Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–16 of 16 results for author: Bajpai, A

Searching in archive cs. Search in all archives.
.
  1. arXiv:2607.04537  [pdf, ps, other

    cs.SE cs.AI

    Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse

    Authors: Raj Jaiswal, Anany Singh Divy, Savar Bhasin, Adi Bajpai, Tanuja Ganu, Rajiv Ratn Shah

    Abstract: Code language models are now trusted collaborators in production workflows for debugging, refactoring, and iterative repair, and every benchmark that evaluates them assumes the instructions they act on are correct. We study what happens when that assumption breaks. We evaluate code language models across four experiments designed to assess whether models resist or obey incorrect instructions in si… ▽ More

    Submitted 5 July, 2026; originally announced July 2026.

  2. arXiv:2604.17475  [pdf, ps, other

    cs.AI cs.CL cs.LG

    Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception

    Authors: Ashutosh Bajpai, Tamal Majumder, Akshay Nambi, Tanmoy Chakraborty

    Abstract: Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration. They typically require expensive supervised trajectory tuning to mitigate these deficits. In this work, we propose Self-supervised Perception Enabled by Cascaded Tool Rollout Alignment (SPECTRA), a supervision-free framework that bootstraps agentic capabilities… ▽ More

    Submitted 19 April, 2026; originally announced April 2026.

    Comments: ACL 2026 Findings

    MSC Class: 68T50 ACM Class: I.2.7; I.2.10; I.2.6

  3. arXiv:2601.17489  [pdf, ps, other

    cs.LG cs.CL cs.CV

    SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving

    Authors: Ashutosh Bajpai, Akshat Bhandari, Akshay Nambi, Tanmoy Chakraborty

    Abstract: Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information but still face significant limitations in visual comprehension and mathematical reasoning, particularly in geometric problems with diverse levels of visual infusion. Current models struggle to accurately decompose intricate visual inputs and connect perceptio… ▽ More

    Submitted 24 January, 2026; originally announced January 2026.

    ACM Class: I.2.7; I.2.10; I.2.6

  4. arXiv:2510.15513  [pdf, ps, other

    cs.CL

    Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References?

    Authors: Ashutosh Bajpai, Tanmoy Chakraborty

    Abstract: The increasing acceptance of large language models (LLMs) as an alternative to knowledge sources marks a significant paradigm shift across various domains, including time-sensitive fields such as law, healthcare, and finance. To fulfill this expanded role, LLMs must not only be factually accurate but also demonstrate consistency across temporal dimensions, necessitating robust temporal reasoning c… ▽ More

    Submitted 17 October, 2025; originally announced October 2025.

    Comments: EMNLP Main Long Paper 2025

    ACM Class: I.2.7

  5. arXiv:2501.16857  [pdf, other

    cs.SE

    Comparing Human and LLM Generated Code: The Jury is Still Out!

    Authors: Sherlock A. Licorish, Ansh Bajpai, Chetan Arora, Fanyu Wang, Kla Tantithamthavorn

    Abstract: Much is promised in relation to AI-supported software development. However, there has been limited evaluation effort in the research domain aimed at validating the true utility of such techniques, especially when compared to human coding outputs. We bridge this gap, where a benchmark dataset comprising 72 distinct software engineering tasks is used to compare the effectiveness of large language mo… ▽ More

    Submitted 28 January, 2025; originally announced January 2025.

    Comments: 10 pages, 6 figures

    ACM Class: D.2.4; D.2.5; D.2.8

  6. arXiv:2412.08090  [pdf, other

    cs.CL cs.AI cs.LG

    Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages

    Authors: Ashutosh Bajpai, Tanmoy Chakraborty

    Abstract: The unwavering disparity in labeled resources between resource-rich languages and those considered low-resource remains a significant impediment for Large Language Models (LLMs). Recent strides in cross-lingual in-context learning (X-ICL), mainly through semantically aligned examples retrieved from multilingual pre-trained transformers, have shown promise in mitigating this issue. However, our inv… ▽ More

    Submitted 24 February, 2025; v1 submitted 10 December, 2024; originally announced December 2024.

    ACM Class: I.2.7

  7. Temporally Consistent Factuality Probing for Large Language Models

    Authors: Ashutosh Bajpai, Aaryan Goyal, Atif Anwer, Tanmoy Chakraborty

    Abstract: The prolific use of Large Language Models (LLMs) as an alternate knowledge base requires them to be factually consistent, necessitating both correctness and consistency traits for paraphrased queries. Recently, significant attempts have been made to benchmark datasets and metrics to evaluate LLMs for these traits. However, structural simplicity (subject-relation-object) and contemporary associatio… ▽ More

    Submitted 17 October, 2024; v1 submitted 21 September, 2024; originally announced September 2024.

  8. arXiv:2404.00645  [pdf, ps, other

    cs.CV

    Attire-Based Anomaly Detection in Restricted Areas Using YOLOv8 for Enhanced CCTV Security

    Authors: Abdul Aziz A. B, Aindri Bajpai

    Abstract: This research introduces an innovative security enhancement approach, employing advanced image analysis and soft computing. The focus is on an intelligent surveillance system that detects unauthorized individuals in restricted areas by analyzing attire. Traditional security measures face challenges in monitoring unauthorized access. Leveraging YOLOv8, an advanced object detection algorithm, our sy… ▽ More

    Submitted 4 January, 2026; v1 submitted 31 March, 2024; originally announced April 2024.

    Comments: 9 pages, 6 figures

    MSC Class: 68T40; 68T45; 68T05; 68U20

  9. arXiv:2401.17705  [pdf

    cs.LG cs.HC

    Predicting suicidal behavior among Indian adults using childhood trauma, mental health questionnaires and machine learning cascade ensembles

    Authors: Akash K Rao, Gunjan Y Trivedi, Riri G Trivedi, Anshika Bajpai, Gajraj Singh Chauhan, Vishnu K Menon, Kathirvel Soundappan, Hemalatha Ramani, Neha Pandya, Varun Dutt

    Abstract: Among young adults, suicide is India's leading cause of death, accounting for an alarming national suicide rate of around 16%. In recent years, machine learning algorithms have emerged to predict suicidal behavior using various behavioral traits. But to date, the efficacy of machine learning algorithms in predicting suicidal behavior in the Indian context has not been explored in literature. In th… ▽ More

    Submitted 31 January, 2024; originally announced January 2024.

    Comments: 11 pages, presnted at the 4th International Conference on Frontiers in Computing and Systems (COMSYS 2023), Himachal Pradesh, October 2023

  10. Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection

    Authors: Sarah Masud, Ashutosh Bajpai, Tanmoy Chakraborty

    Abstract: Although pretrained large language models (PLMs) have achieved state-of-the-art on many natural language processing (NLP) tasks, they lack an understanding of subtle expressions of implicit hate speech. Various attempts have been made to enhance the detection of implicit hate by augmenting external context or enforcing label separation via distance-based metrics. Combining these two approaches, we… ▽ More

    Submitted 10 November, 2024; v1 submitted 21 September, 2023; originally announced September 2023.

    Comments: 23 pages, 6 Figures, 9 Tables. Accepted at NLE

    Journal ref: Nat. lang. process. 31 (2025) 1323-1349

  11. arXiv:2305.13941  [pdf

    cs.CV cs.AI cs.LG

    A Comparative Analysis of Techniques and Algorithms for Recognising Sign Language

    Authors: Rupesh Kumar, Ayush Sinha, Ashutosh Bajpai, S. K Singh

    Abstract: Sign language is a visual language that enhances communication between people and is frequently used as the primary form of communication by people with hearing loss. Even so, not many people with hearing loss use sign language, and they frequently experience social isolation. Therefore, it is necessary to create human-computer interface systems that can offer hearing-impaired people a social plat… ▽ More

    Submitted 24 May, 2023; v1 submitted 5 May, 2023; originally announced May 2023.

    Comments: 6 pages, 1 table

  12. arXiv:2305.05296  [pdf

    cs.CV cs.LG

    Mediapipe and CNNs for Real-Time ASL Gesture Recognition

    Authors: Rupesh Kumar, Ashutosh Bajpai, Ayush Sinha

    Abstract: This research paper describes a realtime system for identifying American Sign Language (ASL) movements that employs modern computer vision and machine learning approaches. The suggested method makes use of the Mediapipe library for feature extraction and a Convolutional Neural Network (CNN) for ASL gesture classification. The testing results show that the suggested system can detect all ASL alphab… ▽ More

    Submitted 24 May, 2023; v1 submitted 9 May, 2023; originally announced May 2023.

    Comments: 5 pages, 6 figures, 2 tables

  13. arXiv:2002.07375  [pdf, other

    cs.LG cs.AI stat.ML

    Symbolic Network: Generalized Neural Policies for Relational MDPs

    Authors: Sankalp Garg, Aniket Bajpai, Mausam

    Abstract: A Relational Markov Decision Process (RMDP) is a first-order representation to express all instances of a single probabilistic planning domain with possibly unbounded number of objects. Early work in RMDPs outputs generalized (instance-independent) first-order policies or value functions as a means to solve all instances of a domain at once. Unfortunately, this line of work met with limited succes… ▽ More

    Submitted 29 June, 2020; v1 submitted 18 February, 2020; originally announced February 2020.

    Comments: In Proceeding of ICML 2020. Code can be found at https://github.com/dair-iitd/symnet

  14. arXiv:1909.08388  [pdf, other

    cs.NI

    Rural wireless deployments in India

    Authors: Arpit Bajpai

    Abstract: The Internet provides access to communications, information and opportunity to people. Growth of technology and its benefits should penetrate down to every citizen of a country. Rural Areas without Internet access risk being left behind in the information age. To be competitive, they must have broad and sustainable Internet services. Internet connectivity is especially important in developing coun… ▽ More

    Submitted 4 September, 2019; originally announced September 2019.

    Comments: 6 pages, 2 figures

  15. arXiv:1902.03081  [pdf, other

    cs.LG stat.ML

    Size Independent Neural Transfer for RDDL Planning

    Authors: Sankalp Garg, Aniket Bajpai, Mausam

    Abstract: Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These scale well with large domains, but are sample inefficient and time-consuming to train from scratch for each new problem. To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on other problems of the same domain can rapidly transfer to a new problem. However, th… ▽ More

    Submitted 4 April, 2019; v1 submitted 8 February, 2019; originally announced February 2019.

    Comments: Published in ICAPS 2019

  16. arXiv:1810.11488  [pdf, other

    cs.AI

    Transfer of Deep Reactive Policies for MDP Planning

    Authors: Aniket Bajpai, Sankalp Garg, Mausam

    Abstract: Domain-independent probabilistic planners input an MDP description in a factored representation language such as PPDDL or RDDL, and exploit the specifics of the representation for faster planning. Traditional algorithms operate on each problem instance independently, and good methods for transferring experience from policies of other instances of a domain to a new instance do not exist. Recently,… ▽ More

    Submitted 26 October, 2018; originally announced October 2018.

    Comments: To appear at NIPS 2018