全部收录论文
论文
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 1 / 141 页
查找论文请用站内搜索。
- RecMem: Recurrent Memory Compression for Long-Sequence Generative Recommendation
- RACE: Ranking-Uncertainty Aware Capacity-Adaptive Customization for Efficient Sequential Recommendation
- Learning nonlinear interactions and cross-feature couplings with product-unit residual networks
- RAG-FGO: Dynamic Optimization of Query-Rewriting Agents for Generative RAG
- Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders
- AI-Voyager: A Public-Interest System for Human-AI Civic Reasoning to Contest and Shape the Rules That Govern AI
- Towards High-Performance Multimodal Discovery: Evaluating Retrieval Efficacy and Operational Scalability in Digital Libraries
- MeReader: An Offline, Privacy-Preserving, Progress-Aware AI Assistant for Narrative eBook Reading
- Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent
- Evaluating Large Language Models for Scientific Paper Search: Retrieval Success and Inference Latency on Mac Studio and NVIDIA A100
- Lens: Training-Free Semantic Search for Cross-Tile Object and Scene Retrieval in Satellite Imagery
- Tabular Population Priors as Structured Retrieval for EHR Medication Set Prediction
- AmbiSteer: Selectively Eliciting Ambiguity-Aware Responses in Vision-Language Models
- Advancing Quantization for R&R Models with Microscaling Formats
- TIDE: Reclaiming Lost Performance In On-Policy Reinforcement Learning
- Zero-SM NCCL: A Systematic Guide to Designing and Deploying SM-Free GPU Communication
- Compiling Specialized GPU-Initiated Networking
- User-Schedulable Approximations for Quantized Tensor Programs
- Direction or Magnitude? Learning Scalars over Task-Calibrated Directions
- TailGuard-GDS: Tail-Safe Control of GPU Storage Data Movement
- VelServe: Taming Decode Jitters in LLM Inference with Tail-Calibrated Scheduling
- Callo: Serving Cache-Miss Requests with Speculative Decoding on Invalidated KV under Prefill-Decode Disaggregation
- AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs
- Training Reasoning Models in Simulation to Natively Use Real Robots
- X-Nav Technical Report: Real-World Long-Horizon Indoor-to-Outdoor Navigation on a Humanoid Robot
- Reusing Locomotion Training Recipes Across Humanoids via Body-Aligned Virtual Joints
- ERA: Error-Resistant Autonomous Object Navigation with Predicted Depth
- Agentic-Teacher: An Agentic Data Engine for Failure-Driven VLA Post-Training
- Imitation Policies Learn a Proprioceptive Anchor: A Predictive Law for Perception Noise and Its Closed Loop Cost
- PROOF: Perceptive Robustness via Out-of-Distribution Fallback for Legged Locomotion
- Objectives as Policies: Vision-Language Model Cost Programs for Contact-Rich Manipulation
- On the Utility of Pre-Trained Visual Representations for Policy Learning of Contact-Rich Insertion Tasks
- TouchTwin: Scaling Human Touch Data via Real-to-Sim-to-Real
- ReSID: Rethinking Long-Tail Retrieval in Generative Recommendation through Item Reachability
- TriGen: A Generative Paradigm for Trigger-Induced Recommendation
- SimRec: Learning to Search, Ask, and Recommend from Simulated Interaction
- From Tokens to Behaviors: Rethinking Generative Recommendation for User Trajectory Prediction
- When Does a Recommendation Spark Curiosity? Theory, Measurement, and Field Evidence
- Serving-Aligned Entire-Space Conversion Modeling via Click-Through Rate Knowledge Distillation
- Measuring, Revealing and Mitigating Harmful Content Propagation in Recommender Systems
- Sheaf-Inspired Structured Scoring Extensions of LightGCN for Collaborative Filtering
- KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation
- Too much of a good thing: Why 20 candidates beat 200 when reranking search results
- CURATOR: Scalable Fine-grained Evidence Selection for Retrieval-Augmented Generation using Decision Models
- AntEmbed: Dual-Mode Multimodal Embedding Model for Efficient and Fine-Grained Retrieval
- UMER: Unifying Embedding and Ranking via Pair-Aware Discriminative Reasoning for Universal Multimodal Retrieval
- Calibration and Conformal Prediction for Medical Question Answering in Arabic and English: Evidence from Two Non-Parallel Benchmarks
- Authenticated Approximate Nearest Neighbor Search in Outsourced Vector Databases
- Benchmarking tiered KV cache offloading on H100 GPUs in OpenShift AI 3.5
- SoScale: Second-Order Scale Search for FP4 Quantization