全部收录论文
论文 · 第 104 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 104 / 141 页
查找论文请用站内搜索。
- LAER-MoE: Load-Adaptive Expert Re-layout for Efficient Mixture-of-Experts Training
- Efficient Listwise Reranking with Compressed Document Representations
- Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction
- When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
- Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
- CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation
- AgentSim: A Platform for Verifiable Agent-Trace Simulation
- Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
- SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
- Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
- GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
- ProMax: Exploring the Potential of LLM-derived Profiles with Distribution Shaping for Recommender Systems
- Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective
- Hierarchical Long-Term Semantic Memory for LinkedIn's Hiring Agent
- Explaining the "Why": A Unified Framework for the Additive Attribution of Changes in Arbitrary Measures
- CARD: Non-Uniform Quantization of Visual Semantic Unit for Generative Recommendation
- The Bandit's Blind Spot: The Critical Role of User State Representation in Recommender Systems
- Factorized Latent Reasoning for LLM-based Recommendation
- TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation
- PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems
- Meta-Learning and Targeted Differential Privacy to Improve the Accuracy-Privacy Trade-off in Recommendations
- Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI
- CogRAG+: Cognitive-Level Guided Diagnosis and Remediation of Memory and Reasoning Deficiencies in Professional Exam QA
- Retrieval-Augmented LLMs for Evidence Localization in Clinical Trial Recruitment from Longitudinal EHR Narratives
- Auto-ARGUE: LLM-Based Report Generation Evaluation
- Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval
- HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models
- BioGraphletQA: Knowledge-Anchored Generation of Complex QA Datasets
- Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An Evaluation Study for Bachelor Projects
- Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge Graphs
- Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence
- SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
- ClawGym: A Scalable Framework for Building Effective Claw Agents
- How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1
- ReD-RAG: Rewritable Decomposition-Guided Iterative Retrieval-Augmented Generation for Open-Domain Multi-hop Reasoning
- TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents
- Training Computer Use Agents to Assess the Usability of Graphical User Interfaces
- RAG-Enhanced Kernel-Based Heuristic Synthesis (RKHS): A Structured Methodology Using Large Language Models for Hardware Design
- EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation
- Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
- PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference
- Scheduling the Unschedulable: Taming Black-Box LLM Inference at Scale
- DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
- Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter
- Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU
- K-CARE: Knowledge-driven Symmetrical Contextual Anchoring and Analogical Prototype Reasoning for E-commerce Relevance
- From Citation Selection to Citation Absorption: A Measurement Framework for Generative Engine Optimization Across AI Search Platforms
- Health System Scale Semantic Search Across Unstructured Clinical Notes
- BridgeRAG: Training-Free Bridge-Conditioned Retrieval for Multi-Hop Question Answering
- Don't Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination