Text knowledge is not sufficient for scientific discovery. Language models lack physical grounding. They only have a high level of understanding but cannot simulate physical phenomena. Image and video models focus on "looking good" vs. being physically valid. We’re teaching
MACHINE LEARNING
-
Meeting Pioneer Professor Shun-Ichi Amari on Neural Networks
By
–
I had the honor to meet Professor Shun-Ichi Amari, a pioneer in neural networks, at the University of Tokyo. He worked on early neural nets using pen and paper, before running computing experiments in the future. He talked not only about AI, but human evolution and consciousness.
-
Moving AI IoT Projects Beyond Proof of Concept Phase
By
–
Many #AI and #IoT initiatives get stuck in PoC purgatory. Here’s how to make sure yours doesn’t: https://
buff.ly/41WuyZZ Sponsored #retrocausal_iiot @IIoT_World via @fogoros -
VideoJAM: Joint Appearance-Motion Representations for Video Generation
By
–
JAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Models VideoJAM introduces a framework that improves motion coherence in video generation by learning a joint appearance-motion representation. This framework uses a modified training
-
Radiant Foam: Real-Time Differentiable Ray Tracing Technique
By
–
Radiant Foam: Real-Time Differentiable Ray Tracing Radiant Foam introduces a real-time differentiable ray tracing technique using a volumetric mesh to model light transport, offering speed and quality similar to 3D Gaussian Splatting (3DGS) without requiring special hardware.
-
Flow Q-Learning: Offline RL with Flow-Matching Policies
By
–
Flow Q-Learning Flow Q-Learning (FQL) is an offline reinforcement learning (RL) method that uses flow-matching policies to model complex action distributions. It avoids the challenges of iterative action generation by training an expressive one-step policy with RL, which
-
LIMO: Mathematical Reasoning Emerges From Few Examples
By
–
LIMO: Less is More for Reasoning LIMO challenges the belief that complex reasoning requires vast datasets, showing that mathematical reasoning abilities can emerge with just a few examples. It achieves high accuracy on benchmarks with only 817 training samples. Problem:
-
Inference-Time Compute Improves Adversarial Robustness
By
–
Trading Inference-Time Compute for Adversarial Robustness This paper explores how increasing inference-time compute improves the adversarial robustness of reasoning models (OpenAI o1-preview and o1-mini) without adversarial training. Problem: Adversarial attacks remain a major
-
Long Chain-of-Thought Reasoning Emergence in LLMs
By
–
Demystifying Long Chain-of-Thought Reasoning in LLMs This paper investigates the emergence of long chain-of-thought (CoT) reasoning in LLMs, focusing on factors that enable structured reasoning strategies like backtracking and error correction. It analyzes the role of supervised
-
Artificial Intelligence Improves Breast Cancer Diagnosis
By
–
Artificial Intelligence Improves Breast Cancer Diagnosis
#AI #AIio #AIInnovation #ML #DataScience #Futureofwork @lexfridman @sama @kaifulee @ID_AA_Carmack @karpathy @2morrowknight @ylecun