Anuj Sharma

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

Document layout understanding remains data-intensive despite advances in semi-supervised learning. We present a framework that enhances semi-supervised detection by fusing visual predictions with structural priors from text-pretrained LLMs via principled probabilistic weighting. Given unlabeled documents, an OCR-LLM pipeline infers hierarchical regions which are combined with teacher detector outputs through inverse-variance fusion to generate refined pseudo-labels.Our method demonstrates consistent gains across model scales. With a lightweight SwiftFormer backbone (26M params), we achieve 88.2$\pm$0.3 AP using only 5\% labels on PubLayNet. When applied to document-pretrained LayoutLMv3 (133M params), our fusion framework reaches 89.7$\pm$0.4 AP, surpassing both LayoutLMv3 with standard semi-supervised learning (89.1$\pm$0.4 AP, p=0.02) and matching UDOP~\cite{udop} (89.8 AP) which requires 100M+ pages of multimodal pretraining. This demonstrates that LLM structural priors are complementary to both lightweight and pretrained architectures. Key findings include: (1) learned instance-adaptive gating improves over fixed weights by +0.9 AP with data-dependent PAC bounds correctly predicting convergence; (2) open-source LLMs enable privacy-preserving deployment with minimal loss (Llama-3-70B: 87.1 AP lightweight, 89.4 AP with LayoutLMv3); (3) LLMs provide targeted semantic disambiguation (18.7\% of cases, +3.8 AP gain) beyond simple text heuristics.Total system cost includes \$12 for GPT-4o-mini API or 17 GPU-hours for local Llama-3-70B per 50K pages, amortized across training runs.

Vinod Kumar Chauhan, Anuj Sharma, Kalpana Dahiya

LIBS2ML is a library based on scalable second order learning algorithms for solving large-scale problems, i.e., big data problems in machine learning. LIBS2ML has been developed using MEX files, i.e., C++ with MATLAB/Octave interface to take the advantage of both the worlds, i.e., faster learning using C++ and easy I/O using MATLAB. Most of the available libraries are either in MATLAB/Python/R which are very slow and not suitable for large-scale learning, or are in C/C++ which does not have easy ways to take input and display results. So LIBS2ML is completely unique due to its focus on the scalable second order methods, the hot research topic, and being based on MEX files. Thus it provides researchers a comprehensive environment to evaluate their ideas and it also provides machine learning practitioners an effective tool to deal with the large-scale learning problems. LIBS2ML is an open-source, highly efficient, extensible, scalable, readable, portable and easy to use library. The library can be downloaded from the URL: \url{https://github.com/jmdvinodjmd/LIBS2ML}.

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

Temporal action localization requires both precise boundary detection and computational efficiency. Current methods apply uniform computation across all temporal positions, wasting resources on easy boundaries while struggling with ambiguous ones. We address this through two complementary innovations: Boundary Distance Regression (BDR), which replaces classification-based boundary detection with signed-distance regression achieving 3.3--16.7$\times$ lower variance; and Adaptive Temporal Refinement (ATR), which allocates transformer depth continuously ($τ\in[0,1]$) to concentrate computation near difficult boundaries. On THUMOS14, our method achieves 56.5\% mAP@0.7 and 58.2\% average mAP@[0.3:0.7] with 151G FLOPs, using 36\% fewer FLOPs than ActionFormer++ (55.7\% mAP@0.7 at 235G). Compared to uniform baselines, we achieve +2.9\% mAP@0.7 (+1.8\% avg mAP, 5.4\% relative) with 24\% fewer FLOPs and 29\% lower latency, with particularly strong gains on short actions (+4.2\%, 8.6\% relative). Training requires 1.29$\times$ baseline FLOPs, but this one-time cost is amortized over many inference runs; knowledge distillation further reduces this to 1.1$\times$ while retaining 99.5\% accuracy. Our contributions include: (i) a theoretically-grounded distance formulation with information-theoretic analysis showing optimal variance scaling; (ii) a continuous depth allocation mechanism avoiding discrete routing complexity; and (iii) consistent improvements across four datasets with gains correlating with boundary heterogeneity.

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

Reward hacking in Reinforcement Learning (RL) systems poses a critical threat to the deployment of autonomous agents, where agents exploit flaws in reward functions to achieve high scores without fulfilling intended objectives. Despite growing awareness of this problem, systematic detection and mitigation approaches remain limited. This paper presents a large-scale empirical study of reward hacking across diverse RL environments and algorithms. We analyze 15,247 training episodes across 15 RL environments (Atari, MuJoCo, custom domains) and 5 algorithms (PPO, SAC, DQN, A3C, Rainbow), implementing automated detection algorithms for six categories of reward hacking: specification gaming, reward tampering, proxy optimization, objective misalignment, exploitation patterns, and wireheading. Our detection framework achieves 78.4% precision and 81.7% recall across environments, with computational overhead under 5%. Through controlled experiments varying reward function properties, we demonstrate that reward density and alignment with true objectives significantly impact hacking frequency ($p < 0.001$, Cohen's $d = 1.24$). We validate our approach through three simulated application studies representing recommendation systems, competitive gaming, and robotic control scenarios. Our mitigation techniques reduce hacking frequency by up to 54.6% in controlled scenarios, though we find these trade-offs are more challenging in practice due to concept drift, false positive costs, and adversarial adaptation. All detection algorithms, datasets, and experimental protocols are publicly available to support reproducible research in RL safety.

Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma

The integration of Large Language Models (LLMs) with computer vision is profoundly transforming perception tasks like image segmentation. For intelligent transportation systems (ITS), where accurate scene understanding is critical for safety and efficiency, this new paradigm offers unprecedented capabilities. This survey systematically reviews the emerging field of LLM-augmented image segmentation, focusing on its applications, challenges, and future directions within ITS. We provide a taxonomy of current approaches based on their prompting mechanisms and core architectures, and we highlight how these innovations can enhance road scene understanding for autonomous driving, traffic monitoring, and infrastructure maintenance. Finally, we identify key challenges, including real-time performance and safety-critical reliability, and outline a perspective centered on explainable, human-centric AI as a prerequisite for the successful deployment of this technology in next-generation transportation systems.

Sukhdeep Singh, Sudhir Rohilla, Anuj Sharma

Deep learning expresses a category of machine learning algorithms that have the capability to combine raw inputs into intermediate features layers. These deep learning algorithms have demonstrated great results in different fields. Deep learning has particularly witnessed for a great achievement of human level performance across a number of domains in computer vision and pattern recognition. For the achievement of state-of-the-art performances in diverse domains, the deep learning used different architectures and these architectures used activation functions to perform various computations between hidden and output layers of any architecture. This paper presents a survey on the existing studies of deep learning in handwriting recognition field. Even though the recent progress indicates that the deep learning methods has provided valuable means for speeding up or proving accurate results in handwriting recognition, but following from the extensive literature survey, the present study finds that the deep learning has yet to revolutionize more and has to resolve many of the most pressing challenges in this field, but promising advances have been made on the prior state of the art. Additionally, an inadequate availability of labelled data to train presents problems in this domain. Nevertheless, the present handwriting recognition survey foresees deep learning enabling changes at both bench and bedside with the potential to transform several domains as image processing, speech recognition, computer vision, machine translation, robotics and control, medical imaging, medical information processing, bio-informatics, natural language processing, cyber security, and many others.

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

Traffic crash detection in long-form surveillance videos is essential for improving emergency response and infrastructure planning, yet remains difficult due to the brief and infrequent nature of crash events. We present \textbf{HybridMamba}, a novel architecture integrating visual transformers with state-space temporal modeling to achieve high-precision crash time localization. Our approach introduces multi-level token compression and hierarchical temporal processing to maintain computational efficiency without sacrificing temporal resolution. Evaluated on a large-scale dataset from the Iowa Department of Transportation, HybridMamba achieves a mean absolute error of \textbf{1.50 seconds} for 2-minute videos ($p<0.01$ compared to baselines), with \textbf{65.2%} of predictions falling within one second of the ground truth. It outperforms recent video-language models (e.g., TimeChat, VideoLLaMA-2) by up to 3.95 seconds while using significantly fewer parameters (3B vs. 13--72B). Our results demonstrate effective temporal localization across various video durations (2--40 minutes) and diverse environmental conditions, highlighting HybridMamba's potential for fine-grained temporal localization in traffic surveillance while identifying challenges that remain for extended deployment.

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

Integrating large language models (LLMs) as priors in reinforcement learning (RL) offers significant advantages but comes with substantial computational costs. We present a principled cache-efficient framework for posterior sampling with LLM-derived priors that dramatically reduces these costs while maintaining high performance. At the core of our approach is an adaptive caching mechanism, where cache parameters are meta-optimized using surrogate gradients derived from policy performance. This design enables efficient inference across both discrete text environments (e.g., TextWorld, ALFWorld) and continuous control domains (e.g., MuJoCo), achieving a 3.8--4.7$\times$ reduction in LLM queries and 4.0--12.0$\times$ lower median latencies (85--93\,ms on a consumer GPU) while retaining 96--98\% of uncached performance. Our theoretical analysis provides KL divergence bounds on approximation quality, validated empirically. The framework extends to offline RL, where our CQL-Prior variant improves performance by 14--29\% and reduces training time by 38--40\%. Extensive evaluations across a diverse suite of eight tasks demonstrate the generalizability and practical viability of LLM-guided RL in resource-constrained settings.

Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma

We introduce Sequential-EDFL (Empirical Dynamic Formal Lift), applying anytime-valid sequential testing to language model generation stopping. Our approach tracks information lift -- the log-likelihood ratio between full models and deliberately weakened "skeleton" baselines -- using self-normalized empirical-Bernstein e-processes that provide formal delta-level error control regardless of stopping time. We handle unknown centering through online mean estimation, combine multiple parameters via mixture e-processes, and support adaptive resets under distributional drift. On six benchmarks, Sequential-EDFL reduces generation by 22-28% vs. sequential baselines while maintaining delta-level control with 12% computational overhead. We introduce automated skeletons (distilled submodels, randomized logits) and show robustness across skeleton families. Composing EDFL with a lightweight correctness gate (sentence boundaries + verifier) improves end-task correctness while preserving anytime-valid guarantees by only delaying stopping. Our certificates control information sufficiency, not factual correctness -- 10.9% of stopped sequences remain incorrect even with the gate (13.2-22.7% without it). EDFL serves as a first-stage filter reducing verification burden by 83%, not as a standalone solution for safety-critical domains.

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

Sparse-reward reinforcement learning (RL) remains fundamentally hard: without structure, any agent needs $Ω(|\mathcal{S}||\mathcal{A}|/p)$ samples to recover rewards. We introduce Policy-Aware Matrix Completion (PAMC) as a first concrete step toward a structural reward learning framework. Our key idea is to exploit approximate low-rank + sparse structure in the reward matrix, under policy-biased (MNAR) sampling. We prove recovery guarantees with inverse-propensity weighting, and establish a visitation-weighted error-to-regret bound linking completion error to control performance. Importantly, when assumptions weaken, PAMC degrades gracefully: confidence intervals widen and the algorithm abstains, ensuring safe fallback to exploration. Empirically, PAMC improves sample efficiency across Atari-26 (10M steps), DM Control, MetaWorld MT50, D4RL offline RL, and preference-based RL benchmarks, outperforming DrQ-v2, DreamerV3, Agent57, T-REX/D-REX, and PrefPPO under compute-normalized comparisons. Our results highlight PAMC as a practical and principled tool when structural rewards exist, and as a concrete first instantiation of a broader structural reward learning perspective.

Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma

The reasoning processes of large language models often lack faithfulness; a model may generate a correct answer while relying on a flawed or irrelevant reasoning trace. This behavior, a direct consequence of training objectives that solely reward final-answer correctness, severely undermines the trustworthiness of these models in high-stakes domains. This paper introduces \textbf{Counterfactual Sensitivity Regularization (CSR)}, a novel training objective designed to forge a strong, causal-like dependence between a model's output and its intermediate reasoning steps. During training, CSR performs automated, operator-level interventions on the generated reasoning trace (e.g., swapping ``+'' with ``-'') to create a minimally-perturbed counterfactual. A regularization term then penalizes the model if this logically flawed trace still yields the original answer. Our efficient implementation adds only 8.7\% training overhead through warm-start curriculum and token-subset optimization. We evaluate faithfulness using \textbf{Counterfactual Outcome Sensitivity (COS)}, a metric quantifying how sensitive the final answer is to such logical perturbations. Across diverse structured reasoning benchmarks -- arithmetic (GSM8K), logical deduction (ProofWriter), multi-hop QA (HotpotQA), and code generation (MBPP) -- models trained with CSR demonstrate a vastly superior trade-off between accuracy and faithfulness. CSR improves faithfulness over standard fine-tuning and process supervision by up to 70 percentage points, with this learned sensitivity generalizing to larger models and enhancing the performance of inference-time techniques like self-consistency.

Sudesh Bhagat, Raghupathi Kandiboina, Ibne Farabi Shihab et al.

Road traffic crashes are a significant global cause of fatalities, emphasizing the urgent need for accurate crash data to enhance prevention strategies and inform policy development. This study addresses the challenge of alcohol inference mismatch (AIM) by employing database narrative alignment to identify AIM in crash data. A framework was developed to improve data quality in crash management systems and reduce the percentage of AIM crashes. Utilizing the BERT model, the analysis of 371,062 crash records from Iowa (2016-2022) revealed 2,767 AIM incidents, resulting in an overall AIM percentage of 24.03%. Statistical tools, including the Probit Logit model, were used to explore the crash characteristics affecting AIM patterns. The findings indicate that alcohol-related fatal crashes and nighttime incidents have a lower percentage of the mismatch, while crashes involving unknown vehicle types and older drivers are more susceptible to mismatch. The geospatial cluster as part of this study can identify the regions which have an increased need for education and training. These insights highlight the necessity for targeted training programs and data management teams to improve the accuracy of crash reporting and support evidence-based policymaking.

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

Quantum machine learning for spin and molecular systems faces critical challenges of scarce labeled data and computationally expensive simulations. To address these limitations, we introduce Hamiltonian-Masked Autoencoding (HMAE), a novel self-supervised framework that pre-trains transformers on unlabeled quantum Hamiltonians, enabling efficient few-shot transfer learning. Unlike random masking approaches, HMAE employs a physics-informed strategy based on quantum information theory to selectively mask Hamiltonian terms based on their physical significance. Experiments on 12,500 quantum Hamiltonians (60% real-world, 40% synthetic) demonstrate that HMAE achieves 85.3% $\pm$ 1.5% accuracy in phase classification and 0.15 $\pm$ 0.02 eV MAE in ground state energy prediction with merely 10 labeled examples - a statistically significant improvement (p < 0.01) over classical graph neural networks (78.1% $\pm$ 2.1%) and quantum neural networks (76.8% $\pm$ 2.3%). Our method's primary advantage is exceptional sample efficiency - reducing required labeled examples by 3-5x compared to baseline methods - though we emphasize that ground truth values for fine-tuning and evaluation still require exact diagonalization or tensor networks. We explicitly acknowledge that our current approach is limited to small quantum systems (specifically limited to 12 qubits during training, with limited extension to 16-20 qubits in testing) and that, while promising within this regime, this size restriction prevents immediate application to larger systems of practical interest in materials science and quantum chemistry.

Anuj Sharma, Sukhdeep Singh, S Ratna

The graph neural networks has been proved to be an efficient machine learning technique in real life applications. The handwritten recognition is one of the useful area in real life use where both offline and online handwriting recognition are required. The chain code as feature extraction technique has shown significant results in literature and we have been able to use chain codes with graph neural networks. To the best of our knowledge, this work presents first time a novel combination of handwritten trajectories features as chain codes and graph neural networks together. The handwritten trajectories for offline handwritten text has been evaluated using recovery of drawing order, whereas online handwritten trajectories are directly used with chain codes. Our results prove that present combination surpass previous results and minimize error rate in few epochs only.

Charanjeet, Anuj Sharma

The second order method as Newton Step is a suitable technique in Online Learning to guarantee regret bound. The large data is a challenge in Newton method to store second order matrices as hessian. In this paper, we have proposed an modified online Newton step that store first and second order matrices of dimension m (classes) by d (features). we have used element wise arithmetic operation to retain matrices size same. The modified second order matrix size results in faster computations. Also, the mistake rate is at par with respect to popular methods in literature. The experiments outcome indicate that proposed method could be helpful to handle large multi class datasets in common desktop machines using second order method as Newton step.

Charanjeet, Anuj Sharma

Online learning makes sequence of decisions with partial data arrival where next movement of data is unknown. In this paper, we have presented a new technique as multiple times weight updating that update the weight iteratively forsame instance. The proposed technique analyzed with popular state-of-art algorithms from literature and experimented using established tool. The results indicates that mistake rate reduces to zero or close to zero for various datasets and algorithms. The overhead running cost is not too expensive and achieving mistake rate close to zero further strengthen the proposed technique. The present work include bound nature of weight updating for single instance and achieve optimal weight value. This proposed work could be extended to big datasets problems to reduce mistake rate in online learning environment. Also, the proposed technique could be helpful to meet real life challenges.

Vinod Kumar Chauhan, Anuj Sharma, Kalpana Dahiya

Nowadays, the major challenge in machine learning is the Big Data challenge. The big data problems due to large number of data points or large number of features in each data point, or both, the training of models have become very slow. The training time has two major components: Time to access the data and time to process (learn from) the data. So far, the research has focused only on the second part, i.e., learning from the data. In this paper, we have proposed one possible solution to handle the big data problems in machine learning. The idea is to reduce the training time through reducing data access time by proposing systematic sampling and cyclic/sequential sampling to select mini-batches from the dataset. To prove the effectiveness of proposed sampling techniques, we have used Empirical Risk Minimization, which is commonly used machine learning problem, for strongly convex and smooth case. The problem has been solved using SAG, SAGA, SVRG, SAAG-II and MBSGD (Mini-batched SGD), each using two step determination techniques, namely, constant step size and backtracking line search method. Theoretical results prove the same convergence for systematic sampling, cyclic sampling and the widely used random sampling technique, in expectation. Experimental results with bench marked datasets prove the efficacy of the proposed sampling techniques and show up to six times faster training.

Sanjog Ray, Anuj Sharma

In management education programmes today, students face a difficult time in choosing electives as the number of electives available are many. As the range and diversity of different elective courses available for selection have increased, course recommendation systems that help students in making choices about courses have become more relevant. In this paper we extend the concept of collaborative filtering approach to develop a course recommendation system. The proposed approach provides student an accurate prediction of the grade they may get if they choose a particular course, which will be helpful when they decide on selecting elective courses, as grade is an important parameter for a student while deciding on an elective course. We experimentally evaluate the collaborative filtering approach on a real life data set and show that the proposed system is effective in terms of accuracy.