全部收录论文
论文 · 第 125 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 125 / 141 页
查找论文请用站内搜索。
- Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective
- On the Challenges and Opportunities of Learned Sparse Retrieval for Code
- Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning
- Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach
- PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs
- Graph-Based Re-ranking: Emerging Techniques, Limitations, and Opportunities
- s3: You Don't Need That Much Data to Train a Search Agent via RL
- PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost
- AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling
- Bypassing Document Ingestion: An MCP Approach to Financial Q&A
- Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
- KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning
- OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
- WebNavigator: Global Web Navigation via Interaction Graph Retrieval
- Toward a Theory of Hierarchical Memory for Language Agents
- The Library Theorem: How External Organization Governs Agentic Reasoning Capacity
- AngelSlim: A More Accessible, Comprehensive, and Efficient Toolkit for Large Model Compression
- DRTriton: Large-Scale Synthetic Data Reinforcement Learning for Triton Kernel Generation
- Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs
- The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
- Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression
- Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels
- AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search
- TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference
- Speculating Experts Accelerates Inference for Mixture-of-Experts
- LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
- The Residual Stream Is All You Need: On the Redundancy of the KV Cache in Transformer Inference
- Predictive Scaling Laws for Efficient GRPO Training of Large Reasoning Models
- Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions
- CoverageBench: Evaluating Information Coverage across Tasks and Domains
- Speculating Experts Accelerates Inference for Mixture-of-Experts
- FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data
- Best-of-Both-Worlds Multi-Dueling Bandits: Unified Algorithms for Stochastic and Adversarial Preferences under Condorcet and Borda Objectives
- PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization
- Inducing Sustained Creativity and Diversity in Large Language Models
- Warm-Start Flow Matching for Guaranteed Fast Text/Image Generation
- AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query Recommendation
- GenFacet: End-to-End Generative Faceted Search via Multi-Task Preference Alignment in E-Commerce
- From Token to Item: Enhancing Large Language Models for Recommendation via Item-aware Attention Mechanism
- MOSAIC: Modular Opinion Summarization using Aspect Identification and Clustering
- How Well Does Generative Recommendation Generalize?
- Maximizing mutual information between user-contexts and responses improve LLM personalization with no additional data
- DALI: LLM-Agent Enhanced Dual-Stream Adaptive Leadership Identification for Group Recommendations
- Reviewing the Reviewer: Graph-Enhanced LLMs for E-commerce Appeal Adjudication
- Spectral Tempering for Embedding Compression in Dense Passage Retrieval
- A Super Fast K-means for Indexing Vector Embeddings
- Spelling Correction in Healthcare Query-Answer Systems: Methods, Retrieval Impact, and Empirical Evaluation
- The End of Rented Discovery: How AI Search Redistributes Power Between Hotels and Intermediaries
- URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models
- Ranking Engineer Agent (REA): The Autonomous AI Agent Accelerating Meta's Ads Ranking Innovation