Showing 1–12 of 12 results for author: Khurana, A

Benchmarking the Generality of Vision-Language-Action Models

Authors: Pranav Guruprasad, Sudipta Chowdhury, Harsh Sikka, Mridul Sharma, Helen Lu, Sean Rivera, Aryan Khurana, Hangliang Ren, Yangyue Wang

Abstract: Generalist multimodal agents are expected to unify perception, language, and control - operating robustly across diverse real world domains. However, current evaluation practices remain fragmented across isolated benchmarks, making it difficult to assess whether today's foundation models truly generalize beyond their training distributions. We introduce MultiNet v1.0, a unified benchmark for measu… ▽ More Generalist multimodal agents are expected to unify perception, language, and control - operating robustly across diverse real world domains. However, current evaluation practices remain fragmented across isolated benchmarks, making it difficult to assess whether today's foundation models truly generalize beyond their training distributions. We introduce MultiNet v1.0, a unified benchmark for measuring the cross domain generality of vision language models (VLMs) and vision language action models (VLAs) across six foundational capability regimes. Visual grounding, spatial reasoning, tool use, physical commonsense, multi agent coordination, and continuous robot control. Evaluating GPT 5, Pi0, and Magma, we find that no model demonstrates consistent generality. All exhibit substantial degradation on unseen domains, unfamiliar modalities, or cross domain task shifts despite strong performance within their training distributions.These failures manifest as modality misalignment, output format instability, and catastrophic knowledge degradation under domain transfer.Our findings reveal a persistent gap between the aspiration of generalist intelligence and the actual capabilities of current foundation models.MultiNet v1.0 provides a standardized evaluation substrate for diagnosing these gaps and guiding the development of future generalist agents.Code, data, and leaderboards are publicly available. △ Less

Submitted 12 December, 2025; originally announced December 2025.

Comments: 23 pages, 7 figures, and 1 table

I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2

Authors: Oliver McLaughlin, Arjun Khurana, Jack Merullo

Abstract: Large language models demonstrate proficiency on phonetic tasks, such as rhyming, without explicit phonetic or auditory grounding. In this work, we investigate how \verb|Llama-3.2-1B-Instruct| represents token-level phonetic information. Our results suggest that Llama uses a rich internal model of phonemes to complete phonetic tasks. We provide evidence for high-level organization of phoneme repre… ▽ More Large language models demonstrate proficiency on phonetic tasks, such as rhyming, without explicit phonetic or auditory grounding. In this work, we investigate how \verb|Llama-3.2-1B-Instruct| represents token-level phonetic information. Our results suggest that Llama uses a rich internal model of phonemes to complete phonetic tasks. We provide evidence for high-level organization of phoneme representations in its latent space. In doing so, we also identify a ``phoneme mover head" which promotes phonetic information during rhyming tasks. We visualize the output space of this head and find that, while notable differences exist, Llama learns a model of vowels similar to the standard IPA vowel chart for humans, despite receiving no direct supervision to do so. △ Less

Submitted 15 October, 2025; v1 submitted 4 August, 2025; originally announced August 2025.

Do It For Me vs. Do It With Me: Investigating User Perceptions of Different Paradigms of Automation in Copilots for Feature-Rich Software

Authors: Anjali Khurana, Xiaotian Su, April Yi Wang, Parmit K Chilana

Abstract: Large Language Model (LLM)-based in-application assistants, or copilots, can automate software tasks, but users often prefer learning by doing, raising questions about the optimal level of automation for an effective user experience. We investigated two automation paradigms by designing and implementing a fully automated copilot (AutoCopilot) and a semi-automated copilot (GuidedCopilot) that autom… ▽ More Large Language Model (LLM)-based in-application assistants, or copilots, can automate software tasks, but users often prefer learning by doing, raising questions about the optimal level of automation for an effective user experience. We investigated two automation paradigms by designing and implementing a fully automated copilot (AutoCopilot) and a semi-automated copilot (GuidedCopilot) that automates trivial steps while offering step-by-step visual guidance. In a user study (N=20) across data analysis and visual design tasks, GuidedCopilot outperformed AutoCopilot in user control, software utility, and learnability, especially for exploratory and creative tasks, while AutoCopilot saved time for simpler visual tasks. A follow-up design exploration (N=10) enhanced GuidedCopilot with task-and state-aware features, including in-context preview clips and adaptive instructions. Our findings highlight the critical role of user control and tailored guidance in designing the next generation of copilots that enhance productivity, support diverse skill levels, and foster deeper software engagement. △ Less

Submitted 21 April, 2025; originally announced April 2025.

Comments: Accepted for publication in the CHI Conference on Human Factors in Computing Systems (CHI 2025), April 26 - May 1, 2025, Yokohama, Japan

Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking

Authors: Anjali Khurana, Hari Subramonyam, Parmit K Chilana

Abstract: Large Language Model (LLM) assistants, such as ChatGPT, have emerged as potential alternatives to search methods for helping users navigate complex, feature-rich software. LLMs use vast training data from domain-specific texts, software manuals, and code repositories to mimic human-like interactions, offering tailored assistance, including step-by-step instructions. In this work, we investigated L… ▽ More Large Language Model (LLM) assistants, such as ChatGPT, have emerged as potential alternatives to search methods for helping users navigate complex, feature-rich software. LLMs use vast training data from domain-specific texts, software manuals, and code repositories to mimic human-like interactions, offering tailored assistance, including step-by-step instructions. In this work, we investigated LLM-generated software guidance through a within-subject experiment with 16 participants and follow-up interviews. We compared a baseline LLM assistant with an LLM optimized for particular software contexts, SoftAIBot, which also offered guidelines for constructing appropriate prompts. We assessed task completion, perceived accuracy, relevance, and trust. Surprisingly, although SoftAIBot outperformed the baseline LLM, our results revealed no significant difference in LLM usage and user perceptions with or without prompt guidelines and the integration of domain context. Most users struggled to understand how the prompt's text related to the LLM's responses and often followed the LLM's suggestions verbatim, even if they were incorrect. This resulted in difficulties when using the LLM's advice for software tasks, leading to low task completion rates. Our detailed analysis also revealed that users remained unaware of inaccuracies in the LLM's responses, indicating a gap between their lack of software expertise and their ability to evaluate the LLM's assistance. With the growing push for designing domain-specific LLM assistants, we emphasize the importance of incorporating explainable, context-aware cues into LLMs to help users understand prompt-based interactions, identify biases, and maximize the utility of LLM assistants. △ Less

Submitted 12 February, 2024; originally announced February 2024.

Comments: Accepted for publication in the Proceedings of the 29th International Conference on Intelligent User Interfaces (IUI'24), March 18--21, 2024, in Greenville, SC, USA

Personalized Summarization of Scientific Scholarly Texts

Authors: Alka Khurana, Vasudha Bhatnagar, Vikas Kumar

Abstract: In this paper, we present a proposal for an unsupervised algorithm, P-Summ, that generates an extractive summary of scientific scholarly text to meet the personal knowledge needs of the user. The method delves into the latent semantic space of the document exposed by Weighted Non-negative Matrix Factorization, and scores sentences in consonance with the knowledge needs of the user. The novelty of… ▽ More In this paper, we present a proposal for an unsupervised algorithm, P-Summ, that generates an extractive summary of scientific scholarly text to meet the personal knowledge needs of the user. The method delves into the latent semantic space of the document exposed by Weighted Non-negative Matrix Factorization, and scores sentences in consonance with the knowledge needs of the user. The novelty of the algorithm lies in its ability to include desired knowledge and eliminate unwanted knowledge in the personal summary. We also propose a multi-granular evaluation framework, which assesses the quality of generated personal summaries at three levels of granularity - sentence, terms and semantic. The framework uses system generated generic summary instead of human generated summary as gold standard for evaluating the quality of personal summary generated by the algorithm. The effectiveness of the algorithm at the semantic level is evaluated by taking into account the reference summary and the knowledge signals. We evaluate the performance of P-Summ algorithm over four data-sets consisting of scientific articles. Our empirical investigations reveal that the proposed method has the capability to meet negative (or positive) knowledge preferences of the user. △ Less

Submitted 27 October, 2024; v1 submitted 15 June, 2023; originally announced June 2023.

An Artificial Intelligence Dataset for Solar Energy Locations in India

Authors: Anthony Ortiz, Dhaval Negandhi, Sagar R Mysorekar, Joseph Kiesecker, Shivaprakash K Nagaraju, Caleb Robinson, Priyal Bhatia, Aditi Khurana, Jane Wang, Felipe Oviedo, Juan Lavista Ferres

Abstract: Rapid development of renewable energy sources, particularly solar photovoltaics (PV), is critical to mitigate climate change. As a result, India has set ambitious goals to install 500 gigawatts of solar energy capacity by 2030. Given the large footprint projected to meet renewables energy targets, the potential for land use conflicts over environmental values is high. To expedite development of so… ▽ More Rapid development of renewable energy sources, particularly solar photovoltaics (PV), is critical to mitigate climate change. As a result, India has set ambitious goals to install 500 gigawatts of solar energy capacity by 2030. Given the large footprint projected to meet renewables energy targets, the potential for land use conflicts over environmental values is high. To expedite development of solar energy, land use planners will need access to up-to-date and accurate geo-spatial information of PV infrastructure. In this work, we developed a spatially explicit machine learning model to map utility-scale solar projects across India using freely available satellite imagery with a mean accuracy of 92%. Our model predictions were validated by human experts to obtain a dataset of 1363 solar PV farms. Using this dataset, we measure the solar footprint across India and quantified the degree of landcover modification associated with the development of PV infrastructure. Our analysis indicates that over 74% of solar development In India was built on landcover types that have natural ecosystem preservation, or agricultural value. △ Less

Submitted 30 June, 2022; v1 submitted 31 January, 2022; originally announced February 2022.

Comments: Accepted for publication in Nature Scientific Data

Unsupervised Adaptation of Semantic Segmentation Models without Source Data

Authors: Sujoy Paul, Ansh Khurana, Gaurav Aggarwal

Abstract: We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims to adapt a model learned on the labeled source data, to a new unlabeled target dataset. Existing methods assume that the source data is available along with the target data during adaptation. However, in practical scenari… ▽ More We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims to adapt a model learned on the labeled source data, to a new unlabeled target dataset. Existing methods assume that the source data is available along with the target data during adaptation. However, in practical scenarios, we may only have access to the source model and the unlabeled target data, but not the labeled source, due to reasons such as privacy, storage, etc. In this work, we propose a self-training approach to extract the knowledge from the source model. To compensate for the distribution shift from source to target, we first update only the normalization parameters of the network with the unlabeled target data. Then we employ confidence-filtered pseudo labeling and enforce consistencies against certain transformations. Despite being very simple and intuitive, our framework is able to achieve significant performance gains compared to directly applying the source model on the target data as reflected in our extensive experiments and ablation studies. In fact, the performance is just a few points away from the recent state-of-the-art methods which use source data for adaptation. We further demonstrate the generalisability of the proposed approach for fully test-time adaptation setting, where we do not need any target training data and adapt only during test-time. △ Less

Submitted 4 December, 2021; originally announced December 2021.

SITA: Single Image Test-time Adaptation

Authors: Ansh Khurana, Sujoy Paul, Piyush Rai, Soma Biswas, Gaurav Aggarwal

Abstract: In Test-time Adaptation (TTA), given a source model, the goal is to adapt it to make better predictions for test instances from a different distribution than the source. Crucially, TTA assumes no access to the source data or even any additional labeled/unlabeled samples from the target distribution to finetune the source model. In this work, we consider TTA in a more pragmatic setting which we ref… ▽ More In Test-time Adaptation (TTA), given a source model, the goal is to adapt it to make better predictions for test instances from a different distribution than the source. Crucially, TTA assumes no access to the source data or even any additional labeled/unlabeled samples from the target distribution to finetune the source model. In this work, we consider TTA in a more pragmatic setting which we refer to as SITA (Single Image Test-time Adaptation). Here, when making a prediction, the model has access only to the given single test instance, rather than a batch of instances, as typically been considered in the literature. This is motivated by the realistic scenarios where inference is needed on-demand instead of delaying for an incoming batch or the inference is happening on an edge device (like mobile phone) where there is no scope for batching. The entire adaptation process in SITA should be extremely fast as it happens at inference time. To address this, we propose a novel approach AugBN that requires only a single forward pass. It can be used on any off-the-shelf trained model to test single instances for both classification and segmentation tasks. AugBN estimates normalization statistics of the unseen test distribution from the given test image using only one forward pass with label-preserving transformations. Since AugBN does not involve any back-propagation, it is significantly faster compared to recent test time adaptation methods. We further extend AugBN to make the algorithm hyperparameter-free. Rigorous experimentation show that our simple algorithm is able to achieve significant performance gains for a variety of datasets, tasks, and network architectures. △ Less

Submitted 7 September, 2022; v1 submitted 4 December, 2021; originally announced December 2021.

Investigating Entropy for Extractive Document Summarization

Authors: Alka Khurana, Vasudha Bhatnagar

Abstract: Automatic text summarization aims to cut down readers time and cognitive effort by reducing the content of a text document without compromising on its essence. Ergo, informativeness is the prime attribute of document summary generated by an algorithm, and selecting sentences that capture the essence of a document is the primary goal of extractive document summarization. In this paper, we employ Sh… ▽ More Automatic text summarization aims to cut down readers time and cognitive effort by reducing the content of a text document without compromising on its essence. Ergo, informativeness is the prime attribute of document summary generated by an algorithm, and selecting sentences that capture the essence of a document is the primary goal of extractive document summarization. In this paper, we employ Shannon entropy to capture informativeness of sentences. We employ Non-negative Matrix Factorization (NMF) to reveal probability distributions for computing entropy of terms, topics, and sentences in latent space. We present an information theoretic interpretation of the computed entropy, which is the bedrock of the proposed E-Summ algorithm, an unsupervised method for extractive document summarization. The algorithm systematically applies information theoretic principle for selecting informative sentences from important topics in the document. The proposed algorithm is generic and fast, and hence amenable to use for summarization of documents in real time. Furthermore, it is domain-, collection-independent and agnostic to the language of the document. Benefiting from strictly positive NMF factor matrices, E-Summ algorithm is transparent and explainable too. We use standard ROUGE toolkit for performance evaluation of the proposed method on four well known public data-sets. We also perform quantitative assessment of E-Summ summary quality by computing its semantic similarity w.r.t the original document. Our investigation reveals that though using NMF and information theoretic approach for document summarization promises efficient, explainable, and language independent text summarization, it needs to be bolstered to match the performance of deep neural methods. △ Less

Submitted 29 September, 2021; v1 submitted 22 September, 2021; originally announced September 2021.

Multi-Stage Fusion for One-Click Segmentation

Authors: Soumajit Majumder, Ansh Khurana, Abhinav Rai, Angela Yao

Abstract: Segmenting objects of interest in an image is an essential building block of applications such as photo-editing and image analysis. Under interactive settings, one should achieve good segmentations while minimizing user input. Current deep learning-based interactive segmentation approaches use early fusion and incorporate user cues at the image input layer. Since segmentation CNNs have many layers… ▽ More Segmenting objects of interest in an image is an essential building block of applications such as photo-editing and image analysis. Under interactive settings, one should achieve good segmentations while minimizing user input. Current deep learning-based interactive segmentation approaches use early fusion and incorporate user cues at the image input layer. Since segmentation CNNs have many layers, early fusion may weaken the influence of user interactions on the final prediction results. As such, we propose a new multi-stage guidance framework for interactive segmentation. By incorporating user cues at different stages of the network, we allow user interactions to impact the final segmentation output in a more direct way. Our proposed framework has a negligible increase in parameter count compared to early-fusion frameworks. We perform extensive experimentation on the standard interactive instance segmentation and one-click segmentation benchmarks and report state-of-the-art performance. △ Less

Submitted 20 October, 2020; v1 submitted 19 October, 2020; originally announced October 2020.

Comments: A preprint of the accepted paper at GCPR 2020

CuttleSys: Data-Driven Resource Management forInteractive Applications on Reconfigurable Multicores

Authors: Neeraj Kulkarni, Gonzalo Gonzalez-Pumariega, Amulya Khurana, Christine Shoemaker, Christina Delimitrou, David Albonesi

Abstract: Multi-tenancy for latency-critical applications leads to re-source interference and unpredictable performance. Core reconfiguration opens up more opportunities for colocation,as it allows the hardware to adjust to the dynamic performance and power needs of a specific mix of co-scheduled applications. However, reconfigurability also introduces challenges, as even for a small number of reconfigurabl… ▽ More Multi-tenancy for latency-critical applications leads to re-source interference and unpredictable performance. Core reconfiguration opens up more opportunities for colocation,as it allows the hardware to adjust to the dynamic performance and power needs of a specific mix of co-scheduled applications. However, reconfigurability also introduces challenges, as even for a small number of reconfigurable cores, exploring the design space becomes more time- and resource-demanding. We present CuttleSys, a runtime for reconfigurable multi-cores that leverages scalable and lightweight data mining to quickly identify suitable core and cache configurations for a set of co-scheduled applications. The runtime combines collaborative filtering to infer the behavior of each job on every core and cache configuration, with Dynamically Dimensioned Search to efficiently explore the configuration space. We evaluate CuttleSys on multicores with tens of reconfigurable cores and show up to 2.46x and 1.55x performance improvements compared to core-level gating and oracle-like asymmetric multicores respectively, under stringent power constraints. △ Less

Submitted 1 August, 2020; originally announced August 2020.

Video Moment Localization using Object Evidence and Reverse Captioning

Authors: Madhawa Vidanapathirana, Supriya Pandhre, Sonia Raychaudhuri, Anjali Khurana

Abstract: We address the problem of language-based temporal localization of moments in untrimmed videos. Compared to temporal localization with fixed categories, this problem is more challenging as the language-based queries have no predefined activity classes and may also contain complex descriptions. Current state-of-the-art model MAC addresses it by mining activity concepts from both video and language m… ▽ More We address the problem of language-based temporal localization of moments in untrimmed videos. Compared to temporal localization with fixed categories, this problem is more challenging as the language-based queries have no predefined activity classes and may also contain complex descriptions. Current state-of-the-art model MAC addresses it by mining activity concepts from both video and language modalities. This method encodes the semantic activity concepts from the verb/object pair in a language query and leverages visual activity concepts from video activity classification prediction scores. We propose "Multi-faceted VideoMoment Localizer" (MML), an extension of MAC model by the introduction of visual object evidence via object segmentation masks and video understanding features via video captioning. Furthermore, we improve language modelling in sentence embedding. We experimented on Charades-STA dataset and identified that MML outperforms MAC baseline by 4.93% and 1.70% on R@1 and R@5metrics respectively. Our code and pre-trained model are publicly available at https://github.com/madhawav/MML. △ Less

Submitted 17 June, 2020; originally announced June 2020.

Comments: 7 pages. 6 figures. For source code, refer https://github.com/madhawav/MML