digitado

Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for multi-task reinforcement learning (RL), where multiple tasks have the same state-action space and transition probabilities, but different rewards. We consider T linear Markov Decision Processes (MDPs) where the reward functions and transition dynamics admit linear feature embeddings of dimension d. The relatedness among the tasks is captured by a […]

Ver mais

I’ve open-sourced GS-DroneGym, a drone-first research stack for vision-language-action work. Main idea: instead of only using synthetic assets, it can render observations from 3D Gaussian Splatting scenes, so you can prototype aerial waypoint policies in environments much closer to real visual conditions. Current features: – 6-DOF quadrotor dynamics – waypoint controller for [x, y, z, yaw] – gsplat renderer with CPU fallback – navigation tasks: PointNav, ObjectNav, ObstacleSlalom, DynamicFollow, NarrowCorridor – live viewer with RGB / depth / […]

Ver mais

Federated learning (FL) enables multiple clients to collaboratively train a global machine learning model via a server without sharing their private training data. In traditional FL, the system follows a synchronous approach, where the server waits for model updates from numerous clients before aggregating them to update the global model. However, synchronous FL is hindered by the straggler problem. To address this, the asynchronous FL architecture allows the server to update the global model immediately upon receiving any […]

Ver mais

I’ve open-sourced GS-DroneGym, a drone-first research stack for vision-language-action work. Main idea: instead of only using synthetic assets, it can render observations from 3D Gaussian Splatting scenes, so you can prototype aerial waypoint policies in environments much closer to real visual conditions. Current features: – 6-DOF quadrotor dynamics – waypoint controller for [x, y, z, yaw] – gsplat renderer with CPU fallback – navigation tasks: PointNav, ObjectNav, ObstacleSlalom, DynamicFollow, NarrowCorridor – live viewer with RGB / depth / […]

Ver mais

The Rust team is happy to announce a new version of Rust, 1.76.0. Rust is a programming language empowering everyone to build reliable and efficient software. If you have a previous version of Rust installed via rustup, you can get 1.76.0 with: $ rustup update stable If you don’t have it already, you can get rustup from the appropriate page on our website, and check out the detailed release notes for 1.76.0. If you’d like to help us out by testing future […]

Ver mais

Tested on: RTX 5060 · PyTorch 2.7 · CUDA 13.1 · Windows 11 You moved your model to the GPU. You watched nvidia-smi climb toward 100%. You assumed you were done. You probably aren’t. GPU utilization is a coarse, 100ms-sampled metric. A GPU can report 80% utilization while spending most of that time idle between kernels, starved by a DataLoader that can’t keep up, or stalled waiting for your Python code to read a loss value. We’ll cover […]

Ver mais

Hi all, Tara here, The Markup’s education reporter. You may have read my story about how college students are tracked by one system or another near constantly as they study and move around campus. I focused on a community college in Southern California and a student there who is particularly troubled by the digital privacy sacrifices required to pursue a degree. One part of campus I barely touched on was the library, and that’s why I’m back in your inboxes […]

Ver mais

I’m working on a project where I’ll be fine-tuning LLMs with GRPO on a 170K-sample dataset for explainable LJP (legal judgment prediction, where the model predicts case outcomes and generates step-by-step reasoning citing the facts). I’m considering models like GPT OSS 20B or Qwen 3.5 27B, with a slight preference for Qwen 3.5 27B because of its strong reasoning capabilities. I recently obtained a 96GB VRAM workstation (RTX PRO 6000) to handle the RL rollouts, which should give […]

Ver mais

How are you, hacker? 🪐 What’s happening in tech today, April 4, 2026? The HackerNoon Newsletter brings the HackerNoon homepage straight to your inbox. On this day, Martin Luther King Assassination in 1968, Microsoft is founded in 1975, Apollo 6 launched in 1968, and we present you with these top quality stories. Want to Have Successful OpenTelemetry Projects? Implement This One Tip By @nfrankel [ 4 Min read ] In this post, I want to tackle a real-world […]

Ver mais