全部收录论文
论文 · 第 89 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 89 / 141 页
查找论文请用站内搜索。
- Uniboost: Global Coordination with Value Alignment for Fair and Efficient Traffic Allocation
- Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation
- L2Rec: Towards Dual-View Understanding of LLMs for Personalized Recommendation
- VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
- BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback
- Exploration on Demand: From Algorithmic Control to User Empowerment
- RAGEAR: Retrieval-Augmented Graph-Enhanced Academic Recommender
- Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
- Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking
- Is Position Bias in Dense Retrievers Built In-or Learned from Data?
- The Coverage Illusion: From Pre-retrieval Routing Failure to Post-retrieval Cascades in a Production RAG System
- Generalized Range Filtering Approximate Nearest Neighbor Search: Containment and Overlap [Technical Report]
- From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering
- LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval
- Rethinking Agentic RAG: Toward LLM-Driven Logical Retrieval Beyond Embeddings
- RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
- The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
- RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
- Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement
- Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments
- Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows
- SPEAR: Code-Augmented Agentic Prompt Optimization
- Building self-improving tax agents with Codex
- Memory Architectures for Multi-Turn Text-to-SQL: A Benchmark and Empirical Study
- SilverTorch: Index as Model — A New Retrieval Paradigm for Recommendation Systems
- MobileMoE: Scaling On-Device Mixture of Experts
- Develop High-Performance GPU Kernels in C++ with NVIDIA CUDA Tile
- RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
- Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling
- Extract More Kernel Performance with NVIDIA CompileIQ Auto-Tuning
- NVIDIA CUDA 13.3 Enhances GPU Development with Tile Programming in C++, Compiler Autotuning, and Python Updates
- In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
- From Item-Only to Query-Item: Query-Conditioned Generative Search with QGS in Quark
- Memento: Personalized RAG-Style Long-Retention Data Scaling for META Ads Recommendation
- Equip Pre-ranking with Target Attention by Residual Quantization (TARQ)
- How Reliable Are Semantic-ID Tokenizer Comparisons in Generative Recommendation?
- DeGRe: Dense-supervised Generative Reranking for Recommendation
- BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
- SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling
- RecGOAT: Graph Optimal Adaptive Transport for LLM-Enhanced Multimodal Recommendation with Dual Semantic Alignment
- Self-Balancing Gradient Allocation for Heterogeneity-Aware Feature Generation in CTR Prediction (HeteGenCTR)
- Channel-wise Vector Quantization (CVQ)
- Equip Pre-ranking with Target Attention by Residual Quantization (TARQ)
- Memento: Personalized RAG-Style Long-Retention Data Scaling for META Ads Recommendation
- SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling
- From Item-Only to Query-Item: Query-Conditioned Generative Search with QGS in Quark
- LENS: A Staged Design for Interaction Granularity in Sequential CTR Prediction
- DeGRe: Dense-supervised Generative Reranking for Recommendation
- Selective Test-Time Compute Scaling for CTR Prediction via Uncertainty-Triggered Feature Path Exploration (UTTSI)
- HeteGenCTR: Self-Balancing Gradient Allocation for Heterogeneity-Aware Feature Generation in CTR Prediction