March 2026

Here is a PyTorch port of the Disco103 update rule: https://github.com/asystemoffields/disco-torch pip install disco-torch The port loads the pretrained disco_103.npz weights and reproduces the reference Catch benchmark (99% catch rate at 1000 steps). All meta-network outputs match the JAX implementation within float32 precision (<1e-6 max diff), and the full value pipeline is verified (14 fields, <6e-4 max diff). It includes a high-level DiscoTrainer API that handles meta-state management, target networks, replay buffer, and the training loop: from disco_torch […]

Ver mais

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing and difficulty scaling. We introduce a four-stage Data Processing Framework encompassing collection, processing, filtering, and verification, incorporating Automatic Difficulty Filtering via an LLM-based predict-calibrate-select framework that leverages multi-dimensional difficulty metrics across five weighted dimensions to retain challenging problems while removing simplistic ones. The resulting MicroCoder dataset comprises tens of thousands […]

Ver mais

Inferring the dynamical generator of a many-body quantum system from measurement data is essential for the verification, calibration, and control of quantum processors. When the system is open, this task becomes considerably harder than in the purely unitary case, because coherent and dissipative mechanisms can produce similar measurement statistics and long-time data can be insensitive to coherent couplings. Here we tackle this so-called Lindbladian learning problem of open-system characterisation with maximum-likelihood on Pauli measurements at multiple experimentally friendly […]

Ver mais

Modern code generation models exhibit longer outputs, accelerated capability growth, and changed training dynamics, rendering traditional training methodologies, algorithms, and datasets ineffective for improving their performance. To address these training bottlenecks, we propose MicroCoder-GRPO, an improved Group Relative Policy Optimization approach with three innovations: conditional truncation masking to improve long output potential while maintaining training stability, diversity-determined temperature selection to maintain and encourage output diversity, and removal of KL loss with high clipping ratios to facilitate solution diversity. […]

Ver mais

Federated Graph Learning (FedGL) is vulnerable to malicious attacks, yet developing a truly effective and stealthy attack method remains a significant challenge. Existing attack methods suffer from low attack success rates, high computational costs, and are easily identified and smoothed by defense algorithms. To address these challenges, we propose textbf{FedShift}, a novel two-stage "Hide and Find" distributed adversarial attack. In the first stage, before FedGL begins, we inject a learnable and hidden "shifter" into part of the training […]

Ver mais

Greedy algorithms are central to sparse approximation and stage-wise learning methods such as matching pursuit and boosting. It is known that the Power-Relaxed Greedy Algorithm with step sizes $m^{-α}$ may fail to converge when $α>1$ in general Hilbert spaces. In this work, we revisit this phenomenon from a sparse learning perspective. We study realizable regression problems with controlled feature coherence and derive explicit lower bounds on the residual norm, showing that over-decaying step-size schedules induce structural stagnation even […]

Ver mais

Hey, I’ve been going down the rabbit hole of sim-to-real RL and I’m trying to understand where the ACTUAL bottlenecks are for people doing this in practice (not just in papers). From what I’ve read, domain randomization and system identification help close the gap, but it seems like there’s still a lot of pain around rare/adversarial scenarios that you can’t really plan for in sim. For those of you actually deploying RL policies on physical robots: What part […]

Ver mais

Modern applications process massive data volumes that overwhelm the storage and retrieval capabilities of memory systems, making memory the primary performance and energy-efficiency bottleneck of computing systems. Although many microarchitectural techniques attempt to hide or tolerate long memory access latency, rapidly growing data footprints continue to outpace technology scaling, requiring more effective solutions. This dissertation shows that modern processors observe large amounts of application and system data during execution, yet many microarchitectural mechanisms make decisions largely independent of […]

Ver mais

Partial differential equations (PDEs) govern physical phenomena across the full range of scientific scales, yet their computational solution remains one of the defining challenges of modern science. This critical review examines two mature but epistemologically distinct paradigms for PDE solution, classical numerical methods and machine learning approaches, through a unified evaluative framework organized around six fundamental computational challenges. Classical methods are assessed for their structure-preserving properties, rigorous convergence theory, and scalable solver design; their persistent limitations in high-dimensional […]

Ver mais