全部收录论文
论文 · 第 127 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 127 / 141 页
查找论文请用站内搜索。
- A Family of LLMs Liberated from Static Vocabularies
- Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models
- Role-Augmented Intent-Driven Generative Search Engine Optimization
- Deploying Semantic ID-based Generative Retrieval for Large-Scale Podcast Discovery at Spotify
- A Unified Language Model for Large Scale Search, Recommendation, and Reasoning
- HierarchicalKV: A GPU Hash Table with Cache Semantics for Continuous Online Embedding Storage
- Learning Evolving Preferences: A Federated Continual Framework for User-Centric Recommendation
- VLM2Rec: Resolving Modality Collapse in Vision-Language Model Embedders for Multimodal Sequential Recommendation
- Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)
- Embedding World Knowledge into Tabular Models: Towards Best Practices for Embedding Pipeline Design
- ListK: Semantic ORDER BY and LIMIT K with Listwise Prompting
- MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment
- OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
- Negation is Not Semantic: Diagnosing Dense Retrieval Failure Modes for Trade-offs in Contradiction-Aware Biomedical QA
- Training-Induced Bias Toward LLM-Generated Content in Dense Retrieval
- Visual Product Search Benchmark
- The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA
- Public Profile Matters: A Scalable Integrated Approach to Recommend Citations in the Wild
- From Isolated Scoring to Collaborative Ranking: A Comparison-Native Framework for LLM-Based Paper Evaluation
- Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search
- How often do Answers Change? Estimating Recency Requirements in Question Answering
- PJB: A Reasoning-Aware Benchmark for Person-Job Retrieval
- TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
- PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization
- CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
- InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
- RAGXplain: From Explainable Evaluation to Actionable Guidance of RAG Pipelines
- Tree Search for LLM Agent Reinforcement Learning
- Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
- Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
- Facts as First Class Objects: Knowledge Objects for Persistent LLM Memory
- Alternating Reinforcement Learning with Contextual Rubric Rewards
- FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
- ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
- The 1/W Law: An Analytical Study of Context-Length Routing Topology and GPU Generation Gains for LLM Inference Energy Efficiency
- BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization
- RAMP: Reinforcement Adaptive Mixed Precision Quantization for Efficient On Device LLM Inference
- Efficient Reasoning on the Edge
- Speculative Decoding: Performance or Illusion?
- MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios
- Learning When to Attend: Conditional Memory Access for Long-Context LLMs
- PRISM: Demystifying Retention and Interaction in Mid-Training
- Quantized Inference for OneRec-V2
- SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation
- UserSimCRS v2: Simulation-Based Evaluation for Conversational Recommender Systems
- RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments
- Answer Bubbles: Information Exposure in AI-Mediated Search
- MemX: A Local-First Long-Term Memory System for AI Assistants
- AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents
- PREFINE: Personalized Story Generation via Simulated User Critics and User-Specific Rubric Generation