Why LLMs cannot reach GenAI, but why it looked like they could
haversine.substack.com·11h·
Discuss: Substack
🧠Intelligence Compression
Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data
arxiv.org·1d
🧠Machine Learning
Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor-EM Method
arxiv.org·3d
🌀Differential Geometry
A Systematic Evaluation of Self-Supervised Learning for Label-Efficient Sleep Staging with Wearable EEG
arxiv.org·1d
🧠Machine Learning
Causality Guided Representation Learning for Cross-Style Hate Speech Detection
arxiv.org·1d
🎙️Whisper
GNN Predictions: Hidden Bugs and the Verification Nightmare by Arvind Sundararajan
dev.to·12h·
Discuss: DEV
⚙️Proof Engineering
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
arxiv.org·1d
⚡Proof Automation
Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space
arxiv.org·4d
⧗Information Bottleneck
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·12h·
Discuss: DEV
📊Multi-vector RAG
Retentive Relevance: Capturing Long-Term User Value in Recommendation Systems
arxiv.org·1d
🎯Content Recommendation
A Total Variation Regularized Framework for Epilepsy-Related MRI Image Segmentation
arxiv.org·2d
⧗Information Bottleneck
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
arxiv.org·1d
💻Local LLMs
Characteristic Learning for Provable One Step Generation
arxiv.org·4d
🤖Grammar Induction
Unsupervised Active Learning via Natural Feature Progressive Framework
arxiv.org·4d
🧠Machine Learning
Detecting and Mitigating Insertion Hallucination in Video-to-Audio Generation
arxiv.org·1d
👁️Perceptual Coding
Automated Anomaly Detection in Account Takeover via Multi-Modal Graph Neural Network Fusion
dev.to·6h·
Discuss: DEV
🔍Vector Forensics
Improving Artifact Robustness for CT Deep Learning Models Without Labeled Artifact Images via Domain Adaptation
arxiv.org·2d
🤖Advanced OCR
Geometry Meets Vision: Revisiting Pretrained Semantics in Distilled Fields
arxiv.org·5d
🌀Differential Geometry
Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
arxiv.org·2d
⧗Information Bottleneck
Addressing the ID-Matching Challenge in Long Video Captioning
arxiv.org·2d
📐Vector Similarity