全部收录论文
论文 · 第 39 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 39 / 141 页
查找论文请用站内搜索。
- SPAR: Enhancing Industrial-Scale Generative POI Recommendation via Real-World Spatial Perception
- hLLM: Single Pass Decoding for Generative Reranking
- MERGED: Multimodal Entity Resolution via Generated Expert Reasoning Distillation
- RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems
- Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization
- ViSAR: Training-Free Adaptive- Retrieval for Visual Document Question Answering
- PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation
- Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA
- Incremental Pooled LLM Evaluation for Cost-Effective Retrieval Model Selection
- Skim and Skip: Hierarchical Adaptive Inference for Efficient Multimodal Retrieval
- From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendation Models
- Not All Matches Are Equally Valuable: An Online Experiment of Retention-Focused Recommendation in a Job-Matching Platform
- Recommender System as Slow and Fast Thinkers
- GenCAR: Generative Counterfactual Alignment with Risk-Controlled Selection for Out-of-Distribution Recommendation
- Beyond Modality Harmony: Orthogonal Purification and Topology-Guided MoE for Conflict-Aware Multimodal Recommendation
- Training seeds and model-selection stability in recommender-system evaluation
- MGDiff: Multi-Interest Sequence Recommendation with Masking GNN-Guided Diffusion
- CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation
- The Utility of LLMs in Recommender Systems Explanation Evaluation
- 美团智播——数字人直播技术创新与实践
- The Vocabulary Gap Is an Equity Gap: Register Mismatch in Retrieval Systems for Public-Benefits Access
- Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per-Chunk Grounded Evaluation for Enterprise Document Search
- A Power Law in Logarithm's Clothing: On the Scalability of Graph-Based Vector Search
- Index-Free Dynamic Edge Retrieval with Energy-Tail-Aware Partial Scans
- NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
- Group-Aware Adaptive Retrieval for Evidence Navigation
- ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval
- Marginal Expected Revenue for Jointly Ranking Auction and Fixed-Price Listings in E-Commerce Sponsored Search
- MESSY STREETS: A Benchmark for Geocoding Real-World Addresses
- MELON: A Large-Scale Dataset for Multi-Event Text-to-Long-Video Retrieval
- KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation
- Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
- Imagine Before Retrieval: Prospective Skill Retrieval for LLM Agents
- Multi-Agent Retrieval-Augmented Generation for Efficient Cloud Knowledge Base Search in Telecom SNOC Environment
- Incident Memory: Training-Free Operational Memory through Sequential Pattern Mining and Velocity-Stratified Retrieval
- EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
- Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents
- Counter-GEO-Bench: Evaluating Defenses Against Information-Distorting Generative Engine Optimization
- Cite or Decline: A Strict Course-Grounded Chatbot for STEM Lecture Videos
- Legora reviewed 41 documents in minutes with GPT-6 Astra
- Language Models Can Control Their Own Attention
- NVIDIA PAIR Virtual Inference Router Expands Available Compute on Your Local Network
- Adaptive Test-Time Inference for Text2Cypher with Trace Budgeting and Selective Refinement
- ZGateway: Learnings from Putting a Proxy in Front of ZippyDB
- Elasticsearch Service 智能搜索开发概述
- VibeVoice-ASR-Streaming Technical Report
- Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
- Seed-Anchored Budget-Bounded Graph Rendering for Question Answering on Industry-Standard Power-Grid Information and Exchange Models
- SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
- PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation