digitado

This article presents an argument for why quantum computers could unlock new methods for machine learning. We argue that spectral methods, in particular those that learn, regularise, or otherwise manipulate the Fourier spectrum of a machine learning model, are often natural for quantum computers. For example, if a generative machine learning model is represented by a quantum state, the Quantum Fourier Transform allows us to manipulate the Fourier spectrum of the state using the entire toolbox of quantum […]

Ver mais

We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps to 1 – achieving 80x speedup while maintaining visual interpretability. Training RL policies on real-world driving data incurs prohibitive costs and safety risks. While existing pixel-level diffusion world models enable safe imagination-based training, they suffer from multi-step diffusion inference latency (2s/frame) that prevents high-frequency RL interaction. Our approach leverages denoised latent features from video […]

Ver mais

LiteLLM Hack: Were You One of the 47,000? Daniel Hnyk used the BigQuery PyPI dataset to determine how many downloads there were of the exploited LiteLLM packages during the 46 minute period they were live on PyPI. The answer was 46,996 across the two compromised release versions (1.82.7 and 1.82.8). They also identified 2,337 packages that depended on LiteLLM – 88% of which did not pin versions in a way that would have avoided the exploited version. Via […]

Ver mais

Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop. The second […]

Ver mais

The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates can be expensive on embedded hardware, especially when models are complex or horizons are long. Learning-based NMPC approximations shift this computation offline but typically demand large expert datasets and costly training. We propose Sequential-AMPC, a sequential neural policy that generates MPC candidate control sequences by sharing parameters across the prediction horizon. For deployment, we wrap […]

Ver mais

This is a very premature and early proof of concept. But I figured I would show it because this is how I imagine the future of OOD autnomous driving to be solved, albeit with a lot more complexity and engineering. While this is still IID training, and not an OOD task, the concept still works in OOD tasks. Model was trained on racetrack oval, racetrack, and racetrack large. Conv3D encoder. Some intrinsic motivation magic. And uhh… PPO. 5120 […]

Ver mais