hallucination mitigation 1language model limitations 1personal AI assistants 1sycophancy reduction 1user modeling 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CL2026
The Severance Problem: LLMs are Unaware of the Person Beyond the Prompt
Dor Litvak, Liu Leqi
The paper identifies the "Severance Problem"—the lack of an explicit representation of a user beyond the prompt—in current LLM-based personal assistants, and proposes a "Severance…
cs.CV2024
Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos
Keqiang Sun, Dor Litvak, Yunzhi Zhang +3
We introduce a new method for learning a generative model of articulated 3D animal motions from raw, unlabeled online videos. Unlike existing approaches for 3D motion synthesis, ou…
cs.CV2024
Learning the 3D Fauna of the Web
Zizhang Li, Dor Litvak, Ruining Li +6
Learning 3D models of all animals on the Earth requires massively scaling up existing solutions. With this ultimate goal in mind, we develop 3D-Fauna, an approach that learns a pan…