Forem

Deep Learning

This tag is for discussing, sharing articles, and asking questions primarily on deep learning - a subfield of machine learning.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Beyond the Black Box: Making LLM Decoding Truly End-to-End

Beyond the Black Box: Making LLM Decoding Truly End-to-End

Comments
2 min read
AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4DScenes
Cover image for AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4DScenes

AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4DScenes

Comments
1 min read
DocReward: A Document Reward Model for Structuring and Stylizing
Cover image for DocReward: A Document Reward Model for Structuring and Stylizing

DocReward: A Document Reward Model for Structuring and Stylizing

Comments
1 min read
Building Intelligent AI Agents with Modular Reinforcement Learning

Building Intelligent AI Agents with Modular Reinforcement Learning

Comments
13 min read
The Role of GPUs in Accelerating Deep Learning Training
Cover image for The Role of GPUs in Accelerating Deep Learning Training

The Role of GPUs in Accelerating Deep Learning Training

Comments
5 min read
Convexity Switching: The Secret to Faster, Smarter Neural Net Training?

Convexity Switching: The Secret to Faster, Smarter Neural Net Training?

Comments
2 min read
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
Cover image for SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

Comments
1 min read
Why GPUs Are the Secret Weapon for Faster Deep Learning Training
Cover image for Why GPUs Are the Secret Weapon for Faster Deep Learning Training

Why GPUs Are the Secret Weapon for Faster Deep Learning Training

Comments
6 min read
Geometric Nets: Unleashing the Power of Shape in AI by Arvind Sundararajan

Geometric Nets: Unleashing the Power of Shape in AI by Arvind Sundararajan

Comments
2 min read
Diagnosing layer sensitivity during post training quantization
Cover image for Diagnosing layer sensitivity during post training quantization

Diagnosing layer sensitivity during post training quantization

6
Comments
4 min read
Resonant Convergence Analysis (RCA): Intelligent Early Stopping That Cuts Training Time by 35–45%

Resonant Convergence Analysis (RCA): Intelligent Early Stopping That Cuts Training Time by 35–45%

2
Comments
2 min read
Unlocking AI's Hidden Geometry: A New Path to True Understanding by Arvind Sundararajan

Unlocking AI's Hidden Geometry: A New Path to True Understanding by Arvind Sundararajan

Comments
2 min read
Temporal Prompting Matters: Rethinking Referring Video Object Segmentation
Cover image for Temporal Prompting Matters: Rethinking Referring Video Object Segmentation

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation

Comments
1 min read
Unlocking Neural Network Secrets: The Geometric Awakening by Arvind Sundararajan

Unlocking Neural Network Secrets: The Geometric Awakening by Arvind Sundararajan

Comments
2 min read
Chiplet Chokepoints: Optimizing Interconnects for Peak AI Performance

Chiplet Chokepoints: Optimizing Interconnects for Peak AI Performance

Comments
2 min read
Unleash AI Performance: How Chiplets and Smart Networks Are Democratizing Custom Silicon by Arvind Sundararajan

Unleash AI Performance: How Chiplets and Smart Networks Are Democratizing Custom Silicon by Arvind Sundararajan

Comments
2 min read
Reality Rewritten: How Differentiable Worlds Are Transforming AI

Reality Rewritten: How Differentiable Worlds Are Transforming AI

Comments
2 min read
Zero-Degradation Training: 92% ImageNet-100 Accuracy with 61% Energy Savings

Zero-Degradation Training: 92% ImageNet-100 Accuracy with 61% Energy Savings

Comments
4 min read
Sparsity Unleashed: Dynamic Activations for Leaner AI

Sparsity Unleashed: Dynamic Activations for Leaner AI

Comments
2 min read
Squeezing Every Last Flop: The INT vs. FP Showdown for AI Dominance

Squeezing Every Last Flop: The INT vs. FP Showdown for AI Dominance

Comments
2 min read
Squeezing AI into Tiny Spaces: The Integer Revolution

Squeezing AI into Tiny Spaces: The Integer Revolution

Comments
2 min read
Daily Artificial Intelligence Digest - Oct 23, 2025

Daily Artificial Intelligence Digest - Oct 23, 2025

Comments
3 min read
Unlock AI's Potential: Differentiable Dynamic Programming

Unlock AI's Potential: Differentiable Dynamic Programming

Comments
2 min read
Diffusion Models and the Attention Abyss: Why Some Tokens Hog the Spotlight by Arvind Sundararajan

Diffusion Models and the Attention Abyss: Why Some Tokens Hog the Spotlight by Arvind Sundararajan

Comments
2 min read
Beats as Objects: A Computer Vision Hack for Music Analysis by Arvind Sundararajan

Beats as Objects: A Computer Vision Hack for Music Analysis by Arvind Sundararajan

Comments
2 min read
loading...