全部收录论文
论文 · 第 78 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 78 / 141 页
查找论文请用站内搜索。
- Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction
- CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG
- Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints
- Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agents
- Autodata: An agentic data scientist to create high quality synthetic data
- Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
- The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
- AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
- BitNet Text Embeddings
- Boost Inference Performance up to 15x on NVIDIA Blackwell Using DFlash Speculative Decoding
- Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding
- Scaling AI Inference Across Multiple GPUs Using NVIDIA TensorRT with Multi-Device Inference Support
- Run DiffusionGemma on NVIDIA for Developer-Ready, High-Throughput Text Generation
- Maximize AI Factory Energy Efficiency Through Full-Stack Inference and Training Optimizations
- Optimizing cloud economics with linear elastic caching
- Improved Large Language Diffusion Models
- DREAM: Dense Retrieval Embeddings via Autoregressive Modeling
- Unifying Search and Recommendation in LLMs via Gradient Multi-Subspace Tuning
- Reasoning over Semantic IDs Enhances Generative Recommendation
- Verifiable Reasoning for LLM-based Generative Recommendation
- Dialogue to Discovery: Attribute-Aware Preference Elicitation for Conversational Product Search Assistants
- INSPIRE: Intent-aware Neural Sponsored Product Retrieval for E-commerce
- Unified Multi-Task Relevance Modeling for E-Commerce: Comparing Task Routing Architectures Across LLMs and Cross-Encoders
- Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
- Scaling Dense Retrieval with LLM-Annotated Training Data: Structured Mining and Progressive Curriculum for E-Commerce Sponsored Search
- Quantifying Prior Dominance in RAG Systems
- Thinking to recall: How reasoning unlocks parametric knowledge in LLMs
- Unified Dominance Graph for Interval-Predicate Approximate Nearest Neighbor Search
- Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs
- MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval
- ChartWalker: Benchmarking the Cross-Chart RAG Task
- Does My Embedding Reflect That A = B? Evaluating Mathematical Equivalence in Embedding Models
- The P-Completeness of Inverted Index Traversal: On the Complexity of Evaluating Boolean Query DAGs
- When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agents
- OpenThoughts-Agent: Data Recipes for Agentic Models
- Qwen-AgentWorld: Language World Models for General Agents
- Metis: Bridging Text and Code Memory for Self-Evolving Agents
- EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL
- Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
- AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning
- ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection
- Talos: Scaling rare disease diagnosis with automated, iterative genomic reanalysis
- Are We Ready For An Agent-Native Memory System?
- Towards Fast Domain Adaptation and Fine-Grained User Simulation for Evaluating Conversational Recommender Systems
- URecJPQ: Memory-efficient Multimodal Recommendation Models through RecJPQ in Large-Scale Scenarios
- TailorMind: Towards Preference-Aligned Multimodal Content Generation
- Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs
- The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders
- LLM-as-a-Judge for Reliable and Explainable Offline Evaluation in Top-K Recommendation
- Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filtering