Marathi is one of the most widely used languages in the world. One might expect that the latest advances in NLP research in languages like English reach such a large community. However, NLP advancements in English didn't immediately reach Indian languages like Marathi. There were several reasons for this. They included diversity of scripts used, lack of (publicly available) resources like tokenization strategies, high quality datasets \& benchmarks, and evaluation metrics. In addition to this, the morphologically rich nature of Marathi, made NLP tasks challenging. Advances in Neural Network (NN) based models and tools since the early 2000s helped improve this situation and make NLP research more accessible. In the past 10 years, significant efforts were made to improve language resources for all 22 scheduled languages of India. This paper presents a broad overview of evolution of NLP research in Indic languages with a focus on Marathi and state-of-the-art resources and tools available to the research community. It also provides an overview of tools \& techniques associated with Marathi NLP tasks.

To that end, the college now encompasses multiple existing labs and centers, including the Computer Science and Artificial Intelligence Laboratory (CSAIL), and multiple academic units, including the Department of Electrical Engineering and Computer Science. At the same time, the college has embarked on a plan to hire 50 new faculty members, half of whom will have shared appointments in other departments across all five schools to create a true Institute-wide entity. Those faculty members--two-thirds of whom have already been hired--will conduct research at the boundaries of advanced computing and AI. "We want to do two things: ensure that MIT stays at the forefront of computer science, AI research, and education and infuse the forefront of computing into disciplines across MIT." The new faculty members have already begun helping the college respond to an undeniable reality facing many students: They've been overwhelmingly drawn to advanced computing tools, yet computer science classes are often too technical for nonmajors who want to apply those tools in other disciplines.

Unsupervised anomaly detection methods can identify surface defects in industrial images by leveraging only normal samples for training. Due to the risk of overfitting when learning from a single class, anomaly synthesis strategies are introduced to enhance detection capability by generating artificial anomalies. However, existing strategies heavily rely on anomalous textures from auxiliary datasets. Moreover, their limitations in the coverage and directionality of anomaly synthesis may result in a failure to capture useful information and lead to significant redundancy. To address these issues, we propose a novel Progressive Boundary-guided Anomaly Synthesis (PBAS) strategy, which can directionally synthesize crucial feature-level anomalies without auxiliary textures. It consists of three core components: Approximate Boundary Learning (ABL), Anomaly Feature Synthesis (AFS), and Refined Boundary Optimization (RBO). To make the distribution of normal samples more compact, ABL first learns an approximate decision boundary by center constraint, which improves the center initialization through feature alignment. AFS then directionally synthesizes anomalies with more flexible scales guided by the hypersphere distribution of normal features. Since the boundary is so loose that it may contain real anomalies, RBO refines the decision boundary through the binary classification of artificial anomalies and normal features. Experimental results show that our method achieves state-of-the-art performance and the fastest detection speed on three widely used industrial datasets, including MVTec AD, VisA, and MPDD. The code will be available at: https://github.com/cqylunlun/PBAS.

This study explores the use of LLM (Large language models) to analyze therapist remarks in a psychotherapeutic setting. The paper focuses on the application of BERTopic, a machine learning-based topic modeling tool, to the dialogue of two different groups of therapists--classical and modern--which makes it possible to identify and describe a set of topics that consistently emerge across these groups. The paper describes in detail the chosen algorithm for BERTopic, which included creating a vector space from a corpus of therapist remarks, reducing its dimensionality, clustering the space, and creating and optimizing topic representation. Along with the automatic topical modeling by the BERTopic, the research involved an expert assessment of the findings and manual topic structure optimization. The topic modeling results highlighted the most common and stable topics in therapists' speech, offering insights into how language patterns in therapy develop and remain stable across different therapeutic styles. This work contributes to the growing field of machine learning in psychotherapy by demonstrating the potential of automated methods to improve both the practice and training of therapists. The study highlights the value of topic modeling as a tool for gaining a deeper understanding of therapeutic dialogue and offers new opportunities for improving therapeutic effectiveness and clinical supervision.

Machine learning is an interdisciplinary field that studies how computers can learn and simulate human learning behaviour. By acquiring new knowledge, machine learning aims to reorganize existing knowledge structures to continuously improve its own performance. Machine learning was proposed in the mid-1950s, and over the next 30 years, related research in the field of machine learning continued to develop. Machine learning has interdisciplinary attributes and has been widely applied in the field of artificial intelligence. Zhang and Wang [2016] argue that the way to transform big data into more valuable knowledge is by applying machine learning techniques.

Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks on LLM reasoning are constrained by specific settings or lack of imperceptibility, limiting their feasibility and generalizability. To address these challenges, we propose the Stepwise rEasoning Error Disruption (SEED) attack, which subtly injects errors into prior reasoning steps to mislead the model into producing incorrect subsequent reasoning and final answers. Unlike previous methods, SEED is compatible with zero-shot and few-shot settings, maintains the natural reasoning flow, and ensures covert execution without modifying the instruction. Extensive experiments on four datasets across four different models demonstrate SEED's effectiveness, revealing the vulnerabilities of LLMs to disruptions in reasoning processes. These findings underscore the need for greater attention to the robustness of LLM reasoning to ensure safety in practical applications.

This study explores the effectiveness of using knowledge graphs generated by large language models to decompose high school-level physics questions into sub-questions. We introduce a pipeline aimed at enhancing model response quality for Question Answering tasks. By employing LLMs to construct knowledge graphs that capture the internal logic of the questions, these graphs then guide the generation of subquestions. We hypothesize that this method yields sub-questions that are more logically consistent with the original questions compared to traditional decomposition techniques. Our results show that sub-questions derived from knowledge graphs exhibit significantly improved fidelity to the original question's logic. This approach not only enhances the learning experience by providing clearer and more contextually appropriate sub-questions but also highlights the potential of LLMs to transform educational methodologies. The findings indicate a promising direction for applying AI to improve the quality and effectiveness of educational content.

Point cloud registration, a fundamental task in 3D vision, has achieved remarkable success with learning-based methods in outdoor environments. Unsupervised outdoor point cloud registration methods have recently emerged to circumvent the need for costly pose annotations. However, they fail to establish reliable optimization objectives for unsupervised training, either relying on overly strong geometric assumptions, or suffering from poor-quality pseudo-labels due to inadequate integration of low-level geometric and high-level contextual information. We have observed that in the feature space, latent new inlier correspondences tend to cluster around respective positive anchors that summarize features of existing inliers. Motivated by this observation, we propose a novel unsupervised registration method termed INTEGER to incorporate high-level contextual information for reliable pseudo-label mining. Specifically, we propose the Feature-Geometry Coherence Mining module to dynamically adapt the teacher for each mini-batch of data during training and discover reliable pseudo-labels by considering both high-level feature representations and low-level geometric cues. Furthermore, we propose Anchor-Based Contrastive Learning to facilitate contrastive learning with anchors for a robust feature space. Lastly, we introduce a Mixed-Density Student to learn density-invariant features, addressing challenges related to density variation and low overlap in the outdoor scenario. Extensive experiments on KITTI and nuScenes datasets demonstrate that our INTEGER achieves competitive performance in terms of accuracy and generalizability.

Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks like GSM8K or MATH are now being solved with high accuracy (e.g., OpenAI o1 achieves 94.8\% on MATH dataset), indicating their inadequacy for truly challenging these models. To bridge this gap, we propose a comprehensive and challenging benchmark specifically designed to assess LLMs' mathematical reasoning at the Olympiad level. Unlike existing Olympiad-related benchmarks, our dataset focuses exclusively on mathematics and comprises a vast collection of 4428 competition-level problems with rigorous human annotation. These problems are meticulously categorized into over 33 sub-domains and span more than 10 distinct difficulty levels, enabling a holistic assessment of model performance in Olympiad-mathematical reasoning. Furthermore, we conducted an in-depth analysis based on this benchmark. Our experimental results show that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems, with 60.54\% and 52.55\% accuracy, highlighting significant challenges in Olympiad-level mathematical reasoning.

We have witnessed superhuman intelligence thanks to the fast development of large language models and multimodal language models. As the application of such superhuman models becomes more and more popular, a critical question arises here: how can we ensure superhuman models are still safe, reliable and aligned well to human values? In this position paper, we discuss the concept of superalignment from the learning perspective to answer this question by outlining the learning paradigm shift from large-scale pretraining, supervised fine-tuning, to alignment training. We define superalignment as designing effective and efficient alignment algorithms to learn from noisy-labeled data (point-wise samples or pair-wise preference data) in a scalable way when the task becomes very complex for human experts to annotate and the model is stronger than human experts. We highlight some key research problems in superalignment, namely, weak-to-strong generalization, scalable oversight, and evaluation. We then present a conceptual framework for superalignment, which consists of three modules: an attacker which generates adversary queries trying to expose the weaknesses of a learner model; a learner which will refine itself by learning from scalable feedbacks generated by a critic model along with minimal human experts; and a critic which generates critics or explanations for a given query-response pair, with a target of improving the learner by criticizing. We discuss some important research problems in each component of this framework and highlight some interesting research ideas that are closely related to our proposed framework, for instance, self-alignment, self-play, self-refinement, and more. Last, we highlight some future research directions for superalignment, including identification of new emergent risks and multi-dimensional alignment.