arXiv subjects

Rishabh Singh

Publications and source records attributed to Rishabh Singh.

At least 19 recordsLinked to original sources

arXiv2026

Revisiting Electron Heating in Capacitively Coupled Plasma (CCP) Discharges: A Nonlinear Dynamics Perspective

Despite decades of research, the electron heating mechanisms in capacitively coupled plasma (CCP) discharges over a wide range of operating conditions is not fully understood. Although stochastic heating is generally regarded as the dominant collisionless heating mechanism at low pressures, the inherently nonlinear electron dynamics responsible for this process have not been fully quantified. These nonlinear interactions drive stochastic heating, a mechanism considered crucial for energy transfer in CCPs, yet its quantitative impact on plasma parameters remains insufficiently explored. In this work, we investigate electron dynamics in steady-state CCP discharges and demonstrate that electron motion in the plasma bulk exhibits intrinsically chaotic behavior. The onset of chaos is identified using Poincare sections and quantified through Lyapunov exponent analysis. To further quantify this behavior, we map the spatial distribution of the Lyapunov exponent-normalized by the electron-neutral collision frequency-across the plasma bulk for different pressures and RF voltages. The normalized Lyapunov exponent increases systematically with decreasing pressure and increasing RF voltage, indicating enhanced stochasticity and a stronger sensitivity of electron trajectories to initial conditions. These results establish the Lyapunov exponent as a quantitative measure of effective stochastic scattering in collisionless CCPs and provide a direct comparison with the classical stochastic collision frequency proposed by Popov and Godyak [Journal of Applied Physics 57, 53-58 (1985)]. The present analysis offers a unified nonlinear dynamical framework for understanding stochastic electron heating in low-pressure RF plasmas.

physics.plasm-ph↗

arXiv2026

Reading Between the Lines: The One-Sided Conversation Problem

Conversational AI is constrained in many real-world settings where only one side of a dialogue can be recorded, such as telemedicine, call centers, and smart glasses. We formalize this as the one-sided conversation problem (1SC): inferring and learning from one side of a conversation. We study two tasks: (1) reconstructing the missing speaker's turns for real-time use cases, and (2) generating summaries from one-sided transcripts. Evaluating prompting and finetuned models on MultiWOZ, DailyDialog, and Candor with both human A/B testing and LLM-as-a-judge metrics, we find that access to one future turn and information about utterance length improves reconstruction, placeholder prompting helps to mitigate hallucination, and while large models generate promising reconstructions with prompting, smaller models require finetuning. Further, high-quality summaries can be generated without reconstructing missing turns. We present 1SC as a novel challenge and report promising results that mark a step toward privacy-aware conversational AI.

cs.CL↗

arXiv2025

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). While DeepSeek-R1 and other follow-up work primarily focus on applying RL to competitive coding and math problems, this paper introduces SWE-RL, the first approach to scale RL-based LLM reasoning for real-world software engineering. Leveraging a lightweight rule-based reward (e.g., the similarity score between ground-truth and LLM-generated solutions), SWE-RL enables LLMs to autonomously recover a developer's reasoning processes and solutions by learning from extensive open-source software evolution data -- the record of a software's entire lifecycle, including its code snapshots, code changes, and events such as issues and pull requests. Trained on top of Llama 3, our resulting reasoning model, Llama3-SWE-RL-70B, achieves a 41.0% solve rate on SWE-bench Verified -- a human-verified collection of real-world GitHub issues. To our knowledge, this is the best performance reported for medium-sized (<100B) LLMs to date, even comparable to leading proprietary LLMs like GPT-4o. Surprisingly, despite performing RL solely on software evolution data, Llama3-SWE-RL has even emerged with generalized reasoning skills. For example, it shows improved results on five out-of-domain tasks, namely, function coding, library use, code reasoning, mathematics, and general language understanding, whereas a supervised-finetuning baseline even leads to performance degradation on average. Overall, SWE-RL opens up a new direction to improve the reasoning capabilities of LLMs through reinforcement learning on massive software engineering data.

cs.SE↗

arXiv2025

Growth and characterization of single crystal cubic TaN and hexagonal Ta$_2$N films on c-plane Sapphire

Two single crystal phases of tantalum nitride were stabilized on c-plane sapphire using molecular beam epitaxy. The phases were identified to be $δ$-TaN with a rocksalt cubic structure and $γ$-Ta$_2$N with a hexagonal structure. Atomic force microscopy scans revealed smooth surfaces for both the films with root mean square roughnesses less than 0.3 nm. Phase-purity of these films was determined by x-ray diffraction. Raman spectrum of the phase-pure $δ$-TaN and $γ$-Ta$_2$N obtained will serve as a future reference to determine phase-purity of tantalum nitride films. Further, the room-temperature and low-temperature electronic transport measurements indicated that both of these phases are metallic at room temperature with resistivities of 586.2 $μΩ$-cm for the 30 nm $δ$-TaN film and 75.5 $μΩ$-cm for the 38 nm $γ$-Ta$_2$N film and become superconducting below 3.6 K and 0.48 K respectively. The superconducting transition temperature reduces with applied magnetic field as expected. Ginzburg-Landau fitting revealed a 0 K critical magnetic field and coherence length of 18 T and 4.2 nm for the 30 nm $δ$-TaN film and 96 mT and 59 nm for the 38 nm $γ$-Ta$_2$N film. These tantalum nitride films are of high interest for superconducting resonators and qubits.

cond-mat.supr-con↗

arXiv2025

EdgeFlowNet: 100FPS@1W Dense Optical Flow For Tiny Mobile Robots

Optical flow estimation is a critical task for tiny mobile robotics to enable safe and accurate navigation, obstacle avoidance, and other functionalities. However, optical flow estimation on tiny robots is challenging due to limited onboard sensing and computation capabilities. In this paper, we propose EdgeFlowNet , a high-speed, low-latency dense optical flow approach for tiny autonomous mobile robots by harnessing the power of edge computing. We demonstrate the efficacy of our approach by deploying EdgeFlowNet on a tiny quadrotor to perform static obstacle avoidance, flight through unknown gaps and dynamic obstacle dodging. EdgeFlowNet is about 20 faster than the previous state-of-the-art approaches while improving accuracy by over 20% and using only 1.08W of power enabling advanced autonomy on palm-sized tiny mobile robots.

cs.RO↗

arXiv2023

Measuring The Impact Of Programming Language Distribution

Current benchmarks for evaluating neural code models focus on only a small subset of programming languages, excluding many popular languages such as Go or Rust. To ameliorate this issue, we present the BabelCode framework for execution-based evaluation of any benchmark in any language. BabelCode enables new investigations into the qualitative performance of models' memory, runtime, and individual test case results. Additionally, we present a new code translation dataset called Translating Python Programming Puzzles (TP3) from the Python Programming Puzzles (Schuster et al. 2021) benchmark that involves translating expert-level python functions to any language. With both BabelCode and the TP3 benchmark, we investigate if balancing the distributions of 14 languages in a training dataset improves a large language model's performance on low-resource languages. Training a model on a balanced corpus results in, on average, 12.34% higher $pass@k$ across all tasks and languages compared to the baseline. We find that this strategy achieves 66.48% better $pass@k$ on low-resource languages at the cost of only a 12.94% decrease to high-resource languages. In our three translation tasks, this strategy yields, on average, 30.77% better low-resource $pass@k$ while having 19.58% worse high-resource $pass@k$.

cs.LG↗

arXiv2022

Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS

Deep learning models for semantic segmentation are prone to poor performance in real-world applications due to the highly challenging nature of the task. Model uncertainty quantification (UQ) is one way to address this issue of lack of model trustworthiness by enabling the practitioner to know how much to trust a segmentation output. Current UQ methods in this application domain are mainly restricted to Bayesian based methods which are computationally expensive and are only able to extract central moments of uncertainty thereby limiting the quality of their uncertainty estimates. We present a simple framework for high-resolution predictive uncertainty quantification of semantic segmentation models that leverages a multi-moment functional definition of uncertainty associated with the model's feature space in the reproducing kernel Hilbert space (RKHS). The multiple uncertainty functionals extracted from this framework are defined by the local density dynamics of the model's feature space and hence automatically align themselves at the tail-regions of the intrinsic probability density function of the feature space (where uncertainty is the highest) in such a way that the successively higher order moments quantify the more uncertain regions. This leads to a significantly more accurate view of model uncertainty than conventional Bayesian methods. Moreover, the extraction of such moments is done in a single-shot computation making it much faster than Bayesian and ensemble approaches (that involve a high number of forward stochastic passes of the model to quantify its uncertainty). We demonstrate these advantages through experimental evaluations of our framework implemented over four different state-of-the-art model architectures that are trained and evaluated on two benchmark road-scene segmentation datasets (Camvid and Cityscapes).

cs.CV↗

arXiv2022

Robust Dependence Measure using RKHS based Uncertainty Moments and Optimal Transport

Reliable measurement of dependence between variables is essential in many applications of statistics and machine learning. Current approaches for dependence estimation, especially density-based approaches, lack in precision, robustness and/or interpretability (in terms of the type of dependence being estimated). We propose a two-step approach for dependence quantification between random variables: 1) We first decompose the probability density functions (PDF) of the variables involved in terms of multiple local moments of uncertainty that systematically and precisely identify the different regions of the PDF (with special emphasis on the tail-regions). 2) We then compute an optimal transport map to measure the geometric similarity between the corresponding sets of decomposed local uncertainty moments of the variables. Dependence is then determined by the degree of one-to-one correspondence between the respective uncertainty moments of the variables in the optimal transport map. We utilize a recently introduced Gaussian reproducing kernel Hilbert space (RKHS) based framework for multi-moment uncertainty decomposition of the variables. Being based on the Gaussian RKHS, our approach is robust towards outliers and monotone transformations of data, while the multiple moments of uncertainty provide high resolution and interpretability of the type of dependence being quantified. We support these claims through some preliminary results using simulated data.

eess.SP↗

arXiv2022

A Physics inspired Functional Operator for Model Uncertainty Quantification in the RKHS

Accurate uncertainty quantification of model predictions is a crucial problem in machine learning. Existing Bayesian methods, being highly iterative, are expensive to implement and often fail to accurately capture a model's true posterior because of their tendency to select only central moments. We propose a fast single-shot uncertainty quantification framework where, instead of working with the conventional Bayesian definition of model weight probability density function (PDF), we utilize physics inspired functional operators over the projection of model weights in a reproducing kernel Hilbert space (RKHS) to quantify their uncertainty at each model output. The RKHS projection of model weights yields a potential field based interpretation of model weight PDF which consequently allows the definition of a functional operator, inspired by perturbation theory in physics, that performs a moment decomposition of the model weight PDF (the potential field) at a specific model output to quantify its uncertainty. We call this representation of the model weight PDF as the quantum information potential field (QIPF) of the weights. The extracted moments from this approach automatically decompose the weight PDF in the local neighborhood of the specified model output and determine, with great sensitivity, the local heterogeneity of the weight PDF around a given prediction. These moments therefore provide sharper estimates of predictive uncertainty than central stochastic moments of Bayesian methods. Experiments evaluating the error detection capability of different uncertainty quantification methods on covariate shifted test data show our approach to be more precise and better calibrated than baseline methods, while being faster to compute.

cs.LG↗

arXiv2022

TF-Coder: Program Synthesis for Tensor Manipulations

The success and popularity of deep learning is on the rise, partially due to powerful deep learning frameworks such as TensorFlow and PyTorch that make it easier to develop deep learning models. However, these libraries also come with steep learning curves, since programming in these frameworks is quite different from traditional imperative programming with explicit loops and conditionals. In this work, we present a tool called TF-Coder for programming by example in TensorFlow. TF-Coder uses a bottom-up weighted enumerative search, with value-based pruning of equivalent expressions and flexible type- and value-based filtering to ensure that expressions adhere to various requirements imposed by the TensorFlow library. We train models to predict TensorFlow operations from features of the input and output tensors and natural language descriptions of tasks, to prioritize relevant operations during search. TF-Coder solves 63 of 70 real-world tasks within 5 minutes, sometimes finding simpler solutions in less time compared to experienced human programmers.

cs.PL↗

arXiv2022

MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning

Rapid advancements in deep learning have led to many recent breakthroughs. While deep learning models achieve superior performance, often statistically better than humans, their adoption into safety-critical settings, such as healthcare or self-driving cars is hindered by their inability to provide safety guarantees or to expose the inner workings of the model in a human understandable form. We present MoËT, a novel model based on Mixture of Experts, consisting of decision tree experts and a generalized linear model gating function. Thanks to such gating function the model is more expressive than the standard decision tree. To support non-differentiable decision trees as experts, we formulate a novel training procedure. In addition, we introduce a hard thresholding version, MoËTH, in which predictions are made solely by a single expert chosen via the gating function. Thanks to that property, MoËTH allows each prediction to be easily decomposed into a set of logical rules in a form which can be easily verified. While MoËT is a general use model, we illustrate its power in the reinforcement learning setting. By training MoËT models using an imitation learning procedure on deep RL agents we outperform the previous state-of-the-art technique based on decision trees while preserving the verifiability of the models. Moreover, we show that MoËT can also be used in real-world supervised problems on which it outperforms other verifiable machine learning models.

cs.LG↗

arXiv2021

Buoyancy effects on film boiling heat transfer over a sphere at low velocities

A theoretical model is developed for the forced convection film boiling phenomenon over a heated sphere moving vertically downwards in the water. Unprecedented to the previous analytical studies, this model accounts for the buoyancy effects while solving the momentum, and energy equations in the vapor phase to obtain the velocity, and the temperature distribution in terms of the vapor boundary layer thickness. To calculate the vapor boundary layer thickness an energy balance is applied at the vapor-liquid interface. The flow of liquid around the sphere is considered to be governed by the potential theory, and the energy equation in liquid is then solved for the known velocity distribution. We find that the vapor boundary layer thickness increases with an increase in the sphere, and the bulk water temperature, and a decrease in the free stream velocity. This further results in a decrease in the film boiling heat transfer coefficient. The present study concludes that at low free stream velocities ($< 0.5$ m/s) buoyancy becomes significant in delaying the separation, and when the velocity is further reduced the separation angle approaches $180^{\circ}$.

physics.flu-dyn↗

arXiv2021

BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration

Program synthesis is challenging largely because of the difficulty of search in a large space of programs. Human programmers routinely tackle the task of writing complex programs by writing sub-programs and then analyzing their intermediate results to compose them in appropriate ways. Motivated by this intuition, we present a new synthesis approach that leverages learning to guide a bottom-up search over programs. In particular, we train a model to prioritize compositions of intermediate values during search conditioned on a given set of input-output examples. This is a powerful combination because of several emergent properties. First, in bottom-up search, intermediate programs can be executed, providing semantic information to the neural network. Second, given the concrete values from those executions, we can exploit rich features based on recent work on property signatures. Finally, bottom-up search allows the system substantial flexibility in what order to generate the solution, allowing the synthesizer to build up a program from multiple smaller sub-programs. Overall, our empirical evaluation finds that the combination of learning and bottom-up search is remarkably effective, even with simple supervised learning approaches. We demonstrate the effectiveness of our technique on two datasets, one from the SyGuS competition and one of our own creation.

cs.PL↗

arXiv2021

Deep Geospatial Interpolation Networks

Interpolation in Spatio-temporal data has applications in various domains such as climate, transportation, and mining. Spatio-Temporal interpolation is highly challenging due to the complex spatial and temporal relationships. However, traditional techniques such as Kriging suffer from high running time and poor performance on data that exhibit high variance across space and time dimensions. To this end, we propose a novel deep neural network called as Deep Geospatial Interpolation Network(DGIN), which incorporates both spatial and temporal relationships and has significantly lower training time. DGIN consists of three major components: Spatial Encoder to capture the spatial dependencies, Sequential module to incorporate the temporal dynamics, and an Attention block to learn the importance of the temporal neighborhood around the gap. We evaluate DGIN on the MODIS reflectance dataset from two different regions. Our experimental results indicate that DGIN has two advantages: (a) it outperforms alternative approaches (has lower MSE with p-value < 0.01) and, (b) it has significantly low execution time than Kriging.

cs.LG↗

arXiv2021

Latent Programmer: Discrete Latent Codes for Program Synthesis

In many sequence learning tasks, such as program synthesis and document summarization, a key problem is searching over a large space of possible output sequences. We propose to learn representations of the outputs that are specifically meant for search: rich enough to specify the desired output but compact enough to make search more efficient. Discrete latent codes are appealing for this purpose, as they naturally allow sophisticated combinatorial search strategies. The latent codes are learned using a self-supervised learning principle, in which first a discrete autoencoder is trained on the output sequences, and then the resulting latent codes are used as intermediate targets for the end-to-end sequence prediction task. Based on these insights, we introduce the \emph{Latent Programmer}, a program synthesis method that first predicts a discrete latent code from input/output examples, and then generates the program in the target language. We evaluate the Latent Programmer on two domains: synthesis of string transformation programs, and generation of programs from natural language descriptions. We demonstrate that the discrete latent representation significantly improves synthesis accuracy.

cs.LG↗

arXiv2021

SpreadsheetCoder: Formula Prediction from Semi-structured Context

Spreadsheet formula prediction has been an important program synthesis problem with many real-world applications. Previous works typically utilize input-output examples as the specification for spreadsheet formula synthesis, where each input-output pair simulates a separate row in the spreadsheet. However, this formulation does not fully capture the rich context in real-world spreadsheets. First, spreadsheet data entries are organized as tables, thus rows and columns are not necessarily independent from each other. In addition, many spreadsheet tables include headers, which provide high-level descriptions of the cell data. However, previous synthesis approaches do not consider headers as part of the specification. In this work, we present the first approach for synthesizing spreadsheet formulas from tabular context, which includes both headers and semi-structured tabular data. In particular, we propose SpreadsheetCoder, a BERT-based model architecture to represent the tabular context in both row-based and column-based formats. We train our model on a large dataset of spreadsheets, and demonstrate that SpreadsheetCoder achieves top-1 prediction accuracy of 42.51%, which is a considerable improvement over baselines that do not employ rich tabular context. Compared to the rule-based system, SpreadsheetCoder assists 82% more users in composing formulas on Google Sheets.

cs.SE↗

arXiv2021

Image to Image Translation : Generating maps from satellite images

Generation of maps from satellite images is conventionally done by a range of tools. Maps became an important part of life whose conversion from satellite images may be a bit expensive but Generative models can pander to this challenge. These models aims at finding the patterns between the input and output image. Image to image translation is employed to convert satellite image to corresponding map. Different techniques for image to image translations like Generative adversarial network, Conditional adversarial networks and Co-Variational Auto encoders are used to generate the corresponding human-readable maps for that region, which takes a satellite image at a given zoom level as its input. We are training our model on Conditional Generative Adversarial Network which comprises of Generator model which which generates fake images while the discriminator tries to classify the image as real or fake and both these models are trained synchronously in adversarial manner where both try to fool each other and result in enhancing model performance.

cs.LG↗

arXiv2021

Scaling Symbolic Methods using Gradients for Neural Model Explanation

Symbolic techniques based on Satisfiability Modulo Theory (SMT) solvers have been proposed for analyzing and verifying neural network properties, but their usage has been fairly limited owing to their poor scalability with larger networks. In this work, we propose a technique for combining gradient-based methods with symbolic techniques to scale such analyses and demonstrate its application for model explanation. In particular, we apply this technique to identify minimal regions in an input that are most relevant for a neural network's prediction. Our approach uses gradient information (based on Integrated Gradients) to focus on a subset of neurons in the first layer, which allows our technique to scale to large networks. The corresponding SMT constraints encode the minimal input mask discovery problem such that after masking the input, the activations of the selected neurons are still above a threshold. After solving for the minimal masks, our approach scores the mask regions to generate a relative ordering of the features within the mask. This produces a saliency map which explains "where a model is looking" when making a prediction. We evaluate our technique on three datasets - MNIST, ImageNet, and Beer Reviews, and demonstrate both quantitatively and qualitatively that the regions generated by our approach are sparser and achieve higher saliency scores compared to the gradient-based methods alone. Code and examples are at - https://github.com/google-research/google-research/tree/master/smug_saliency

cs.LG↗