We propose a novel loss function called Energy Discrepancy (ED) which does not rely on the computation of scores or expensive Markov chain Monte Carlo.

In this section, we show that Cold Sampling is an approximation of the Euler method for (5). The intuition is as follows. B.2 Why is cold sampling better than naive sampling? Naive sampling does not have this property. The proof relied on applying definitions of Lipschitz functions twice.

Dynamics forecasting refers to the task of predicting the future behavior of a dynamic system, involving learning the underlying dynamics governing the system's evolution to make accurate predictions

M-7B significantly improves the performance on real-world long-context tasks (e.g., 23.5

In such situations, the successor representation (SR) is a popular framework which supports rapid policy evaluation by decoupling a policy's