Autoregressive Universal Video Segmentation Model
arxiv.org·16h
📊Rate-Distortion Theory
SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation
arxiv.org·16h
📊Rate-Distortion Theory
TRIM: Accelerating High-Dimensional Vector Similarity Search with Enhanced Triangle-Inequality-Based Pruning
arxiv.org·1d
🗂️Vector Databases
ModAn-MulSupCon: Modality-and Anatomy-Aware Multi-Label Supervised Contrastive Pretraining for Medical Imaging
arxiv.org·16h
📊Learned Metrics
Joint Time-Position Statistics and Fisher Information in Drift-Diffusion Molecular Channels
arxiv.org·16h
📡Information theory
MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs
arxiv.org·1d
🧮Kolmogorov Complexity
Drama Model Inference Efficiency Boosted by 1.7x-2.3x
pytorch.org·20h·
Discuss: Hacker News
🚀SIMD Text Processing
MobileDenseAttn:A Dual-Stream Architecture for Accurate and Interpretable Brain Tumor Detection
arxiv.org·16h
🧠Machine Learning
CLARIFY: A Specialist-Generalist Framework for Accurate and Lightweight Dermatological Visual Question Answering
arxiv.org·16h
🔍Information Retrieval
E-BayesSAM: Efficient Bayesian Adaptation of SAM with Self-Optimizing KAN-Based Interpretation for Uncertainty-Aware Ultrasonic Segmentation
arxiv.org·1d
🧠Machine Learning
An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentation
arxiv.org·1d
📊Learned Metrics
DiCache: Let Diffusion Model Determine Its Own Cache
arxiv.org·1d
🧠Machine Learning
Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
arxiv.org·1d
🤝Consensus Algorithms
Federated Learning with Heterogeneous and Private Label Sets
arxiv.org·16h
💻Local LLMs
ROSE: Remove Objects with Side Effects in Videos
arxiv.org·16h
⟷Bidirectional Programming
Flatness-aware Curriculum Learning via Adversarial Difficulty
arxiv.org·16h
📊Learned Metrics
How Retrieval Algorithms Shape Better LLM Responses?
dev.to·1d·
Discuss: DEV
🔍Information Retrieval
MicroDetect-Net (MDN): Leveraging Deep Learning to Detect Microplastics in Clam Blood, a Step Towards Human Blood Analysis
arxiv.org·16h
🧠Machine Learning
Generative Interfaces for Language Models
arxiv.org·16h
⚙️Parser Generators
Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models
arxiv.org·1d
🧠Neural Codecs