Text-to-image generation has reached photorealistic quality, yet state-of-the-art systems remain unreliable at producing scientific diagrams, whose value depends not on appearance but on physical faithfulness: correct force directions, valid coordinate systems, consistent thermodynamic states, and equations matching the depicted scenario. Trained on web imagery with physically shallow captions, generic models produce diagrams that look plausible but are physically wrong, harmful in education and scientific communication.
Diffusion Transformer Text-to-Video models have achieved remarkable synthesis quality, yet fine-grained spatial controllability remains a significant challenge. While existing training-free methods produce solid overall results in spatially grounded generation, \ie, placing a specific object in a designated location, they rely on gradient-based optimization techniques that incur prohibitive computational overhead, a bottleneck amplified in modern large-scale architectures.
Score Distillation Sampling (SDS) enables text-to-3D generation by optimizing rendered images with a pretrained diffusion prior, but latent SDS often produces structured color artifacts and high-frequency texture noise. We identify a failure mode of latent SDS caused by VAE-induced pixel drift: the optimized image can move along pixel-space directions that are weakly constrained by the VAE encoder, so its latent representation remains clean and semantically meaningful while the image itself accumulates visible artifacts.
Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control. The core challenge is structural: VLA inference is not a single bottleneck but a cascade of four.
arXiv:2608. 12290v1 Announce Type: cross Abstract: Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows.
By Aman Tyagi, Hemanth Boinpally, Jonathan Chen, Douglas Gebert, Steven Hickson
arXiv:2608. 11235v1 Announce Type: new Abstract: Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon.
By Yifan Wu, Yufeng Zhang, Kenli Li
arXiv:2608. 12083v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) achieve strong predictive performance on graph-structured data across domains such as chemistry, biology, and network analysis, yet they provide no intrinsic explanation of their predictions.
By David Bechtoldt, Sidney Bender
arXiv:2605. 02961v2 Announce Type: replace-cross Abstract: Most modern bridge-diffusion methods achieve finite-time transport by specifying an interpolation, Schrodinger-bridge, or stochastic-control objective and then learning the associated score or drift field with a neural network.
By Michael Chertkov
arXiv:2608. 11249v1 Announce Type: cross Abstract: We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual data - including plain text, source code, and structured formats such as XML - and by recent advances in neural language model-based compression.
By Angelo Nardone, Paolo Ferragina
arXiv:2605. 12236v2 Announce Type: replace-cross Abstract: Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream exploration.
By Matthew M. Hong, Jesse Zhang, Anusha Nagabandi, Abhishek Gupta
arXiv:2608. 11521v1 Announce Type: cross Abstract: World action models (WAMs) condition robot actions on predicted futures, but iterative video rollout increases deployment latency.
By Chushan Zhang, Jinguang Tong, Xuesong Li, Yikai Wang, Hongdong Li
arXiv:2608. 11884v1 Announce Type: cross Abstract: Quantum generative adversarial networks (QGANs) have attracted increasing attention for image generation using parameterized quantum circuits.
By Xue Yang, Rigui Zhou, ShiZheng Jia, Dax Enshan Koh, Siong Thye Goh, Young-Wook Cho, YaoChong Li, Xuezhi Ma, Hongyu Chen, Xin Wang
arXiv:2608. 12308v1 Announce Type: cross Abstract: Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan future actions, and determine when it has reached a navigation goal under partial observability.
By Yan Deng, Fei Xu
arXiv:2608. 12032v1 Announce Type: cross Abstract: Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and duration grow.
By Enhuai Liu, Yunke Wang, Yutong Wang, Changming Sun, Chang Xu
arXiv:2608. 11419v1 Announce Type: new Abstract: Assortment optimization is a fundamental problem in revenue management, typically addressed using parametric choice models such as the multinomial logit (MNL) and its variants.
By Junyi Liao, Xiaohui Jiang, Zhengwei Tong, Ethan X. Fang, Vahid Tarokh
arXiv:2603. 29426v2 Announce Type: replace-cross Abstract: Multi-agent reinforcement learning (MARL) provides a promising solution for cooperative target tracking in networks of autonomous underwater vehicles (AUVs).
By Jiaao Ma, Chuan Lin, Guangjie Han, Shengchao Zhu, Zhenyu Wang, Chen An
arXiv:2608. 11732v1 Announce Type: cross Abstract: Proprietary text-to-image diffusion models are increasingly distributed as hosted services and downloadable checkpoints, making their intellectual property (IP) protection an increasingly critical concern when model leakage, copying, or unauthorized fine-tuning is disputed.
By Yuanmin Huang, Chen Chen, Geng Hong, Xiaoyu You, Hui Xue, Zhenxing Qian, Mi Zhang, Min Yang
arXiv:2608. 11562v1 Announce Type: cross Abstract: Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vision tasks.
By Zepeng Wang, Jiagao Hu, Fuhao Li, Yuxuan Chen, Fei Wang, Daiguo Zhou
arXiv:2608. 11452v1 Announce Type: cross Abstract: Text-to-image (T2I) models are increasingly asked to illustrate literary and cultural content, yet we cannot measure how well an image renders the meaning of a poem.
By Haoqi Hu, Tongji Luo, Li Zhang, Boning Zhou
arXiv:2605. 07339v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks.
By Tairan Huang, Siyu Shang, Qiang Chen, Xiu Su, Yi Chen