全部收录论文
论文 · 第 10 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 10 / 141 页
查找论文请用站内搜索。
- How BERT-based Cross-Encoders Model Relevance in Information Retrieval?
- ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science
- Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings
- Prevented is Not Protected: What Attack Success Rate Hides about RAG
- Pix2Evidence: A Multimodal RAG System for Text and Visual Evidence
- Search When Needed, Proceed When Reliable: Metacognitive Reliability Supervision for Efficient Agentic Search
- Context as Infrastructure: Knowledge Compilation for Retrieval in Agentic Systems with Harnesses
- Defining Page-Centric Visual Document Retrieval and Evaluating Existing Benchmarks
- LEAP: Efficient LLM Inference Scheduling with Generalizable Length Prediction
- HiState: Hierarchical Prefix Cache Management for Hybrid LLM Serving in Agentic Workloads
- MemX: Memory-Aware Automatic Parallelism for Cross-Vendor Heterogeneous GPU Training
- Matching Workloads to Blackwell: Power-Resolved Benchmarking of NVIDIA B200 and B300 across HPC and AI Workloads
- Flide: Accelerating Decision Inference with Exact State Forking
- Trainable Vector Quantization for Large Language Models
- ACCT: Asymmetric Cross-LLM Context Transfer
- Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity
- ARK: Avoiding Routing Collisions for KV Cache Transfer in Disaggregated LLM Inference
- Making Kubernetes AI-Ready for NVIDIA Vera Rubin on Day One
- Contact Imitation Interface: Transferring Dexterous Skills by Showing How Contact Unfolds
- LeRobot: An Open-Source Library for End-to-End Robot Learning
- From Teleoperation to Long-Horizon Dexterity: Evaluating Visuomotor Skills and Offline Proxies for Dexterous Manipulation
- Learning from Fleet Experience: Collective Experience Learning Across 96 Robots
- I3L: Iterative Interactive Imitation Learning for Whole-Body Mobile Manipulation
- DiffWBC: Unlocking Steerable General Humanoid Motion Tracking via One-Step Diffusion Whole-Body Control
- RTPolicy: Real-Time (32.9 Hz) Multi-View Visuomotor Policy for Robotic Manipulation on Edge Devices
- TacClaw-Infinity: A Large-Scale Vision-Tactile-Language-Action Dataset for Dexterous Manipulation
- Vela: Scaling Vision-Language-Action Models with Adaptive Action Curve Parametrization
- Build World Models for Interactive Simulation with NVIDIA Cosmos
- Towards Reliable, Scalable, and Value-Aligned Generative Recommendation for Large-Scale Advertising
- PFA: Attention Can Be Progressively Focused in Long-Sequence Generative Recommendation
- UGR: Unified Generative Ranking for Heterogeneous E-commerce Recommendation
- RoFiGR: Coarse Routing, Fine Refinement via Level-Adaptive Distillation in Multimodal Generative Recommendation
- R2QRec: Learning Recommendation Queries from Retrieval Feedback
- Statistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence
- Merge and Branch: Efficient Tree-Structured Supervised Fine-Tuning of LLMs for Recommendation
- Federated Recommender Agents
- PALATE: Pretrained Autoregressive LATent Embeddings
- Category-Anchored Large Language Models for Next POI Recommendation
- PRISM: Personalized Item Representations in User History
- Read More, Reason Deeper: Latent Workspaces for Long-Sequence Recommendation
- Beyond IPS: Reliable Counterfactual Evaluation in Multi-Stage Ad Systems without Logged Propensities
- Floor It, Then Fill It: Simulating Creator Ecosystems for Fair Video-Content Recommendation Systems at Billion User Scale
- Revisiting Temporal Link Prediction through Structural Proximity
- CASH: A Capability-Aware Subsidy Harness for Advertiser Subsidy Allocation
- Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs
- DeepCommerceRec: a graph- and sequence-aware deep learning recommender system with cold-start adaptation for large-scale e-commerce platforms
- Hidden Disparities in Ranking: Category-Aware Fairness via Distributional Stability
- Reinforcement Learning Under Runtime Confounding: Policy Learning and Off-Policy Evaluation
- Contextual Embeddings Beyond the Gold Chunk
- Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation