Recent vision-and-language navigation (VLN) systems increasingly adopt streaming Video-LLM policies that map egocentric RGB observations and instructions directly to low-level actions. Yet these policies inherit weak 3D geometric priors from 2D pretraining. Existing geometry-aware extensions charge a persistent inferen...
Yi-Xuan Jiang, Wen-Tong Li, An Liu et al.· 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.
HAM-VLN is presented, a decision-coupled, agent-authored memory that equips the robot with a persistent, depth-grounded world graph and reduces the context length by more than 65% compared to previous methods.
An Liu, Bingxi Liu, Hongyu Ding et al.· arXiv.org· 1 citation
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...
