全部收录论文
论文 · 第 110 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 110 / 141 页
查找论文请用站内搜索。
- Multi-LLM Token Filtering and Routing for Sequential Recommendation
- HorizonBench: Long-Horizon Personalization with Evolving Preferences
- Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems
- On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability
- GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing
- Training for Compositional Sensitivity Reduces Dense Retrieval Generalization
- Beyond Single-Score Ranking: Facet-Aware Reranking for Controllable Diversity in Paper Recommendation
- DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
- FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG
- LiteSemRAG: Lightweight LLM-Free Semantic-Aware Graph Retrieval for Robust RAG
- ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generation
- Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers
- ReasoningBank: Enabling agents to learn from experience
- MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
- AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
- GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning
- Benchmarking Real-Time Question Answering via Executable Code Workflows
- When Can LLMs Learn to Reason with Weak Supervision?
- Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
- On the Reliability of Computer Use Agents
- Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
- RLM-on-KG: Heuristics First, LLMs When Needed: Adaptive Retrieval Control over Mention Graphs for Scattered Evidence
- A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search
- GLM-5.1: Agentic Engineering Open-Source LLM (MIT License)
- Gemma 4: Google Open-Weight Model Family (Apache 2.0)
- River-LLM: Large Language Model Seamless Exit Based on KV Share
- Architecture Matters More Than Scale: A Comparative Study of Retrieval and Memory Augmentation for Financial QA Under SME Compute Constraints
- DeepSeek V4: Open-Weight Foundation Model Release
- The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
- FedCRF: A Federated Cross-domain Recommendation Method with Semantic-driven Deep Knowledge Fusion
- Domain-Specific Query Understanding for Automotive Applications: A Modular and Scalable Approach
- AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval
- Accelerating open-source infrastructure development for frontier AI at scale
- On the Equivalence Between Auto-Regressive Next Token Prediction and Full-Item-Vocabulary Maximum Likelihood Estimation in Generative Recommendation
- From Features to Transformers: Redefining Ranking for Scalable Impact
- Does LLM Focus on the Right Words? Mitigating Context Bias in LLM-based Recommenders
- RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models
- Towards Comprehensible Recommendation with Large Language Model Fine-tuning
- Diffusion-Based Cloud-Edge-Device Collaborative Learning for Next POI Recommendations
- Multi-Epoch Learning with Data Augmentation for Deep Click-Through Rate Prediction
- Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models
- What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context
- Beyond One-Size-Fits-All: Adaptive Test-Time Augmentation for Sequential Recommendation
- Learning Behaviorally Grounded Item Embeddings via Personalized Temporal Contexts
- A Universal Framework for Compressing Embeddings in CTR Prediction
- A multi-task heterogeneous graph learning with cross-attention fusion for robust recommendation
- SRSUPM: Sequential Recommender System Based on User Psychological Motivation
- Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
- Intent Propagation Contrastive Collaborative Filtering
- vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents