Paper Archive

Yuheng Liu, Xin Lin, Xinke Li, Baihan Yang, Chen Wang, Kalyan Sunkavalli, Yannick Hold-Geoffroy, Hao Tan, Kai Zhang, Xiaohui Xie, Zifan Shi, Yiwei Hu 3/31/2026 arxiv

Modeling scenes using video generation models has garnered growing research interest in recent years. However, most existing approaches rely on perspective video models that synthesize only limited observations of a scene, leading to issues of completeness and global consistency. We propose OmniRoam...

Kaleb Newman, Tyler Zhu, Olga Russakovsky 3/31/2026 arxiv

Video diffusion models exhibit emergent reasoning capabilities like solving mazes and puzzles, yet little is understood about how they reason during generation. We take a first step towards understanding this and study the internal planning dynamics of video models using 2D maze solving as a control...

Izavan dos S. Correia, Henrique C. T. Santos, Tiago A. E. Ferreira 3/31/2026 arxiv

Automatic parallelization remains a challenging problem in software engineering, particularly in identifying code regions where loops can be safely executed in parallel on modern multi-core architectures. Traditional static analysis techniques, such as dependence analysis and polyhedral models, ofte...

Wenyi Li, Renkai Luo, Yue Yu, Huan-ang Gao, Mingju Gao, Li Yuan, Chaoyou Fu, Hao Zhao 3/31/2026 arxiv

AI-assisted coding has rapidly reshaped software practice and research workflows, yet today's models still struggle to produce correct code for complex 3D geometric vision. If models could reliably write such code, the research of our community would change substantially. To measure progress toward ...

Max Kaufmann, David Lindner, Roland S. Zimmermann, and Rohin Shah 3/31/2026 arxiv

Chain-of-Thought (CoT) monitoring, in which automated systems monitor the CoT of an LLM, is a promising approach for effectively overseeing AI systems. However, the extent to which a model's CoT helps us oversee the model - the monitorability of the CoT - can be affected by training, for instance by...

Timon Klein, Jonas Kusch, Sebastian Sager, Stefan Schnake, Steffen Schotthöfer 3/31/2026 arxiv

The pursuit of reducing the memory footprint of the self-attention mechanism in multi-headed self attention (MHA) spawned a rich portfolio of methods, e.g., group-query attention (GQA) and multi-head latent attention (MLA). The methods leverage specialized low-rank factorizations across embedding di...

Paige Tuttösí, Angelica Lim, H. Henny Yeung, Yue Wang, Jean-Julien Aucouturier 3/31/2026 arxiv

Human talkers often address listeners with language-comprehension challenges, such as hard-of-hearing or non-native adults, by globally slowing down their speech. However, it remains unclear whether this strategy actually makes speech more intelligible. Here, we take advantage of recent advancements...

Md Saad, Sajjad Hussain, Mohd Suhaib 3/31/2026 arxiv

This paper introduces a new hybrid framework that combines Reinforcement Learning (RL) and Large Language Models (LLMs) to improve robotic manipulation tasks. By utilizing RL for accurate low-level control and LLMs for high level task planning and understanding of natural language, the proposed fram...

Derek Anderson, Amit Bashyal, Markus Diefenthaler, Cristiano Fanelli, Wen Guan, Tanja Horn, Alex Jentsch Meifeng Lin, Tadashi Maeno, Kei Nagai, Hemalata Nayak, Connor Pecar, Karthik Suresh, Fang-Ying Tsai, Anselm Vossen, Tianle Wang, Torre Wenaus 3/31/2026 arxiv

The Production and Distributed Analysis (PanDA) system, originally developed for the ATLAS experiment at the CERN Large Hadron Collider (LHC), has evolved into a robust platform for orchestrating large-scale workflows across distributed computing resources. Coupled with its intelligent Distributed D...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 3/31/2026 huggingface

Interleaved text-and-image generation represents a significant frontier for Multimodal Large Language Models (MLLMs), offering a more intuitive way to convey complex information. Current paradigms rely on either image generation or retrieval augmentation, yet they typically treat the two as mutually...