Paper Archive

Xuweiyi Chen, Wentao Zhou, Zezhou Cheng 1/15/2026 arxiv

We present WildRayZer, a self-supervised framework for novel view synthesis (NVS) in dynamic environments where both the camera and objects move. Dynamic content breaks the multi-view consistency that static NVS models rely on, leading to ghosting, hallucinated geometry, and unstable pose estimation...

Navami Kairanda, Shanthika Naik, Marc Habermann, Avinash Sharma, Christian Theobalt, Vladislav Golyanik 1/15/2026 arxiv

We present a novel differentiable grid-based representation for efficiently solving differential equations (DEs). Widely used architectures for neural solvers, such as sinusoidal neural networks, are coordinate-based MLPs that are both computationally intensive and slow to train. Although grid-based...

Tal Reiss, Daniel Winter, Matan Cohen, Alex Rav-Acha, Yael Pritch, Ariel Shamir, Yedid Hoshen 1/15/2026 arxiv

We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, material, and even the shape of an object, while preserving its perceived identity and scene context. Existing approaches either rely on unsupervised priors th...

Changle Qu, Sunhao Dai, Hengyi Cai, Jun Xu, Shuaiqiang Wang, Dawei Yin 1/15/2026 arxiv

Tool-Integrated Reasoning (TIR) empowers large language models (LLMs) to tackle complex tasks by interleaving reasoning steps with external tool interactions. However, existing reinforcement learning methods typically rely on outcome- or trajectory-level rewards, assigning uniform advantages to all ...

Cheng Chen, Yuyu Guo, Pengpeng Zeng, Jingkuan Song, Peng Di, Hang Yu, Lianli Gao 1/15/2026 arxiv

Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection that links only the output of the vision encoder to the input of the large language model (LLM). This static architecture fundamentally limits the ability of LLMs to achieve comprehensive ...

Khashayar Gatmiry, Sitan Chen, Adil Salim 1/15/2026 arxiv

Diffusion models have shown remarkable empirical success in sampling from rich multi-modal distributions. Their inference relies on numerically solving a certain differential equation. This differential equation cannot be solved in closed form, and its resolution via discretization typically require...

Amir Mallak, Erfan Aasi, Shiva Sreeram, Tsun-Hsuan Wang, Daniela Rus, Alaa Maalouf 1/15/2026 arxiv

Recent advances in end-to-end autonomous driving show that policies trained on patch-aligned features extracted from foundation models generalize better to Out-of-Distribution (OOD). We hypothesize that due to the self-attention mechanism, each patch feature implicitly embeds/contains information fr...

Keval Jain, Anant Raj, Saurav Prakash, Girish Varma 1/15/2026 arxiv

We study a semi-asynchronous client-server perceptron trained via iterative parameter mixing (IPM-style averaging): clients run local perceptron updates and a server forms a global model by aggregating the updates that arrive in each communication round. The setting captures three system effects in ...

Ruozhen Yang, Yucheng Jiang, Yueqi Jiang, Priyanka Kargupta, Yunyi Zhang, Jiawei Han 1/15/2026 arxiv

Deploying large language models in long-horizon, goal-oriented interactions remains challenging because similar entities and facts recur under different latent goals and constraints, causing memory systems to retrieve context-mismatched evidence. We propose STITCH (Structured Intent Tracking in Cont...

Chun Hei Michael Shiu, Chih Wei Ling 1/15/2026 arxiv

Federated learning enables multiple parties to jointly train learning models without sharing their own underlying data, offering a practical pathway to privacy-preserving collaboration under data-governance constraints. Continued study of federated learning is essential to address key challenges in ...