全部收录论文
论文 · 第 135 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 135 / 141 页
查找论文请用站内搜索。
- From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings
- ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval
- ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval
- MMTEB: Massive Multilingual Text Embedding Benchmark
- Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAG
- ExcluIR: Exclusionary Neural Information Retrieval
- Linguistically Informed Graph Model and Semantic Contrastive Learning for Korean Short Text Classification
- Towards Effective and Efficient Sparse Neural Information Retrieval
- RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
- From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
- ToolRLA: Multiplicative Reward Decomposition for Tool-Integrated Agents
- Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
- Towards Personalized Deep Research: Benchmarks and Evaluations
- MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
- Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants
- Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
- AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
- Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows
- DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation
- Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention
- HyperParallel: A Supernode-Affinity AI Framework
- Litespark Technical Report: High-Throughput, Energy-Efficient LLM Training Framework
- Accelerating OpenPangu Inference on NPU via Speculative Decoding
- Activation Outliers in Transformer Quantization: Reproduction, Statistical Analysis, and Deployment Tradeoffs
- stratum: A System Infrastructure for Massive Agent-Centric ML Workloads
- Investing in Infrastructure: Meta's Renewed Commitment to jemalloc
- Training-free Dropout Sampling for Semantic Token Acceptance in Speculative Decoding
- Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving
- A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications
- Model Editing for New Document Integration in Generative Information Retrieval
- OxygenREC: An Instruction-Following Generative Framework for E-commerce Recommendation
- DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendation
- Order-agnostic Identifier for Large Language Model-based Generative Recommendation
- Learnable Item Tokenization for Generative Recommendation
- Multimodal Quantitative Language for Generative Recommendation
- Q-BERT4Rec: Quantized Semantic-ID Representation Learning for Multimodal Recommendation
- Generative Recommendation Models: Progress and Directions
- Diffusion-EXR: Controllable Review Generation for Explainable Recommendation via Diffusion Models
- Sensory-Aware Sequential Recommendation via Review-Distilled Representations
- OneRanker: Unified Generation and Ranking with One Model in Industrial Advertising Recommendation
- SOLAR: SVD-Optimized Lifelong Attention for Recommendation
- Zenith: Scaling up Ranking Models for Billion-scale Livestreaming Recommendation
- MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms
- FlashEvaluator: Expanding Search Space with Parallel Evaluation
- Compress, Cross and Scale: Multi-Level Compression Cross Networks for Efficient Scaling in Recommender Systems
- AlphaFree: Recommendation Free from Users, IDs, and GNNs
- APAO: Adaptive Prefix-Aware Optimization for Generative Recommendation
- S2CDR: Smoothing-Sharpening Process Model for Cross-Domain Recommendation
- MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommendation
- Relevance Matters: A Multi-Task and Multi-Stage Large Language Model Approach for E-commerce Query Rewriting