全部收录论文
论文 · 第 67 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 67 / 141 页
查找论文请用站内搜索。
- SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
- Agent 时代下大模型推理系统的架构优化和工程实践
- Multi-level context Modeling for consistent expert selection in Mixture-of-Experts
- Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs.
- Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation
- Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation
- Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View
- Distilling LLM Reasoning into Dense Encoders: Bridging the Accuracy-Efficiency Gap in Recommendation
- Continuous-time Discrete-space Diffusion Model for Recommendation.
- Data-Efficient Adaptation to Contextual Shifts in LLM-based Conversational Recommendation
- What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context
- HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation
- CEILLM: Confidence-Aware Dynamic Fusion of Collaborative Embedding-Infused Large Language Models for Conversational Recommendation
- RecGPT-V3 Technical Report
- RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation
- From Insight to Intervention: Interpretable Neuron Steering for Controlling Popularity Bias in Recommender Systems.
- Adaptive Continual Learning with User-Incremental Forward Compatibility for Meta-Augmented Cold-Start Recommenders.
- How Does Empowering Users with Greater System Control Affect News Filter Bubbles?
- Auditing Textual Context in Sequence-Aware Explainable Recommendation.
- 推荐算法日报 - 2026-07-01
- Multi-Task Sequential Recommendation Based on Gradient Segmentation
- Emotion-based Recommender System
- From Skill Extraction to Multistakeholder Recommendation: A Two-Stage Framework for Bias Governance in Skills-Based Job Matching
- LLM-Based Re-Ranking for Real Estate Search
- Efficient and Effective In-place Graph-based Vector Index Updates
- Scientific Claim-Source Retrieval Revisited: A Comparative Study of Style Transfer and Re-Ranking
- UTRAG at SemEval-2026 Task 8: History-Aware Query Rewriting and LoRA-Finetuned Generation for Multi-Turn RAG
- Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search
- JCT at SemEval-2026 Task 8: Resource-Efficient Multi-Turn RAG via Nano-LLM Rewriting and Hybrid Reranking
- LLMs Encode Relevance as a Layer-Wise Cross-Lingual Signal
- What Do Chinese-Language Generative Search Engines Cite and Surface? A Large-Scale Empirical Study
- Adaptive Retrieval Strategies for Biomedical Question Answering
- 大模型应用:从粗排到大模型生成:交叉熵、余弦重排序的全流程实践.97
- PCTD: Preference-Guided Counterfactual Task Decomposition for Agent Tool Retrieval
- Agentic Deep Research: How LLM Search Agents Plan, Retrieve, and Synthesize Across Dozens of Sources
- Process Reward Informed Tree Rollout for Effective Multi-Turn RL
- SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents
- Safety and alignment in an era of long-horizon models
- ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning
- What Is Your AI Agent Buying? Evaluation, Biases, Model Dependence, & Emerging Implications of Agentic E-Commerce.
- EpiNarrate: Agentic Generation of Grounded Narratives from Epidemiological Scenario Projections
- Scholar API: Search and Recommendations for Academic Search.
- CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration
- VarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMs
- Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers
- An MLIR-Based Compilation Method for Large Language Models
- Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning
- H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving
- NVIDIA NVLink: The Scale-Up Network for AI Factories
- Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content