Long-context LLMs enable advanced applications such as repository-level code analysis, long-document question-answering, and many-shot in-context learning by supporting extended context […]
Category: Machine Learning
CMU Researchers Propose miniCodeProps: A Minimal AI Benchmark for Proving Code Properties
Recently, AI agents have demonstrated very promising developments in automating mathematical theorem proving and code correctness verification using tools like […]
ProteinZen: An All-Atom Protein Structure Generation Method Using Machine Learning
Generating all-atom protein structures is a significant challenge in de novo protein design. Current generative models have improved significantly for […]
EnzymeCAGE: A Deep Learning Framework Designed to Predict Enzyme-Reaction Catalytic Specificity by Encoding both Pocket-Specific Enzyme Structures and Chemical Reactions
Enzymes are indispensable molecular catalysts that facilitate the biochemical processes vital to life. They play crucial roles across metabolism, industry, […]
Infinigence AI Releases Megrez-3B-Omni: A 3B On-Device Open-Source Multimodal Large Language Model MLLM
The integration of artificial intelligence into everyday life faces notable hurdles, particularly in multimodal understanding—the ability to process and analyze […]
Self-Calibrating Conformal Prediction: Enhancing Reliability and Uncertainty Quantification in Regression Tasks
In machine learning, reliable predictions and uncertainty quantification are critical for decision-making, particularly in safety-sensitive domains like healthcare. Model calibration […]
Mechanisms of Localized Receptive Field Emergence in Neural Networks
A notable aspect of peripheral responses in the animal nervous system is localization, where the linear receptive fields of simple-cell […]
Technology Innovation Institute TII-UAE Just Released Falcon 3: A Family of Open-Source AI Models with 30 New Model Checkpoints from 1B to 10B
The advancements in large language models (LLMs) have created opportunities across industries, from automating content creation to improving scientific research. […]
Researchers from Sakana AI Introduce NAMMs: Optimized Memory Management for Efficient and High-Performance Transformer Models
Transformers have become the backbone of deep learning models for tasks requiring sequential data processing, such as natural language understanding, […]
This AI Paper from Microsoft and Novartis Introduces Chimera: A Machine Learning Framework for Accurate and Scalable Retrosynthesis Prediction
Chemical synthesis is essential in developing new molecules for medical applications, materials science, and fine chemicals. This process, which involves […]