全部收录论文
论文 · 第 108 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 108 / 141 页
查找论文请用站内搜索。
- Visual Reasoning through Tool-supervised Reinforcement Learning
- Optimizing Large Batched LLM Inference with Global Prefix
- Scalable AI Inference: Performance Analysis and Optimization of AI Model Serving
- Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects
- vLLM-Omni: Fully Disaggregated Serving for Any-to-Any Multimodal Models
- WorldDB: A Vector Graph-of-Worlds Memory Engine with Ontology-Aware Write-Time Reconciliation
- Computational Caching-Empowered Collaborative LLM Inference Framework in VEC Networks
- ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
- SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation
- LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
- OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
- DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
- Near-Future Policy Optimization
- Image Generators are Generalist Vision Learners
- From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
- HaS: Accelerating RAG through Homology-Aware Speculative Retrieval
- Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMs
- Break the Optimization Barrier of LLM-Enhanced Recommenders: A Theoretical Analysis and Practical Framework
- Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization
- ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation
- Cognis: Context-Aware Memory for Conversational AI Agents
- Discrete Preference Learning for Personalized Multimodal Generation
- AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce
- From Raw Features to Effective Embeddings: A Three-Stage Approach for Multimodal Recipe Recommendation
- From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents
- Semantic Recall for Vector Search
- Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation
- Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models
- Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge
- CRAFT: Training-Free Cascaded Retrieval for Tabular QA
- Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation
- LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent
- SWE-chat: Coding Agent Interactions From Real Users in the Wild
- A Reproducibility Study of Metacognitive Retrieval-Augmented Generation
- SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
- Deep Researcher Agent: An Autonomous Framework for 24/7 Deep Learning Experimentation with Zero-Cost Monitoring
- SweRank: Software Issue Localization with Code Ranking
- Do Hallucination Neurons Generalize? Evidence from Cross-Domain Transfer in LLMs
- ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score Prediction
- LLM Agents Predict Social Media Reactions but Do Not Outperform Text Classifiers: Benchmarking Simulation Accuracy Using 120K+ Personas of 1511 Humans
- Enhancing Research Idea Generation through Combinatorial Innovation and Multi-Agent Iterative Search Strategies
- TTKV: Temporal-Tiered KV Cache for Long-Context LLM Inference
- vLLM v0.19.0: The Most Widely Adopted Open-Source LLM Serving Engine
- XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference
- COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
- 大模型推理优化关键技术及应用实践研究报告 (2026年) — 中国信通院
- Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items
- Think Before Writing: Feature-Level Multi-Objective Optimization for Generative Citation Visibility
- Remask, Don't Replace: Token-to-Mask Refinement in Masked Diffusion Language Models
- RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models