全部收录论文
论文 · 第 117 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 117 / 141 页
查找论文请用站内搜索。
- Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC
- AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention
- Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression
- Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees
- DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
- BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
- Next-Scale Generative Reranking: A Tree-based Generative Rerank Method at Meituan
- ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking
- Pay Attention to Sequence Split: Uncovering the Impacts of Sub-Sequence Splitting on Sequential Recommendation Models
- Content Fuzzing for Escaping Information Cocoons on Digital Social Media
- CURE: Circuit-Aware Unlearning for LLM-based Recommendation
- Automating Personalization: Prompt Optimization for Recommendation Reranking
- From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation
- Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation
- Curr-RLCER: Curriculum Reinforcement Learning For Coherence Explainable Recommendation
- Learning to Trust: Dynamic Utilization of Retrieval-Augmented Generation for E-commerce Search Relevance
- Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead
- AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inference
- Retrieval Augmented Conversational Recommendation with Reinforcement Learning
- NVIDIA recsys-examples: Efficient Training and Inference for Generative Recommender Systems
- LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation
- Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval
- LLM-based Listwise Reranking under the Effect of Positional Bias
- Many Preferences, Few Policies: Towards Scalable Language Model Personalization
- DARE: Diffusion Large Language Models Alignment and Reinforcement Executor
- Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices
- SLSREC: Self-Supervised Contrastive Learning for Adaptive Fusion of Long- and Short-Term User Interests
- FLAME: Condensing Ensemble Diversity into a Single Network for Efficient Sequential Recommendation
- Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation
- Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation
- FAVE: Flow-based Average Velocity Establishment for Sequential Recommendation
- User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation
- Joint Behavior-guided and Modality-coherence Conditional Graph Diffusion Denoising for Multi Modal Recommendation
- A Logical-Rule Autoencoder for Interpretable Recommendations
- MMP-Refer: Multimodal Path Retrieval-augmented LLMs For Explainable Recommendation
- Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment
- Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
- Reinforced Latent Reasoning for LLM-based Recommendation
- Synapse: Evolving Job-Person Fit with Explainable Two-phase Retrieval and LLM-guided Genetic Resume Optimization
- SelRoute: Query-Type-Aware Routing for Long-Term Conversational Memory Retrieval
- Towards Position-Robust Talent Recommendation via Large Language Models
- Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
- MBGR: Multi-Business Prediction for Generative Recommendation at Meituan
- 2026 大模型×智能体×搜广推深度调研报告
- Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits
- Modeling and Controlling Deployment Reliability under Temporal Distribution Shift
- LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
- Bilateral Intent-Enhanced Sequential Recommendation with Embedding Perturbation-Based Contrastive Learning
- Relative Contrastive Learning for Sequential Recommendation with Similarity-based Positive Pair Selection
- VALOR: Value-Aware Revenue Uplift Modeling with Treatment-Gated Representation for B2B Sales