Written after I fucked up my therapy due to gastrointestinal disorder as a remainder. Don't take it seriously.

Macro-o1 7B is the first o1-like open source LLM. In this post, we will dive into its training paradigm and its inference implementation.

The trading behavior in a market is often backed by asymmetric information, making the market a asymmetric game. Albert S. Kyle proposed a micro-structure formulation in 1985, stating that such market consists of three players: an insider, a random noise trader, and a market maker. His successors also proved that there exist an equilibrium with additional conditions. In this post, we will discuss the formulation of Kyle's model formulated as an extensive form game and an Optimal-Transport based setting of equilibrium.

In this post, we will try to connect Energy-Based Model with classical optimal control frameworks like Model-Predictive Control from the perspective of Lagrangian optimization.

In this note we connect the energy concepts including Lagrangian Dynamics and Gibbs Formula to measuring the quality of prediction. Then we go over the inferencing and training in multi-modal scenarios.

In short, using diffusion process instead of directly applying MSE loss on trajectories enables a wider variety of trajectory solutions learnt from imitation data, instead of the trajectory provided by dataset(s), which is beneficial for small-set imitation learning. In this blog post, we will discuss how and why diffusion process can achieve such and trajectory-agnostic result.

ScoreGrad is a EBM make use of iterative conditional SDE sampling via diffusion to perform multi-variate probabilistic time series prediction. Basically it uses RNN/LSTM/GRU to encode past time series as a condition and sample a probability distribution of predicting time series based on this.

ABSTRACT: This paper introduces a self-supervised, end-to-end architecture that learns part-level implicit shape and appearance models and optimizes motion parameters jointly without requiring any 3D supervision, motion, or semantic annotation. The training process is similar to original NeRF but and extend the ray marching and volumetric rendering procedure to compose the two fields.

This paper propose a way to form articulation model of articulated objects by encoding the features and find the correspondence of static and mobile part via visual observation before and after the interaction.

The paper proposed a way of modeling interactive objects in a large-scale 3D space by making affordance predictions and inferring the articulation properties from the visual observations before and after the self-driven interaction.