How are you, hacker? 🪐Want to know what’s trending right now?: The Techbeat by HackerNoon has got you covered with fresh content from our trending stories of the day! Set email preference here. ## The End of CI/CD Pipelines: The Dawn of Agentic DevOps By @davidiyanu [ 10 Min read ] GitHub’s agent fixed my flaky test in 11 minutes. No human wrote code. But when it fails, instead of a stack trace, you get an outcome. Read […]

Ver mais

Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant. At the same time, SFT may harm the fundamental capabilities of an LLM, particularly after long pretraining: a phenomenon known as catastrophic overtraining (Springer et al., 2025). To understand overtraining, we first investigate catastrophic forgetting in finetuning through the lens of implicit regularization of the learning rate. For models trained to the same […]

Ver mais

The Engineer’s Dilemma Engineers, architects, and developers share a common flaw: we hate ambiguity. We build systems based on logic, predictable inputs, and measurable outputs. Yet, the most important metric of our existence—Happiness—is usually treated as a vague, ethereal concept that “just happens.” I don’t like things that “just happen.” I like things I can track, optimize, and debug. If life is a system, then Happiness is the output. If the output is inconsistent, the code is buggy. […]

Ver mais

We present a unified algorithmic framework for the numerical solution, constrained optimization, and physics-informed learning of PDEs with a variational structure. Our framework is based on a Galerkin discretization of the underlying variational forms, and its high efficiency stems from a novel highly-optimized and GPU-compliant TensorGalerkin framework for linear system assembly (stiffness matrices and load vectors). TensorGalerkin operates by tensorizing element-wise operations within a Python-level Map stage and then performs global reduction with a sparse matrix multiplication that […]

Ver mais

State-of-the-art cloud-native applications require intelligent schedulers that can effectively balance system stability, resource utilisation, and associated costs. While Kubernetes provides feasibility-based placement by default, recent research efforts have explored the use of reinforcement learning (RL) for more intelligent scheduling decisions. However, current RL-based schedulers have three major limitations. First, most of these schedulers use monolithic centralised agents, which are non-scalable for large heterogeneous clusters. Second, the ones that use multi-objective reward functions assume simple, static, linear combinations of […]

Ver mais

arXiv:2604.07380v1 Announce Type: new Abstract: We decompose the spectral edge — the dominant direction of the Gram matrix of parameter updates — into its gradient and weight-decay components during grokking in two sequence tasks (Dyck-1 and SCAN). We find a sharp two-phase lifecycle: before grokking the edge is gradient-driven and functionally active; at grokking, gradient and weight decay align, and the edge becomes a compression axis that is perturbation-flat yet ablation-critical (>4000x more impactful than random directions). Three […]

Ver mais

Braking system, the key module to ensure the safety and steer-ability of current vehicles, relies on extensive manual calibration during production. Reducing labor and time consumption while maintaining the Vehicle Braking Controller (VBC) performance greatly benefits the vehicle industry. Model-based methods in offline reinforcement learning, which facilitate policy exploration within a data-driven dynamics model, offer a promising solution for addressing real-world control tasks. This work proposes ReinVBC, which applies an offline model-based reinforcement learning approach to deal with […]

Ver mais

arXiv:2602.09041v1 Announce Type: new Abstract: Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference steps, existing methods often suffer from process variance due to endpoint error accumulation. Moreover, directly reusing continuous-time architectures for discrete, fixed-step generation introduces structural parameter inefficiencies. To address these challenges, we introduce DSFlow, a modular distillation framework for few-step and one-step synthesis. DSFlow reformulates […]

Ver mais

arXiv:2602.06195v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference labels presents a severe cost and scalability bottleneck. To overcome this, We propose a semi-supervised framework augmenting limited human data with a large corpus of unlabeled pairs annotated via cost-effective synthetic AI feedback. Our paper introduces Debiased DPO (DeDPO), which uniquely integrates a debiased […]

Ver mais