Table of Links Abstract and 1. Introduction Some recent trends in theoretical ML 2.1 Deep Learning via continuous-time controlled dynamical system 2.2 Probabilistic modeling and inference in DL 2.3 Deep Learning in non-Euclidean spaces 2.4 Physics Informed ML Kuramoto model 3.1 Kuramoto models from the geometric point of view 3.2 Hyperbolic geometry of Kuramoto ensembles 3.3 Kuramoto models with several globally coupled sub-ensembles Kuramoto models on higher-dimensional manifolds 4.1 Non-Abelian Kuramoto models on Lie groups 4.2 Kuramoto models […]

Ver mais

arXiv:2602.11249v1 Announce Type: new Abstract: The check-in service is often provided as an incentive system by online learning platforms to help users establish a learning routine and achieve accomplishment. However, according to the questionnaire conducted in this study, 82.5% of users of online English learning platforms that feature a check-in service have failed to maintain the daily check-in behavior for long-term language learning, mainly by reason of demotivation, forgetfulness, boredom, and insufficient time. As a language learner, I […]

Ver mais

Robotic imitation learning typically requires models that capture multimodal action distributions while operating at real-time control rates and accommodating multiple sensing modalities. Although recent generative approaches such as diffusion models, flow matching, and Implicit Maximum Likelihood Estimation (IMLE) have achieved promising results, they often satisfy only a subset of these requirements. To address this, we introduce PRISM, a single-pass policy based on a batch-global rejection-sampling variant of IMLE. PRISM couples a temporal multisensory encoder (integrating RGB, depth, tactile, […]

Ver mais

🧪 I was able to finally solve DeepMind’s Alchemy Meta RL benchmark using a new theoretical framework: Epiplexity For many years, I’ve been working on DeepMind’s Alchemy meta-reinforcement learning benchmark as a side project – a notoriously difficult task that requires agents to discover hidden “chemistry rules” that get shuffled each episode. The breakthrough: Instead of only selecting models by reward, I select by epiplexity – a measure of structural information extraction from the recent paper “From Entropy […]

Ver mais

Counterfactual explanations are increasingly vital for understanding and trusting machine learning models. This study presents, Desirability Rating based Counterfactual (DeRaC), a generalized framework for generating valid counterfactual explanations applicable to multi-dimensional classification problems, including single and multi-output classification with binary and multi-label outputs. By expanding the definition of counterfactual validity through a novel “desirability rating,” the approach addresses limitations in existing methods for complex output spaces. This work details a novel framework, introducing concepts like partially valid counterfactuals […]

Ver mais

arXiv:2601.21084v1 Announce Type: new Abstract: Integrating front-end speech enhancement (SE) models with self-supervised learning (SSL)-based speech models is effective for downstream tasks in noisy conditions. SE models are commonly fine-tuned using SSL representations with mean squared error (MSE) loss between enhanced and clean speech. However, MSE is prone to exploiting positional embeddings in SSL models, allowing the objective to be minimised through positional correlations instead of content-related information. This work frames the problem as a general limitation of […]

Ver mais

arXiv:2402.04177v3 Announce Type: replace-cross Abstract: Scaling laws provide important insights that can guide the design of large language models (LLMs). Existing work has primarily focused on studying scaling laws for pretraining (upstream) loss. However, in transfer learning settings, in which LLMs are pretrained on an unsupervised dataset and then finetuned on a downstream task, we often also care about the downstream performance. In this work, we study the scaling behavior in a transfer learning setting, where LLMs are […]

Ver mais