Deep Learning

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Aditya Gupta

Mar 21

Identifying Early Warning Signs of Attention Mechanism Instability

#ai #deeplearning #llm #machinelearning

5 min read

Aditya Gupta

Mar 21

The Challenge of Unverifiable AI Rewards

#ai #deeplearning #llm #machinelearning

7 min read

Kamolchanok Saengtong

Mar 21

Adversarial Attacks and Defenses in Deep Learning Systems: Threats, Mechanisms, and Countermeasures

#cybersecurity #machinelearning #princeofsongklauniversity #deeplearning

6 min read

Alan West

Mar 21

Standard Transformer Attention vs. Attention-Residuals: A Practical Comparison

#transformers #deeplearning #attentionmechanism #pytorch

5 min read

ThanidaSangkasanya

Mar 21

Invited talk about: Adversarial Attacks and Defenses in Deep Learning Systems: Threats, Mechanisms, and Countermeasures

#computerscience #cybersecurity #deeplearning #machinelearning

1 min read

Sherin Joseph Roy

Mar 21

I Thought I Understood the Autonomous Vehicle Problem. Indian Roads Corrected Me.

#autonomouscar #ai #computervision #deeplearning

6 min read

Aditya Gupta

Mar 21

The Proliferation of Specialized LLMs and the Retraining Dilemma

#ai #deeplearning #llm #machinelearning

5 min read

Aditya Gupta

Mar 21

The Pervasive Role and Hidden Limitations of Softmax

#ai #algorithms #deeplearning #machinelearning

6 min read

Aditya Gupta

Mar 21

Revisiting the Causal Mechanisms Behind Policy Gradients

#ai #algorithms #deeplearning #machinelearning

5 min read

Aditya Gupta

Mar 21

The Bottleneck of Dense Attention in Long Contexts

#ai #architecture #deeplearning #llm

6 min read

Aditya Gupta

Mar 21

The Intricate Dance of Self-Attention: What Can Go Wrong?

#ai #deeplearning #machinelearning #performance

5 min read

Kevin

Mar 21

Mamba-3 and AttnRes: AI Architecture Research Is Finally Building for Inference, Not Just Training

#ai #machinelearning #architecture #deeplearning

7 min read

Auryth Team

Mar 20

5 architectures replacing brute-force AI scaling (and what they mean for your stack)

#ai #machinelearning #architecture #deeplearning

3 min read

Ramratan Padhy

Mar 19

The Mathematics That Make 1.58-bit Weights Work: How BitNet b1.58 Survives Its Own Quantization

#architecture #deeplearning #llm #machinelearning

7 min read

Thomas Emad

Mar 18

Exploring an AST-Based Template Engine in PHP — Thoughts?

#laravel #deeplearning #systemdesign #php

1 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.