Rohit Agarwal

Jui-Hui Chung, Ziyang Cai, Zihao Li et al.

We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement. A blueprint is a dependency graph of definitions and lemmas that builds up to the main theorem. First, Goedel-Architect generates a blueprint of formally stated definitions and lemmas, along with declared dependencies. This blueprint is optionally guided by a natural language proof. Then, a tool-equipped Lean prover component closes each open lemma node in parallel using relevant dependencies. Failed lemmas in turn drive refinement of the global blueprint. This strategy contrasts with other mainstream approaches which use recursive lemma decomposition, and can inefficiently loop on dead-end strategies. Using the open-weight DeepSeek-V4-Flash (284B-A13B) as the backbone, Goedel-Architect attains 99.2% pass@1 on MiniF2F-test and 75.6% pass@1 on PutnamBench. With an optional natural-language proof seeding the initial blueprint on the harder problems, we additionally close the remaining two MiniF2F-test problems (reaching 100%), lift PutnamBench to 88.8% (597/672), and solve 4/6 on IMO 2025, 11/12 on Putnam 2025, and 3/6 on USAMO 2026. This represents state-of-the-art performance for an open-source pipeline at a price point up to 500x less than comparable open-source pipelines.

Rohit Agarwal, Deepak Gupta, Alexander Horsch et al.

Many real-world applications based on online learning produce streaming data that is haphazard in nature, i.e., contains missing features, features becoming obsolete in time, the appearance of new features at later points in time and a lack of clarity on the total number of input features. These challenges make it hard to build a learnable system for such applications, and almost no work exists in deep learning that addresses this issue. In this paper, we present Aux-Drop, an auxiliary dropout regularization strategy for online learning that handles the haphazard input features in an effective manner. Aux-Drop adapts the conventional dropout regularization scheme for the haphazard input feature space ensuring that the final output is minimally impacted by the chaotic appearance of such features. It helps to prevent the co-adaptation of especially the auxiliary and base features, as well as reduces the strong dependence of the output on any of the auxiliary inputs of the model. This helps in better learning for scenarios where certain features disappear in time or when new features are to be modelled. The efficacy of Aux-Drop has been demonstrated through extensive numerical experiments on SOTA benchmarking datasets that include Italy Power Demand, HIGGS, SUSY and multiple UCI datasets. The code is available at https://github.com/Rohit102497/Aux-Drop.

Rohit Agarwal, Aman Sinha, Ayan Vishwakarma et al.

Modeling irregularly-sampled time series (ISTS) is challenging because of missing values. Most existing methods focus on handling ISTS by converting irregularly sampled data into regularly sampled data via imputation. These models assume an underlying missing mechanism, which may lead to unwanted bias and sub-optimal performance. We present SLAN (Switch LSTM Aggregate Network), which utilizes a group of LSTMs to model ISTS without imputation, eliminating the assumption of any underlying process. It dynamically adapts its architecture on the fly based on the measured sensors using switches. SLAN exploits the irregularity information to explicitly capture each sensor's local summary and maintains a global summary state throughout the observational period. We demonstrate the efficacy of SLAN on two public datasets, namely, MIMIC-III, and Physionet 2012.

Alloy Das, Rohit Agarwal, Rituparna Singh et al.

The infectious disease caused by novel corona virus (2019-nCoV) has been widely spreading since last year and has shaken the entire world. It has caused an unprecedented effect on daily life, global economy and public health. Hence this disease detection has life-saving importance for both patients as well as doctors. Due to limited test kits, it is also a daunting task to test every patient with severe respiratory problems using conventional techniques (RT-PCR). Thus implementing an automatic diagnosis system is urgently required to overcome the scarcity problem of Covid-19 test kits at hospital, health care systems. The diagnostic approach is mainly classified into two categories-laboratory based and Chest radiography approach. In this paper, a novel approach for computerized corona virus (2019-nCoV) detection from lung x-ray images is presented. Here, we propose models using deep learning to show the effectiveness of diagnostic systems. In the experimental result, we evaluate proposed models on publicly available data-set which exhibit satisfactory performance and promising results compared with other previous existing methods.

Rohit Agarwal, Arijit Das, Alexander Horsch et al.

The domain of online learning has experienced multifaceted expansion owing to its prevalence in real-life applications. Nonetheless, this progression operates under the assumption that the input feature space of the streaming data remains constant. In this survey paper, we address the topic of online learning in the context of haphazard inputs, explicitly foregoing such an assumption. We discuss, classify, evaluate, and compare the methodologies that are adept at modeling haphazard inputs, additionally providing the corresponding code implementations and their carbon footprint. Moreover, we classify the datasets related to the field of haphazard inputs and introduce evaluation metrics specifically designed for datasets exhibiting imbalance. The code of each methodology can be found at https://github.com/Rohit102497/HaphazardInputsReview

Xingyu Dang, Rohit Agarwal, Rodrigo Porto et al.

In the past year, custom and unreleased math reasoning models reached gold medal performance on the International Mathematical Olympiad (IMO). Similar performance was then reported using large-scale inference on publicly available models but at prohibitive costs (e.g., 3000 USD per problem). In this work, we present an inference pipeline that attains best-in-class performance on IMO-style math problems at an average inference cost orders of magnitude below competing methods while using only general-purpose off-the-shelf models. Our method relies on insights about grader failure in solver-grader pipelines, which we call the Cognitive Well (iterative refinement converging to a wrong solution that the solver as well as the pipeline's internal grader consider to be basically correct). Our pipeline addresses these failure modes through conjecture extraction, wherein candidate lemmas are isolated from generated solutions and independently verified alongside their negations in a fresh environment (context detachment). On IMO-ProofBench Advanced (PB-Adv), our pipeline achieves 67.1 percent performance using Gemini 3.0 Pro with an average cost per question of approximately 31 USD. At the time of evaluation, this represented the state-of-the-art on PB-Adv among both public and unreleased models, and more than doubles the success rate of the next best publicly accessible pipeline, all at a fraction of the cost.

Rohit Agarwal, Gyanendra Das, Saksham Aggarwal et al.

Image retrieval has garnered growing interest in recent times. The current approaches are either supervised or self-supervised. These methods do not exploit the benefits of hybrid learning using both supervision and self-supervision. We present a novel Master Assistant Buddy Network (MABNet) for image retrieval which incorporates both learning mechanisms. MABNet consists of master and assistant blocks, both learning independently through supervision and collectively via self-supervision. The master guides the assistant by providing its knowledge base as a reference for self-supervision and the assistant reports its knowledge back to the master by weight transfer. We perform extensive experiments on public datasets with and without post-processing.

Himanshu Buckchash, Momojit Biswas, Rohit Agarwal et al.

Handling haphazard streaming data, such as data from edge devices, presents a challenging problem. Over time, the incoming data becomes inconsistent, with missing, faulty, or new inputs reappearing. Therefore, it requires models that are reliable. Recent methods to solve this problem depend on a hedging-based solution and require specialized elements like auxiliary dropouts, forked architectures, and intricate network design. We observed that hedging can be reduced to a special case of weighted residual connection; this motivated us to approximate it with plain self-attention. In this work, we propose HapNet, a simple baseline that is scalable, does not require online backpropagation, and is adaptable to varying input types. All present methods are restricted to scaling with a fixed window; however, we introduce a more complex problem of scaling with a variable window where the data becomes positionally uncorrelated, and cannot be addressed by present methods. We demonstrate that a variant of the proposed approach can work even for this complex scenario. We extensively evaluated the proposed approach on five benchmarks and found competitive performance.

Rohit Agarwal, Aryan Dessai, Arif Ahmed Sekh et al.

The field of varying feature space in online learning settings, also known as haphazard inputs, is very prominent nowadays due to its applicability in various fields. However, the current solutions to haphazard inputs are model-dependent and cannot benefit from the existing advanced deep-learning methods, which necessitate inputs of fixed dimensions. Therefore, we propose to transform the varying feature space in an online learning setting to a fixed-dimension image representation on the fly. This simple yet novel approach is model-agnostic, allowing any vision-based models to be applicable for haphazard inputs, as demonstrated using ResNet and ViT. The image representation handles the inconsistent input data seamlessly, making our proposed approach scalable and robust. We show the efficacy of our method on four publicly available datasets. The code is available at https://github.com/Rohit102497/HaphazardInputsAsImages.

Rohit Agarwal, Joshua Lin, Mark Braverman et al.

We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from violation against the probability of detection and the severity of punishment. We argue that the same logic arises naturally in agentic AI pipelines. A solver may benefit from producing a persuasive but incorrect answer, hiding uncertainty, or exploiting spurious shortcuts, while an auditor or verifier must decide whether costly monitoring is worthwhile. Alignment is therefore a fixed-point problem: stronger penalties may deter solver misbehavior, but they can also reduce the auditor's incentive to inspect, since auditing then mainly incurs cost on a population that appears increasingly aligned. This perspective also changes what should count as a post-training signal. Standard feedback often attaches reward to the final answer alone, but a solver-auditor pipeline exposes the full correction event: whether the solver erred, whether the auditor inspected, whether the error was caught, and whether oversight incentives remained active. We formalize this interaction in a two-agent model in which a principal chooses rewards over joint correction outcomes, inducing both solver behavior and auditor monitoring. Reward design is therefore a bilevel optimization problem: rewards are judged not by their immediate semantic meaning, but by the behavioral equilibrium they induce. We propose a bandit-based outer-loop procedure for searching over reward profiles using noisy interaction feedback. Experiments on an LLM coding pipeline show that adaptive reward profiles can maintain useful oversight pressure and improve principal-aligned outcomes relative to static hand-designed rewards, including a substantial reduction in hallucinated incorrect attempts.

Qiaojun Yu, Ce Hao, Xibin Yuan et al.

Manipulating articulated objects with robotic arms is challenging due to the complex kinematic structure, which requires precise part segmentation for efficient manipulation. In this work, we introduce a novel superpoint-based perception method designed to improve part segmentation in 3D point clouds of articulated objects. We propose a learnable, part-aware superpoint generation technique that efficiently groups points based on their geometric and semantic similarities, resulting in clearer part boundaries. Furthermore, by leveraging the segmentation capabilities of the 2D foundation model SAM, we identify the centers of pixel regions and select corresponding superpoints as candidate query points. Integrating a query-based transformer decoder further enhances our method's ability to achieve precise part segmentation. Experimental results on the GAPartNet dataset show that our method outperforms existing state-of-the-art approaches in cross-category part segmentation, achieving AP50 scores of 77.9% for seen categories (4.4% improvement) and $39.3\%$ for unseen categories (11.6% improvement), with superior results in 5 out of 9 part categories for seen objects and outperforming all previous methods across all part categories for unseen objects.

Rohit Agarwal, Karaka Prasanth Naidu, Alexander Horsch et al.

We study the online learning problem characterized by the varying input feature space of streaming data. Although LSTMs have been employed to effectively capture the temporal nature of streaming data, they cannot handle the dimension-varying streams in an online learning setting. Therefore, we propose a dynamic LSTM-based novel method, called packetLSTM, to model the dimension-varying streams. The packetLSTM's dynamic framework consists of an evolving packet of LSTMs, each dedicated to processing one input feature. Each LSTM retains the local information of its corresponding feature, while a shared common memory consolidates global information. This configuration facilitates continuous learning and mitigates the issue of forgetting, even when certain features are absent for extended time periods. The idea of utilizing one LSTM per feature coupled with a dimension-invariant operator for information aggregation enhances the dynamic nature of packetLSTM. This dynamic nature is evidenced by the model's ability to activate, deactivate, and add new LSTMs as required, thus seamlessly accommodating varying input dimensions. The packetLSTM achieves state-of-the-art results on five datasets, and its underlying principle is extended to other RNN types, like GRU and vanilla RNN.

Federica Gamba, Aman Sinha, Timothee Mickus et al.

We introduce the CAP (Confabulations from ACL Publications) dataset, a multilingual resource for studying hallucinations in large language models (LLMs) within scientific text generation. CAP focuses on the scientific domain, where hallucinations can distort factual knowledge, as they frequently do. In this domain, however, the presence of specialized terminology, statistical reasoning, and context-dependent interpretations further exacerbates these distortions, particularly given LLMs' lack of true comprehension, limited contextual understanding, and bias toward surface-level generalization. CAP operates in a cross-lingual setting covering five high-resource languages (English, French, Hindi, Italian, and Spanish) and four low-resource languages (Bengali, Gujarati, Malayalam, and Telugu). The dataset comprises 900 curated scientific questions and over 7000 LLM-generated answers from 16 publicly available models, provided as question-answer pairs along with token sequences and corresponding logits. Each instance is annotated with a binary label indicating the presence of a scientific hallucination, denoted as a factuality error, and a fluency label, capturing issues in the linguistic quality or naturalness of the text. CAP is publicly released to facilitate advanced research on hallucination detection, multilingual evaluation of LLMs, and the development of more reliable scientific NLP systems.

Mrinmay Sen, Shruti Aparna, Rohit Agarwal et al.

Federated Learning (FL) is a learning mechanism that falls under the distributed training umbrella, which collaboratively trains a shared global model without disclosing the raw data from different clients. This paper presents an extensive survey on the impact of partial client participation in federated learning. While much of the existing research focuses on addressing issues such as generalization, robustness, and fairness caused by data heterogeneity under the assumption of full client participation, limited attention has been given to the practical and theoretical challenges arising from partial client participation, which is common in real-world scenarios. This survey provides an in-depth review of existing FL methods designed to cope with partial client participation. We offer a comprehensive analysis supported by theoretical insights and empirical findings, along with a structured categorization of these methods, highlighting their respective advantages and disadvantages.

Prithviraj Purushottam Naik, Rohit Agarwal

Multimodal search has revolutionized the fashion industry, providing a seamless and intuitive way for users to discover and explore fashion items. Based on their preferences, style, or specific attributes, users can search for products by combining text and image information. Text-to-image searches enable users to find visually similar items or describe products using natural language. This paper presents an innovative approach called ENCLIP, for enhancing the performance of the Contrastive Language-Image Pretraining (CLIP) model, specifically in Multimodal Search targeted towards the domain of fashion intelligence. This method focuses on addressing the challenges posed by limited data availability and low-quality images. This paper proposes an algorithm that involves training and ensembling multiple instances of the CLIP model, and leveraging clustering techniques to group similar images together. The experimental findings presented in this study provide evidence of the effectiveness of the methodology. This approach unlocks the potential of CLIP in the domain of fashion intelligence, where data scarcity and image quality issues are prevalent. Overall, the ENCLIP method represents a valuable contribution to the field of fashion intelligence and provides a practical solution for optimizing the CLIP model in scenarios with limited data and low-quality images.

Deepanshu Pandey, Pradyumna Gupta, Sumit Bhattacharya et al.

Region proposal based methods like R-CNN and Faster R-CNN models have proven to be extremely successful in object detection and segmentation tasks. Recently, Transformers have also gained popularity in the domain of Computer Vision, and are being utilised to improve the performance of conventional models. In this paper, we present a relatively new transformer based approach to enhance the performance of the conventional convolutional feature extractor in the existing region proposal based methods. Our approach merges the convolutional feature maps with transformer-based token embeddings by applying a projection operation similar to self-attention in transformers. The results of our experiments show that transformer assisted feature extractor achieves a significant improvement in mIoU (mean Intersection over Union) scores compared to vanilla convolutional backbone.

Sirigireddy Dhanalaxmi, Rohit Agarwal, Aman Sinha

Social media such as Twitter is a hotspot of user-generated information. In this ongoing Covid-19 pandemic, there has been an abundance of data on social media which can be classified as informative and uninformative content. In this paper, we present our work to detect informative Covid-19 English tweets using RoBERTa model as a part of the W-NUT workshop 2020. We show the efficacy of our model on a public dataset with an F1-score of 0.89 on the validation dataset and 0.87 on the leaderboard.

Rohit Agarwal, Arif Ahmed Sekh, Krishna Agarwal et al.

Streaming classification methods assume the number of input features is fixed and always received. But in many real-world scenarios demand is some input features are reliable while others are unreliable or inconsistent. In this paper, we propose a novel deep learning-based model called Auxiliary Network (Aux-Net), which is scalable and agile. It employs a weighted ensemble of classifiers to give a final outcome. The Aux-Net model is based on the hedging algorithm and online gradient descent. It employs a model of varying depth in an online setting using single pass learning. Aux-Net is a foundational work towards scalable neural network model for a dynamic complex environment requiring ad hoc or inconsistent input data. The efficacy of Aux-Net is shown on public dataset.

Arif Ahmed Sekh, Ida S. Opstad, Rohit Agarwal et al.

In many real-world scientific problems, generating ground truth (GT) for supervised learning is almost impossible. The causes include limitations imposed by scientific instrument, physical phenomenon itself, or the complexity of modeling. Performing artificial intelligence (AI) tasks such as segmentation, tracking, and analytics of small sub-cellular structures such as mitochondria in microscopy videos of living cells is a prime example. The 3D blurring function of microscope, digital resolution from pixel size, optical resolution due to the character of light, noise characteristics, and complex 3D deformable shapes of mitochondria, all contribute to making this problem GT hard. Manual segmentation of 100s of mitochondria across 1000s of frames and then across many such videos is not only herculean but also physically inaccurate because of the instrument and phenomena imposed limitations. Unsupervised learning produces less than optimal results and accuracy is important if inferences relevant to therapy are to be derived. In order to solve this unsurmountable problem, we bring modeling and deep learning to a nexus. We show that accurate physics based modeling of microscopy data including all its limitations can be the solution for generating simulated training datasets for supervised learning. We show here that our simulation-supervised segmentation approach is a great enabler for studying mitochondrial states and behaviour in heart muscle cells, where mitochondria have a significant role to play in the health of the cells. We report unprecedented mean IoU score of 91% for binary segmentation (19% better than the best performing unsupervised approach) of mitochondria in actual microscopy videos of living cells. We further demonstrate the possibility of performing multi-class classification, tracking, and morphology associated analytics at the scale of individual mitochondrion.