It is shown that the choice of $\ell_1$ or $\ell_2$ is suboptimal in most cases and the optimal $p$ value is dependent on the specific task, highlighting the importance of principled norm selection when designing and evaluating adversarial attacks.
C. Duhme, Florian Eilers, Xiao-Yi Jiang· arXiv.org· 0 citations
It is shown that in some scenarios CVNNs are more robust than RVNNs and that both are very susceptible to phase changes with the Phase Attacks decreasing the model performance more, than equally strong regular attacks, which can attack both phase and magnitude.
Florian Eilers, C. Duhme, Xiao-Yi Jiang· arXiv.org· 0 citations
This work proposes an inverse molecular design framework based on causal language models, and represents the first successful adaptation of LLMs specifically for the OLED domain, bridging the gap between generic molecular generation and the stringent structural requirements of optoelectronic materials.
Fu-Kang Wen, Yu-Chong Tang, Jingyuan Li et al.· arXiv.org· 0 citations
A 170M-parameter M2S model trained on about 262B OpenWebText token slots outperforms the evaluated pure-uniform SEDD, GIDD, and Neural CTMC checkpoints at every tested sampling budget, reaching generative PPL $143.3$ at 128 steps versus $183.6$ for the strongest pure-uniform baseline.
This work proposes a simple continual pre-training approach for directly adapting pretrained GPT2 checkpoints to uniform-noise diffusion, and establishes connections among SEDD, MDLM/GIDD, M2S, and Neural CTMC by expressing their conditional losses as a single generalized Kullback--Leibler objective over model reverse...
