Accurate assessment of spheno-occipital synchondrosis (SOS) maturation is a key indicator of craniofacial growth and a critical determinant for orthodontic and surgical timing. However, SOS staging from cone-beam CT (CBCT) relies on subtle, continuously evolving morphological cues, leading to high inter-observer variability and poor reproducibility, especially at transitional fusion stages. We frame SOS assessment as a fine-grained visual recognition problem and propose a progressive representation-learning framework that explicitly mirrors how expert clinicians reason about synchondral fusion: from coarse […]

Ver mais

We present AutoResearch-RL, a framework in which a reinforcement learning agent conducts open-ended neural architecture and hyperparameter research without human supervision, running perpetually until a termination oracle signals convergence or resource exhaustion. At each step the agent proposes a code modification to a target training script, executes it under a fixed wall clock time budget, observes a scalar reward derived from validation bits-per-byte (val-bpb), and updates its policy via Proximal Policy Optimisation (PPO). The key design insight is […]

Ver mais

arXiv:2603.06957v1 Announce Type: new Abstract: We study post-training linear autoregressive models with outcome and process rewards. Given a context $boldsymbol{x}$, the model must predict the response $boldsymbol{y} in Y^N$, a sequence of length $N$ that satisfies a $gamma$ margin condition, an extension of the standard separability to sequences. We prove that on test samples where the base model achieves a non-trivial likelihood $alpha$, a variant of policy gradient (PG) can achieve likelihood $1 – varepsilon$ with an essentially […]

Ver mais

arXiv:2601.03261v1 Announce Type: new Abstract: Deep Research agents predominantly optimize search policies to maximize retrieval probability. However, we identify a critical bottleneck: the retrieval-utilization gap, where models fail to use gold evidence even after it is retrieved, due to context blindness in noisy environments. To bridge this gap, we propose DeepResearch-Slice, a simple yet effective neuro-symbolic framework. Unlike implicit attention, our approach predicts precise span indices to perform a deterministic hard filter before reasoning. Extensive evaluations across six […]

Ver mais

The hacker used an employee’s credentials to access source code, which revealed how Suno scraped decades of audio.

Ver mais

arXiv:2602.21259v1 Announce Type: new Abstract: Hybrid Unmanned Aerial Underwater Vehicles (HUAUVs) have emerged as platforms capable of operating in both aerial and underwater environments, enabling applications such as inspection, mapping, search, and rescue in challenging scenarios. However, the development of novel methodologies poses significant challenges due to the distinct dynamics and constraints of the air and water domains. In this work, we present persistent monitoring tasks for HUAUVs by combining Deep Reinforcement Learning (DRL) and Transfer Learning to […]

Ver mais

arXiv:2602.00957v1 Announce Type: new Abstract: Model adaptation to production environment is critical for reliable Machine Learning Operations (MLOps), less attention is paid to developing systematic framework for updating the ML models when they fail under data drift. This paper compares the transfer learning enabled model update strategies including ensemble transfer learning (ETL), all-layers transfer learning (ALTL), and last-layer transfer learning (LLTL) for updating the failed feedforward artificial neural network (ANN) model. The flue gas differential pressure across the […]

Ver mais

EvoPPO: Modular Vision & Audio Reinforcement Learning Framework A highly scalable, multi-modal Reinforcement Learning (RL) framework built in Python. This repository provides a complete pipeline to train Proximal Policy Optimization (PPO) agents using decoupled vision (RGB/Grayscale) and audio inputs. The entire training process is managed via an intuitive, real-time local web interface. Key Features Multi-Modal Inputs: Seamlessly train agents using visual data, acoustic data, or a combination of both. Dynamic Vision Toggle: Switch instantly between full RGB color […]

Ver mais

​ Built a Python framework that adds cognitive middleware (Memory, Reflection, Structured Rewards) to any RL environment. Agents remember past mistakes and get hints Q-Learning, SARSA, Genetic Algorithms, not just LLMs. Zero dependencies. “pip install cognicore-env” What is this? CogniCore is a reinforcement learning framework where every environment comes with built-in cognitive middleware: – Memory agent remembers outcomes from past episodes (which states led to traps, which strategies worked) – Reflection auto-generates hints from past mistakes (“You failed […]

Ver mais