全部收录论文
论文 · 第 131 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 131 / 141 页
查找论文请用站内搜索。
- Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
- Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
- DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering
- One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries
- WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
- Safe and Scalable Web Agent Learning via Recreated Websites
- WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
- VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
- LongFlow: Efficient KV Cache Compression for Reasoning Models
- Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models
- Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability
- NVIDIA Nemotron 3: Efficient and Open Intelligence
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
- AutoScout: Structured Optimization for Automating ML System Configuration
- MuxTune: Efficient Multi-Task LLM Fine-Tuning in Multi-Tenant Datacenters via Spatial-Temporal Backbone Multiplexing
- Speculative Decoding Scaling Laws (SDSL): Throughput Optimization Made Simple
- HAKES: Scalable Vector Database for Embedding Search Service
- MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization
- The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?
- TaoSR1: The Thinking Model for E-commerce Relevance Search
- Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval
- The Inequality: Quantifying the Double Penalty of Mixture-of-Experts at Inference
- RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation
- ThinkQE: Query Expansion via an Evolving Thinking Process
- Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models
- What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Arms, Compliance, and Exploration
- Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
- Verifiable Reasoning for LLM-based Generative Recommendation
- One Model Is Enough: Native Retrieval Embeddings from LLM Agent Hidden States
- Deep Research for Recommender Systems
- Scaling Multilingual Semantic Search in Uber Eats Delivery
- Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
- High-Fidelity Pruning for Large Language Models
- ERASE -- A Real-World Aligned Benchmark for Unlearning in Recommender Systems
- Why Large Language Models can Secretly Outperform Embedding Similarity in Information Retrieval
- PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents
- Rank4Gen: RAG-Preference-Aligned Document Set Selection and Ranking
- Isotonic Layer: A Universal Framework for Generic Recommendation Debiasing
- Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction
- Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization
- Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation
- T-REX: Transformer-Based Category Sequence Generation for Grocery Basket Recommendation
- Rethinking Personalization in Large Language Models at the Token Level
- Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss
- Benchmark Leakage Trap: Can We Trust LLM-based Recommendation?
- Multi-TAP: Multi-criteria Target Adaptive Persona Modeling for Cross-Domain Recommendation
- LMMRec: LLM-driven Motivation-aware Multimodal Recommendation
- A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity
- Approximate Nearest Neighbor Search for Modern AI: A Projection-Augmented Graph Approach
- MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation