Vaibhav Kumar

Elaine Lau, Markus Dücker, Ronak Chaudhary et al. · mit

Existing AI benchmarks lack the fidelity to assess economically meaningful progress on professional workflows. To evaluate frontier AI agents in a high-value, labor-intensive profession, we introduce BankerToolBench (BTB): an open-source benchmark of end-to-end analytical workflows routinely performed by junior investment bankers. To develop an ecologically valid benchmark grounded in representative work environments, we collaborated with 502 investment bankers from leading firms. BTB requires agents to execute senior banker requests by navigating data rooms, using industry tools (market data platform, SEC filings database), and generating multi-file deliverables--including Excel financial models, PowerPoint pitch decks, and PDF/Word reports. Completing a BTB task takes bankers up to 21 hours, underscoring the economic stakes of successfully delegating this work to AI. BTB enables automated evaluation of any LLM or agent, scoring deliverables against 100+ rubric criteria defined by veteran investment bankers to capture stakeholder utility. Testing 9 frontier models, we find that even the best-performing model (GPT-5.4) fails nearly half of the rubric criteria and bankers rate 0% of its outputs as client-ready. Our failure analysis reveals key obstacles (such as breakdowns in cross-artifact consistency) and improvement directions for agentic AI in high-stakes professional workflows.

Minqian Liu, Ying Shen, Zhiyang Xu et al.

Natural Language Generation (NLG) typically involves evaluating the generated text in various aspects (e.g., consistency and naturalness) to obtain a comprehensive assessment. However, multi-aspect evaluation remains challenging as it may require the evaluator to generalize to any given evaluation aspect even if it's absent during training. In this paper, we introduce X-Eval, a two-stage instruction tuning framework to evaluate the text in both seen and unseen aspects customized by end users. X-Eval consists of two learning stages: the vanilla instruction tuning stage that improves the model's ability to follow evaluation instructions, and an enhanced instruction tuning stage that exploits the connections between fine-grained evaluation aspects to better assess text quality. To support the training of X-Eval, we collect AspectInstruct, the first instruction tuning dataset tailored for multi-aspect NLG evaluation spanning 27 diverse evaluation aspects with 65 tasks. To enhance task diversity, we devise an augmentation strategy that converts human rating annotations into diverse forms of NLG evaluation tasks, including scoring, comparison, ranking, and Boolean question answering. Extensive experiments across three essential categories of NLG tasks: dialogue generation, summarization, and data-to-text coupled with 21 aspects in meta-evaluation, demonstrate that our X-Eval enables even a lightweight language model to achieve a comparable if not higher correlation with human judgments compared to the state-of-the-art NLG evaluators, such as GPT-4.

Vaibhav Kumar, Ahmad Bazzi, Christina Pöpper et al.

ISAC systems introduce new privacy risks because an unintended sensing node may exploit the shared radio waveform to infer transmitter-related information even when the communication payload remains secure. This paper investigates transmitter privacy, defined as limiting unauthorized inference of transmitter-related information through channel estimation, in a RIS-aided multi-antenna wireless system with a transmitter, a legitimate receiver, a malicious sensor, and a RIS. The malicious sensor is assumed to estimate the transmitter--sensor channel, and the resulting channel state information can then support unauthorized sensing, inference, or related signal processing. To mitigate this threat, we consider a privacy-oriented design in which the transmitter adopts superposition-based signaling with a message signal and transmit-side artificial noise, while the RIS shapes the propagation environment in a privacy-aware manner. The channel-estimation performance at the malicious sensor is first analyzed under imperfect prior knowledge, and both the true and predicted mean-square-error expressions are derived. Based on this analysis, we formulate a joint active--passive beamforming design problem that maximizes the malicious sensor's predicted channel-estimation error subject to a communication quality-of-service constraint, a transmit-power budget, and the unit-modulus constraints of the RIS. The resulting non-convex problem is handled through a numerically efficient alternating-optimization framework based on an augmented Lagrangian reformulation. Numerical results show that RIS-assisted propagation shaping can substantially degrade unauthorized channel estimation relative to the non-RIS case while preserving reliable communication, and further show that the privacy gains also improve a more direct sensing metric, namely the malicious sensor's angle-of-arrival estimation accuracy.

Abhishek Kuriyal, Vaibhav Kumar, Bharat Lohani

LiDAR-generated point clouds are crucial for perceiving outdoor environments. The segmentation of point clouds is also essential for many applications. Previous research has focused on using self-attention and convolution (local attention) mechanisms individually in semantic segmentation architectures. However, there is limited work on combining the learned representations of these attention mechanisms to improve performance. Additionally, existing research that combines convolution with self-attention relies on global attention, which is not practical for processing large point clouds. To address these challenges, this study proposes a new architecture, pCTFusion, which combines kernel-based convolutions and self-attention mechanisms for better feature learning and capturing local and global dependencies in segmentation. The proposed architecture employs two types of self-attention mechanisms, local and global, based on the hierarchical positions of the encoder blocks. Furthermore, the existing loss functions do not consider the semantic and position-wise importance of the points, resulting in reduced accuracy, particularly at sharp class boundaries. To overcome this, the study models a novel attention-based loss function called Pointwise Geometric Anisotropy (PGA), which assigns weights based on the semantic distribution of points in a neighborhood. The proposed architecture is evaluated on SemanticKITTI outdoor dataset and showed a 5-7% improvement in performance compared to the state-of-the-art architectures. The results are particularly encouraging for minor classes, often misclassified due to class imbalance, lack of space, and neighbor-aware feature encoding. These developed methods can be leveraged for the segmentation of complex datasets and can drive real-world applications of LiDAR point cloud.

Vaibhav Kumar, Kaiwalya Joshi, Bhavya Dixit et al.

We propose a novel quantum-resistant mutual authentication scheme for radio-frequency identification (RFID) systems. Our scheme uses lattice-based cryptography and, in particular, achieves quantum-resistance by leveraging the hardness of the inhomogeneous short integer solution (ISIS) problem. In contrast to prior work, which assumes that the reader-server communication channel is secure, our scheme is secure even when both the reader-server and tag-reader communication channels are insecure. Our proposed protocol provides robust security against man-in-the-middle (MITM), replay, impersonation, and reflection attacks, while also ensuring unforgeability and preserving anonymity. We present a detailed security analysis, including semi-formal analysis and formal verification using the Automated Validation of Internet Security Protocols and Applications (AVISPA) tool. In addition, we analyze the storage, computation, and communication costs of the proposed protocol and compare its security properties with those of existing protocols, demonstrating that our scheme offers strong security guarantees. To the best of our knowledge, this paper is the first quantum-resistant authentication protocol for RFID systems that comprehensively addresses the insecurity of both the reader-server and tag-reader communication channels.

Abhishek Kuriyal, Vaibhav Kumar

Semantic Segmentation (SS) of LiDAR point clouds is essential for many applications, such as urban planning and autonomous driving. While much progress has been made in interpreting SS predictions for images, interpreting point cloud SS predictions remains a challenge. This paper introduces pGS-CAM, a novel gradient-based method for generating saliency maps in neural network activation layers. Inspired by Grad-CAM, which uses gradients to highlight local importance, pGS-CAM is robust and effective on a variety of datasets (SemanticKITTI, Paris-Lille3D, DALES) and 3D deep learning architectures (KPConv, RandLANet). Our experiments show that pGS-CAM effectively accentuates the feature learning in intermediate activations of SS architectures by highlighting the contribution of each point. This allows us to better understand how SS models make their predictions and identify potential areas for improvement. Relevant codes are available at https://github.com/geoai4cities/pGS-CAM.

Vaibhav Kumar, Hana Koorehdavoudi, Masud Moshtaghi et al.

We propose CHRT (Control Hidden Representation Transformation) - a controlled language generation framework that steers large language models to generate text pertaining to certain attributes (such as toxicity). CHRT gains attribute control by modifying the hidden representation of the base model through learned transformations. We employ a contrastive-learning framework to learn these transformations that can be combined to gain multi-attribute control. The effectiveness of CHRT is experimentally shown by comparing it with seven baselines over three attributes. CHRT outperforms all the baselines in the task of detoxification, positive sentiment steering, and text simplification while minimizing the loss in linguistic qualities. Further, our approach has the lowest inference latency of only 0.01 seconds more than the base model, making it the most suitable for high-performance production environments. We open-source our code and release two novel datasets to further propel controlled language generation research.

Yash Jakhotiya, Vaibhav Kumar, Ashwin Pathak et al.

Large Language Models have been successful in a wide variety of Natural Language Processing tasks by capturing the compositionality of the text representations. In spite of their great success, these vector representations fail to capture meaning of idiomatic multi-word expressions (MWEs). In this paper, we focus on the detection of idiomatic expressions by using binary classification. We use a dataset consisting of the literal and idiomatic usage of MWEs in English and Portuguese. Thereafter, we perform the classification in two different settings: zero shot and one shot, to determine if a given sentence contains an idiom or not. N shot classification for this task is defined by N number of common idioms between the training and testing sets. In this paper, we train multiple Large Language Models in both the settings and achieve an F1 score (macro) of 0.73 for the zero shot setting and an F1 score (macro) of 0.85 for the one shot setting. An implementation of our work can be found at https://github.com/ashwinpathak20/Idiomaticity_Detection_Using_Few_Shot_Learning.

Arijit Ghosh Chowdhury, Md Mofijul Islam, Vaibhav Kumar et al.

Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text. However, with their rising prominence, the security and vulnerability aspects of these models have garnered significant attention. This paper presents a comprehensive survey of the various forms of attacks targeting LLMs, discussing the nature and mechanisms of these attacks, their potential impacts, and current defense strategies. We delve into topics such as adversarial attacks that aim to manipulate model outputs, data poisoning that affects model training, and privacy concerns related to training data exploitation. The paper also explores the effectiveness of different attack methodologies, the resilience of LLMs against these attacks, and the implications for model integrity and user trust. By examining the latest research, we provide insights into the current landscape of LLM vulnerabilities and defense mechanisms. Our objective is to offer a nuanced understanding of LLM attacks, foster awareness within the AI community, and inspire robust solutions to mitigate these risks in future developments.

Mohammad Kachuee, Sarthak Ahuja, Vaibhav Kumar et al.

Using tools by Large Language Models (LLMs) is a promising avenue to extend their reach beyond language or conversational settings. The number of tools can scale to thousands as they enable accessing sensory information, fetching updated factual knowledge, or taking actions in the real world. In such settings, in-context learning by providing a short list of relevant tools in the prompt is a viable approach. To retrieve relevant tools, various approaches have been suggested, ranging from simple frequency-based matching to dense embedding-based semantic retrieval. However, such approaches lack the contextual and common-sense understanding required to retrieve the right tools for complex user requests. Rather than increasing the complexity of the retrieval component itself, we propose leveraging LLM understanding to generate a retrieval query. Then, the generated query is embedded and used to find the most relevant tools via a nearest-neighbor search. We investigate three approaches for query generation: zero-shot prompting, supervised fine-tuning on tool descriptions, and alignment learning by iteratively optimizing a reward metric measuring retrieval performance. By conducting extensive experiments on a dataset covering complex and multi-tool scenarios, we show that leveraging LLMs for query generation improves the retrieval for in-domain (seen tools) and out-of-domain (unseen tools) settings.

Suchetan G. Uppur, Hemant Kumar, Vaibhav Kumar

Training autonomous driving and navigation systems requires large and diverse point cloud datasets that capture complex edge case scenarios from various dynamic urban settings. Acquiring such diverse scenarios from real-world point cloud data, especially for critical edge cases, is challenging, which restricts system generalization and robustness. Current methods rely on simulating point cloud data within handcrafted 3D virtual environments, which is time-consuming, computationally expensive, and often fails to fully capture the complexity of real-world scenes. To address some of these issues, this research proposes a novel approach that addresses the problem discussed by editing real-world LiDAR scans using semantic mask-based guidance to generate novel synthetic LiDAR point clouds. We incorporate range image projection and semantic mask conditioning to achieve diffusion-based generation. Point clouds are transformed to 2D range view images, which are used as an intermediate representation to enable semantic editing using convex hull-based semantic masks. These masks guide the generation process by providing information on the dimensions, orientations, and locations of objects in the real environment, ensuring geometric consistency and realism. This approach demonstrates high-quality LiDAR point cloud generation, capable of producing complex edge cases and dynamic scenes, as validated on the KITTI-360 dataset. This offers a cost-effective and scalable solution for generating diverse LiDAR data, a step toward improving the robustness of autonomous driving systems.

Bhanu Pratap Paregi, Vaibhav Kumar

Recent point cloud completion models, including transformer-based, denoising-based, and other state-of-the-art approaches, generate globally plausible shapes from partial inputs but often leave local geometric inconsistencies. We propose RL-AD-Net, a reinforcement learning (RL) refinement framework that operates in the latent space of a pretrained point autoencoder. The autoencoder encodes completions into compact global feature vectors (GFVs), which are selectively adjusted by an RL agent to improve geometric fidelity. To ensure robustness, a lightweight non-parametric PointNN selector evaluates the geometric consistency of both the original completion and the RL-refined output, retaining the better reconstruction. When ground truth is available, both Chamfer Distance and geometric consistency metrics guide refinement. Training is performed separately per category, since the unsupervised and dynamic nature of RL makes convergence across highly diverse categories challenging. Nevertheless, the framework can be extended to multi-category refinement in future work. Experiments on ShapeNetCore-2048 demonstrate that while baseline completion networks perform reasonable under their training-style cropping, they struggle in random cropping scenarios. In contrast, RL-AD-Net consistently delivers improvements across both settings, highlighting the effectiveness of RL-guided ensemble refinement. The approach is lightweight, modular, and model-agnostic, making it applicable to a wide range of completion networks without requiring retraining.

Pushpendra Dhakara, Prachi Chachodhia, Vaibhav Kumar

Unstructured urban environments present unique challenges for scene understanding and generalization due to their complex and diverse layouts. We introduce SynthGenNet, a self-supervised student-teacher architecture designed to enable robust test-time domain generalization using synthetic multi-source imagery. Our contributions include the novel ClassMix++ algorithm, which blends labeled data from various synthetic sources while maintaining semantic integrity, enhancing model adaptability. We further employ Grounded Mask Consistency Loss (GMC), which leverages source ground truth to improve cross-domain prediction consistency and feature alignment. The Pseudo-Label Guided Contrastive Learning (PLGCL) mechanism is integrated into the student network to facilitate domain-invariant feature learning through iterative knowledge distillation from the teacher network. This self-supervised strategy improves prediction accuracy, addresses real-world variability, bridges the sim-to-real domain gap, and reliance on labeled target data, even in complex urban areas. Outcomes show our model outperforms the state-of-the-art (relying on single source) by achieving 50% Mean Intersection-Over-Union (mIoU) value on real-world datasets like Indian Driving Dataset (IDD).

Vaibhav Kumar, Tenzin Singhay Bhotia, Vaibhav Kumar et al.

Euclidean word embedding models such as GloVe and Word2Vec have been shown to reflect human-like gender biases. In this paper, we extend the study of gender bias to the recently popularized hyperbolic word embeddings. We propose gyrocosine bias, a novel measure for quantifying gender bias in hyperbolic word representations and observe a significant presence of gender bias. To address this problem, we propose Poincaré Gender Debias (PGD), a novel debiasing procedure for hyperbolic word representations. Experiments on a suit of evaluation tests show that PGD effectively reduces bias while adding a minimal semantic offset.

Vaibhav Kumar, Tenzin Singhay Bhotia, Vaibhav Kumar

Non-contextual word embedding models have been shown to inherit human-like stereotypical biases of gender, race and religion from the training corpora. To counter this issue, a large body of research has emerged which aims to mitigate these biases while keeping the syntactic and semantic utility of embeddings intact. This paper describes Fair Embedding Engine (FEE), a library for analysing and mitigating gender bias in word embeddings. FEE combines various state of the art techniques for quantifying, visualising and mitigating gender bias in word embeddings under a standard abstraction. FEE will aid practitioners in fast track analysis of existing debiasing methods on their embedding models. Further, it will allow rapid prototyping of new methods by evaluating their performance on a suite of standard metrics.

Vaibhav Kumar, Vikas Raunak, Jamie Callan

Given a natural language query, teaching machines to ask clarifying questions is of immense utility in practical natural language processing systems. Such interactions could help in filling information gaps for better machine comprehension of the query. For the task of ranking clarification questions, we hypothesize that determining whether a clarification question pertains to a missing entry in a given post (on QA forums such as StackExchange) could be considered as a special case of Natural Language Inference (NLI), where both the post and the most relevant clarification question point to a shared latent piece of information or context. We validate this hypothesis by incorporating representations from a Siamese BERT model fine-tuned on NLI and Multi-NLI datasets into our models and demonstrate that our best performing model obtains a relative performance improvement of 40 percent and 60 percent respectively (on the key metric of Precision@1), over the state-of-the-art baseline(s) on the two evaluation sets of the StackExchange dataset, thereby, significantly surpassing the state-of-the-art.

Vaibhav Kumar, Alan W. black

Question answering and conversational systems are often baffled and need help clarifying certain ambiguities. However, limitations of existing datasets hinder the development of large-scale models capable of generating and utilising clarification questions. In order to overcome these limitations, we devise a novel bootstrapping framework (based on self-supervision) that assists in the creation of a diverse, large-scale dataset of clarification questions based on post-comment tuples extracted from stackexchange. The framework utilises a neural network based architecture for classifying clarification questions. It is a two-step method where the first aims to increase the precision of the classifier and second aims to increase its recall. We quantitatively demonstrate the utility of the newly created dataset by applying it to the downstream task of question-answering. The final dataset, ClarQ, consists of ~2M examples distributed across 173 domains of stackexchange. We release this dataset in order to foster research into the field of clarification question generation with the larger goal of enhancing dialog and question answering systems.

Vaibhav Kumar, Tenzin Singhay Bhotia, Vaibhav Kumar et al.

Word embeddings are the standard model for semantic and syntactic representations of words. Unfortunately, these models have been shown to exhibit undesirable word associations resulting from gender, racial, and religious biases. Existing post-processing methods for debiasing word embeddings are unable to mitigate gender bias hidden in the spatial arrangement of word vectors. In this paper, we propose RAN-Debias, a novel gender debiasing methodology which not only eliminates the bias present in a word vector but also alters the spatial distribution of its neighbouring vectors, achieving a bias-free setting while maintaining minimal semantic offset. We also propose a new bias evaluation metric - Gender-based Illicit Proximity Estimate (GIPE), which measures the extent of undue proximity in word vectors resulting from the presence of gender-based predilections. Experiments based on a suite of evaluation metrics show that RAN-Debias significantly outperforms the state-of-the-art in reducing proximity bias (GIPE) by at least 42.02%. It also reduces direct bias, adding minimal semantic disturbance, and achieves the best performance in a downstream application task (coreference resolution).

Vikas Raunak, Vaibhav Kumar, Florian Metze

We investigate two specific manifestations of compositionality in Neural Machine Translation (NMT) : (1) Productivity - the ability of the model to extend its predictions beyond the observed length in training data and (2) Systematicity - the ability of the model to systematically recombine known parts and rules. We evaluate a standard Sequence to Sequence model on tests designed to assess these two properties in NMT. We quantitatively demonstrate that inadequate temporal processing, in the form of poor encoder representations is a bottleneck for both Productivity and Systematicity. We propose a simple pre-training mechanism which alleviates model performance on the two properties and leads to a significant improvement in BLEU scores.

Vikas Raunak, Vaibhav Kumar, Vivek Gupta et al.

Word embeddings have become a staple of several natural language processing tasks, yet much remains to be understood about their properties. In this work, we analyze word embeddings in terms of their principal components and arrive at a number of novel and counterintuitive observations. In particular, we characterize the utility of variance explained by the principal components as a proxy for downstream performance. Furthermore, through syntactic probing of the principal embedding space, we show that the syntactic information captured by a principal component does not correlate with the amount of variance it explains. Consequently, we investigate the limitations of variance based embedding post-processing and demonstrate that such post-processing is counter-productive in sentence classification and machine translation tasks. Finally, we offer a few precautionary guidelines on applying variance based embedding post-processing and explain why non-isotropic geometry might be integral to word embedding performance.

Sourya Dipta Das, Himanshu Ladia, Vaibhav Kumar et al.

The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. In offline (static) signature verification, the dynamic information of the signature writing process is lost, and it is difficult to design good feature extractors that can distinguish genuine signatures and skilled forgeries. This verification task is even harder in writer independent scenarios which is undeniably fiscal for realistic cases. In this paper, we have proposed an Ensemble model for offline writer, independent signature verification task with Deep learning. We have used two CNNs for feature extraction, after that RGBT for classification & Stacking to generate final prediction vector. We have done extensive experiments on various datasets from various sources to maintain a variance in the dataset. We have achieved the state of the art performance on various datasets.

Vaibhav Kumar, Mrinal Dhar, Dhruv Khattar et al.

In order to expand their reach and increase website ad revenue, media outlets have started using clickbait techniques to lure readers to click on articles on their digital platform. Having successfully enticed the user to open the article, the article fails to satiate his curiosity serving only to boost click-through rates. Initial methods for this task were dependent on feature engineering, which varies with each dataset. Industry systems have relied on an exhaustive set of rules to get the job done. Neural networks have barely been explored to perform this task. We propose a novel approach considering different textual embeddings of a news headline and the related article. We generate sub-word level embeddings of the title using Convolutional Neural Networks and use them to train a bidirectional LSTM architecture. An attention layer allows for calculation of significance of each term towards the nature of the post. We also generate Doc2Vec embeddings of the title and article text and model how they interact, following which it is concatenated with the output of the previous component. Finally, this representation is passed through a neural network to obtain a score for the headline. We test our model over 2538 posts (having trained it on 17000 records) and achieve an accuracy of 83.49% outscoring previous state-of-the-art approaches.

Vaibhav Kumar, Dhruv Khattar, Siddhartha Gairola et al.

Online media outlets, in a bid to expand their reach and subsequently increase revenue through ad monetisation, have begun adopting clickbait techniques to lure readers to click on articles. The article fails to fulfill the promise made by the headline. Traditional methods for clickbait detection have relied heavily on feature engineering which, in turn, is dependent on the dataset it is built for. The application of neural networks for this task has only been explored partially. We propose a novel approach considering all information found in a social media post. We train a bidirectional LSTM with an attention mechanism to learn the extent to which a word contributes to the post's clickbait score in a differential manner. We also employ a Siamese net to capture the similarity between source and target information. Information gleaned from images has not been considered in previous approaches. We learn image embeddings from large amounts of data using Convolutional Neural Networks to add another layer of complexity to our model. Finally, we concatenate the outputs from the three separate components, serving it as input to a fully connected layer. We conduct experiments over a test corpus of 19538 social media posts, attaining an F1 score of 65.37% on the dataset bettering the previous state-of-the-art, as well as other proposed approaches, feature engineering or otherwise.