CORE: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning
arxiv.org·2h
⚙️Compression Benchmarking
Optical generative models
nature.com·15h
🌈Holographic Archives
A 20-Year-Old Algorithm Can Help Us Understand Transformer Embeddings
ai.stanford.edu·12h·
Discuss: Hacker News
🧮Vector Embeddings
ByteDance releases OmniHuman-1.5: long-form, emotion-aware AI avatars
omnihuman-lab.github.io·10h·
Discuss: Hacker News
🧠Learned Codecs
Quantization Robustness to Input Degradations for Object Detection
arxiv.org·2h
📊Quantization
BW21-CBV-Kit——Home Video Monitoring and Playback System
hackster.io·1d
🎬Video Codecs
Human-Inspired Computing for Robust and Efficient Audio-Visual Speech Recognition
arxiv.org·2h
🎧Learned Audio
Comparing Six Deep Learning Feature Extractors for CBIR Tasks
hackernoon.com·23h
📊Learned Metrics
Introduction to Artificial Neural Networks – Part 1 (2013)
theprojectspot.com·1d·
Discuss: Hacker News
🧠Machine Learning
NVFP4 Trains with Precision of 16-Bit and Speed and Efficiency of 4-Bit
developer.nvidia.com·3d·
Discuss: Hacker News, Hacker News
🧠Learned Codecs
Critiques of World Models
arxiviq.substack.com·9h·
Discuss: Substack
🔲Cellular Automata
Predictive Corrosion Analysis of Flexible Packaging Using Dynamic Moisture Mapping & Machine Learning
dev.to·52m·
Discuss: DEV
🌡️Preservation Physics
Positional Embeddings in Transformers: A Math Guide to RoPE & ALiBi
towardsdatascience.com·1d
📐Geometric Hashing
Drama Model Inference Efficiency Boosted by 1.7x-2.3x
pytorch.org·1d·
Discuss: Hacker News
🚀SIMD Text Processing
EffNetViTLoRA: An Efficient Hybrid Deep Learning Approach for Alzheimer's Disease Diagnosis
arxiv.org·2h
🧠Machine Learning
MAPo : Motion-Aware Partitioning of Deformable 3D Gaussian Splatting for High-Fidelity Dynamic Scene Reconstruction
arxiv.org·2h
📐Projective Geometry
Wan-S2V: Audio-Driven Cinematic Video Generation
humanaigc.github.io·1d·
Discuss: Hacker News
⏱️SMPTE Timecode
Model Merging – A Biased Overview
crisostomi.github.io·14h·
Discuss: Hacker News
🔲Cellular Automata
Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models
arxiv.org·2d
📊Learned Metrics
PRISM: A Framework Harnessing Unsupervised Visual Representations and Textual Prompts for Explainable MACE Survival Prediction from Cardiac Cine MRI
arxiv.org·2h
⧗Information Bottleneck