全部收录论文
论文 · 第 123 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 123 / 141 页
查找论文请用站内搜索。
- UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking
- Entire Space Counterfactual Learning for Reliable Content Recommendations
- CollectiveKV: Decoupling and Sharing Collaborative Information in Sequential Recommendation
- Sequence-aware Large Language Models for Explainable Recommendation
- Lightweight Fairness for LLM-Based Recommendations via Kernelized Projection and Gated Adapters
- SumRank: Aligning Summarization Models for Long-Document Listwise Reranking
- Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction
- Accelerating Matrix Factorization by Dynamic Pruning for Fast Recommendation
- An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System
- Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
- Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG
- Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
- CoCR-RAG: Enhancing Retrieval-Augmented Generation in Web Q&A via Concept-oriented Context Reconstruction
- Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agents
- S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering
- Mixture of Demonstrations for Textual Graph Understanding and Question Answering
- MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG
- Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval
- MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
- RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use
- Composer 2 Technical Report
- Environment Maps: Structured Environmental Representations for Long-Horizon Agents
- Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling
- FinToolSyn: A Forward Synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
- Willful Disobedience: Automatically Detecting Failures in Agentic Traces
- The Cognitive Firewall: Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense
- AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model
- Efficient Benchmarking of AI Agents
- MoE-Sieve: Routing-Guided LoRA for Efficient MoE Fine-Tuning
- LMetric: Simple is Better - Multiplication May Be All You Need for LLM Request Scheduling
- Diet Your LLM: Dimension-wise Global Pruning of LLMs via Merging Task-specific Importance Score
- VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions
- TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models
- MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens
- Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding
- The Compression Paradox in LLM Inference: Provider-Dependent Energy Effects of Prompt Compression
- LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load
- AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization
- Masked Diffusion Generative Recommendation
- Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation
- ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment
- KARMA: Knowledge-Action Regularized Multimodal Alignment for Personalized Search at Taobao
- GateSID: Adaptive Gating for Semantic-Collaborative Alignment in Cold-Start Recommendation
- Training-free Adjustable Polynomial Graph Filtering for Ultra-fast Multimodal Recommendation
- Variational Bayesian Personalized Ranking
- E-CARE: An Efficient LLM-based Commonsense-Augmented Framework for E-Commerce
- On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding
- Personalized Federated Sequential Recommender
- A Collaborative Ensemble Framework for CTR Prediction
- Multi-objective Recommendation via Multi-population Auxiliary Evolution Framework (MOEA-MIAE)