Rohit Sinha

Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti et al.

Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains less understood. We introduce "Mind's Eye", a multiple-choice benchmark of eight visuo-cognitive tasks inspired by classic human intelligence tests and organized under a novel "A-R-T" taxonomy: Abstraction, Relation, and Transformation. The tasks probe core processes of fluid intelligence such as pattern induction, analogical relation mapping, and mental transformation. We evaluate a diverse suite of closed-source and open-source MLLMs and compare their performance with human participants. Humans achieve 80% accuracy, while top performing MLLMs remain below 50%. Error analysis reveals failures in: (i) visual attention allocation, (ii) internal perceptual manipulation, and (iii) weak abstraction of underlying visual concepts. Our findings suggest that current MLLMs exhibit limited visuospatial reasoning capabilities, when compared with human participants, highlighting the need for more cognitively grounded evaluation frameworks.

Rohit Sinha, Kunal Tilaganji, Tanuja Ganu et al.

Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations. Learned critics need extensive labeled data and show inconsistent performance across different tasks. Meanwhile, existing training-free methods simply average scores from different sources, missing a key insight: when these scores disagree, that disagreement itself carries important information about whether a reasoning step is truly valid or not. We propose a training-free verification approach that treats step-wise verification as a coordination problem among specialized judges. We formalize these judges' interaction as a Nash equilibrium game where agreement signals valid steps while disagreement reveals instability. Our method computes equilibrium scores through a closed-form solution, enabling both disagreement-aware filtering and stability-conscious ranking of reasoning steps. Evaluated across six benchmarks, our approach achieves consistent improvements of 2.4% to 5.2% over baseline models and shows competitive performance against learned critics, demonstrating that cross-modal agreement (not just average confidence) provides robust verification signals without task-specific adaptation.

Rohan Kumar Gupta, Rohit Sinha

The primary method for identifying mental disorders automatically has traditionally involved using binary classifiers. These classifiers are trained using behavioral data obtained from an interview setup. In this training process, data from individuals with the specific disorder under consideration are categorized as the positive class, while data from all other participants constitute the negative class. In practice, it is widely recognized that certain mental disorders share similar symptoms, causing the collected behavioral data to encompass a variety of attributes associated with multiple disorders. Consequently, attributes linked to the targeted mental disorder might also be present within the negative class. This data impurity may lead to sub-optimal training of the classifier for a mental disorder of interest. In this study, we investigate this hypothesis in the context of major depressive disorder (MDD) and post-traumatic stress disorder detection (PTSD). The results show that upon removal of such data impurity, MDD and PTSD detection performances are significantly improved.

Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha et al.

Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchmarks. However, we observe that accuracy gains often come at the cost of reasoning quality: generated Chain-of-Thought (CoT) traces are frequently inconsistent with the final answer and poorly grounded in the visual evidence. We systematically study this phenomenon across seven challenging real-world spatial reasoning benchmarks and find that it affects contemporary MRMs such as ViGoRL-Spatial, TreeVGR as well as our own models trained with standard Group Relative Policy Optimization (GRPO). We characterize CoT reasoning quality along two complementary axes: "logical consistency" (does the CoT entail the final answer?) and "visual grounding" (does each reasoning step accurately describe objects, attributes, and spatial relationships in the image?). To address this, we propose Faithful GRPO (FGRPO), a variant of GRPO that enforces consistency and grounding as constraints via Lagrangian dual ascent. FGRPO incorporates batch-level consistency and grounding constraints into the advantage computation within a group, adaptively adjusting the relative importance of constraints during optimization. We evaluate FGRPO on Qwen2.5-VL-7B and 3B backbones across seven spatial datasets. Our results show that FGRPO substantially improves reasoning quality, reducing the inconsistency rate from 24.5% to 1.7% and improving visual grounding scores by +13%. It also improves final answer accuracy over simple GRPO, demonstrating that faithful reasoning enables better answers.

Rohan Kumar Gupta, Rohit Sinha

Self-supervised learning (SSL) has been investigated to generate task-agnostic representations across various domains. However, such investigation has not been conducted for detecting multiple mental disorders. The rationale behind the existence of a task-agnostic representation lies in the overlapping symptoms among multiple mental disorders. Consequently, the behavioural data collected for mental health assessment may carry a mixed bag of attributes related to multiple disorders. Motivated by that, in this study, we explore a task-agnostic representation derived through SSL in the context of detecting major depressive disorder (MDD) and post-traumatic stress disorder (PTSD) using audio and video data collected during interactive sessions. This study employs SSL models trained by predicting multiple fixed targets or masked frames. We propose a list of fixed targets to make the generated representation more efficient for detecting MDD and PTSD. Furthermore, we modify the hyper-parameters of the SSL encoder predicting fixed targets to generate global representations that capture varying temporal contexts. Both these innovations are noted to yield improved detection performances for considered mental disorders and exhibit task-agnostic traits. In the context of the SSL model predicting masked frames, the generated global representations are also noted to exhibit task-agnostic traits.

Protima Nomo Sudro, Rohan Kumar Das, Rohit Sinha et al.

The automatic recognition of pathological speech, particularly from children with any articulatory impairment, is a challenging task due to various reasons. The lack of available domain specific data is one such obstacle that hinders its usage for different speech-based applications targeting pathological speakers. In line with the challenge, in this work, we investigate a few data augmentation techniques to simulate training data for improving the children speech recognition considering the case of cleft lip and palate (CLP) speech. The augmentation techniques explored in this study, include vocal tract length perturbation (VTLP), reverberation, speaking rate, pitch modification, and speech feature modification using cycle consistent adversarial networks (CycleGAN). Our study finds that the data augmentation methods significantly improve the CLP speech recognition performance, which is more evident when we used feature modification using CycleGAN, VTLP and reverberation based methods. More specifically, the results from this study show that our systems produce an improved phone error rate compared to the systems without data augmentation.

Protima Nomo Sudro, Rohit Sinha, S. R. Mahadeva Prasanna

The cleft lip and palate (CLP) speech intelligibility is distorted due to the deformation in their articulatory system. For addressing the same, a few previous works perform phoneme specific modification in CLP speech. In CLP speech, both the articulation error and the nasalization distorts the intelligibility of a word. Consequently, modification of a specific phoneme may not always yield in enhanced entire word-level intelligibility. For such cases, it is important to identify and isolate the phoneme specific error based on the knowledge of acoustic events. Accordingly, the phoneme specific error modification algorithms can be exploited for transforming the specified errors and enhance the word-level intelligibility. Motivated by that, in this work, we combine some of salient phoneme specific enhancement approaches and demonstrate their effectiveness in improving the word-level intelligibility of CLP speech. The enhanced speech samples are evaluated using subjective and objective evaluation metrics.

Shubham Sahai, Rohit Sinha, Pramod Subramanyan

Many important cryptographic primitives offer probabilistic guarantees of security that can be specified as quantitative hyperproperties; these are specifications that stipulate the existence of a certain number of traces in the system satisfying certain constraints. Verification of such hyperproperties is extremely challenging because they involve simultaneous reasoning about an unbounded number of different traces. In this paper, we introduce a technique for verification of quantitative hyperproperties based on the notion of trace enumeration relations. These relations allow us to reduce the problem of trace-counting into one of model-counting of formulas in first-order logic. We also introduce a set of inference rules for machine-checked reasoning about the number of satisfying solutions to first-order formulas (aka model counting). Putting these two components together enables semi-automated verification of quantitative hyperproperties on infinite state systems. We use our methodology to prove confidentiality of access patterns in Path ORAMs of unbounded size, soundness of a simple interactive zero-knowledge proof protocol as well as other applications of quantitative hyperproperties studied in past work.

Kunal Dhawan, Ganji Sreeram, Kumar Priyadarshi et al.

End-to-end (E2E) systems are fast replacing the conventional systems in the domain of automatic speech recognition. As the target labels are learned directly from speech data, the E2E systems need a bigger corpus for effective training. In the context of code-switching task, the E2E systems face two challenges: (i) the expansion of the target set due to multiple languages involved, and (ii) the lack of availability of sufficiently large domain-specific corpus. Towards addressing those challenges, we propose an approach for reducing the number of target labels for reliable training of the E2E systems on limited data. The efficacy of the proposed approach has been demonstrated on two prominent architectures, namely CTC-based and attention-based E2E networks. The experimental validations are performed on a recently created Hindi-English code-switching corpus. For contrast purpose, the results for the full target set based E2E system and a hybrid DNN-HMM system are also reported.

Sreeram Ganji, Kunal Dhawan, Kumar Priyadarshi et al.

Language identification (LID) has relevance in many speech processing applications. For the automatic recognition of code-switching speech, the conventional approaches often employ an LID system for detecting the languages present within an utterance. In the existing works, the LID on code-switching speech involves modelling of the underlying languages separately. In this work, we propose a joint modelling based LID system for code-switching speech. To achieve the same, an attention-based end-to-end (E2E) network has been explored. For the development and evaluation of the proposed approach, a recently created Hindi-English code-switching corpus has been used. For the contrast purpose, an LID system employing the connectionist temporal classification-based E2E network is also developed. On comparing both the LID systems, the attention based approach is noted to result in better LID accuracy. The effective location of code-switching boundaries within the utterance by the proposed approach has been demonstrated by plotting the attention weights of E2E network.

Ganji Sreeram, Kunal Dhawan, Rohit Sinha

Code-switching refers to the usage of two languages within a sentence or discourse. It is a global phenomenon among multilingual communities and has emerged as an independent area of research. With the increasing demand for the code-switching automatic speech recognition (ASR) systems, the development of a code-switching speech corpus has become highly desirable. However, for training such systems, very limited code-switched resources are available as yet. In this work, we present our first efforts in building a code-switching ASR system in the Indian context. For that purpose, we have created a Hindi-English code-switching speech database. The database not only contains the speech utterances with code-switching properties but also covers the session and the speaker variations like pronunciation, accent, age, gender, etc. This database can be applied in several speech signal processing applications, such as code-switching ASR, language identification, language modeling, speech synthesis etc. This paper mainly presents an analysis of the statistics of the collected code-switching speech corpus. Later, the performance results for the ASR task have been reported for the created database.

Ganji Sreeram, Rohit Sinha

Lately, the problem of code-switching has gained a lot of attention and has emerged as an active area of research. In bilingual communities, the speakers commonly embed the words and phrases of a non-native language into the syntax of a native language in their day-to-day communications. The code-switching is a global phenomenon among multilingual communities, still very limited acoustic and linguistic resources are available as yet. For developing effective speech based applications, the ability of the existing language technologies to deal with the code-switched data can not be over emphasized. The code-switching is broadly classified into two modes: inter-sentential and intra-sentential code-switching. In this work, we have studied the intra-sentential problem in the context of code-switching language modeling task. The salient contributions of this paper includes: (i) the creation of Hindi-English code-switching text corpus by crawling a few blogging sites educating about the usage of the Internet (ii) the exploration of the parts-of-speech features towards more effective modeling of Hindi-English code-switched data by the monolingual language model (LM) trained on native (Hindi) language data, and (iii) the proposal of a novel textual factor referred to as the code-switch factor (CS-factor), which allows the LM to predict the code-switching instances. In the context of recognition of the code-switching data, the substantial reduction in the PPL is achieved with the use of POS factors and also the proposed CS-factor provides independent as well as additive gain in the PPL.

Nagendra Kumar, Rohit Sinha

In recent years, the creation of block-structured dictionary has attracted a lot of interest. Learning such dictionaries involve two step process: block formation and dictionary update. Both these steps are important in producing an effective dictionary. The existing works mostly assume that the block structure is known a priori while learning the dictionary. For finding the unknown block structure given a dictionary commonly sparse agglomerative clustering (SAC) is used. It groups atoms based on their consistency in sparse coding with respect to the unstructured dictionary. This paper explores two innovations towards improving the reconstruction as well as the classification ability achieved with the block-structured dictionary. First, we propose a novel block structuring approach that makes use of the correlation among dictionary atoms. Unlike the SAC approach, which groups diverse atoms, in the proposed approach the blocks are formed by grouping the top most correlated atoms in the dictionary. The proposed block clustering approach is noted to yield significant reductions in redundancy as well as provides a direct control on the block size when compared with the existing SAC-based block structuring. Later, motivated by works using supervised \emph{a priori} known block structure, we also explore the incorporation of class information in the proposed block formation approach to further enhance the classification ability of the block dictionary. For assessment of the reconstruction ability with proposed innovations is done on synthetic data while the classification ability has been evaluated in large variability speaker verification task.

Mrinal Haloi, Samarendra Dandapat, Rohit Sinha

In this work, we have presented a novel method for detection of retinal image features, the optic disc and the fovea, from colour fundus photographs of dilated eyes for Computer-aided Diagnosis(CAD) system. A saliency map based method was used to detect the optic disc followed by an unsupervised probabilistic Latent Semantic Analysis for detection validation. The validation concept is based on distinct vessels structures in the optic disc. By using the clinical information of standard location of the fovea with respect to the optic disc, the macula region is estimated. Accuracy of 100\% detection is achieved for the optic disc and the macula on MESSIDOR and DIARETDB1 and 98.8\% detection accuracy on STARE dataset.

Mrinal Haloi, Samarendra Dandapat, Rohit Sinha

In the context of Computer Aided Diagnosis system for diabetic retinopathy, we present a novel method for detection of exudates and their classification for disease severity prediction. The method is based on Gaussian scale space based interest map and mathematical morphology. It makes use of support vector machine for classification and location information of the optic disc and the macula region for severity prediction. It can efficiently handle luminance variation and it is suitable for varied sized exudates. The method has been probed in publicly available DIARETDB1V2 and e-ophthaEX databases. For exudate detection the proposed method achieved a sensitivity of 96.54% and prediction of 98.35% in DIARETDB1V2 database.