全部收录论文
论文 · 第 51 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 51 / 141 页
查找论文请用站内搜索。
- The Clustering Strikes Back: Building Cost-Effective and High-Performance ANNS at Scale with HELMSMAN
- Jais 2: A Family of Arabic-Centric Open Large Language Models
- BCMT: Blockwise Causal Memory Transformer
- APAO: Bridging the Training-Inference Gap in Generative Recommendation via Adaptive Prefix-Aware Optimization
- LLM Retrieval for Stable and Predictable Ad Recommendations
- OneReason Technical Report
- FEDIN: Frequency-Enhanced Deep Interest Network for Click-Through Rate Prediction
- Context-aware diffusion model for sequential recommendation
- TF-Rec: Time–Frequency Enhanced Sequential Recommendation Based on Adaptive Intent Clustering
- Gradient-enhanced evolutionary multi-objective optimization (GEEMOO): Balancing relevance, learning outcomes, and diversity in educational recommendation systems
- Metric Distortion with Preference Intensities.
- Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
- SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges
- Reducing Hallucinations in RAG through Multi-Signal Relevance Scoring
- A Mechanistic Analysis of Gender Sensitivity in Dense Retrieval Models
- 多路召回与融合排序:RRF + Rerank + 动态 TopK 的工程实践
- Discovery to Execution: Scaling Agents with Toolboxes and Routines in Microsoft Foundry
- GRASP: 粒度感知的智能体检索增强生成搜索策略
- MARS-RL: Enhancing Multi-Agent RAG Systems for Multi-Modal Documents via Strategic Reasoning with Reinforcement Learning
- Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning
- RAISE: RAG Design as an Architecture Search Problem
- Optimizing Deployment Configurations for LLM Inference
- TriInfer: Hybrid EPD Disaggregation for Efficient Multimodal Large Language Model Inference
- Optimal Scheduling Algorithms for LLM Inference: Theory and Practice
- Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving
- 负载感知路由实践
- GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving
- PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
- SHIP: SRAM-Based Huge Inference Pipelines for Fast LLM Serving
- 2026 企业大模型服务商选择:技术、架构与落地约束全解析
- HCGRec: Hint-Conditioned Generative Recommendation with Semantic IDs
- Token-Level Credit Assignment Optimization for Generative Document Retrieval
- LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence
- Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
- Total Recall at What Cost? Benchmarking the Serving Cost of Agentic Memory Systems
- A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench
- From Overlooked to Explored: Recovering Item Relations via Mixture of Perspectives for Sequential Recommendation
- Making Collaborative Signals Count: Graph-Aware Large Language Models for Sequential Recommendation
- VLM2Rec: Resolving Modality Collapse in Vision-Language Model Embedders for Multimodal Sequential Recommendation
- FunnelCausalNet: Funnel-aware Joint Conversion-Revenue Uplift for Multi-tier Coupon Allocation
- Sci-Surf: Navigating Scientific Literature Discovery through Human Feedback and Intelligent Summarizatio
- RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecycle
- Locating and Controlling Implicit Personalization in Large Language Models
- Designing Recommendation Infrastructure: Candidates, Ranking, and the 100ms Funnel
- RecSys Weekly 2026-W29: Recommendation Systems Weekly Papers
- From Clicks to Trust: Rethinking Recommendations
- Can Frontier LLMs Match Natively Multimodal Embeddings? A Comparison on Hard-Negative Text-to-Image Retrieval
- 混合检索RAG:多路召回+Reranker重排模型实战
- Exploring the Social Life of Data: Finding Data You Can Trust
- RAG 系统性能优化:从向量检索到混合排序的工程实践