Tootfinder

Yesterday, I learned that Martin Volk, Professor of Computational Linguistics at UZH, passed away on Monday, September 15, at the age of 64. What devastating news 😢
#nlproc #RIP

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
Hamed Mahdavi (Pennsylvania State University), Pouria Mahdavinia (Pennsylvania State University), Samira Malek (Pennsylvania State University), Pegah Mohammadipour (Pennsylvania State University), Alireza Hashemi (City University of New York), Majid Daliri (New York University), Alireza Farhadi (Amirkabir University of Technology), Amir Khasahmadi (Autodesk), Niloofar Mireshghallah (Carnegie Mellon …

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
State-of-the-art (SOTA) LLMs have progressed from struggling on proof-based Olympiad problems to solving most of the IMO 2025 problems, with leading systems reportedly handling 5 of 6 problems. Given this progress, we assess how well these models can grade proofs: detecting errors, judging their severity, and assigning fair scores beyond binary correctness. We study proof-analysis capabilities using a corpus of 90 Gemini 2.5 Pro-generated solutions that we grade on a 1-4 scale with detailed err…

NLAFormer: Transformers Learn Numerical Linear Algebra Operations
Zhantao Ma, Yihang Gao, Michael K. Ng
https://arxiv.org/abs/2508.19557 https://arxiv.org/…

NLAFormer: Transformers Learn Numerical Linear Algebra Operations
Transformers are effective and efficient at modeling complex relationships and learning patterns from structured data in many applications. The main aim of this paper is to propose and design NLAFormer, which is a transformer-based architecture for learning numerical linear algebra operations: pointwise computation, shifting, transposition, inner product, matrix multiplication, and matrix-vector multiplication. Using a linear algebra argument, we demonstrate that transformers can express such o…

VL-KnG: Visual Scene Understanding for Navigation Goal Identification using Spatiotemporal Knowledge Graphs
Mohamad Al Mdfaa, Svetlana Lukina, Timur Akhtyamov, Arthur Nigmatzyanov, Dmitrii Nalberskii, Sergey Zagoruyko, Gonzalo Ferrer
https://arxiv.org/abs/2510.01483

VL-KnG: Visual Scene Understanding for Navigation Goal Identification using Spatiotemporal Knowledge Graphs
Vision-language models (VLMs) have shown potential for robot navigation but encounter fundamental limitations: they lack persistent scene memory, offer limited spatial reasoning, and do not scale effectively with video duration for real-time application. We present VL-KnG, a Visual Scene Understanding system that tackles these challenges using spatiotemporal knowledge graph construction and computationally efficient query processing for navigation goal identification. Our approach processes vid…

Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation
Jaechul Roh, Zachary Novack, Yuefeng Peng, Niloofar Mireshghallah, Taylor Berg-Kirkpatrick, Amir Houmansadr
https://arxiv.org/abs/2507.17937

Bob's Confetti: Phonetic Memorization Attacks in Music and Video Generation
Lyrics-to-Song (LS2) generation models promise end-to-end music synthesis from text, yet their vulnerability to training data memorization remains underexplored. We introduce Adversarial PhoneTic Prompting (APT), a novel attack where lyrics are semantically altered while preserving their acoustic structure through homophonic substitutions (e.g., Eminem's famous "mom's spaghetti" $\rightarrow$ "Bob's confetti"). Despite these distortions, we uncover a powerful form of sub-lexical memorization: m…

Lasso Penalization for High-Dimensional Beta Regression Models: Computation, Analysis, and Inference
Niloofar Ramezani, Martin Slawski
https://arxiv.org/abs/2507.20079 https://

Lasso Penalization for High-Dimensional Beta Regression Models: Computation, Analysis, and Inference
Beta regression is commonly employed when the outcome variable is a proportion. Since its conception, the approach has been widely used in applications spanning various scientific fields. A series of extensions have been proposed over time, several of which address variable selection and penalized estimation, e.g., with an $\ell_1$-penalty (LASSO). However, a theoretical analysis of this popular approach in the context of Beta regression with high-dimensional predictors is lacking. In this pape…

Airborne acoustic emission enables sub-scanline keyhole porosity quantification and effective process characterization for metallic laser powder bed fusion
Haolin Liu, David Guirguis, Xuzhe Zeng, Logan Maurer, Vigknesh Rajan, Niloofar Sanaei, Chi-Ta Yang, Jack L. Beuth, Anthony D. Rollett, Levent Burak Kara
https://arxiv.org/abs/2508.13492…

Airborne acoustic emission enables sub-scanline keyhole porosity quantification and effective process characterization for metallic laser powder bed fusion
Keyhole-induced (KH) porosity, which arises from unstable vapor cavity dynamics under excessive laser energy input, remains a significant challenge in laser powder bed fusion (LPBF). This study presents an integrated experimental and data-driven framework using airborne acoustic emission (AE) to achieve high-resolution quantification of KH porosity. Experiments conducted on an LPBF system involved in situ acquisition of airborne AE and ex situ porosity imaging via X-ray computed tomography (XCT…