research

For anyone who is worried about the communist threat facing America, here is some important information: No one was eating the dogs or the c…

For anyone who is worried about the communist threat facing America, here is some important information: No one was eating the dogs or the cats. No country emptied it's asylums or prisons into America

Research

In the future, there will be 'Latent Space Archaeologists' who investigate the model weights of the 21st century to reconstruct a long extin…

DGX agent

Francois Chollet proposes a speculative future concept where 'Latent Space Archaeologists' will study the trained weights of 21st-century AI models as historical artifacts to reconstruct extinct knowl

researchfrancois-chollet--x

5 Jul 2026

President Trump relaxes gun laws, allowing some people with mental illness who had been barred from possessing firearms to have them. https:…

President Trump relaxes gun laws, allowing some people with mental illness who had been barred from possessing firearms to have them. https://www.nytimes.com/2026/07/05/us/politics/trump-gun-rights-la

Surprising (not really) stat from the new UBS Global Wealth Report 2026. The US ranks #2 when you look at average (mean) wealth per adult, b…

Surprising (not really) stat from the new UBS Global Wealth Report 2026. The US ranks #2 when you look at average (mean) wealth per adult, but drops to #28 when you look at the median. https://www.ubs

The funding headline is only half the story. Yann LeCun told BBC that large language models are not a path to human-like or animal-like inte…

The funding headline is only half the story. Yann LeCun told BBC that large language models are not a path to human-like or animal-like intelligence... #AI https://stechtimes.com/en/article/yann-lecun

Trump not only seeks vengeance against his enemies but also fleeces his own supporters.

Trump not only seeks vengeance against his enemies but also fleeces his own supporters. Nearly a Million Investors Lost a Total of $3.8 Billion on Trump Crypto Coin https://www.nytimes.com/2026/07/04/

Warm take: Your world model should never stop learning Introducing AdaJEPA, an adaptive WM that plans, acts, and adapts in a closed loop. Ev…

Warm take: Your world model should never stop learning Introducing AdaJEPA, an adaptive WM that plans, acts, and adapts in a closed loop. Every action leads to a new observation, and every transition

America is where anything is possible

researchfrancois-chollet--x

This post likely reflects on American ideals of opportunity and possibility, discussing the cultural narrative that America enables people to pursue diverse ambitions and achieve goals regardless of b

@elonmusk @Devon_Eriksen_ If there were any lingering doubts that you and your friends were against the very principles of democracy, you ju…

Yann LeCun posted a critical response to Elon Musk and Devon Eriksen regarding their positions on democratic principles, suggesting their actions contradict democratic values. The post appears to be a

Fifty years later the semiquincentennial is tainted by fears that the country is no longer a democracy. But the Supreme Court has slapped do…

Fifty years later the semiquincentennial is tainted by fears that the country is no longer a democracy. But the Supreme Court has slapped down many of the President's pet projects, and an electoral re

How? Instead of closed-source frontier labs running the same training runs in secret and siloes, open science and open-source AI allows them…

How? Instead of closed-source frontier labs running the same training runs in secret and siloes, open science and open-source AI allows them to mutualize spending and compute making them an order of m

On our 250th birthday, celebrating the contribution of immigrants and international collaboration —46% of people with doctoral-level degrees…

On our 250th birthday, celebrating the contribution of immigrants and international collaboration —46% of people with doctoral-level degrees working in US science and engineering fields are foreign-bo

That's a great speech that captures the essence of American exceptionalism. It is not based on innate superiority, power or wealth, but rath…

researchfrancois-chollet--x

That's a great speech that captures the essence of American exceptionalism. It is not based on innate superiority, power or wealth, but rather on the fact that the outcasts of the world could set foot

The only long term bottlenecks are information and energy.

researchfrancois-chollet--x

Francois Chollet argues that information and energy are the fundamental long-term constraints on technological and civilizational progress, rather than physical materials or other resources. This pers

While Trump walked away with a 636 million profit from his crypto venture, nearly 1 million people who bought into it lost a total of 3.81…

While Trump walked away with a 636 million profit from his crypto venture, nearly 1 million people who bought into it lost a total of 3.81 billion through the end of June. They were probably mostly hi

A device that revives eyeballs from dead donors could make eye transplants possible

It’s not easy to transplant a whole human eye. The surgery is difficult. And the eyes themselves start to degenerate as soon as they’ve left the body. When surgeons attempted it a few years ago, the n

researchmit-tech-review

A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets

arXiv:2607.02303v1 Announce Type: new Abstract: Linear-attention and state-space language models compress the prefix into a fixed-size recurrent state, yielding O(1) memory at the cost of a lossy exac

A Mathematical Introduction to Diffusion Models

arXiv:2607.01693v1 Announce Type: new Abstract: These notes give a proof-oriented introduction to diffusion models from the viewpoint of sampling, tracing a single arc from classical sampling dynamics

A Multi-Branch Hierarchy-Aware Framework for Heterogeneous Audio Classification

arXiv:2607.01974v1 Announce Type: cross Abstract: This technical report describes our system for Task 1 of the DCASE 2026 Challenge, which aims to classify heterogeneous audio recordings according to

A Novel Machine Learning Approach for Central Nervous System Tumor Classification from DNA Methylation

arXiv:2607.01307v1 Announce Type: new Abstract: NA methylation profiling has become a powerful approach for central nervous system (CNS) tumor classification, yet important challenges remain regarding

A Reconfigurable Rocker-Bogie Robot for High Step Climbing and Turning

arXiv:2607.01554v1 Announce Type: new Abstract: This study proposes a reconfigurable rocker-bogie mechanism that achieves efficient turning motion with a small number of actuators while maintaining hi

researcharxiv-cs-ro

A Stereo Visual SLAM System Using Object-Level Motion Estimation and Geometric Filtering Based on Cross Disparity

arXiv:2607.02005v1 Announce Type: new Abstract: This paper presents OCD SLAM, a dynamic stereo visual SLAM framework that extends ORB-SLAM2 by jointly addressing dynamic objects and dynamic features i

researcharxiv-cs-ro

A Storm-Centric 250 m NEXRAD Level-II Dataset for High-Resolution ML Nowcasting

arXiv:2510.16031v2 Announce Type: replace-cross Abstract: Machine learning-based precipitation nowcasting relies on high-fidelity radar reflectivity sequences to model the short-term evolution of conv

A Wearable Device Dataset for Mental Health Assessment Using Laser Doppler Flowmetry and Fluorescence Spectroscopy Sensors

arXiv:2502.00973v2 Announce Type: replace Abstract: Mental health problems such as stress, anxiety, and depression affect millions of people worldwide. These conditions are usually assessed using ques

ACID: Action Consistency via Inverse Dynamics for Planning with World Models

arXiv:2607.02403v1 Announce Type: cross Abstract: Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost ju

Actual causality in fault trees

arXiv:2607.01840v1 Announce Type: new Abstract: Fault trees are a widely used as effective risk models for complex systems, answering the question 'what can go wrong?', especially through minimal cut

Adaptive Contracts for Cost-Effective AI Delegation

arXiv:2603.17212v2 Announce Type: replace-cross Abstract: When organizations delegate text generation tasks to AI providers via pay-for-performance contracts, expected payments rise when evaluation is

Adaptive Group-Based Counterfactual Explanations for Time-Series Rehabilitation Data

arXiv:2607.01838v1 Announce Type: new Abstract: Counterfactual explanations (CEs) for multivariate time-series classifiers are often difficult to interpret in domains where experts reason in terms of

Adaptively trained Physics-informed Radial Basis Function Neural Networks for Solving Multi-asset Option Pricing Problems

arXiv:2601.12704v2 Announce Type: replace Abstract: The present study investigates the numerical solution of Black-Scholes partial differential equation (PDE) for option valuation with multiple underl

ADMC: Attention-based Diffusion Model for Missing Modalities Feature Completion

arXiv:2507.05624v2 Announce Type: replace Abstract: Multimodal emotion and intent recognition is essential for automated human-computer interaction, It aims to analyze users' speech, text, and visual

Aggregation with Exponential Weights is Optimal in Expectation

arXiv:2607.02247v1 Announce Type: cross Abstract: The aggregation with exponential weights (AEW) estimator is not fully understood in the basic setting of model selection aggregation with squared loss

AI Virtue: What is 'Good' Knowledge in the Age of Artificial Intelligence?

arXiv:2607.01776v1 Announce Type: cross Abstract: In the age of AI, what will be good knowledge? This article, which is accepted and forthcoming in a special issue of Modern Fiction Studies on 'Cultur

AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs

arXiv:2601.22710v2 Announce Type: replace-cross Abstract: Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to exte

An Additive MLP-GNN Framework for Characterizing Chemical and Structural Contributions to Aqueous Solubility

arXiv:2607.02212v1 Announce Type: cross Abstract: Aqueous solubility is a key property in early-stage drug discovery, but most predictive models merge physicochemical descriptors and molecular graph i

An Exploratory Study on LLM-Generated Code and Comments in Code Repositories

arXiv:2607.01867v1 Announce Type: cross Abstract: The use of LLMs in software development has become increasingly widespread on tasks such as code generation and summarization. Reports from large tech

An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks

arXiv:2607.02194v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have emerged as a promising route to solve partial differential equations, yet they have struggled to reach the

Artificial Intelligence-Enabled Accounting Information Systems and Fraud Detection in Nigeria's Financial Services Sector: The Moderating Role of Natural Language Processing

arXiv:2607.01257v1 Announce Type: cross Abstract: The rapid digitalisation of financial systems has improved operational efficiency and financial inclusion while simultaneously increasing exposure to

Audio-Based Understanding of Audiobook Narration Appeal

arXiv:2607.02473v1 Announce Type: new Abstract: Narration is central to the audiobook listening experience, shaping how listeners engage with and understand the content. This work explores how narrati

Autorelevance function and other feature relevance measures for univariate time series

arXiv:2607.01959v1 Announce Type: cross Abstract: We propose a model agnostic methodology to measure lag relevance in machine learning forecasting models applied to univariate time series. Particularl

BamiBERT: A New BERT-based Language Model for Vietnamese

arXiv:2607.02259v1 Announce Type: new Abstract: In this paper, we introduce BamiBERT, a new BERT-based pre-trained language model for Vietnamese that addresses key limitations of PhoBERT -- the curren

Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials

arXiv:2607.02499v1 Announce Type: cross Abstract: Machine learning interatomic potentials (MLIPs) have become a hallmark of AI for scientific simulation. While efforts on new architectures and dataset

Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers

arXiv:2607.01679v1 Announce Type: cross Abstract: Adversarial attacks on cybersecurity classifiers pose a dual threat: degrading predictions and destabilising the SHAP-based explanations that security

Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum Distributionally Robust Optimization for Spatially Correlated Domains

arXiv:2607.02055v1 Announce Type: cross Abstract: Performance evaluation in AI systems commonly assumes that random dataset splits produce independent and identically distributed (i.i.d.) subsets. We

Brazenly self-serving: the Trump family’s earnings during his first year in office 'have moved him into an echelon of enrichment more associ…

Brazenly self-serving: the Trump family’s earnings during his first year in office 'have moved him into an echelon of enrichment more associated with strongmen in Russia and Turkey.' https://trib.al/i

CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection

arXiv:2607.01870v1 Announce Type: new Abstract: Camouflaged Object Detection (COD) aims to locate and segment objects that blend into their surroundings, presenting challenges due to weak edge cues an

Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale

arXiv:2607.01538v1 Announce Type: new Abstract: Language models (LMs) raise an intriguing alternative to vector-based retrieval: conditioning on an in-context corpus and directly generating a relevant

Causal Explanations for Image Classifiers

arXiv:2411.08875v4 Announce Type: replace Abstract: Existing algorithms for explaining the output of image classifiers use different definitions of explanations and a variety of techniques to find the

Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning

arXiv:2607.01474v1 Announce Type: new Abstract: Class imbalance poses a critical challenge in federated learning (FL), where underrepresented classes suffer from poor predictive performance yet cannot