全部收录论文
论文 · 第 121 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 121 / 141 页
查找论文请用站内搜索。
- M-RAG: Making RAG Faster, Stronger, and More Efficient
- Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG
- Resolving the Robustness-Precision Trade-off in Financial RAG through Hybrid Document-Routed Retrieval
- Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
- The Price of Meaning: Why Every Semantic Memory System Forgets
- Towards Hyper-Efficient RAG Systems in VecDBs: Distributed Parallel Multi-Resolution Vector Search
- Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval
- Seed1.8 Model Card: Towards Generalized Real-World Agency
- AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
- Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
- MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
- Gen-Searcher: Reinforcing Agentic Search for Image Generation
- GroupRAG: Cognitively Inspired Group-Aware Retrieval and Reasoning via Knowledge-Driven Problem Structuring
- PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering
- Dynamic Dual-Granularity Skill Bank for Agentic RL
- Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification
- MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences
- From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification
- Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers
- Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
- ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM Inference
- TAPS: Task Aware Proposal Distributions for Speculative Sampling
- KVSculpt: KV Cache Compression as Distillation
- RSR-core: A High-Performance Engine for Low-Bit Matrix-Vector Multiplication
- WVA: A Global Optimization Control Plane for llmd
- ParoQuant: Efficient Post-Training Quantization for Reasoning LLMs
- Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use
- T*: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning
- Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns
- MORA-LLM: Enhancing Multi-Objective Optimization Recommendation Algorithm by Integrating Large Language Models
- Dual-objective Language Models: Training Efficiency Without Overfitting
- When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models
- Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
- Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory
- Towards Transfer-Efficient Multi-modal Sequential Recommendation with State Space Duality
- MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalization
- The Value of Personalized Recommendations: Evidence from Netflix
- NextQuill: Causal Preference Modeling for Enhancing LLM Personalization
- Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems
- Diffusion Recommender Models and the Illusion of Progress: A Concerning Study of Reproducibility and a Conceptual Mismatch
- AgenticRS-Architecture: System Design for Agentic Recommender Systems
- CTR Prediction on Alibaba Taobao Advertising Dataset Using Traditional and Deep Learning Models
- mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT
- Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing
- Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers
- Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models
- Insider Knowledge: How Much Can RAG Systems Gain from Evaluation Secrets?
- Can Small Models Reason About Legal Documents? A Comparative Study
- Incorporating Q&A Nuggets into Retrieval-Augmented Generation
- Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio