activity
20242026
collaborators

7 papers

cs.CV2026

ClimateVID -- Social Media Videos Analysis and Challenges Involved

Shiqi Xu, Moritz Burmester, Katharina Prasse +3

The pervasive growth of digital content, specifically short videos on social media platforms, has significantly altered how topics are discussed and understood in public discourse.…

cs.CV2026

From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media

Katharina Prasse, Steffen Jung, Isaac Bravo +4

Social media platforms have become primary arenas for climate communication, generating millions of images and posts that - if systematically analysed - can reveal which communicat…

cs.LG2026

MaxSup: Overcoming Representation Collapse in Label Smoothing

Yuxuan Zhou, Heng Li, Zhi-Qi Cheng +4

Label Smoothing (LS) is widely adopted to reduce overconfidence in neural network predictions and improve generalization. Despite these benefits, recent studies reveal two critical…

cs.CV2025

VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis

Yumeng Li, William Beluch, Margret Keuper +2

Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolvin…

cs.CL2025

Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation

Yuxuan Zhou, Margret Keuper, Mario Fritz

Sampling-based decoding strategies have been widely adopted for Large Language Models (LLMs) in numerous applications, targeting a balance between diversity and quality via tempera…

cs.LG2025

MultiMax: Sparse and Multi-Modal Attention Learning

Yuxuan Zhou, Mario Fritz, Margret Keuper

SoftMax is a ubiquitous ingredient of modern machine learning algorithms. It maps an input vector onto a probability simplex and reweights the input by concentrating the probabilit…