全部收录论文
论文 · 第 92 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 92 / 141 页
查找论文请用站内搜索。
- Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables
- You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
- MagenticLite, MagenticBrain, Fara1.5: An agentic experience optimized for small models
- Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
- IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
- Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
- Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs
- PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models
- SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
- MemConflict: Evaluating Long-Term Memory Systems Under Memory Conflicts
- CALMem: Application-Layer Dual Memory for Conversational AI
- Predictive Prefetching for Retrieval-Augmented Generation
- Test-Time Speculation
- OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under Optimal Squared-error Quantization
- Get Real-Time Visibility into GPU Usage Across Kubernetes Clusters
- GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems
- Improving Efficiency of GPU Kernel Optimization Agents using a Domain-Specific Language and Speed-of-Light Guidance
- UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training
- Unlock Exascale Performance on NVIDIA GB200 NVL72 with Slurm Topology-Aware Job Scheduling
- Trust or Abstain? A Self-Aware RAG Approach
- Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
- Stage-adaptive Token Selection for Efficient Omni-modal LLMs
- CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization
- STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation
- Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees
- PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset
- CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition
- Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation
- LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation
- SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation
- ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation
- RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents
- SAGE: Scalable Automatic Gating Ensemble for Confident Negative Harvesting in Fraud Detection
- Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data
- AllSERP: Exhaustive Per-Element Enrichment of the Versatile AdSERP Dataset
- A Reproducibility Analysis of PO4ISR: Diagnosing and Mitigating Semantic Drift in LLM-Based Session Recommendation
- Towards FairRAG: Preventing Representational Harm in Retrieval-Augmented Generation by Enforcing Fair Exposure at Retrieval Time
- The 99% Success Paradox: When Near-Perfect Retrieval Equals Random Selection
- DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking
- Where Does Authorship Signal Emerge in Encoder-Based Language Models?
- Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance
- DOTRAG: Retrieval-Time Reasoning Along Paths
- Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
- BiRD: A Bidirectional Ranking Defense Mechanism for Retrieval Augmented Generation
- PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
- Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs
- Add a Specialized Deep Research Skill to Agent Harnesses
- CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
- GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
- Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization