全部收录论文
论文 · 第 45 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 45 / 141 页
查找论文请用站内搜索。
- Solving Agentic AI Fleet Challenges with NVIDIA Vera CPU
- Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction
- Towards a Densing Law for User Representation Learning at Billion-Scale Capacity
- Cascading Relevance-driven Recommendation Network for CTR Prediction in Trigger-Introduced Recommendation
- A Dual-Expert Strategy Integrating LLMs to Mitigate Negative Transfer in Cross-Domain Sequential Recommendation
- One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders
- Enhancing Group Recommendation with Memory-Augmented Reasoning in LLM Agent
- Why didn't more people see it? Recommendation: Transparency for providers
- Revisiting N2DCG: An Empirically Grounded Reformulation of Carousel Recommendation Evaluation
- Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals
- Balancing preference and compatibility: A multiobjective optimization framework for outfit recommendation
- Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling
- Robustness of IR Models to Collection Growth
- The Emergence of Relevance Through Axiomatic Attention Patterns During LoRA Fine-Tuning
- Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA
- Retrieval Needs Multivectors: An Exponential Separation
- KSE-Web: An Analysis of Hybrid Retrieval and LLM-Assisted Query Expansion for Low-Resource Khmer Semantic Search
- HIRA: A Human-in-the-Loop Retrieval-Augmented Cascade for Document Classification in Regulated Industries
- Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval
- Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports
- TSWAP: A Multilingual Retrieval-Augmented Thai Wellness Advisor
- Enrich-Retrieve-Rank: Scaling Capability Discovery Beyond In-Context Routing
- Prompt-Based Abstention Fails Under Misleading Context: A Controlled Study of Small Frozen RAG Models
- Training a Knowledge Base: Supervised Structure Learning for Agent-Curated Document Stores
- Risk-Aware Reranking for Agentic Tool Retrieval
- Better Retrieval, Worse Robustness:How Multi-hop RAG Amplifies Upstream ASR Errors
- Which RAG Paradigm Wins at Scale? A Scaling Study of Retrieval-Augmented Generation Paradigms
- LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks
- MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks
- Apodex 1.1: Scaling Agentic Intelligence for Complex Work
- Agent RAG architecture: components, control loop, and tradeoffs
- ASH: Asymmetric Scalar Hashing With Learned Dimensionality Reduction for High-Fidelity Vector Quantization
- AIRS: Scaling Live Inference in Resource Constrained Environments
- GEAR: An Efficient Error Reduction Framework for KV Cache Compression in LLM Inference
- Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines
- Cache Saver: A Modular Framework for Efficient, Affordable, and Reproducible LLM Inference
- Large-scale optimization
- CUDA Python 1.0: Stable APIs, One Foundation, Full Platform Access
- PAI 产品架构:覆盖训练、推理与搜索推荐的全链路 AI 平台
- Jalapeño’s first results show industry-leading speed and efficiency in AI inference
- zkGPT: An Efficient Non-interactive Zero-knowledge Proof Framework for LLM Inference
- From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation
- Adaptive Semantic Capacity Allocation for Parallel Generative Recommendation
- LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience
- Conversational recommender systems with large language models: A review of current developments
- Measuring Prosodic Richness in LLM-Generated Responses for Conversational Recommendation
- SORT: A Systematically Optimized Ranking Transformer for Industrial-scale Recommenders
- One Hierarchy, Two Systems: Semantic Product IDs for Discovery-Surface Ranking and Search-Page Query Reformulation
- Towards Faithful Simulation of Human Shopping Behavior
- Profiling What Matters: Context-Aware Item Profiles from Large-Scale Metadata for LLM Recommenders