📡 Information Theory - 2601

The Bioelectrical Information Theory: Investigating the theoretical compression limit of bioelectrical signals under artificial intelligence

Elements of Cryptanalysis: From Al-Kindi to Post-Quantum Standards — Elements of Cryptanalysis: From Al-Kindi to Post-Quantum Standards

📓Jupyter Notebooks

bnaskrecki.faculty.wmi.amu.edu.pl·

Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs

💬Prompt Engineering Academic

arxiv.org·

Reorgs happen

👥Engineering Management Blog

ben.balter.com··Hacker News

Less-relevant results

KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.

🧩Cognitive Science Code

github.com··Hacker News

DIFFRACT: Neuralized Utility Maximization for Wireless Networks by Differentiable Programming

🔍Neural Architecture Search Academic

arxiv.org·

Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers

🐍Mamba SSM Academic

arxiv.org·

Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation

🚂Error Propagation Academic

arxiv.org·

fastai: style

🤖AI Reference

docs.fast.ai··Hacker News

FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models

🪜Recursive Descent Academic

arxiv.org·

Adapting Diffusion Language Models for Lossless Pixel-Level Image Transmission

💡Explainable AI Academic

arxiv.org·

The Confidence Trap: Calibration Attacks for Graph Neural Networks

🗺️Region Inference Academic

arxiv.org·

Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages

✨Effect Inference Academic

arxiv.org·

Constructing VAE Latent Spaces with Prescribed Topology

🐍Mamba SSM Academic

arxiv.org·

Synthetic Personalities: How Well Can LLMs Mimic Individual Respondents Using Socio-Economic Microdata?

🌱Minimal ML Academic

arxiv.org·

A Temporal Spatial Minimax Rate for Smoothly-Varying Distributions in Wasserstein Space

🎲Probabilistic Programming Academic

arxiv.org·

Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillatio

🗺️Region Inference Academic

arxiv.org·

The Bioelectrical Information Theory: Investigating the theoretical compression limit of bioelectrical signals under artificial intelligence

Cosmos-Research-Institute/Emulation/Life at main · cosmosoneness/Cosmos-Research-Institute

Good teachers don’t cheat

Minimum Distortion Quantization with Specified Output Distribution

Elements of Cryptanalysis: From Al-Kindi to Post-Quantum Standards — Elements of Cryptanalysis: From Al-Kindi to Post-Quantum Standards

Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs

Reorgs happen

KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.

DIFFRACT: Neuralized Utility Maximization for Wireless Networks by Differentiable Programming

Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers

Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation

fastai: style

FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models

Adapting Diffusion Language Models for Lossless Pixel-Level Image Transmission

The Confidence Trap: Calibration Attacks for Graph Neural Networks

Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages

Constructing VAE Latent Spaces with Prescribed Topology

Synthetic Personalities: How Well Can LLMs Mimic Individual Respondents Using Socio-Economic Microdata?

A Temporal Spatial Minimax Rate for Smoothly-Varying Distributions in Wasserstein Space

Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillatio