8 papers
Retrofitting Recurrent Vision-Language Models from Pretrained Backbones
Madhav Iyengar, Andreas Geiger, Hilde Kühne
Recent work shows that depth recurrence can be retrofitted into pretrained language models. In this work, we adapt this paradigm for visual understanding, using depth recurrence to…
LLM4Impact: Integrating Heterogeneous Information for Scientific Impact Prediction
Yong Cao, Markus Flicke, Haoyu He +2
Predicting the future impact of a newly published paper is challenging because it must be inferred from heterogeneous evidence available at publication time. Existing approaches of…
MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models
Haoyu He, Katrin Renz, Yong Cao +1
Diffusion language models, as a promising alternative to traditional autoregressive (AR) models, enable faster generation and richer conditioning on bidirectional context. However,…
3D-LATTE: Latent Space 3D Editing from Textual Instructions
Maria Parelli, Michael Oechsle, Michael Niemeyer +2
Despite the recent success of multi-view diffusion models for text/image-based 3D asset generation, instruction-based editing of 3D assets lacks surprisingly far behind the quality…
MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction
Zijian Dong, Longteng Duan, Jie Song +2
We present MoGA, a novel method to reconstruct high-fidelity 3D Gaussian avatars from a single-view image. The main challenge lies in inferring unseen appearance and geometric deta…
Scholar Inbox: Personalized Paper Recommendations for Scientists
Markus Flicke, Glenn Angrabeit, Madhav Iyengar +10
Scholar Inbox is a new open-access platform designed to address the challenges researchers face in staying current with the rapidly expanding volume of scientific literature. We pr…
Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
Steffen Eger, Yong Cao, Jennifer D'Souza +11
With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. An emerging ecosystem of models and tools aims to su…
HDT: Hierarchical Document Transformer
Haoyu He, Markus Flicke, Jan Buchmann +2
In this paper, we propose the Hierarchical Document Transformer (HDT), a novel sparse Transformer architecture tailored for structured hierarchical documents. Such documents are ex…