全部收录论文
论文 · 第 66 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 66 / 141 页
查找论文请用站内搜索。
- Answer-Reconstruction Search Density: Measuring the Query and Source Work Compressed by Conversational Answers
- RF-Agent: A Practical Framework for Building Language Agents for RFIC Design
- Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains
- A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification
- Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training
- HPD-Parsing: Hierarchical Parallel Document Parsing
- LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters
- Convolution for Large Language Models
- Di-PS: System-Algorithm Co-Design for Asynchronous and Heterogeneous Cross-cluster LLM Training at Scale
- ISO: An RLVR-Native Optimization Stack
- Generative World Renderer at the Speed of Play
- CECAIServe: Facilitating ML inference serving across the cloud-edge-continuum
- 2026 大语言模型推理应用开发框架盘点推荐:国产昇腾 MindIE LLM 成国产化落地核心选择
- GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation
- Differentiable Semantic ID for Generative Recommendation
- LLM-RS: A Large Language Model-Based Sequential Recommendation with Reasoning
- Leveraging graph path evidence for explainable recommender systems
- Uncertainty as Remedy: Mitigating Satisfaction Label Bias in Short Video Multi-Objective Ensemble Ranking
- WHALE: A Scalable Unified Model for Recommendation with Wukong-HSTU Architecture
- Learning Sparse Representations of Multimodal Content for Enhanced Cold Item Recommendation
- RAMP: Robust Ad Recommendation Under Limited Personalized-Feature Availability via Masking and Alignment Pathways
- HyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation
- 2026 腾讯广告算法大赛高分方案启示:行为条件赋能多模态生成推荐模型
- jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation
- AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis
- TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization
- ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search
- 交互式推荐概述——数据智能体 DataAgent(私有化)
- 大语言模型时代:统一搜索与推荐开启信息获取新探索
- Adapting Embedding Models for Agent Capability Retrieval
- Bayesian Rational Search Engine User
- Fenced Citation-Context Retrieval for Case Law: Temporal Leakage and Degree Control Across Two Jurisdictions
- 美团ASX团队顶会论文解读:大模型Agent与搜索推荐前沿技术
- Evidence-in-the-Loop: Trace-Driven Optimization for Customer-Service LLM Agents
- FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering
- DRNOISE: Benchmarking Deep Research Agents in Misleading Evidence Environments
- RIMS: Preference Optimization via Smoothed Multi-pair Aggregation for Small-Scale LLM Retrieval-Augmented Generation
- MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking
- Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries
- From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents
- NVIDIA Vera CPU: Olympus Cores Built for Maximum Single-Thread Performance in Agentic AI
- WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting
- Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering
- C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference
- SpecLA: Efficient Speculative Decoding for Linear-Attention Models
- VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval
- Setting a World Record for MoE Pre-Training on NVIDIA GB300 NVL72
- Inside NVIDIA Rubin GPU Architecture: Powering the Era of Agentic AI
- Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices
- OpenLanguageModel: Readable and Composable Small-Language-Model Pretraining for Education and Research