全部收录论文
论文 · 第 15 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 15 / 141 页
查找论文请用站内搜索。
- From Noisy Retrieval to Decision Evidence: Silver Evidence Demonstrations for In-Context Learning
- The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering
- Before the Ticket: Grounding HPC User Support in Documentation and Resolved Tickets with an Agentic LLM Assistant
- GeoLEON-CLIP: Graph-Anchored Multimodal Contrastive Learning for Geographic Region Representation
- Synthetic-to-Real Text-Based Person Anomaly Search via Multi-Model Retrieval Fusion and Cross-Encoder Reranking
- KVStream: Adaptive Parallel Storage Management for KV Caching in Large-Scale LLM Serving
- Advancing Generative Recommendation Inference: our collaboration with NVIDIA on TensorRT LLM
- BiLoCo: Binary Low-Rank Corrections for Post-Training Quantization
- GS-MoE: Training-Free MoE Compression via Groupwise Subspace Sharing and Pruning
- HyScale: Scaling Long-Context Training for Learned Sparse Attention
- Nested Sparsity for Scalable Pretraining and Continual Learning
- Efficient Omni-modal Large Language Model Inference via Per-Query Modality Selection
- Tensormesh Launches Tensormesh Platform to Cut LLM Inference Costs by Reusing KV Cache at Enterprise Scale
- Kolibri: A Sovereign European Model on the Pareto Frontier
- 人工智能平台 PAI:模型蒸馏(ModelDistill)
- How Language Models Learn Taste: Brand Preference in LLMs
- A Cue's Hidden Price: Auditing Seller Influence on AI Shoppers
- LLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades
- Prompting Strategy Effects Depend on the Judge: A Multilingual Study of LLM-as-a-Judge Robustness
- PAIR: Preference-Aligned Intent Retrieval for Premium People Recommendation at LinkedIn
- Ranking Bandits for Carousel Interfaces with Observable Browsing Depth
- Bezier-Guided Adaptive Flow for Cross-domain Sequential Recommendation
- Behavior lifetime modeling uses time sensitive behavioral signals to rank candidate items for purchase in E commerce recommendation
- MAPS: A Multi-Agent Personalized Script-Driven Video Advertising System Enhanced by Reinforcement Learning
- UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents
- FairFRESH: A Neuro-Symbolic Framework for Fair and Explainable Household Food Recommendation
- Truthful by Omission: Click Thinning for LLM-Native Advertising
- From Scores to Safe Sets: Exact Safety--Constrained Decoding for Medication Recommendation
- FAIRGate: Agentic Runtime Policy Selection and Verified Repair for Fairer Recommendation Delivery
- When Agentic Retrieval Fails Silently: Framework and Production Evidence from a Creative AI Assistant
- AutoSim: A Self-Improving User Simulator for Conversational Search Evaluation
- Learning Marginal Viewpoint Utility for Budgeted Evidence Selection in RAG
- ULME: Predictive Coupling for Mutually Reinforcing Embedding and Language Modeling
- Rubric-Calibrated Preferences: Cross-Query Calibration of LLM Judgments via Item Response Theory
- Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models
- Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation
- ERCLIP: Small-Data Adaptation of CLIP for Free-Length Image-Text Retrieval
- FlexVDR: Learning to Allocate Matryoshka Representation Budgets for Visual Document Retrieval
- Unbalanced Optimal Transport for Efficient Visual Document Retrieval
- ATTUNE: Agentic Throughput Tuning for LLM Training
- uGDS: A User-Space Development Kit for High-Performance GPU Direct Storage
- RACE: RoPE-Aligned Attention Compression Based on Query-Key Activation Energies
- Cache Engineering for Agents
- Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity
- Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 2
- When PTQ Calibration Helps or Hurts: Dose-Driven Collapse and Validation-Gated Abstention in Quantized Text Embedders
- Gandalf: Flash Shall Not Die! Increasing Flash Storage Lifetime for KV Cache Offloading in LLM Serving
- Lychee: Certified Screening of Inverted Lists for High-Recall Vector Search
- Scaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 1
- UniRec: A Unified Expressive-Aligned Generative Recommendation Framework for E-commerce