全部收录论文
论文 · 第 56 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 56 / 141 页
查找论文请用站内搜索。
- Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs
- WatchLens: A Configurable Platform for Online Video Recommendation Experiments
- The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads
- DEGR: Dual Exploration-Driven Generative Re-Ranking for Adaptive Cross-Request Context Bridging
- Removing Hidden Confounding in Recommendation: A Unified Multi-Task Learning Approach
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- MTRec: Multi-Task Learning over BERT for News Recommendation
- Adaptive collaborative filtering for multi-objective Top-N recommendations with implicit feedback
- Skills Know Their Neighbors: Cluster-Contrastive Capability Pages for Skill Retrieval
- EdgeLM: Edge Demonstrations for Language Models' Table Understanding
- LLM-confidence reranker: A training-free approach for enhancing retrieval-augmented generation systems
- Neighborhood-Aware Dual Biomedical Entity Linking
- Right Reset: Chunking by Prefix Removal
- Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory Systems
- UniHEAR: Unified Heterogeneous-Source Attentive Retrieval for Knowledge-Based Visual Question Answering
- GigitAI at SemEval-2026 Task 8: Hybrid Sparse-Dense Retrieval and ...
- A Theoretical Framework for Risk Analysis of Stochastic Rankers
- How Google Search helps you find original, high-quality content
- Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming
- Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks
- FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation
- Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary
- Google Search's I/O 2026 updates: AI agents and more
- FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory
- When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents
- Characterizing the Evolving Landscape of Modern Information Seeking
- WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models
- ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation
- A Technical Report on the Second Place Solution for the CIKM 2025 AnalytiCup Competition
- 97% 召回率、900 QPS:Apache Doris 4.1 生产级向量检索的工程实践
- Getting Started with DeepSpeed for Inferencing Transformer based Models
- DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning
- What Is Compute Power? Meta's AI Infrastructure Explained
- How NVIDIA's Inference Software Stack Powers the Lowest Token Cost
- 34 Amazon Research Awards Build on Trainium recipients announced
- Data center and global networks built for AI era
- CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models
- NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap
- DualGR: Generative Retrieval with Long and Short-Term Interests Modeling
- Configure HSTU generative ranking in PAI-Rec: feature engineering, model training, and deployment
- Training Documents Reranker with Search Rubrics for Deep Research Agent
- Search, Inspect, Fetch: Exploiting Boolean Retrieval for Deep-Research Agents
- Generative Conversational Recommender System
- Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivity
- SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
- RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
- Fast and Efficient Approximate Nearest Neighbor Search for High-Dimensional LLM Embeddings
- Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
- Knowledge-Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation
- Heterogeneous Ranking in Industrial-Scale Recommender Systems: A Case Study