Tootfinder

Your left and right brain hear language differently − a neuroscientist explains how https://theconversation.com/your-left-and-right-brain-hear-language-differently-a-neuroscientist-explains-how-257436

Your left and right brain hear language differently − a neuroscientist explains how
Left and right brains hear speech differently, yet how this divide forms was unclear − until mouse studies showed each hemisphere runs on its own developmental clock.

Next stop on our NLP timeline (as part of the #ISE2025 lecture) was Terry Winograd's SHRDLU, an early natural language understanding system developed in 1968-70 that could manipulate blocks in a virtual world.
Winograd, T. Procedures as a Representation for Data in a Computer Program for Understanding Natural Language. MIT AI Technical Report 235.

Positive Varieties of Lattice Languages
Yusuke Inoue, Yuji Komatsu
https://arxiv.org/abs/2506.05824 https://arxiv.org/pdf/2506.05824

Positive Varieties of Lattice Languages
While a language assigns a value of either `yes' or `no' to each word, a lattice language assigns an element of a given lattice to each word. An advantage of lattice languages is that joins and meets of languages can be defined as generalizations of unions and intersections. This fact also allows for the definition of positive varieties -- classes closed under joins, meets, quotients, and inverse homomorphisms -- of lattice languages. In this paper, we extend Pin's positive variety theorem, pro…

Corrector Sampling in Language Models
Itai Gat, Neta Shaul, Uriel Singer, Yaron Lipman
https://arxiv.org/abs/2506.06215 https://arxiv…

Corrector Sampling in Language Models
Autoregressive language models accumulate errors due to their fixed, irrevocable left-to-right token generation. To address this, we propose a new sampling method called Resample-Previous-Tokens (RPT). RPT mitigates error accumulation by iteratively revisiting and potentially replacing tokens in a window of previously generated text. This method can be integrated into existing autoregressive models, preserving their next-token-prediction quality and speed. Fine-tuning a pretrained 8B parameter …

ExAct: A Video-Language Benchmark for Expert Action Analysis
Han Yi, Yulu Pan, Feihong He, Xinyu Liu, Benjamin Zhang, Oluwatumininu Oguntola, Gedas Bertasius
https://arxiv.org/abs/2506.06277

ExAct: A Video-Language Benchmark for Expert Action Analysis
We present ExAct, a new video-language benchmark for expert-level understanding of skilled physical human activities. Our new benchmark contains 3521 expert-curated video question-answer pairs spanning 11 physical activities in 6 domains: Sports, Bike Repair, Cooking, Health, Music, and Dance. ExAct requires the correct answer to be selected from five carefully designed candidate options, thus necessitating a nuanced, fine-grained, expert-level understanding of physical human skills. Evaluating…

Building on the 90s, statistical n-gram language models, trained on vast text collections, became the backbone of NLP research. They fueled advancements in nearly all NLP techniques of the era, laying the groundwork for today's AI.
F. Jelinek (1997), Statistical Methods for Speech Recognition, MIT Press, Cambridge, MA
#NLP

Challenging Vision-Language Models with Surgical Data: A New Dataset and Broad Benchmarking Study
Leon Mayer, Tim R\"adsch, Dominik Michael, Lucas Luttner, Amine Yamlahi, Evangelia Christodoulou, Patrick Godau, Marcel Knopp, Annika Reinke, Fiona Kolbinger, Lena Maier-Hein
https://arxiv.org/abs/2506.06232

Challenging Vision-Language Models with Surgical Data: A New Dataset and Broad Benchmarking Study
While traditional computer vision models have historically struggled to generalize to endoscopic domains, the emergence of foundation models has shown promising cross-domain performance. In this work, we present the first large-scale study assessing the capabilities of Vision Language Models (VLMs) for endoscopic tasks with a specific focus on laparoscopic surgery. Using a diverse set of state-of-the-art models, multiple surgical datasets, and extensive human reference annotations, we address t…

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
Rihui Jin, Zheyu Xin, Xing Xie, Zuoyi Li, Guilin Qi, Yongrui Chen, Xinbang Dai, Tongtong Wu, Gholamreza Haffari
https://arxiv.org/abs/2506.06137

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
Table reasoning (TR) requires structured reasoning over semi-structured tabular data and remains challenging, particularly for small language models (SLMs, e.g., LLaMA-8B) due to their limited capacity compared to large LMs (LLMs, e.g., GPT-4o). To narrow this gap, we explore program-based TR (P-TR), which circumvents key limitations of text-based TR (T-TR), notably in numerical reasoning, by generating executable programs. However, applying P-TR to SLMs introduces two challenges: (i) vulnerabi…

Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu
https://arxiv.org/abs/2506.06242

Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations in visual form, a basic ability of human reasoning. To address this challenge, we introduce the Visual Graph Arena (VGA), a dataset featuring six graph-based tasks designed to evaluate and improve AI systems' capacity for visual abstraction. VGA uses diverse …

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving
Christian Fruhwirth-Reisinger, Du\v{s}an Mali\'c, Wei Lin, David Schinagl, Samuel Schulter, Horst Possegger
https://arxiv.org/abs/2506.06218

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving
We introduce STSBench, a scenario-based framework to benchmark the holistic understanding of vision-language models (VLMs) for autonomous driving. The framework automatically mines pre-defined traffic scenarios from any dataset using ground-truth annotations, provides an intuitive user interface for efficient human verification, and generates multiple-choice questions for model evaluation. Applied to the NuScenes dataset, we present STSnu, the first benchmark that evaluates the spatio-temporal …