Improving Multimodal Learning via Imbalanced Learning
arxiv.org·16h
🧠Machine Learning
Categorical Features: The Backbone of Search & Recs Engineering
shaped.ai·20h
🧠Learned Indexing
Translation using deep neural networks – Transformer
aamster.github.io·1d·
Discuss: Hacker News
🧠Neural Codecs
CLIP Model Overview : Unlocking the Power of Multimodal AI
towardsdatascience.com·1d
🚀SIMD Text Processing
🎯 Building Attention Mechanisms from Scratch: A Complete Guide to Understanding Transformers
dev.to·1d·
Discuss: DEV
🧠Machine Learning
A Training-Free, Task-Agnostic Framework for Enhancing MLLM Performance on High-Resolution Images
arxiv.org·16h
💻Local LLMs
Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning
arxiv.org·1d
🧠Machine Learning
Incomplete Multiview Learning via Wyner Common Information
arxiv.org·16h
⧗Information Bottleneck
Cross-modal Associations in Vision and Language Models: Revisiting the bouba-kiki effect
arxiv.org·16h
🤖Advanced OCR
L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training
arxiv.org·1d
📊Rate-Distortion Theory
Show HN: Context Rot Technical Report – How Input Length Impacts LLM Performance
research.trychroma.com·1d·
Discuss: Lobsters, Hacker News
🔍Information Retrieval
Ambiguity-Aware and High-Order Relation Learning for Multi-Grained Image-Text Matching
arxiv.org·16h
🤖Advanced OCR
CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards
arxiv.org·16h
🔍Information Retrieval
Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift
arxiv.org·16h
🤖Advanced OCR
Accuracy Is Dead: Calibration, Discrimination, and Other Metrics You Actually Need
towardsdatascience.com·19h
🧠Intelligence Compression
Overcoming catastrophic forgetting in neural networks
arxiv.org·16h
🧠Machine Learning
Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning
arxiv.org·16h
🕸️Graph Embeddings
Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting
arxiv.org·16h
🧠Machine Learning
Memory-Efficient Personalization of Text-to-Image Diffusion Models via Selective Optimization Strategies
arxiv.org·16h
🔢Binary Embeddings
RefSTAR: Blind Facial Image Restoration with Reference Selection, Transfer, and Reconstruction
arxiv.org·16h
🤖Advanced OCR