1 citations · 1 across the 7 of their papers we have counts for
4 papers · 1 filter
How to post-train on a surrogate: Envelope sampling mitigates reward hacking
Sanjit Dandapanthula, Shuvom Sadhuka, Samir Khan +3
Large language models (LLMs) are commonly post-trained against LLM judges and other cheap surrogates because the true reward, such as human preference, is too expensive to query at…
Are we really tilting? The mechanics of reward guidance in flow and diffusion models
Sanjit Dandapanthula, Nicholas M. Boffi
Reward guidance algorithms steer a learned generative process toward the reward-tilted measure at inference time. While empirically powerful, these methods are prone to reward hack…
Optimal Transportation and Alignment Between Gaussian Measures
Sanjit Dandapanthula, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan +2
Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for comparing, transforming, and aggregating heterogeneous datasets---tasks…
Gradient descent dynamics for deep equilibrium models
Sanjit Dandapanthula, Aaditya Ramdas
Deep equilibrium models (DEQs) have recently emerged as a powerful paradigm for training infinitely deep weight-tied neural networks that achieve state of the art performance acros…