全部收录论文
论文 · 第 36 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 36 / 141 页
查找论文请用站内搜索。
- Rapidly scaling online storage to serve over 1 billion ChatGPT users
- PATTON: Enabling Commodity PIM for Production LLM Serving
- FlexPosit: Tunable Fractional Precision for LLM Inference Accelerators
- A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware
- Spatial LLM Workload Shifting Needs Foresight: Model Commitment for AI Data Center Operation under Power Grid Constraints
- PDMR: Passage-Driven Multi-ID Document Retrieval
- Purchase Advice and Observable Buyer Responses in Real AI Conversations
- HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization
- From Retrieval to Weights: Parametric Individualization of Small Language Models with Individual Text Corpora
- REDSI: Addressing the Reproducibility and Evaluation Consistency of Differentiable Search Indexing for Document Retrieval
- Exploring Bottom-Up Clustering for Creating Semantic IDs
- Task-Blind No MORE: Multi-Task Information Flow in Unified Ranking Backbones
- SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching
- OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation
- Closing the Long-Short View Gap in Sequential Recommendation without Cached History
- FunnelAudit: Responsibility Auditing in Multi-Route Recommender Systems
- Do All Nodes Benefit Equally from Knowledge Graphs? Adaptive Node-Aware KG Fusion for Recommendation
- What Price Fairness? Evaluating Energy - Fairness - Accuracy Trade-off in Recommender Systems
- Individual Text Corpora Predict User-Specific Knowledge: Benchmarks of Individualized Knowledge Simulation
- Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval
- Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems
- Tracing Query Expansion Effects through Sparse Autoencoder Features
- EigenLI: Spectral Approximations to Late Interaction
- Tool Retrievers Are Underestimated: Annotation Expansion Reveals True Capability
- Better Together: Complementary Query Rewriting Under a Strong RAG Baseline
- Same Problem, Different Field: Cross-Domain Solution Import via Domain-Stripped Computational Fingerprints
- Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval
- Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment
- Cassette: Case-to-Case Structural Distillation for Efficient Legal Case Retrieval
- Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
- Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks
- Explore Before Committing: Hypothesis-Guided Search for Deep Research Agents
- Audit Without Verification: When LLM Accountability Layers Relay Rather Than Check
- RuleMem: Active Rule Memory for Long-Term Conversational Agents
- EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph
- NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
- Beyond Agent Harnesses: Cross-Substrate Authority for Multi-Agent Systems
- CAPMAS: Capability-Based Delegation of Privileges in Multi-Agent Systems
- Omni Interaction Agent Technical Report
- Sample-Guided Exact Top-K Selection for Long-Context Sparse Attention
- Miles v0.1: Production-Level Post-Training
- Elasticsearch Vector Database: Ship in minutes, scale affordably to hundreds of billions
- Analytical Resource Management for Fine-grained MoE Computation-Communication Overlap
- When to Use Encode-Prefill-Decode Disaggregation to Accelerate Multimodal Model Serving
- CUDA Toolkit 13.4 Adds Windows on Arm Support and Greater Control over Shared GPUs
- SemBridge: Compiling Consumer Observations into Cross-Stack Communication Plans
- Sharing a Fabric with Collective Communication: Two Storage Penalties in Deep Learning Training
- Poseidon: DAG-Guided Parallelism Search for LLM Pre-Training on Heterogeneous Clusters
- A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware
- WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval