全部收录论文
论文 · 第 63 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 63 / 141 页
查找论文请用站内搜索。
- Synergistic multi-stage processing for enhanced context relevance in RAG architecture
- Entities as Retrieval Signals: A Systematic Study of Coverage, Supervision, and Evaluation in Entity-Oriented Ranking
- When LLM Judges Inflate Scores: Exploring Overrating in Relevance Assessment
- Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination
- 下一代搜索智能体评测基准!美团开源LoHoSearch,用知识图谱校准AI能力认知
- Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search
- SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
- Rethinking Agentic RAG: Toward LLM-Driven Logical Retrieval Beyond Embeddings
- WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
- Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
- Six Agent Harness Capabilities for Higher Model Performance
- Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings
- TASR: Training-Free Adaptive Stopping for Iterative Retrieval
- Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
- Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA
- NVIDIA Nemotron 3 Ultra Leads Open Models on Accuracy and Efficiency in Agentic RTL Coding
- Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs
- MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond
- MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation
- NVIDIA Ising Enables Fully Automated Quantum Computer Calibration with Enhanced In-Context Learning
- grapheme-kit: Grapheme-Level Metrics and Text Processing for Multilingual NLP
- Scaling Native Multimodal Pre-Training From Scratch
- The Hard Decision Layer: Evidence for Committed Inference in Transformers
- Advancing Semiconductor Innovation Across Materials Engineering and Manufacturing
- OxygenREC: An Instruction-Following Generative Framework for E-commerce Recommendation
- Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation
- Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation
- Can Generative Recommendation Reach Cold Items? A Temporal Perspective on Semantic-ID Generation
- Diffusion Language Model for Recommendation
- On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies
- Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation
- Intuition-Guided Latent Reasoning for LLM-Based Recommendation
- RAGR: Review-Augmented Generative Recommendation
- Factorized Latent Reasoning for LLM-based Recommendation
- Bridging Passive and Active: Enhancing Conversation Starter Recommendation via Active Expression Modeling
- ReST: A Plug-and-Play Spatially-Constrained Representation Enhancement Framework for Local-Life Recommendation
- CASE: Cadence-Aware Set Encoding for Large-Scale Next Basket Repurchase Recommendation
- Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank
- Enriching Semantic Profiles into Knowledge Graph for Recommender Systems Using Large Language Models
- Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing.
- A Bag-of-Documents Model for Query Specificity
- Robust HNSW Vector Retrieval under Dynamic Product Updates via Local Rewiring
- To RAG or Not to RAG? Rethinking Multilingual Spelling Correction at Global Scale
- LoSparse: Low-dimensional Sparse Retrieval Model
- Problem Formulation over Feature Engineering: Evidence from a Production Reranking System in a C2C Marketplace
- SHIFT: Self-reconstruction Harnesses Implicit Fine-grained Thinking for Retrieval
- Dual-layer prompt ensembles: Leveraging system- and user-level instructions for robust LLM-based query expansion and rank fusion
- Improving Pointwise Predictions with a Pairwise Ranker
- LLM 混合检索路由生产实战:用查询分类、RRF 与回退策略稳住 RAG 召回
- Improving E-commerce search queries using transformer-based named entity recognition