technocracy

Hey All, I am currently working on ASR models, and I have gathered some recent literature. From my literature search, it seems like the ASR models are getting more and more powerful due to two main things. Because pseudo-labelled data is growing, supervised models are rising rapidly. Whisper-large-v3 has been trained on 5M hours of weakly supervised data, and Nvidia Parakeet v3 has been trained on 660k hours of labelled data (open-sourced). Funny enough, Nvidia Parakeet v3 actually […]

Ver mais

arXiv:2505.13614v3 Announce Type: replace-cross Abstract: The high-dimensional parameter space of deep neural networks — the neuromanifold — is endowed with a unique metric tensor defined by the Fisher information. Reliable and scalable computation of this metric tensor is valuable for theorists and practitioners. Focusing on neural classifiers, we return to a low-dimensional space of probability distributions, which we call the core space, and examine the spectrum and envelopes of its Fisher information matrix. We extend our discoveries there […]

Ver mais

Recent advances in diffusion-based reinforcement learning (RL) methods have demonstrated promising results in a wide range of continuous control tasks. However, existing works in this field focus on the application of diffusion policies while leaving the diffusion critics unexplored. In fact, since policy optimization fundamentally relies on the critic, accurate value estimation is far more important than policy expressiveness. Furthermore, given the stochasticity of most reinforcement learning tasks, it has been confirmed that the critic is more appropriately […]

Ver mais

arXiv:2603.00601v1 Announce Type: new Abstract: AI code agents excel at isolated tasks yet struggle with complex, multi-file software engineering requiring understanding of how dozens of modules relate. We hypothesize these failures stem from inability to construct, maintain, and update coherent architectural beliefs during codebase exploration. We introduce Theory of Code Space (ToCS), a benchmark that evaluates this capability by placing agents in procedurally generated codebases under partial observability, requiring them to build structured belief states over module dependencies, […]

Ver mais

I’m working with synthetic 2D navigation environments for testing learning-based path planning methods, where the agent must trade off between different criteria like efficiency, safety, and smoothness. One issue I keep running into is that the structure of the environment itself can unintentionally create shortcuts in learning. For example, if certain geometric patterns (like narrow corridors or open spaces) consistently align with specific outcomes, the model tends to pick up on those correlations rather than learning the underlying […]

Ver mais

arXiv:2604.14360v1 Announce Type: new Abstract: Resilience in cyber-physical systems (CPS) is the fundamental ability to maintain safety and critical functionality despite adverse “perturbations,” which includes security attacks, environmental disruptions, and hardware or software failures. This survey provides a comprehensive review of CPS resilience, framing the field through five interconnected themes that are required in an integrated whole to achieve real-world resilience. The article first posits that resilience is a system-wide property emerging from interactions between hardware, software, and […]

Ver mais

arXiv:2603.06611v1 Announce Type: new Abstract: Fecal-contaminated water causes diseases and even death. Current microbial water safety tests require pathogen incubation, taking 24-72 hours and costing $20-$50 per test. This paper presents a solution (DeepScope) exceeding UNICEF’s ideal Target Product Profile requirements for presence/absence testing, with an estimated per-test cost of $0.44. By eliminating the need for pathogen incubation, DeepScope reduces testing time by over 98%. In DeepScope, a dataset of microscope images of bacteria and water samples was […]

Ver mais

arXiv:2603.22302v1 Announce Type: new Abstract: With the development of information technology, the application of artificial intelligence and machine learning in the field of education shows great potential. This study aims to explore how to utilize K-means clustering algorithm to provide accurate career guidance for college students. Existing methods mostly focus on the prediction of career paths, but there are fewer studies on the fitness of students with different combinations of characteristics in specific career directions. In this study, […]

Ver mais

arXiv:2603.28968v1 Announce Type: new Abstract: Many multi-robot applications require tasks to be completed efficiently and in the correct order, so that downstream operations can proceed at the right time. Multi-agent path finding with precedence constraints (MAPF-PC) is a well-studied framework for computing collision-free plans that satisfy ordering relations when task sequences are fixed in advance. In many applications, however, solution quality depends not only on how agents move, but also on which agent performs which task. This motivates […]

Ver mais

arXiv:2604.07396v1 Announce Type: new Abstract: Large Language Model (LLM) inference on edge Neural Processing Units (NPUs) is fundamentally constrained by limited on-chip memory capacity. Although high-density embedded DRAM (eDRAM) is attractive for storing activation workspaces, its periodic refresh consumes substantial energy. Prior work has primarily focused on reducing off-chip traffic or optimizing refresh for persistent Key-Value (KV) caches, while transient and error-resilient Query and Attention Output (QO) activations are largely overlooked. We propose SHIELD, a lifecycle-aware segmented eDRAM […]

Ver mais