Random Feature Pruning for Multi-Class Classification
Weighted sums of random kitchen sinks (W-RKS) is a commonly used feature extraction technique for supervised learning tasks. A…
News
Research & Science
Papers, breakthroughs and what the labs found this week.
623 stories · Every headline links to the original publisher. HapnGo curates and groups; we do not copy articles.
Anchors Enhance Controllability and Reasoning of Diffusion Language Models
Diffusion language models (DLMs) offer new opportunities for controllable text generation. However, their controllability…
Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families
LLM multi-agent systems split work across agents that communicate through text. An agent summarizes its findings, another agent…
VLCQ: Post-training quantization for deep neural networks using variable length coding
Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training…
GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability
As text-to-speech (TTS) systems continue to advance, provenance tracking and security verification of synthesized speech have…
Knowledge transfer between simple discrete worlds
Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic…
On the Theoretical Limits of Learning Unconstrained Interatomic Potentials
Machine-learned interatomic potentials (MLIPs) accelerate molecular dynamics (MD) simulations by learning the energies and forces…
Scientists Detect Record-Breaking Radio Signal from the Ancient Universe
A fast radio burst that traveled across 10 billion light years reached Earth in 2024, doubling the distance record for these…
AI and mathematics
So I have been following the recent release of the mathematical proofs by openai, and in particular this discussion about how the…
Can Language Models Play the Wikipedia Game?
Language models increasingly support or automate information retrieval from document collections too large to index. This task is…
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based…
Constructive Bounds for the Topological Expressivity of Neural Networks
The expressivity of a neural network $Φ$ describes the class of functions that a network can express. The term topological…
AI Models Can Provably Hide Arbitrary Capabilities
Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the…
KL Before and After Mixing: A Round-Complexity Separation in Parallel Sampling
A parallel sampler can choose at random which coordinates to generate together. For a target $p$ and the output law $q_U$ of a…
Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning
Deep-space communications operate under intermittent connectivity, long propagation delays, and relay storage constraints. In…
DyssomniaNN: Multi-Scale Spiking Neural Modeling of Human Sleep Disorders and Perceived Restedness
Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime…
Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping
While deep learning models for tabular data have recently received significant research attention, the choice of objective…
Task Context Shapes Component Roles in Language Models
Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they…
Mathematicians want OpenAI out of math research, but their argument doesn't add up
I would much rather see AHM engage with companies like OpenAI and push them to improve how they publish and verify mathematical…
Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga
Comics are one of the great visual records of the twentieth century: hundreds of thousands of pages in which a mass readership…
Danu Robotics’ fight to build a better recycling robot
For six years, Danu founder Amy Ma has been working on a better way to sort recyclable waste.
SpatialASM: Internalizing Active Mentalization for Spatial Reasoning
When solving complex spatial reasoning tasks, ordinary humans naturally revisit the scenes from task-relevant viewpoints and…
FedPCD: Priority-Constrained Federated Aggregation
Federated learning (FL) seeks to optimize a shared global model from decentralized client data. While effective for average…
Free, daily
The HapnGo Briefing, in your inbox
One email a day with the AI stories that matter, why they matter, and one tool worth trying. No spam, one-click unsubscribe.