Paper Archive

Zeren Jiang, Chuanxia Zheng, Iro Laina, Diane Larlus, Andrea Vedaldi 1/8/2026 arxiv

We propose Mesh4D, a feed-forward model for monocular 4D mesh reconstruction. Given a monocular video of a dynamic object, our model reconstructs the object's complete 3D shape and motion, represented as a deformation field. Our key contribution is a compact latent space that encodes the entire anim...

Yuan-Kang Lee, Kuan-Lin Chen, Chia-Che Chang, Yu-Lun Liu 1/8/2026 arxiv

Nighttime color constancy remains a challenging problem in computational photography due to low-light noise and complex illumination conditions. We present RL-AWB, a novel framework combining statistical methods with deep reinforcement learning for nighttime white balance. Our method begins with a s...

Daniele Lizzio Bosco, Shuteng Wang, Giuseppe Serra, Vladislav Golyanik 1/8/2026 arxiv

Recently, Quantum Visual Fields (QVFs) have shown promising improvements in model compactness and convergence speed for learning the provided 2D or 3D signals. Meanwhile, novel-view synthesis has seen major advances with Neural Radiance Fields (NeRFs), where models learn a compact representation fro...

Zhuoyang Liu, Jiaming Liu, Hao Chen, Ziyu Guo, Chengkai Hou, Chenyang Gu, Jiale Yu, Xiangju Mi, Renrui Zhang, Zhengping Che, Jian Tang, Pheng-Ann Heng, Shanghang Zhang 1/8/2026 arxiv

Vision-Language-Action (VLA) models have recently demonstrated strong generalization capabilities in robotic manipulation. Some existing VLA approaches attempt to improve action accuracy by explicitly generating linguistic reasoning traces or future visual observations before action execution. Howev...

Gangwei Xu, Haotong Lin, Hongcheng Luo, Haiyang Sun, Bing Wang, Guang Chen, Sida Peng, Hangjun Ye, Xin Yang 1/8/2026 arxiv

Recovering clean and accurate geometry from images is essential for robotics and augmented reality. However, existing geometry foundation models still suffer severely from flying pixels and the loss of fine details. In this paper, we present pixel-perfect visual geometry models that can predict high...

Natalie Collina, Jiuyao Lu, Georgy Noarov, Aaron Roth 1/8/2026 arxiv

We prove tight lower bounds for online multicalibration, establishing an information-theoretic separation from marginal calibration. In the general setting where group functions can depend on both context and the learner's predictions, we prove an $Ω(T^{2/3})$ lower bound on expected multicalibrat...

Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, Yu-Gang Jiang 1/8/2026 arxiv

Referring Expression Segmentation (RES) and Comprehension (REC) respectively segment and detect the object described by an expression, while Referring Expression Generation (REG) generates an expression for the selected object. Existing datasets and methods commonly support single-target expressions...

Xingyi He, Adhitya Polavaram, Yunhao Cao, Om Deshmukh, Tianrui Wang, Xiaowei Zhou, Kuan Fang 1/8/2026 arxiv

Functional grasping with dexterous robotic hands is a key capability for enabling tool use and complex manipulation, yet progress has been constrained by two persistent bottlenecks: the scarcity of large-scale datasets and the absence of integrated semantic and geometric reasoning in learned models....

Shih-Yang Liu, Xin Dong, Ximing Lu, Shizhe Diao, Peter Belcak, Mingjie Liu, Min-Hung Chen, Hongxu Yin, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Yejin Choi, Jan Kautz, Pavlo Molchanov 1/8/2026 arxiv

As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety of scenarios. To achieve this, Reinforcement learning (RL) pipelines have begun incorporating multiple rewards, each cap...

Boyang Wang, Haoran Zhang, Shujie Zhang, Jinkun Hao, Mingda Jia, Qi Lv, Yucheng Mao, Zhaoyang Lyu, Jia Zeng, Xudong Xu, Jiangmiao Pang 1/8/2026 arxiv

The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constraints, collecting large-scale real-world manipulation data remains difficult to scale across diverse environments. Recent work uses text-pro...