全部收录论文
论文 · 第 118 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 118 / 141 页
查找论文请用站内搜索。
- User-Aware Conditional Generative Total Correlation Learning for Multi-Modal Recommendation
- Dual-Perspective Disentangled Multi-Intent Alignment for Enhanced Collaborative Filtering
- Meta Adaptive Ranking Model: Bending the Inference Scaling Curve to Serve LLM-Scale Models for Ads
- DiffuRank: Effective Document Reranking with Diffusion Language Models
- Efficient Learning of Sparse Representations from Interactions
- DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries
- LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking
- Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming
- Overcoming the "Impracticality" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework
- Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
- LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
- Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
- Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets
- Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference
- InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking
- Self-Optimizing Multi-Agent Systems for Deep Research
- Terminal Agents Suffice for Enterprise Automation
- Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
- Textual Equilibrium Propagation for Deep Compound AI Systems
- APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay
- ProGraph-R1: Progress-aware Reinforcement Learning for Graph Retrieval Augmented Generation
- KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta
- FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving
- Fast NF4 Dequantization Kernels for Large Language Model Inference
- Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference
- When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
- TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
- Evaluating Small Language Models for Front-Door Routing: A Harmonized Benchmark and Synthetic-Traffic Experiment
- JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
- SLMQuant: Benchmarking Small Language Model Quantization for Practical Deployment
- How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference
- Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
- KernelEvolve: How Meta's Ranking Engineer Agent Optimizes AI Infrastructure
- On the Efficiency of Sequentially Aware Recommender Systems: Cotten4Rec
- Towards Multi-Behavior Multi-Task Recommendation via Behavior-informed Graph Embedding Learning
- Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation
- To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining
- Using Predefined Vector Systems to Speed Up Neural Network Multimillion Class Classification
- Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts
- Universal YOCO for Efficient Depth Scaling
- Toward Holistic Evaluation of Recommender Systems Powered by Generative Models
- DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
- CRoPE: Efficient Parametrization of Rotary Positional Embedding
- Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning
- ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight Budget
- UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems
- Aligning Recommendations with User Popularity Preferences
- GRank: Towards Target-Aware and Streamlined Industrial Retrieval with a Generate-Rank Framework
- Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization
- MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding