Summary of Scimage: How Good Are Multimodal Large Language Models at Scientific Text-to-image Generation?, by Leixin Zhang et al.
ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?by Leixin Zhang, Steffen…
ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?by Leixin Zhang, Steffen…
GerPS-Compare: Comparing NER methods for legal norm analysisby Sarah T. Bachinger, Christoph Unger, Robin Erd,…
Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retrainingby Zongru Wu, Pengzhou Cheng,…
Uncertainty-Aware Regularization for Image-to-Image Translationby Anuja Vats, Ivar Farup, Marius Pedersen, Kiran RajaFirst submitted to…
Digital Epidemiology: Leveraging Social Media for Insight into Epilepsy and Mental Healthby Liza Dahiya, Rachit…
Quantifying the Reliability of Predictions in Detection Transformers: Object-Level Calibration and Image-Level Uncertaintyby Young-Jin Park,…
[CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Fasterby…
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Modelsby Cameron Tice, Philipp Alexander Kreer, Nathan…
IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Modelsby Khaled Abud, Sergey…
RandAR: Decoder-only Autoregressive Visual Generation in Random Ordersby Ziqi Pang, Tianyuan Zhang, Fujun Luan, Yunze…