Machine Learning

What to expect from AlphaZero's value predictions [D]

An AlphaZero agent has learnt to predict the value of a game state by training on data generated by self-play by the model and a series o...

Open Source Projects related to CNNs to Contribute To? [D]

Around a decade a go I was tinkering a lot with CNNs for real time event detection. I enjoyed that a lot and always wanted to get back in...

I Work in Hollywood. Everyone Who Used to Make TV Is Now Secretly Training AI | WIRED

For screenwriters like me—and job seekers all over—AI gig work is the new waiting tables. In eight months, I’ve done 20 of these soul-cru...

What to expect from AlphaZero's value predictions [D]

An AlphaZero agent has learnt to predict the value of a game state by training on data generated by self-play by the model and a series o...

Open Source Projects related to CNNs to Contribute To? [D]

Around a decade a go I was tinkering a lot with CNNs for real time event detection. I enjoyed that a lot and always wanted to get back in...

I Work in Hollywood. Everyone Who Used to Make TV Is Now Secretly Training AI | WIRED

For screenwriters like me—and job seekers all over—AI gig work is the new waiting tables. In eight months, I’ve done 20 of these soul-cru...

Are Enterprises Using AI in the Wrong Places?

Most enterprise AI discussions still revolve around one question: But I’m starting to think that may be the wrong question entirely. The ...

Academy and ASN Joint Task Force Publishes Artificial Intelligence and Machine Learning Resource Guide

Improving AI models’ ability to explain their predictions

New technique makes AI models leaner and faster while they’re still learning

Why Massive AI Models Actually Generalize Better

Teaching AI models to say “I’m not sure”

We cannot have the AI model advising clients. They might think they don’t need us

‘AI is, at its heart and best, a tool’: Students, Faculty Weigh in on the Use of Large Language Models to Read Academic Papers

Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts

Fictional portrayals of artificial intelligence can have a real effect on AI models, according to Anthropic.

I gave a local AI agent system file access and a mechanical "suffering" metric. Scaling the model changed its behavior entirely

I’ve been obsessed with autonomous agents lately, but it got tiring when they keep hitting walls because they didn't have the right capab...

A Geometric Perspective on Robustness in Vision Transformers [R]

Hi everyone! I'm sharing a paper I've been working on that investigates how different positional encoding schemes (learned absolute, sinu...

[2603.18856] Motion-o: Trajectory-Grounded Video Reasoning

Abstract page for arXiv paper 2603.18856: Motion-o: Trajectory-Grounded Video Reasoning

[2602.07026] Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Abstract page for arXiv paper 2602.07026: Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

[2602.02320] A Large-Scale Dataset for Molecular Structure-Language Description via a Rule-Regularized Method

Abstract page for arXiv paper 2602.02320: A Large-Scale Dataset for Molecular Structure-Language Description via a Rule-Regularized Method

[2601.22400] Spectral Filtering for Complex Linear Dynamical Systems

Abstract page for arXiv paper 2601.22400: Spectral Filtering for Complex Linear Dynamical Systems

[2512.14018] PerfCoder: Large Language Models for Interpretable Code Performance Optimization

Abstract page for arXiv paper 2512.14018: PerfCoder: Large Language Models for Interpretable Code Performance Optimization

[2512.09682] Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for MARL scaling studies

Abstract page for arXiv paper 2512.09682: Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for ...