Paper Archive

Haofei Xu, Daniel Barath, Andreas Geiger, Marc Pollefeys 10/9/2025 arxiv

While feed-forward Gaussian splatting models provide computational efficiency and effectively handle sparse input settings, their performance is fundamentally limited by the reliance on a single forward pass during inference. We propose ReSplat, a feed-forward recurrent Gaussian splatting model that...

Rocktim Jyoti Das, Harsh Singh, Diana Turmakhan, Muhammad Abdullah Sohail, Mingfei Han, Preslav Nakov, Fabio Pizzati, Ivan Laptev 10/9/2025 arxiv

Scaling data and models has played a pivotal role in the remarkable progress of computer vision and language. Inspired by these domains, recent efforts in robotics have similarly focused on scaling both data and model size to develop more generalizable and robust policies. However, unlike vision and...

Nimrod Berman, Assaf Hallak, Assaf Shocher 10/9/2025 arxiv

Neural networks are famously nonlinear. However, linearity is defined relative to a pair of vector spaces, $f$$:$$X$$\to$$Y$. Is it possible to identify a pair of non-standard vector spaces for which a conventionally nonlinear function is, in fact, linear? This paper introduces a method that makes s...

Animikh Aich, Adwait Kulkarni, Eshed Ohn-Bar 10/9/2025 arxiv

Real-World evaluation of perception-based planning models for robotic systems, such as autonomous vehicles, can be safely and inexpensively conducted offline, i.e., by computing model prediction error over a pre-collected validation dataset with ground-truth annotations. However, extrapolating from ...

Hongyu Li, Lingfeng Sun, Yafei Hu, Duy Ta, Jennifer Barry, George Konidaris, Jiahui Fu 10/9/2025 arxiv

Enabling robots to execute novel manipulation tasks zero-shot is a central goal in robotics. Most existing methods assume in-distribution tasks or rely on fine-tuning with embodiment-matched data, limiting transfer across platforms. We present NovaFlow, an autonomous manipulation framework that conv...

Qin Liu, Jacob Dineen, Yuxi Huang, Sheng Zhang, Hoifung Poon, Ben Zhou, Muhao Chen 10/9/2025 arxiv

Benchmarks are central to measuring the capabilities of large language models and guiding model development, yet widespread data leakage from pretraining corpora undermines their validity. Models can match memorized content rather than demonstrate true generalization, which inflates scores, distorts...

Tajamul Ashraf, Umair Nawaz, Abdelrahman M. Shaker, Rao Anwer, Philip Torr, Fahad Shahbaz Khan, Salman Khan 10/9/2025 arxiv

Vision language models (VLMs) are increasingly deployed as controllers with access to external tools for complex reasoning and decision-making, yet their effectiveness remains limited by the scarcity of high-quality multimodal trajectories and the cost of manual annotation. We address this challenge...

Zhen Zhu, Yiming Gong, Yao Xiao, Yaoyao Liu, Derek Hoiem 10/9/2025 arxiv

How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills while monitoring general ability on eight held-out benchmarks across three model families. We observe that apparent "forgetting" on held-out tasks after n...

Zhiyu Zheng, Shaoyu Chen, Haoran Yin, Xinbang Zhang, Jialv Zou, Xinggang Wang, Qian Zhang, Lefei Zhang 10/9/2025 arxiv

End-to-end autonomous driving (E2EAD) systems, which learn to predict future trajectories directly from sensor data, are fundamentally challenged by the inherent spatio-temporal imbalance of trajectory data. This imbalance creates a significant optimization burden, causing models to learn spurious c...

El Houcine Bergou, Soumia Boucherouite, Aritra Dutta, Xin Li, Anna Ma 10/9/2025 arxiv

The randomized Kaczmarz (RK) algorithm is one of the most computationally and memory-efficient iterative algorithms for solving large-scale linear systems. However, practical applications often involve noisy and potentially inconsistent systems. While the convergence of RK is well understood for con...