全部收录论文
论文 · 第 103 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 103 / 141 页
查找论文请用站内搜索。
- NorBERTo: A ModernBERT Model Trained for Portuguese with 331 Billion Tokens Corpus
- RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI
- How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework
- Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment
- From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing
- Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
- Lost in State Space: Probing Frozen Mamba Representations
- Building trust into AI
- MTGR:美团外卖生成式推荐 Scaling Law 落地实践
- GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion
- CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation
- GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation
- BehaveGPT: A Foundation Model for Large-scale User Behavior Modeling
- Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation
- One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation
- LLM-Enhanced Topical Trend Detection at Snapchat
- Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation
- Hierarchical Multi-Persona Induction from User Behavioral Logs: Learning Evidence-Grounded and Truthful Personas
- AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization
- LUCid: Redefining Relevance For Lifelong Personalization
- Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies
- A Gated Hybrid Contrastive Collaborative Filtering Recommendation
- A Reproducibility Study of LLM-Based Query Reformulation
- Negative Data Mining for Contrastive Learning in Dense Retrieval at IKEA.com
- When More Reformulations Hurt: Avoiding Drift using Ranker Feedback
- Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing
- How Generative AI Disrupts Search: An Empirical Study of Google Search, Gemini, and AI Overviews
- NuggetIndex: Governed Atomic Retrieval for Maintainable RAG
- LLM-Oriented Information Retrieval: A Denoising-First Perspective
- A Replicability Study of XTR
- FollowTable: A Benchmark for Instruction-Following Table Retrieval
- Reproducing Adaptive Reranking for Reasoning-Intensive IR
- 美团 LongCat-Flash-Thinking-2601:Agentic Search/Tool Use 登顶开源 SOTA
- Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
- Experiential Reflective Learning for Self-Improving LLM Agents
- Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks
- Memory for Autonomous LLM Agents (AgeMem): Mechanisms, Evaluation, and Emerging Frontiers
- Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
- The Amazing Agent Race: Strong Tool Users, Weak Navigators
- Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration
- Agentization of Digital Assets for the Agentic Web: Concepts, Techniques, and Benchmark
- DR3-Eval: Towards Realistic and Reproducible Deep Research Evaluation
- Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
- Scalable Inference Architectures for Compound AI Systems: A Production Deployment Study
- ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training
- AMPD: Efficient Multi-round LLM Inference over Disaggregated Serving
- DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference
- Meituan LongCat-Next: 原生多模态大模型与训练/推理框架协同优化
- LLM-Guided Runtime Parameter Optimization for Energy-Efficient Model Inference
- Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism