artificial intelligence

Feeds to Scour
SubscribedAll
Scoured 39 posts in 11.6 ms

OffQ: Taming Structured Outliers in LLM Quantization by Offsetting

馃LLMsContent type: Academic
arxiv.org

Efficient and accurate neural-field reconstruction using resistive memory

馃敩NeurotechContent type: Academic
nature.com

[AINews] FrontierCode: Benchmarking for Code Quality over Slop

馃claude codeContent type: News
latent.space

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

馃LLMsContent type: NewsContent type: Blog
blog.googleHacker News

Five labs, five minds: building a multi-model finance drama on small models

馃捈AI Business ModelsContent type: Blog
huggingface.co

Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression

馃LLMsContent type: Academic
arxiv.org

Diverse binding poses of agonistic neurotoxins on human Na v 1.6

馃敩NeurotechContent type: Academic
nature.com

[AINews] not much happened today

馃AI AgentsContent type: News
latent.space

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin

馃LLMsContent type: Academic
arxiv.org

Optimal Post-Training Quantization Scales and Where to Find Them

馃LLMsContent type: Academic
arxiv.org

Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment

馃LLMsContent type: Academic
arxiv.org

Value-and-Structure Alignment for Routing-Consistent Quantization of Mixture-of-Experts Models

馃LLMsContent type: Academic
arxiv.org

Trainable Smooth-Rotation Transforms with Learned Channel Scales for LLM Quantization

馃LLMsContent type: Academic
arxiv.org

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

馃搱Tech TrendsContent type: Academic
arxiv.org

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

馃LLMsContent type: Academic
arxiv.org

ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization

馃LLMsContent type: Academic
arxiv.org

Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillatio

馃LLMsContent type: Academic
arxiv.org

LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization

馃LLMsContent type: Academic
arxiv.org

Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning

鈿涳笍Quantum ComputingContent type: Academic
arxiv.org

Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models

馃LLMsContent type: Academic
arxiv.org

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
Save / unsave
s

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