Researcher profile

Aditya Sharma

Aditya Sharma contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Computation and Language Artificial Intelligence hep-th gr-qc Machine Learning Robotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

6works

0followers

6topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

G-Loss: Graph-Guided Fine-Tuning of Language Models

Traditional loss functions, including cross-entropy, contrastive, triplet, and su pervised contrastive losses, used for fine-tuning pre-trained language models such as BERT, operate only within local neighborhoods and fail to account for the global semantic structure. We present G-Loss, a graph-guided loss function that incorporates semi-supervised label propagation to use structural relationships within the embedding manifold. G-Loss builds a document-similarity graph that captures global semantic relationships, thereby guiding the model to learn more discriminative and robust embeddings. We evaluate G-Loss on five benchmark datasets covering key downstream classification tasks: MR (sentiment analysis), R8 and R52 (topic categorization), Ohsumed (medical document classification), and 20NG (news categorization). In the majority of experimental setups, G-Loss converges faster and produces semantically coherent embedding spaces, resulting in higher classification accuracy than models fine-tuned with traditional loss functions.

preprint2026arXiv

Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards

An AI system for professional floor plan design must precisely control room dimensions and areas while respecting the desired connectivity between rooms and maintaining functional and aesthetic quality. Existing generative approaches focus primarily on respecting the requested connectivity between rooms, but do not support generating floor plans that respect numerical constraints. We introduce a text-based floor plan generation approach that fine-tunes a large language model (LLM) on real plans and then applies reinforcement learning with verifiable rewards (RLVR) to improve adherence to topological and numerical constraints while discouraging invalid or overlapping outputs. Furthermore, we design a set of constraint adherence metrics to systematically measure how generated floor plans align with user-defined constraints. Our model generates floor plans that satisfy user-defined connectivity and numerical constraints and outperforms existing methods on Realism, Compatibility, and Diversity metrics. Across all tasks, our approach achieves at least a 94% relative reduction in Compatibility compared with existing methods. Our results demonstrate that LLMs can effectively handle constraints in this setting, suggesting broader applications for text-based generative modeling.

preprint2022arXiv

Multi-Modal Model Predictive Control through Batch Non-Holonomic Trajectory Optimization: Application to Highway Driving

Standard Model Predictive Control (MPC) or trajectory optimization approaches perform only a local search to solve a complex non-convex optimization problem. As a result, they cannot capture the multi-modal characteristic of human driving. A global optimizer can be a potential solution but is computationally intractable in a real-time setting. In this paper, we present a real-time MPC capable of searching over different driving modalities. Our basic idea is simple: we run several goal-directed parallel trajectory optimizations and score the resulting trajectories based on user-defined meta cost functions. This allows us to perform a global search over several locally optimal motion plans. Although conceptually straightforward, realizing this idea in real-time with existing optimizers is highly challenging from technical and computational standpoints. With this motivation, we present a novel batch non-holonomic trajectory optimization whose underlying matrix algebra is easily parallelizable across problem instances and reduces to computing large batch matrix-vector products. This structure, in turn, is achieved by deriving a linearization-free multi-convex reformulation of the non-holonomic kinematics and collision avoidance constraints. We extensively validate our approach using both synthetic and real data sets (NGSIM) of traffic scenarios. We highlight how our algorithm automatically takes lane-change and overtaking decisions based on the defined meta cost function. Our batch optimizer achieves trajectories with lower meta cost, up to 6x faster than competing baselines.

preprint2022arXiv

Quantization of Interacting Galilean Field theories

We present the quantum field description of Galilean electrodynamics minimally coupled to massless Galilean fermion in (3 + 1) dimensions. At the classical level, the Lagrangian is obtained as a null reduction of a relativistic theory in one higher dimension. We use functional techniques to develop the quantum field description of the theory. Quantum corrections to the propagators and vertex are obtained upto first order and the theory is found to be renormalizable to this order. The beta function of the theory is found to grow linearly; the theory is not asymptotically free.

preprint2022arXiv

The BTZ black hole spectrum and partition function

In this article, we revisit the spectrum of the Lorentzian BTZ black hole conformal field theory. Building on a detailed analysis of geodesics, we identify a complete set of states for the harmonic analysis. We then demonstrate that the CFT spectrum is, plausibly, that of $AdS_3$ by rewriting the partition function of the latter CFT.

preprint2020arXiv

Tweets Sentiment Analysis via Word Embeddings and Machine Learning Techniques

Sentiment analysis of social media data consists of attitudes, assessments, and emotions which can be considered a way human think. Understanding and classifying the large collection of documents into positive and negative aspects are a very difficult task. Social networks such as Twitter, Facebook, and Instagram provide a platform in order to gather information about peoples sentiments and opinions. Considering the fact that people spend hours daily on social media and share their opinion on various different topics helps us analyze sentiments better. More and more companies are using social media tools to provide various services and interact with customers. Sentiment Analysis (SA) classifies the polarity of given tweets to positive and negative tweets in order to understand the sentiments of the public. This paper aims to perform sentiment analysis of real-time 2019 election twitter data using the feature selection model word2vec and the machine learning algorithm random forest for sentiment classification. Word2vec with Random Forest improves the accuracy of sentiment analysis significantly compared to traditional methods such as BOW and TF-IDF. Word2vec improves the quality of features by considering contextual semantics of words in a text hence improving the accuracy of machine learning and sentiment analysis.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint