Paper Archive

Haoran Feng, Yifan Niu, Zehuan Huang, Yang-Tian Sun, Chunchao Guo, Yuxin Peng, Lu Sheng 4/17/2026 arxiv

We introduce LaviGen, a framework that repurposes 3D generative models for 3D layout generation. Unlike previous methods that infer object layouts from textual descriptions, LaviGen operates directly in the native 3D space, formulating layout generation as an autoregressive process that explicitly m...

Eric Gan, Aryan Bhatt, Buck Shlegeris, Julian Stastny, Vivek Hebbar 4/17/2026 arxiv

As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results while evading detection. We introduce ASMR-Bench (Auditing for Sabotage in ML Research), a benchmark for evaluating the ability of auditors to detect ...

Sean Hill, Felix X. -F. Ye 4/17/2026 arxiv

Stochastic dynamical systems with slow or metastable behavior evolve, on long time scales, on an unknown low-dimensional manifold in high-dimensional ambient space. Building a reduced simulator from short-burst ambient ensembles is a long-standing problem: local-chart methods like ATLAS suffer from ...

Thomas Bayer, Alexander Lohr, Sarah Weiß, Bernd Michelberger, Wolfram Höpken 4/17/2026 arxiv

Explaining Machine Learning (ML) results in a transparent and user-friendly manner remains a challenging task of Explainable Artificial Intelligence (XAI). In this paper, we present a method to enhance the interpretability of ML models by using a Knowledge Graph (KG). We store domain-specific data a...

Shriram Chennakesavalu, Kirill Shmilovich, Hayley Weir, Colin Grambow, John Bradshaw, Patricia Suriana, Chen Cheng, Kangway Chuang 4/17/2026 arxiv

Large Language Models (LLMs) have the potential to accelerate small molecule drug design due to their ability to reason about information from diverse sources and formats. However, their practical utility remains unclear due to the lack of benchmarks that reflect real-world scenarios. In this work, ...

Van-Truong Le 4/17/2026 arxiv

The complexity of Vietnam's legal texts presents a significant barrier to public access to justice. While Large Language Models offer a promising solution for legal text simplification, evaluating their true capabilities requires a multifaceted approach that goes beyond surface-level metrics. This p...

Tejeswar Pokuri, Shivarth Rai 4/17/2026 arxiv

Underwater images often suffer from severe degradation, such as color distortion, low contrast, and blurred details, due to light absorption and scattering in water. While learning-based methods like CNNs and Transformers have shown promise, they face critical limitations: CNNs struggle to model the...

Aswathi Mundayatt, Jaya Sreevalsan-Nair 4/17/2026 arxiv

Existing multi-hazard susceptibility mapping (MHSM) studies often rely on spatially uniform models, treat hazards independently, and provide limited representation of cross-hazard dependence and uncertainty. To address these limitations, this study proposes a deep learning (DL) workflow for joint fl...

Seulgi Kim, Mohit Prabhushankar, Ghassan AlRegib 4/17/2026 arxiv

Vision Language models (VLMs) have demonstrated strong performance across a wide range of benchmarks, yet they often suffer from modality dominance, where predictions rely disproportionately on a single modality. Prior approaches primarily address this issue by steering model's attention allocation,...

Ruiyang Wang, Hao-Lun Hsu, Jiwoo Kim, Miroslav Pajic 4/17/2026 arxiv

Coordinating multi-robot systems (MRS) to search in unknown environments is particularly challenging for tasks that require semantic reasoning beyond geometric exploration. Classical coordination strategies rely on frontier coverage or information gain and cannot incorporate high-level task intent, ...