📊 Compression Proofs - matmat

durrello/logsentry: Serverless log-scanning pipeline that detects secrets, credentials, and sensitive data in application logs. AWS Lambda + Kinesis + DynamoDB + SNS. Terraform IaC, CI/CD, DevSecOps.

🧱Immutable Infrastructure Code

github.com··DEV

A Note on the Kullback-Leibler Divergence in Discretized Empirical Distributions

🔬Academic Search Academic

arxiv.org·

What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents

🧠Machine Learning Academic

arxiv.org·

Adapting Diffusion Language Models for Lossless Pixel-Level Image Transmission

📐Compression Mathematics Academic

arxiv.org·

Speaker-Invariant Representation Learning for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck

⧗Information Bottleneck Academic

arxiv.org·

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

📊Rate-Distortion Theory Academic

arxiv.org·

Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks

📊Rate-Distortion Theory Academic

arxiv.org·

Code Lifespan Survival Analysis (CLSA): Predicting the Survival of Source Code Lines Using AST-Aware Mining

📈Entropy Estimation Academic

arxiv.org·

SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning

📈Mutual Information Academic

arxiv.org·

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

📈Entropy Estimation Academic

arxiv.org·

Worst-Case Update Complexity of the Preisach Extremum Stack

📐Compression Mathematics Academic

arxiv.org·

Towards Pretraining Text Encoders for TabPFN

🧠Machine Learning Academic

arxiv.org·

CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding

🔤Character Classification Academic

arxiv.org·

Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents

📐Vector Similarity Academic

arxiv.org·

Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability

🧠Machine Learning Academic

arxiv.org·

Information Bottleneck Meets Quantization: Finite Rate Analysis and Optimal Designs

Ice-sheet regime shifts with climate warming

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

The Wrong Epsilon to the Brain

IB-HFN: Information Bottleneck-Driven SAR-Optical Fusion Network for High-Fidelity Cloud Removal

durrello/logsentry: Serverless log-scanning pipeline that detects secrets, credentials, and sensitive data in application logs. AWS Lambda + Kinesis + DynamoDB + SNS. Terraform IaC, CI/CD, DevSecOps.

A Note on the Kullback-Leibler Divergence in Discretized Empirical Distributions

What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents

Adapting Diffusion Language Models for Lossless Pixel-Level Image Transmission

Speaker-Invariant Representation Learning for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck

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

Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks

Code Lifespan Survival Analysis (CLSA): Predicting the Survival of Source Code Lines Using AST-Aware Mining

SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning

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

Worst-Case Update Complexity of the Preisach Extremum Stack

Towards Pretraining Text Encoders for TabPFN

CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding

Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents

Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability