89 papers
LieBN: Batch Normalization over Lie Groups
Ziheng Chen, Yue Song, Rui Wang +2
The paper introduces LieBN, a batch‑normalization framework that works on data lying on Lie groups, providing theoretical control of Riemannian mean and variance across several com…
Harnessing Textual Refusal Directions for Multimodal Safety
Moreno D'IncÃ, Nicu Sebe, Massimiliano Mancini
To improve safety in Large Language Models (LLMs) we can either perform post-training alignment or exploit refusal directions in the activation space. Both strategies are less feas…
Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems
Antonios Tragoudaras, Chenyu Zhang, Daniil Cherniavskii +7
Recent advances in image and video generation raise hopes that these models possess world modeling capabilities-the ability to generate realistic, physically plausible videos. This…
Riemannian Networks over Full-Rank Correlation Matrices
Ziheng Chen, Xiaojun Wu, Bernhard Schölkopf +1
Representations on the Symmetric Positive Definite (SPD) manifold have garnered significant attention across different applications. In contrast, the manifold of full-rank correlat…
Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding
Yue Li, Qi Ma, Runyi Yang +8
While 3DGS has emerged as a high-fidelity scene representation, encoding rich, general-purpose features directly from its primitives remains under-explored. We address this gap by…
Hallucination Early Detection in Diffusion Models
Federico Betti, Lorenzo Baraldi, Rita Cucchiara +1
Text-to-Image generation has seen significant advancements in output realism with the advent of diffusion models. However, diffusion models encounter difficulties when tasked with…