arXiv:2602.05075v1 Announce Type: new Abstract: As the orbital environment around Earth becomes increasingly crowded with debris, active debris removal (ADR) missions face significant challenges in ensuring safe operations while minimizing the risk of in-orbit collisions. This study presents a reinforcement learning (RL) based framework to enhance adaptive collision avoidance in ADR missions, specifically for multi-debris removal using small satellites. Small satellites are increasingly adopted due to their flexibility, cost effectiveness, and maneuverability, making them well suited for dynamic […]

Ver mais

arXiv:2602.21222v1 Announce Type: new Abstract: Parameter efficient fine tuning methods like LoRA have enabled task specific adaptation of large language models, but efficiently composing multiple specialized adapters for unseen tasks remains challenging. We present a novel framework for dynamic LoRA adapter composition that leverages similarity retrieval in vector databases to enable zero-shot generalization across diverse NLP tasks. Our approach constructs a task-aware vector database by embedding training examples from 22 datasets spanning commonsense reasoning, question answering, natural language […]

Ver mais

arXiv:2506.21744v2 Announce Type: replace-cross Abstract: Item Response Theory (IRT) models are widely used to estimate respondents’ latent abilities and calibrate item difficulty. Traditional IRT estimation typically requires centralizing all raw responses, raising privacy and governance concerns. We introduce Federated Item Response Theory (FedIRT), a framework that enables distributed calibration of standard IRT models without transferring individual-level data, thereby preserving confidentiality while retaining statistical efficiency. To provide formal protection, we further develop FedIRT-DP, a user-level differentially private extension. Each […]

Ver mais

The more a thing tends to be permanent, the more it tends to be lifeless. Allan Watts Hey, listen. You’re not lazy. Let’s get that out of the way right now. Lazy people don’t lie awake at night, hearts pounding, staring at the ceiling while mentally screaming at themselves for not sending that email, not starting that proposal, not having that hard conversation. You do. I do. This is the special, advanced-class procrastination reserved for people who are […]

Ver mais

arXiv:2602.12322v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models convert high-level language instructions into concrete, executable actions, a task that is especially challenging in open-world environments. We present Visual Foresight Planning (ForeAct), a general and efficient planner that guides a VLA step-by-step using imagined future observations and subtask descriptions. With an imagined future observation, the VLA can focus on visuo-motor inference rather than high-level semantic reasoning, leading to improved accuracy and generalization. Our planner comprises a highly efficient foresight […]

Ver mais

Beyond Go 1.21’s expanded commitment to backward compatibility, Go 1.21 also introduces better forward compatibility for Go code, meaning that Go 1.21 and later will take better care not to miscompile code that requires an even newer version of Go. Specifically, the go line in go.mod now specifies a minimum required Go toolchain version, while in previous releases it was a mostly unenforced suggestion. To make it easier to keep up with these requirements, Go 1.21 also introduces […]

Ver mais

arXiv:2603.24801v1 Announce Type: new Abstract: Computed tomography image segmentation of complex abdominal aortic aneurysms (AAA) often fails because the models assign internal focus to irrelevant structures or do not focus on thin, low-contrast targets. Where the model looks is the primary training signal, and thus we propose an Explainable AI (XAI) guided encoder shaping framework. Our method computes a dense, attribution-based encoder focus map (“XAI field”) from the final encoder block and uses it in two complementary ways: […]

Ver mais

Hey ! I’m trying to implement a very simple PPO algorithm with numpy but I’m struggling with 2 things : – It seems that the actor net is not learning and I don’t know why. – some values go to nan after some epochs. I tried to comment as well as I could to keep it simple. Thank you very much for taking the time to help me: the environnement : a little grid 2d : “”” GAME […]

Ver mais

arXiv:2602.21230v1 Announce Type: new Abstract: The evaluation of Deep Research Agents is a critical challenge, as conventional outcome-based metrics fail to capture the nuances of their complex reasoning. Current evaluation faces two primary challenges: 1) a reliance on singular metrics like Pass@1, creating a “high-score illusion” that ignores the quality, efficiency, and soundness of the reasoning process; and 2) the failure of static benchmarks to quantify crucial attributes like robustness and latent capability. To address these gaps, we […]

Ver mais

For decades, artificial intelligence transformed digital domains while the physical world, with its unforgiving dynamics and infinite variability, remained largely beyond reach. That boundary is now dissolving: humanoid robots work full shifts on assembly lines, autonomous vehicles make millions of safety-critical decisions daily, and robotic surgical platforms have performed over twenty million procedures worldwide. The convergence of foundation models, high-fidelity simulation, and embodied control is producing Physical AI, machines that perceive, reason, and act reliably in open environments. […]

Ver mais