization
  40. EASformer: Environment-Action-State Alignment for Industrial Generative Ranking2026-10-22 · Personalization
  41. SPAR: Stepwise Personalized Autoregressive Recommendation with Prefix-Balanced Semantic IDs2026-10-22 · Personalization
  42. Robustness Analysis of Pareto-based Joint Evaluation of Fairness and Relevance in Recommender Systems2026-10-22 · Personalization
  43. Do Sequential Recommendation Benchmarks Require Higher-Order Sequence Modelling?2026-10-22 · Personalization
  44. MOSS: A Production Framework for Monitoring and Diagnosing Semantic Failures in Search and Recommendation Systems2026-10-22 · Personalization
  45. Neighborhood-Aware Unlearning for Generative Recommendation2026-10-22 · Personalization
  46. Multimodal Reranking Is a System One Decision2026-10-22 · Personalization
  47. How we built ChatGPT’s novel ad stack for user trust and relevance2026-10-22 · Personalization
  48. UIBK-Embedding: Effective Text Retrieval by Unifying Dense and Late-Interaction Retrieval2026-10-22 · AI Search
  49. FLINT: Fixed-budget Late Interaction2026-10-22 · AI Search
  50. GARRET: Generative Feedback for Region Retrieval in Visual Documents2026-10-22 · AI Search