Feeds to Scour
SubscribedAll
Scoured 24429 posts in 22.0 ms
mmgehlot/bitpolar: BitPolar: near-optimal vector quantization — 3-8 bit compression with zero training. 58 integrations across every major AI framework.  📊Quantization
github.com·2d·Hacker News·
HyVIC: A Metric-Driven Spatio-Spectral Hyperspectral Image Compression Architecture Based on Variational Autoencoders  🧠Neural Compression
arxiv.org·3d·
Fujitsu One Compression (LLM Quantization)  📊Quantization
fujitsuresearch.github.io·15h·Hacker News·
PolarQuant: Optimal Gaussian Weight Quantization via Hadamard Rotation for LLM Compression  📊Quantization
arxiv.org·1d·
Mechanistically Interpreting Compression in Vision-Language Models  🧠Neural Compression
arxiv.org·6d·
TurboAngle: Near-Lossless KV Cache Compression via Uniform Angle Quantization  📦Code Density
arxiv.org·2d·
KVSculpt: KV Cache Compression as Distillation  ⚡Cache Theory
arxiv.org·2d·
A Compression Perspective on Simplicity Bias  🧠Neural Compression
arxiv.org·3d·
KV Cache Quantization for Self-Forcing Video Generation: A 33-Method Empirical Study  🖥️Hardware Architecture
arxiv.org·2d·
Towards Practical Lossless Neural Compression for LiDAR Point Clouds  🧠Neural Compression
arxiv.org·6d·
End-to-End Image Compression with Segmentation Guided Dual Coding for Wind Turbines  🧠Learned Compression
arxiv.org·1d·
Edge Reliability Gap in Vision-Language Models: Quantifying Failure Modes of Compressed VLMs Under Visual Corruption  📊Rate-Distortion Theory
arxiv.org·2d·
Contrastive Learning Boosts Deterministic and Generative Models for Weather Data  🧠Machine Learning
arxiv.org·6d·
Compressing Transformer Language Models via Matrix Product Operator Decomposition: A Case Study on PicoGPT  🧠Learned Compression
arxiv.org·2d·
OneComp: One-Line Revolution for Generative AI Model Compression  🧠Neural Compression
arxiv.org·1d·
Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML  ⚡Compression Hardware
arxiv.org·6d·
Octree-based Learned Point Cloud Geometry Compression: A Lossy Perspective  💎Information Crystallography
arxiv.org·2d·
Extremum-Based Joint Compression and Detection for Distributed Sensing  📐Compression Bounds
arxiv.org·2d·
Label-Free Cross-Task LoRA Merging with Null-Space Compression  🧠Neural Compression
arxiv.org·3d·
Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression  🧠Neural Compression
arxiv.org·2d·

Keyboard Shortcuts

Navigation
Next / previous item
j/k
Open post
oorEnter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help