· ai
AutoAugment: Learning Augmentation Policies from Data
Overview AutoAugment is a method that automatically discovers effective image augmentation policies. By systematically testing many simple transformations—such...
-
- · ai
The Machine Learning “Advent Calendar” Day 24: Transformers for Text in Excel
An intuitive, step-by-step look at how Transformers use self-attention to turn static word embeddings into contextual representations, illustrated with simple e...
- · ai
[Paper] Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertainty
Masked Diffusion Models (MDMs) offer flexible, non-autoregressive generation, but this freedom introduces a challenge: final output quality is highly sensitive ...
- · ai
[Paper] Autonomous Uncertainty Quantification for Computational Point-of-care Sensors
Computational point-of-care (POC) sensors enable rapid, low-cost, and accessible diagnostics in emergency, remote and resource-limited areas that lack access to...
- · ai
[Paper] C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
We present C2LLM - Contrastive Code Large Language Models, a family of code embedding models in both 0.5B and 7B sizes. Building upon Qwen-2.5-Coder backbones, ...
- · ai
[Paper] Measuring all the noises of LLM Evals
Separating signal from noise is central to experimental science. Applying well-established statistical method effectively to LLM evals requires consideration of...
- · ai
[Paper] Parallel Token Prediction for Language Models
We propose Parallel Token Prediction (PTP), a universal framework for parallel sequence generation in language models. PTP jointly predicts multiple dependent t...
- · ai
[Paper] Variationally correct operator learning: Reduced basis neural operator with a posteriori error estimation
Minimizing PDE-residual losses is a common strategy to promote physical consistency in neural operators. However, standard formulations often lack variational c...
- · ai
[Paper] Scaling Laws for Economic Productivity: Experimental Evidence in LLM-Assisted Consulting, Data Analyst, and Management Tasks
This paper derives `Scaling Laws for Economic Impacts' -- empirical relationships between the training compute of Large Language Models (LLMs) and professional ...
- · ai
[Paper] Does the Data Processing Inequality Reflect Practice? On the Utility of Low-Level Tasks
The data processing inequality is an information-theoretic principle stating that the information content of a signal cannot be increased by processing the obse...
- · ai
[Paper] Learning to Solve PDEs on Neural Shape Representations
Solving partial differential equations (PDEs) on shapes underpins many shape analysis and engineering tasks; yet, prevailing PDE solvers operate on polygonal/tr...
- · ai
[Paper] Transcriptome-Conditioned Personalized De Novo Drug Generation for AML Using Metaheuristic Assembly and Target-Driven Filtering
Acute Myeloid Leukemia (AML) remains a clinical challenge due to its extreme molecular heterogeneity and high relapse rates. While precision medicine has introd...