Paper Archive

Prakhar Kaushik, Shravan Chaudhari, Ankit Vaidya, Rama Chellappa, Alan Yuille 12/4/2025 arxiv

We show that deep neural networks trained across diverse tasks exhibit remarkably similar low-dimensional parametric subspaces. We provide the first large-scale empirical evidence that demonstrates that neural networks systematically converge to shared spectral subspaces regardless of initialization...

Tianqi Liu, Zhaoxi Chen, Zihao Huang, Shaocong Xu, Saining Zhang, Chongjie Ye, Bohan Li, Zhiguo Cao, Wei Li, Hao Zhao, Ziwei Liu 12/4/2025 arxiv

Recent advances in illumination control extend image-based methods to video, yet still facing a trade-off between lighting fidelity and temporal consistency. Moving beyond relighting, a key step toward generative modeling of real-world scenes is the joint control of camera trajectory and illuminatio...

Zhen Liu, Tim Z. Xiao, Carles Domingo-Enrich, Weiyang Liu, Dinghuai Zhang 12/4/2025 arxiv

While methods exist for aligning flow matching models--a popular and effective class of generative models--with human preferences, existing approaches fail to achieve both adaptation efficiency and probabilistically sound prior preservation. In this work, we leverage the theory of optimal control an...

Malte Hoffmann, Lilla Zöllei, Adrian V. Dalca 12/4/2025 arxiv

Segmentation of magnetic resonance images (MRI) facilitates analysis of human brain development by delineating anatomical structures. However, in infants and young children, accurate segmentation is challenging due to development and imaging constraints. Pediatric brain MRI is notoriously difficult ...

Hao-Jen Chien, Yi-Chuan Huang, Chung-Ho Wu, Wei-Lun Chao, Yu-Lun Liu 12/4/2025 arxiv

Synthesizing high-fidelity frozen 3D scenes from monocular Mannequin-Challenge (MC) videos is a unique problem distinct from standard dynamic scene reconstruction. Instead of focusing on modeling motion, our goal is to create a frozen scene while strategically preserving subtle dynamics to enable us...

Dongzhi Jiang, Renrui Zhang, Haodong Li, Zhuofan Zong, Ziyu Guo, Jun He, Claire Guo, Junyan Ye, Rongyao Fang, Weijia Li, Rui Liu, Hongsheng Li 12/4/2025 arxiv

Recent unified multimodal large language models (MLLMs) have shown impressive capabilities, incorporating chain-of-thought (CoT) reasoning for enhanced text-to-image generation. However, existing approaches remain limited, either treating the model merely as a standalone generator or relying on abst...

Shengyuan Ding, Xinyu Fang, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiangyu Zhao, Haodong Duan, Xiaoyi Dong, Jianze Liang, Bin Wang, Conghui He, Dahua Lin, Jiaqi Wang 12/4/2025 arxiv

Reward models are critical for aligning vision-language systems with human preferences, yet current approaches suffer from hallucination, weak visual grounding, and an inability to use tools for verification, limiting their reliability on complex multimodal reasoning tasks. We present ARM-Thinker, a...

Feng Xu, Guangyao Zhai, Xin Kong, Tingzhong Fu, Daniel F. N. Gordon, Xueli An, Benjamin Busam 12/4/2025 arxiv

Recent advances in Vision-Language-Action (VLA) models, powered by large language models and reinforcement learning-based fine-tuning, have shown remarkable progress in robotic manipulation. Existing methods often treat long-horizon actions as linguistic sequences and apply trajectory-level optimiza...

Yu Zeng, Charles Ochoa, Mingyuan Zhou, Vishal M. Patel, Vitor Guizilini, Rowan McAllister 12/4/2025 arxiv

Standard diffusion corrupts data using Gaussian noise whose Fourier coefficients have random magnitudes and random phases. While effective for unconditional or text-to-image generation, corrupting phase components destroys spatial structure, making it ill-suited for tasks requiring geometric consist...

Purbesh Mitra, Sennur Ulukus 12/4/2025 arxiv

Long context reasoning in large language models (LLMs) has demonstrated enhancement of their cognitive capabilities via chain-of-thought (CoT) inference. Training such models is usually done via reinforcement learning with verifiable rewards (RLVR) in reasoning based problems, like math and programm...