arXiv:2601.15420v1 Announce Type: new Abstract: Motivated by applications in computable analysis, we study fixpoints of certain endofunctors over categories of containers. More specifically, we focus on fibred endofunctors over the fibrewise opposite of the codomain fibration that can be themselves be represented by families of polynomial endofunctors. In this setting, we show how to compute initial algebras, terminal coalgebras and another kind of fixpoint $zeta$. We then explore a number of examples of derived operators inspired by Weihrauch […]

Ver mais

arXiv:2601.10768v1 Announce Type: new Abstract: This paper investigates complex product-innovation processes using models grounded in a set of heuristics. Each heuristic is expressed through simple trends — increasing, decreasing, or constant — which serve as minimally information-intensive quantifiers, avoiding reliance on numerical values or rough sets. A solution to a trend model is defined as a set of scenarios with possible transitions between them, represented by a transition graph. Any possible future or past behaviour of the system […]

Ver mais

Mamba-2 restructured its recurrence from parallel scans (10-20% Tensor Core utilization) to block-diagonal GEMMs (60-70%). The architecture bent to fit the silicon. RetNet was published by Microsoft Research in July 2023 with promising results at 6.7B. Five months later, the same organization shipped Phi-2, a dense Transformer. Then Phi-3. Then Phi-4. The co-authors didn’t bet on their own architecture. I wrote an analysis of why this pattern keeps repeating. The short version: Transformers and NVIDIA GPUs co-evolved into […]

Ver mais

Machine learning is a powerful method of extracting meaning from data; unfortunately, current digital hardware is extremely energy-intensive. There is interest in an alternative analog computing implementation that could match the performance of traditional machine learning while being significantly more energy-efficient. However, it remains unclear how to train such analog computing systems while adhering to locality constraints imposed by the physical (as opposed to digital) nature of these systems. Local learning algorithms such as Equilibrium Propagation and Coupled […]

Ver mais

arXiv:2601.08784v1 Announce Type: new Abstract: Machine Learning algorithms are ubiquitous in key decision-making contexts such as justice, healthcare and finance, which has spawned a great demand for fairness in these procedures. However, the theoretical properties of such models in relation with fairness are still poorly understood, and the intuition behind the relationship between group and individual fairness is still lacking. In this paper, we provide a theoretical framework based on Sheaf Diffusion to leverage tools based on dynamical […]

Ver mais

A paper from UGA shows you can match SOTA LLM performance with 2000 targeted samples instead of 300000. The secret? Looking inside model’s feature space. A recent paper called Less is Enough from University of Georgia, UC San Diego matched SOTA performance on instruction-following using 2,000 synthetic samples instead of 300,000. That’s 150x less data for the same results. The underlying idea is simple: two texts that look completely different can activate nearly identical features inside the model. […]

Ver mais

Live streaming has become a cornerstone of today’s internet, enabling massive real-time social interactions. However, it faces severe risks arising from sparse, coordinated malicious behaviors among multiple participants, which are often concealed within normal activities and challenging to detect timely and accurately. In this work, we provide a pioneering study on risk assessment in live streaming rooms, characterized by weak supervision where only room-level labels are available. We formulate the task as a Multiple Instance Learning (MIL) problem, […]

Ver mais