Traffic accidents pose a significant societal challenge, with many fatalities being avoidable through timely emergency response. We introduce IMPACT (Integrated Multimodal Pipeline for Rapid Accident Causality Tracking), a scalable AI framework designed for autonomous, rapid traffic incident analysis using existing urban CCTV infrastructure. IMPACT combines a low-latency CPU-based vision module for real-time key-frame filtering (24 FPS) with the causal reasoning capabilities of MLLMs, reducing costly MLLM calls by over 92% compared to naive sparse sampling. We further present TRACE10K, a dataset featuring three-tier textual annotations that describe accident dynamics at the frame-sequence level.

Mental health monitoring faces challenges from fragmented data and opaque risk scores. We present BRI-MH, an in- terpretable multimodal framework combining behavioral sig- nals with cognitive features from large language models to produce a weekly Behavioral Risk Index. Unlike prior work with isolated or black-box scores, BRI-MH offers transpar- ent, actionable insights and links continuous monitoring to adaptive feedback and therapeutic support, bridging digital phenotyping and clinical care.

Bias in Large Language Models (LLMs) is increasingly addressed through fairness-oriented techniques. However, in some cases, these approaches may inadvertently remove genuine cultural differences between groups, leading to “over-normalization” or models losing important socio-cultural distinctions. In this work, we introduce OverNormEval, a benchmark designed to detect when an LLM exhibits such over-normalization. We further explore the use of Direct Preference Optimization (DPO) to mitigate over-normalization.

Navya Gupta, Rishitej Reddy Vyalla, Avinash Anand, Chhavi Kirtani, Erik Cambria, Zhengchen Zhang, Zhengkui Wang, Timothy Liu, Aik Beng Ng, Simon See, Rajiv Ratn Shah. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large language models (LLMs) generate fluent, context-rich text but suffer from hallucinations and limited interpretability. We introduce SenticNet 9, a neurosymbolic framework that automates commonsense reasoning while preserving transparency. It leverages conceptual primitive discovery (CPD) to learn foundational concepts and a time shift mechanism (TSM) to iteratively refine them through temporal feedback. This combination yields a scalable, cognitively inspired architecture that merges symbolic interpretability with LLM generalization. Experiments show SenticNet 9 outperforming embeddings, transformers, and state-of-the-art LLMs across tasks, delivering higher accuracy without sacrificing explainability.

Large Language Models (LLMs) excel in linguistic tasks but struggle with mathematical reasoning, particularly in non- English languages like Hindi. This research aims to en- hance the mathematical reasoning skills of smaller, resource- efficient open-source LLMs in both Hindi and English. We evaluate models like OpenHathi 7B, LLaMA-2 7B, Wizard- Math 7B, Mistral 7B, LLeMMa 7B, MAmmoTH 7B, Gemini Pro, and GPT-4 using zero-shot, few-shot chain-of-thought (CoT) methods, and supervised fine-tuning. Our approach in- corporates curriculum learning, progressively training mod- els on increasingly difficult problems, a novel Decompo- sition Strategy to simplify complex arithmetic operations, and a Structured Solution Design that divides solutions into phases. Our experiments result in notable performance en- hancements. WizardMath 7B exceeds Gemini’s accuracy on English datasets by +6% and matches Gemini’s performance on Hindi datasets. Adopting a bilingual approach that com- bines English and Hindi samples achieves results comparable to individual language models, demonstrating the capability to learn mathematical reasoning in both languages. This re- search highlights the potential for improving mathematical reasoning in open-source LLMs.

The cosmic microwave background (CMB) experiments have reached an era of unprecedented precision and complexity. Aiming to detect the primordial B-mode polarization signal, these experiments will soon be equipped with $10^{4}$ to $10^{5}$ detectors. Consequently, future CMB missions will face the substantial challenge of efficiently processing vast amounts of raw data to produce the initial scientific outputs - the sky maps - within a reasonable time frame and with available computational resources. To address this, we introduce BrahMap, a new map-making framework that will be scalable across both CPU and GPU platforms. Implemented in C++ with a user-friendly Python interface for handling sparse linear systems, BrahMap employs advanced numerical analysis and high-performance computing techniques to maximize the use of super-computing infrastructure. This work features an overview of the BrahMap’s capabilities and preliminary performance scaling results, with application to a generic CMB polarization experiment.

Understanding student engagement in online education is crucial for optimizing learning outcomes. This paper introduces ECLIPSE dataset (Extended Classroom Learning Insights via Prolonged Student Engagement), comprising 10,110 annotated images from a 55-minutes , 30-minutes and 20-minutes online lecture. Annotations include four affective states: engagement, boredom, confusion, and frustration. ECLIPSE enables the investigation of learner attention dynamics over extended periods, overcoming the limitations of short-duration datasets. We establish benchmarks for ECLIPSE using models such as EfficientNet, Vision Transformer, Residual Attention Network, and GLAMOR-Net. We propose NeuralGaze, a novel framework integrating Neural Cellular Automata (NCA) with self-attention mechanisms, demonstrating superior accuracy in engagement level assessment compared to basic single-frame models. Furthermore, we introduce CG-SwT, a content-guided Swin Transformer model, which significantly outperforms the baseline ViT model on the ECLIPSE dataset (with F1-score improvements of 21.12%, 12.5%, 16.77%, and 15.41% for engagement, boredom, frustration, and confusion respectively). Our methods surpass existing single-frame engagement prediction baselines for both EngageNet and DAiSEE datasets by significant margins (7.4% and 6.2%, respectively). The code and dataset will be made publicly available.

The transition to online examinations and assignments raises significant concerns about academic integrity. Traditional plagiarism detection systems often struggle to identify instances of intelligent cheating, particularly when students utilize advanced generative AI tools to craft their responses. This study proposes a keystroke dynamics-based method to differentiate between bona fide and assisted writing within academic contexts. To facilitate this, a dataset was developed to capture the keystroke patterns of individuals engaged in writing tasks, both with and without the assistance of generative AI. The detector, trained using a modified TypeNet architecture, achieved accuracies ranging from 74.98% to 85.72% in condition-specific scenarios and 52.24% to 80.54% in condition-agnostic scenarios. The findings highlight significant differences in keystroke dynamics between genuine and assisted writing. The outcomes of this study enhance our understanding of how users interact with generative AI and have implications for improving the reliability of digital educational platforms.

Large ground-truth datasets and recent advances in deep learning techniques have been useful for layout detection. However, because of the restricted layout diversity of these datasets, training on them requires a sizable number of annotated instances, which is both expensive and time-consuming. As a result, differences between the source and target domains may significantly impact how well these models function. To solve this problem, domain adaptation approaches have been developed that use a small quantity of labeled data to adjust the model to the target domain. In this research, we introduced a synthetic document dataset called RanLayNet, enriched with automatically assigned labels denoting spatial positions, ranges, and types of layout elements. The primary aim of this endeavor is to develop a versatile dataset capable of training models with robustness and adaptability to diverse document formats. Through empirical experimentation, we demonstrate that a deep layout identification model trained on our dataset exhibits enhanced performance compared to a model trained solely on actual documents. Moreover, we conduct a comparative analysis by fine-tuning inference models using both PubLayNet and IIIT-AR-13K datasets on the Doclaynet dataset. Our findings emphasize that models enriched with our dataset are optimal for tasks such as achieving 0.398 and 0.588 mAP95 score in the scientific document domain for the TABLE class.