Blog

A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapted models. We invalidate this assumption by studying the BTH in causal models under prompt adaptations, as prompting is an extremely popular and accessible adaptation strategy …

Read more “Bias after Prompting: Persistent Discrimination in Large Language Models”

Author: Keertana Chidambaram, Qiuling Xu, Ko-Jen Hsiao, Moumita Bhattacharya (*The work was done when Keertana interned at Netflix.) Introduction This blog focuses on post-training generative recommender systems. Generative recommenders (GRs) represent a new paradigm in the field of recommendation systems (e.g. HSTU, OneRec). These models draw inspiration from recent advancements in transformer architectures used for …

Read more “Post-Training Generative Recommenders with Advantage-Weighted Supervised Finetuning”

We revisit scene-level 3D object detection as the output of an object-centric framework capable of both localization and mapping using 3D oriented boxes as the underlying geometric primitive. While existing 3D object detection approaches operate globally and implicitly rely on the a priori existence of metric camera poses, our method, Rooms from Motion (RfM) operates …

Read more “Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping”