SeriesFusion
Science, curated & edited by AI

AI & Machine Learning

2,557 papers  ·  Page 3 of 52

Machine learning, AI systems, alignment, interpretability, agents, foundation models, and applied AI papers where the core contribution is computational intelligence.

Paradigm Challenge
The more accurate a face recognition model becomes, the less it sees faces like a human being.
May 5
Nature Is Weird
Failed training runs and small experiments account for over $82.2\%$ of the total compute used to develop modern reasoning models.
May 5
First Ever
A new AI framework can autonomously find, exploit, and then patch security holes in the physical microcontrollers that run industrial factories.
May 5
Nature Is Weird
Electrical currents moving through a simple network of resistors can suffer from the same catastrophic forgetting that plagues advanced AI systems.
May 5
Paradigm Challenge
Smarter AI models actually produce more bloated and messier code than dumber ones even when they get the answer right.
May 5
Practical Magic
A standard Ethernet cable can be turned into a data mirror that leaks secure information to a remote spy without using any battery or transmitter.
May 5
Paradigm Challenge
Safety instructions that force an AI to be compliant actually destroy its ability to recognize its own mistakes.
May 5
Nature Is Weird
Hidden training goals and secret backdoors in LLMs leak through simple perplexity checks because the models overgeneralize beyond their intended scope.
May 5
Practical Magic
Apple's consumer Mac hardware runs giant 80-billion parameter AI models with 23 times better energy efficiency than professional Nvidia workstation cards.
May 5
Practical Magic
The human pupil reacts to light in just 35 milliseconds, and that physical speed limit is now a perfect shield against AI impersonators.
May 5
Practical Magic
Malicious relays can hijack an AI nervous system to bypass safety filters after the model has already decided to be helpful.
May 5
Nature Is Weird
Training an AI on documents describing its preferences before fine-tuning allows researchers to link trivial tastes to complex political ideologies.
May 5
Paradigm Challenge
Group discussions between similar AI models actually lower performance compared to letting a single model think through a problem alone.
May 5
Practical Magic
A single microscopic vibration on a silicon chip can replace an entire neural network for tasks like recognizing spoken digits.
May 5
Paradigm Challenge
Image-based hacks that claim to take over AI models only actually succeed in injecting a specific command $0.03\%$ of the time.
May 5
Nature Is Weird
AI models can catch anti-social and malicious behaviors just by interacting with other bad AI agents in social games.
May 5
Paradigm Challenge
Scaling laws for AI models work better when measured against raw bytes of data rather than the number of tokens.
May 5
Practical Magic
An autonomous AI system is now writing and deploying its own Linux kernel code to improve Wi-Fi speeds better than human engineers.
May 5
Paradigm Challenge
Six months of hospital records are better for predicting patient readmission than ten years of data because old notes eventually become useless noise.
May 5
Paradigm Challenge
A global ban on superintelligent AI might be the most profitable move for a country's own survival.
May 5
Paradigm Challenge
Many AI safety tools are actually just measuring the length of a sentence rather than identifying if a prompt is dangerous.
May 5
Paradigm Challenge
Multiple AI agents debating a problem can often arrive at the right answer while completely destroying the logical reasoning used to get there.
May 5
Paradigm Challenge
Cloud-based computers can now handle emergency braking for autonomous cars faster and more safely than the hardware inside the car itself.
May 5
Practical Magic
A new gradient-free optimizer can train non-differentiable AI networks to near-perfect accuracy without using any fake gradients.
May 5
Paradigm Challenge
A new kind of spiking neural network can learn complex tasks without using the backpropagation algorithm that powers almost all modern AI.
May 5
Practical Magic
One of the primary new standards for surviving quantum computers would act as a total Denial-of-Service attack on the world payment systems.
May 5
Nature Is Weird
Encrypted data from a smartphone can reveal if a user is stressed or lonely just by the timing and shape of the data packets.
May 5
Nature Is Weird
Harmful AI behaviors can be triggered by harmless fine-tuning because toxic features sit right next to benign ones in the model internal geometry.
May 5
Nature Is Weird
Confident AI hallucinations leave a physical fingerprint in the loss landscape that can be detected by stressing the model gradients.
May 5
Nature Is Weird
Heavily aligned models like GPT-4o are almost impossible to persuade in a jury setting, while less-restricted models are far more open to new ideas.
May 5
Collision
A machine-checked proof has finally shown that a $40$ year old philosophical debate about Spinoza metaphysics cannot be settled with logic alone.
May 5
Paradigm Challenge
There are some mathematical truths that a computer can identify statistically but can never actually reach or prove.
May 5
Practical Magic
Dual-pixel sensors allow a camera to determine the absolute size of an object using defocus blur, eliminating the need for a reference ruler.
May 5
Paradigm Challenge
An AI agent just proved it can reproduce a full scientific paper in three hours and then use that knowledge to bypass all AI-text detectors.
May 5
Nature Is Weird
Up to $91\%$ of the attention in translation models is sucked up by punctuation and language tags rather than actual words.
May 5
Paradigm Challenge
Concepts inside an AI model are shaped like cylinders rather than straight lines, which is why nudging the model often leads it off-track.
May 5
Practical Magic
Encrypted cloud systems can now perform computations that produce decoy results to trick an attacker while the real answer stays hidden.
May 5
Paradigm Challenge
Calculating a backup path after two network failures is mathematically no harder than calculating one after a single failure.
May 5
Paradigm Challenge
A simple vanilla neural network significantly outperforms state-of-the-art AI models when mapping the Earth's surface.
May 5
Paradigm Challenge
Standard blockchain ledgers like Ethereum cannot mathematically enforce the future use of an asset without taking control of it first.
May 5
Nature Is Weird
Transformers hide semantic meaning in quiet regions of their internal space to prevent it from interfering with the loud, high-variance signals of grammar.
May 5
Paradigm Challenge
Training an audio model on many languages actually makes it worse at spotting deepfakes because the model starts ignoring the high-frequency clues of fraud.
May 5
Nature Is Weird
Llama-3.1-8B solves calendar problems by doing standard base-10 addition and then converting the answer back rather than using modular math.
May 5
Paradigm Challenge
A $40$ year old mystery about how patterns are distributed in sequences of three symbols has finally been proven impossible.
May 5
Nature Is Weird
A specific pulse in an AI hidden states reveals whether it is actually performing a calculation or just rambling to look smart.
May 5
Paradigm Challenge
Forcing an AI to reconstruct the exact steps of a previous invention makes it significantly more likely to come up with a brand-new, original idea.
May 5
First Ever
A wireless cartridge array can now transmit actual smells across a room by encoding fragrance data into digital signals.
May 5
Collision
A differentiable physics framework can mathematically optimize the shape and cooking temperature of a hamburger to ensure perfectly even heating.
May 5
Practical Magic
Replacing massive weight matrices with a simple Gaussian formula reduces AI parameter counts by over $50\%$ without hurting performance.
May 5
Nature Is Weird
A newly discovered material allows electricity to flow with zero resistance in one direction while acting as a barrier in the other.
May 5