全部收录论文
论文 · 第 137 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 137 / 141 页
查找论文请用站内搜索。
- Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality
- Rethinking On-policy Optimization for Query Augmentation
- The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems
- LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning
- A Survey of Query Optimization in Large Language Models
- OmniRet: Efficient and High-Fidelity Omni Modality Retrieval
- RaDeR: Reasoning-aware Dense Retrieval Models
- MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product Understanding
- DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent
- FrugalRAG: Less is More in RL Finetuning for Multi-Hop Question Answering
- Tiny-Critic RAG: Empowering Agentic Fallback with Parameter-Efficient Small Language Models
- GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
- Let the Agent Search: Autonomous Exploration Beats Rigid Workflows in Temporal Question Answering
- MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline
- RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
- Expanding LLM Agent Boundaries with Strategy-Guided Exploration
- HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents
- Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents
- OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration
- Attn-QAT: 4-Bit Attention With Quantization-Aware Training
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving
- The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
- Learning to Draft: Adaptive Speculative Decoding with Reinforcement Learning
- Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts
- Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery
- MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core
- Google, ByteDance and Red Hat improve AI on Kubernetes: Optimizing LLM Inference on K8s
- Learning to Reflect and Correct: Towards Better Decoding Trajectories for Large-Scale Generative Recommendation
- Unlocking Scaling Law in Industrial Recommendation Systems with a Three-step Paradigm based Large User Model
- RAD-DPO: Robust Adaptive Denoising Direct Preference Optimization for Generative Retrieval in E-commerce
- Generating Long Semantic IDs in Parallel for Recommendation
- Pre-training Generative Recommender with Multi-Identifier Item Tokenization
- Scaling Sparse and Dense Retrieval in Decoder-Only LLMs
- Graph Retrieval-Augmented LLM for Conversational Recommendation Systems
- Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems
- MLPlatt: Simple Calibration Framework for Ranking Models
- Recommending Search Filters To Improve Conversions At Airbnb
- Unified Learning-to-Rank for Multi-Channel Retrieval in Large-Scale E-Commerce Search
- FuXi-Linear: Unleashing the Power of Linear Attention in Long-term Time-aware Sequential Recommendation
- Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfer
- Cross-Representation Knowledge Transfer for Improved Sequential Recommendations
- Beyond the Click: A Framework for Inferring Cognitive Traces in Search
- U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation
- LLM-Enhanced Multimodal Fusion for Cross-Domain Sequential Recommendation
- Synthetic Data Powers Product Retrieval for Long-tail Knowledge-Intensive Queries in E-commerce Search
- Query-focused and Memory-aware Reranker for Long Context Processing
- From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model
- Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning
- PTEB: Towards Robust Text Embedding Evaluation via Stochastic Paraphrasing at Evaluation Time with LLMs