Machine Learning

2 min read

Mike Young

Jun 4

Kotlin ML Pack: Technical Report

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Training-Free Long-Context Scaling of Large Language Models

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Faithful Logical Reasoning via Symbolic Chain-of-Thought

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration

#machinelearning #ai #beginners #datascience

5 min read

Mike Young

Jun 4

BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Oil & Water? Diffusion of AI Within and Across Scientific Fields

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

Grokfast: Accelerated Grokking by Amplifying Slow Gradients

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Is Complexity an Illusion?

#machinelearning #ai #beginners #datascience

2 min read

Mike Young

Jun 4

The Impacts of Data, Ordering, and Intrinsic Dimensionality on Recall in Hierarchical Navigable Small Worlds

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Easy Problems That LLMs Get Wrong

#machinelearning #ai #beginners #datascience

5

3 min read

Mike Young

Jun 4

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks

#machinelearning #ai #beginners #datascience

5 min read

Mike Young

Jun 4

Certifiably Robust RAG against Retrieval Corruption

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

AnyLoss: Transforming Classification Metrics into Loss Functions

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

The Road Less Scheduled

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Look Once to Hear: Target Speech Hearing with Noisy Examples

#machinelearning #ai #beginners #datascience

5 min read

Mike Young

Jun 4

NPGA: Neural Parametric Gaussian Avatars

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

The rising costs of training frontier AI models

#machinelearning #ai #beginners #datascience

5 min read

Mike Young

Jun 4

MoEUT: Mixture-of-Experts Universal Transformers

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulations

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Diffusion On Syntax Trees For Program Synthesis

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Towards Lightweight Super-Resolution with Dual Regression Learning

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

PlaceFormer: Transformer-based Visual Place Recognition using Multi-Scale Patch Selection and Fusion

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

Neural Network Parameter Diffusion

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Formalizing and Benchmarking Prompt Injection Attacks and Defenses

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Assessing Large Language Models on Climate Information

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Sparse maximal update parameterization: A holistic approach to sparse training dynamics

#machinelearning #ai #beginners #datascience

5 min read

Mike Young

Jun 4

Is In-Context Learning Sufficient for Instruction Following in LLMs?

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Learning to Model the World with Language

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

There and Back Again: The AI Alignment Paradox

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Large Language Models Can Self-Improve At Web Agent Tasks

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

Metaheuristics and Large Language Models Join Forces: Towards an Integrated Optimization Approach

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Privacy-Aware Visual Language Models

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

LLMs achieve adult human performance on higher-order theory of mind tasks

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Executable Code Actions Elicit Better LLM Agents

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

ToonCrafter: Generative Cartoon Interpolation

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

LLaMA Pro: Progressive LLaMA with Block Expansion

#machinelearning #ai #beginners #datascience

5 min read

Mike Young

Jun 4

Text clustering with LLM embeddings

#machinelearning #ai #beginners #datascience

14

4 min read

Mike Young

Jun 4

Arrows of Time for Large Language Models

#machinelearning #ai #beginners #datascience

5 min read

Mike Young

Jun 4

Evaluating AI-generated code for C++, Fortran, Go, Java, Julia, Matlab, Python, R, and Rust

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Simplifying Transformer Blocks

#machinelearning #ai #beginners #datascience

3 min read

Mike Young

Jun 4

Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

You Need to Pay Better Attention: Rethinking the Mathematics of Attention Mechanism

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Generate and Pray: Using SALLMS to Evaluate the Security of LLM Generated Code

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

gzip Predicts Data-dependent Scaling Laws

#machinelearning #ai #beginners #datascience

4 min read

Mike Young

Jun 4

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

#machinelearning #ai #beginners #datascience

1 min read

Pranjal Sharma

Jun 4

Implementation of Perceptron...

#ai #deeplearning #machinelearning #python

4 min read

Khoa Nguyen

May 1

Side Quest Devblog #2: Virtual Insanity

#machinelearning #computervision #datascience

10 min read

Chinnureddy

Jun 3

Ai Will Live and Die By Trust it

#news #ai #machinelearning #webdev

3 min read

Shaique Hossain

Apr 30

Random Forest Algorithm in Machine Learning

#machinelearning #algorithms #regression

1 min read

Jimmy Guerrero for Voxel51

Apr 30

CVPR 2024 Datasets and Benchmarks - Part 2: Benchmarks

#computervision #datascience #ai #machinelearning

15 min read

Pranjal Sharma

Jun 3

Intro to Deep Learning...

#ai #python #datascience #machinelearning

6