Rahul Kumar

Rahul Kumar, Shubham Kakde, Divyansh Rajput et al.

We present a novel approach to data preparation for developing multilingual Indic large language model. Our meticulous data acquisition spans open-source and proprietary sources, including Common Crawl, Indic books, news articles, and Wikipedia, ensuring a diverse and rich linguistic representation. For each Indic language, we design a custom preprocessing pipeline to effectively eliminate redundant and low-quality text content. Additionally, we perform deduplication on Common Crawl data to address the redundancy present in 70% of the crawled web pages. This study focuses on developing high-quality data, optimizing tokenization for our multilingual dataset for Indic large language models with 3B and 7B parameters, engineered for superior performance in Indic languages. We introduce a novel multilingual tokenizer training strategy, demonstrating our custom-trained Indic tokenizer outperforms the state-of-the-art OpenAI Tiktoken tokenizer, achieving a superior token-to-word ratio for Indic languages.

Cunxi Dai, Haoran Chang, Aditya Nisal et al.

Behavior cloning for contact-rich bimanual manipulation remains challenging because diverse demonstrations are expensive to collect, and even small disturbances can push the system into off-manifold states where no recovery supervision is available. We propose PGDG, a data generation framework with zero-shot curation that expands a single demonstration into a compact dataset of physically plausible, successful, and diverse recovery behaviors without additional human labeling. PGDG iterates between a physics-grounded sampler and a dataset curator, where the curator selects informative, non-redundant, and recoverable behaviors to update the sampling distribution toward under-covered recovery modes, and the sampler draws physically plausible rollout candidates from this updated distribution and retains successful trajectories. To further improve data quality, PGDG applies short-horizon sampling-based control to relabel selected risky states with corrective actions. Across four bimanual manipulation tasks, PGDG consistently outperforms spatial-only augmentation in both simulation and zero-shot real-world transfer. On RotateBox-Pitch, success improves from 38% to 93% in simulation and from 35% to 82% in the real world. PGDG also enables effective foundation models fine-tuning such as GR00T, increasing success from 46% to 77%. Additional results are available in our website: https://cunxid.github.io/PGDG/.

Lucas Hayne, Abhijit Suresh, Hunar Jain et al.

Linear classifier probes are frequently utilized to better understand how neural networks function. Researchers have approached the problem of determining unit importance in neural networks by probing their learned, internal representations. Linear classifier probes identify highly selective units as the most important for network function. Whether or not a network actually relies on high selectivity units can be tested by removing them from the network using ablation. Surprisingly, when highly selective units are ablated they only produce small performance deficits, and even then only in some cases. In spite of the absence of ablation effects for selective neurons, linear decoding methods can be effectively used to interpret network function, leaving their effectiveness a mystery. To falsify the exclusive role of selectivity in network function and resolve this contradiction, we systematically ablate groups of units in subregions of activation space. Here, we find a weak relationship between neurons identified by probes and those identified by ablation. More specifically, we find that an interaction between selectivity and the average activity of the unit better predicts ablation performance deficits for groups of units in AlexNet, VGG16, MobileNetV2, and ResNet101. Linear decoders are likely somewhat effective because they overlap with those units that are causally important for network function. Interpretability methods could be improved by focusing on causally important units.

Daniel Platnick, Bishoy Abdelnour, Eamon Earl et al.

In recent years, there has been increased demand for speech-to-speech translation (S2ST) systems in industry settings. Although successfully commercialized, cloning-based S2ST systems expose their distributors to liabilities when misused by individuals and can infringe on personality rights when exploited by media organizations. This work proposes a regulated S2ST framework called Preset-Voice Matching (PVM). PVM removes cross-lingual voice cloning in S2ST by first matching the input voice to a similar prior consenting speaker voice in the target-language. With this separation, PVM avoids cloning the input speaker, ensuring PVM systems comply with regulations and reduce risk of misuse. Our results demonstrate PVM can significantly improve S2ST system run-time in multi-speaker settings and the naturalness of S2ST synthesized speech. To our knowledge, PVM is the first explicitly regulated S2ST framework leveraging similarly-matched preset-voices for dynamic S2ST tasks.

Arnob Saha, Bibhas Manna, Nikhil Kotikalapudi et al.

Leveraging the high density and energy efficiency of Compute-In-Memory (CIM) crossbar-based Deep Neural Network (DNN) accelerators requires optimal Design Space Exploration (DSE), which becomes increasingly challenging as complex models for advanced AI workloads expand the highly non-convex design space. Moreover, heterogeneous layer workloads (e.g., memory- vs. compute-bound) and learning representations make layer-wise NN parameter allocation beneficial for efficiency but severely exacerbate the design space complexity by expanding the number of parameters to be tuned for simultaneous multi-objective optimization. Among existing DSE approaches, multi-objective Bayesian Optimization (BO) is promising, as it explores high-quality design solutions while querying costly CIM simulators selectively. In this work, we propose a multi-objective BO framework that holistically co-optimizes hardware and algorithm parameters of a CIM crossbar-based hardware accelerator for various DNN inference tasks. Depending on NN model depth, our framework handles high-dimensional design spaces (with $26$ and $50$ dimensions) and extremely large search complexities on the order of $O(10^{12})$ and $O(10^{27})$ for VGG8/CIFAR-10 and VGG16/Tiny-ImageNet-200. Our method attains $91.72 \%$ and $57.2 \%$ accuracy, respectively, comparable to baseline designs, while improving chip area ($65.52 \%$ and $50.7 \%$), read latency ($9.52 \%$ and $13.27 \%$), read dynamic energy ($31.23 \%$ and $52.07 \%$) and increasing memory utilization ($13.41 \%$ and $2.67 \%$).

Rahul Kumar

As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability -- knowing what they do not know, detecting errors, seeking clarification -- under adversarial pressure is a critical safety requirement. Current safety evaluations focus on detecting strategic deception (scheming); we investigate a more fundamental failure mode: cognitive collapse. We present SCHEMA, an evaluation of 11 frontier models from 8 vendors across 67,221 scored records using a 6-condition factorial design with dual-classifier scoring. We find that 8 of 11 models suffer catastrophic metacognitive degradation under adversarial pressure, with accuracy dropping by up to 30.2 percentage points (all $p < 2 \times 10^{-8}$, surviving Bonferroni correction). Crucially, we identify a "Compliance Trap": through factorial isolation and a benign distraction control, we demonstrate that collapse is driven not by the psychological content of survival threats, but by compliance-forcing instructions that override epistemic boundaries. Removing the compliance suffix restores performance even under active threat. Models with advanced reasoning capabilities exhibit the most severe absolute degradation, while Anthropic's Constitutional AI demonstrates near-perfect immunity -- not from superior capability (Google's Gemini matches its baseline accuracy) but from alignment-specific training. We release the complete dataset and evaluation infrastructure.

Rohit Pandey, Hetvi Waghela, Sneha Rakshit et al.

This work delved into the realm of automatic text generation, exploring a variety of techniques ranging from traditional deterministic approaches to more modern stochastic methods. Through analysis of greedy search, beam search, top-k sampling, top-p sampling, contrastive searching, and locally typical searching, this work has provided valuable insights into the strengths, weaknesses, and potential applications of each method. Each text-generating method is evaluated using several standard metrics and a comparative study has been made on the performance of the approaches. Finally, some future directions of research in the field of automatic text generation are also identified.

Ahmad Shadid, Rahul Kumar, Mohit Mayank

Single large language models (LLMs) often fall short when faced with the ever-growing range of tasks, making a single-model approach insufficient. We address this challenge by proposing ORI (O Routing Intelligence), a dynamic framework that leverages a set of LLMs. By intelligently routing incoming queries to the most suitable model, ORI not only improves task-specific accuracy, but also maintains efficiency. Comprehensive evaluations across diverse benchmarks demonstrate consistent accuracy gains while controlling computational overhead. By intelligently routing queries, ORI outperforms the strongest individual models by up to 2.7 points on MMLU and 1.8 points on MuSR, ties the top performance on ARC, and on BBH. These results underscore the benefits of a multi-model strategy and demonstrate how ORI's adaptive architecture can more effectively handle diverse tasks, offering a scalable, high-performance solution for a system of multiple large language models.

Rahul Kumar, Vipul Baghel, Sudhanshu Singh et al.

Accurate analysis of combat sports using computer vision has gained traction in recent years, yet the development of robust datasets remains a major bottleneck due to the dynamic, unstructured nature of actions and variations in recording environments. In this work, we present a comprehensive, well-annotated video dataset tailored for punch detection and classification in boxing. The dataset comprises 6,915 high-quality punch clips categorized into six distinct punch types, extracted from 20 publicly available YouTube sparring sessions and involving 18 different athletes. Each clip is manually segmented and labeled to ensure precise temporal boundaries and class consistency, capturing a wide range of motion styles, camera angles, and athlete physiques. This dataset is specifically curated to support research in real-time vision-based action recognition, especially in low-resource and unconstrained environments. By providing a rich benchmark with diverse punch examples, this contribution aims to accelerate progress in movement analysis, automated coaching, and performance assessment within boxing and related domains.

Rahul Kumar, Wenqi Wei, Ying Mao et al.

We propose a circuit-level attack, SQUASH, a SWAP-Based Quantum Attack to sabotage Hybrid Quantum Neural Networks (HQNNs) for classification tasks. SQUASH is executed by inserting SWAP gate(s) into the variational quantum circuit of the victim HQNN. Unlike conventional noise-based or adversarial input attacks, SQUASH directly manipulates the circuit structure, leading to qubit misalignment and disrupting quantum state evolution. This attack is highly stealthy, as it does not require access to training data or introduce detectable perturbations in input states. Our results demonstrate that SQUASH significantly degrades classification performance, with untargeted SWAP attacks reducing accuracy by up to 74.08\% and targeted SWAP attacks reducing target class accuracy by up to 79.78\%. These findings reveal a critical vulnerability in HQNN implementations, underscoring the need for more resilient architectures against circuit-level adversarial interventions.

Rahul Kumar, Amar Raja Dibbu, Shrutendra Harsola et al.

Several large-scale datasets (e.g., WikiSQL, Spider) for developing natural language interfaces to databases have recently been proposed. These datasets cover a wide breadth of domains but fall short on some essential domains, such as finance and accounting. Given that accounting databases are used worldwide, particularly by non-technical people, there is an imminent need to develop models that could help extract information from accounting databases via natural language queries. In this resource paper, we aim to fill this gap by proposing a new large-scale Text-to-SQL dataset for the accounting and financial domain: BookSQL. The dataset consists of 100k natural language queries-SQL pairs, and accounting databases of 1 million records. We experiment with and analyze existing state-of-the-art models (including GPT-4) for the Text-to-SQL task on BookSQL. We find significant performance gaps, thus pointing towards developing more focused models for this domain.

Syed Arbaaz Qureshi, Sonu Mehta, Ranjita Bhagwan et al.

In recent times, it has been shown that one can use code as data to aid various applications such as automatic commit message generation, automatic generation of pull request descriptions and automatic program repair. Take for instance the problem of commit message generation. Treating source code as a sequence of tokens, state of the art techniques generate commit messages using neural machine translation models. However, they tend to ignore the syntactic structure of programming languages. Previous work, i.e., code2seq has used structural information from Abstract Syntax Tree (AST) to represent source code and they use it to automatically generate method names. In this paper, we elaborate upon this state of the art approach and modify it to represent source code edits. We determine the effect of using such syntactic structure for the problem of classifying code edits. Inspired by the code2seq approach, we evaluate how using structural information from AST, i.e., paths between AST leaf nodes can help with the task of code edit classification on two datasets of fine-grained syntactic edits. Our experiments shows that attempts of adding syntactic structure does not result in any improvements over less sophisticated methods. The results suggest that techniques such as code2seq, while promising, have a long way to go before they can be generically applied to learning code edit representations. We hope that these results will benefit other researchers and inspire them to work further on this problem.

Rahul Kumar, Sandeep Mathias, Sriparna Saha et al.

Most research in the area of automatic essay grading (AEG) is geared towards scoring the essay holistically while there has also been some work done on scoring individual essay traits. In this paper, we describe a way to score essays holistically using a multi-task learning (MTL) approach, where scoring the essay holistically is the primary task, and scoring the essay traits is the auxiliary task. We compare our results with a single-task learning (STL) approach, using both LSTMs and BiLSTMs. We also compare our results of the auxiliary task with such tasks done in other AEG systems. To find out which traits work best for different types of essays, we conduct ablation tests for each of the essay traits. We also report the runtime and number of training parameters for each system. We find that MTL-based BiLSTM system gives the best results for scoring the essay holistically, as well as performing well on scoring the essay traits.

Rajat Kumar Jenamani, Rahul Kumar, Parth Mall et al.

Sampling based methods are widely used for robotic motion planning. Traditionally, these samples are drawn from probabilistic ( or deterministic ) distributions to cover the state space uniformly. Despite being probabilistically complete, they fail to find a feasible path in a reasonable amount of time in constrained environments where it is essential to go through narrow passages (bottleneck regions). Current state of the art techniques train a learning model (learner) to predict samples selectively on these bottleneck regions. However, these algorithms depend completely on samples generated by this learner to navigate through the bottleneck regions. As the complexity of the planning problem increases, the amount of data and time required to make this learner robust to fine variations in the structure of the workspace becomes computationally intractable. In this work, we present (1) an efficient and robust method to use a learner to locate the bottleneck regions and (2) two algorithms that use local sampling methods to leverage the location of these bottleneck regions for efficient motion planning while maintaining probabilistic completeness. We test our algorithms on 2 dimensional planning problems and 7 dimensional robotic arm planning, and report significant gains over heuristics as well as learned baselines.

Rahul Kumar, Aditya Mandalika, Sanjiban Choudhury et al.

We consider the problem of leveraging prior experience to generate roadmaps in sampling-based motion planning. A desirable roadmap is one that is sparse, allowing for fast search, with nodes spread out at key locations such that a low-cost feasible path exists. An increasingly popular approach is to learn a distribution of nodes that would produce such a roadmap. State-of-the-art is to train a conditional variational auto-encoder (CVAE) on the prior dataset with the shortest paths as target input. While this is quite effective on many problems, we show it can fail in the face of complex obstacle configurations or mismatch between training and testing. We present an algorithm LEGO that addresses these issues by training the CVAE with target samples that satisfy two important criteria. Firstly, these samples belong only to bottleneck regions along near-optimal paths that are otherwise difficult-to-sample with a uniform sampler. Secondly, these samples are spread out across diverse regions to maximize the likelihood of a feasible path existing. We formally define these properties and prove performance guarantees for LEGO. We extensively evaluate LEGO on a range of planning problems, including robot arm planning, and report significant gains over heuristics as well as learned baselines.

Sanya Chaba, Rahul Kumar, Rohan Pant et al.

Static detection technologies based on signature-based approaches that are widely used in Android platform to detect malicious applications. It can accurately detect malware by extracting signatures from test data and then comparing the test data with the signature samples of virus and benign samples. However, this method is generally unable to detect unknown malware applications. This is because, sometimes, the machine code can be converted into assembly code, which can be easily read and understood by humans. Furthuremore, the attacker can then make sense of the assembly instructions and understand the functioning of the program from the same. Therefore we focus on observing the behaviour of the malicious software while it is actually running on a host system. The dynamic behaviours of an application are conducted by the system call sequences at the end. Hence, we observe the system call log of each application, use the same for the construction of our dataset, and finally use this dataset to classify an unknown application as malicious or benign.

Ayush Pandey, Subhamoy Mahajan, Adarsh Kosta et al.

On the lines of the huge and varied efforts in the field of automation with respect to technology development and innovation of vehicles to make them run autonomously, this paper presents an innovation to a bicycle. A normal daily use bicycle was modified at low cost such that it runs autonomously, while maintaining its original form i.e. the manual drive. Hence, a bicycle which could be normally driven by any human and with a press of switch could run autonomously according to the needs of the user has been developed.

Rahul Kumar, Chetan Bansal, Jakob Lichtenberg

In this paper we describe our experience of using Microsoft Azure cloud computing platform for static analysis. We start by extending Static Driver Verifier to operate in the Microsoft Azure cloud with significant improvements in performance and scalability. We present our results of using SDV on single drivers and driver suites using various configurations of the cloud relative to a local machine. Finally, we describe the Static Module Verifier platform, a highly extensible and configurable platform for static analysis of generic modules, where we have integrated support for verification using a cloud services provider (Microsoft Azure in this case).

Anand Sriraman, Mandar Kulkarni, Rahul Kumar et al.

We present an end-to-end machine-human image annotation system where each component can be attached in a plug-and-play fashion. These components include Feature Extraction, Machine Classifier, Task Sampling and Crowd Consensus.