全部收录论文
论文 · 第 83 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 83 / 141 页
查找论文请用站内搜索。
- SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating
- LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling
- EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge
- The Illusion of Multi-Agent Advantage
- Reward Modeling for Multi-Agent Orchestration
- MiniPIC: Flexible Position-Independent Caching in <100LOC
- MiniMax Sparse Attention
- Can I Buy Your KV Cache?
- TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
- The Hidden Power of Scaling Factor in LoRA Optimization
- Multi-Bitwidth Quantization for LLMs Using Additive Codebooks
- Maestro: Workload-Aware Cross-Cluster Scheduling for LLM-Based Multi-Agent Systems
- ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling
- GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving
- MemRefine: LLM-Guided Compression for Long-Term Agent Memory
- Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations
- Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
- Generative Archetype-Grounded Item Representations for Sequential Recommendation
- Tau-Rec: A Verifiable Benchmark for Agentic Recommender Systems
- SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers
- LLM-Based User Personas for Recommendations at Scale
- DiffCold: A Diffusion-based Generative Model for Cold-Start Item Recommendation
- One Polluted Page Is Enough: Evaluating Web Content Pollution in Generative Recommenders
- Efficient and Robust Online Learning to Rank in Decentralized Systems
- CFALR: Collaborative Filtering-Augmented Large Language Model for Personalized Fashion Outfit Recommendation
- OneRetrieval: Unifying Multi-Branch E-commerce Retrieval with an Editable Generative Model
- CoDeR: Local Constraint-Compatible Retrieval Beyond Semantic Similarity
- Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
- Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning
- How Fine-Grained Should a RAG Benchmark Be? A Hierarchical Framework for Synthetic Question Generation
- When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval
- CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency
- X-MADAM-RAG: Diagnosing and Handling Chinese-English Evidence Conflict in Retrieval-Augmented Generation
- GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
- Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval
- Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation
- Agentic Transformers Provably Learn to Search via Reinforcement Learning
- NVIDIA Achieves Leading Agentic Coding Performance on First Agentic AI Benchmark (AA-AgentPerf)
- IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
- Co-Evolution of Policy and Internal Reward for Language Agents
- Deploy Long-Context Reasoning and Agentic Workflows with MiniMax M3 on NVIDIA Accelerated Infrastructure
- DeepSeek-V4: 1.6T-Parameter MoE with DeepSeek Sparse Attention for Long-Context Reasoning
- VeriCache: Turning Lossy KV Cache into Lossless LLM Inference
- 美团 BI 在指标平台和分析引擎上的探索和实践
- One-Click Multi-Tenant Security with NVIDIA Quantum InfiniBand
- A low-carbon computing platform from your retired phones
- OneFeed: A Unified Generative Framework for Feed Content Enhancement and Query Generation
- Teach Multimodal Recommendation Model to See via Personalized Visual Extraction and Adaptive Learning
- TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
- Popcorn: A Configurable Benchmark for Visual Evidence in Multimodal Movie Recommendation