Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient Clipping
Heavy-tailed noise has been widely observed in modern machine learning, motivating the use of methods like gradient clipping and…
News
Research & Science
Papers, breakthroughs and what the labs found this week.
624 stories · Every headline links to the original publisher. HapnGo curates and groups; we do not copy articles.
Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness…
Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs
GNN-to-MLP distillation aims to retain the predictive accuracy of a message-passing teacher while deploying a graph-free MLP at…
Why Forget-Only Unlearning Needs Memorization
Machine unlearning asks for a deletion algorithm whose output is close to retraining from scratch without the selected forget…
RoboJEPA: Scaling Robotic Latent World Models
Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however…
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional…
EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task…
HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object Interaction
This White Paper gives robotics researchers and engineers an overview of a new large-scale motion capture dataset built to close…
OpenAI drops another batch of mathematical breakthroughs
OpenAI has revealed solutions to a number of long-standing mathematics problems produced by an unreleased frontier model in a…
What AI gets wrong and what failure teaches us
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and…
Sharing AI progress in mathematics
OpenAI publishes new results on open problems in mathematics from an internal frontier model and shares Lean proof formalizations…
Researchers stretch LeCun's JEPA AI into a universal world model that works from physics to biology
Researchers at PhAI Labs have expanded Yann LeCun's JEPA architecture to work across seven fields, from robotics to biomedicine…
All the drama around AI’s takeover of mathematics
This past year, OpenAI, Anthropic, and other labs have announced breakthroughs on numerous long-standing mathematical problems…
Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model
Reka AI's Rho-1 is a 19-billion-parameter omni-model that processes and generates text, images, video, and robot control actions…
AI hiking routes keep looking great on satellite view and terrible on the ground — are we training these models on only our good trips?
Got back from a soggy weekend on what was supposed to be a loop near Mount Hood. The AI-generated route looked great on satellite…
6 Guidelines for Governing AI
For the first 10 years of my career, I worked in product management and data analytics by myself. I wrote database queries that…
Base Models Can Reason By Taking a Cue From Training Data
In this paper, we study how training data creates associations between the tokens at the start of a base model's response and the…
BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance
Worst-group accuracy (WGA) evaluates a trained predictor but does not characterize how its frozen backbone behaves when a new…
Learning to Read the Contextual Tokens in Diffusion Transformers
Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These…
Direct Intermediate Initialization for Tilted Diffusion Samplers
Some diffusion posterior samplers construct Gaussian-tilted intermediate distributions along the reverse process. We observe that…
Towards Looped Models Done Right, Part II: Rethinking at Fixed Points
Every recurrence of a looped language model adds cost in training, decoding, prefill, and reinforcement learning (RL). The closer…
UniSlider: Perceptually Uniform Sliders for Continuous Image Editing
Sliders provide an intuitive interface for continuous image editing. In current generative approaches, however, the slider is…
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.