arXiv subjects

Manjesh Kumar Hanawal

Publications and source records attributed to Manjesh Kumar Hanawal.

At least 19 recordsLinked to original sources

arXiv2026

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference

Large Language Models (LLMs) have achieved remarkable success in natural language understanding and generation, but their deployment is constrained by high computational demands. Deploying smaller LLMs directly on the edge can circumvent this, but with degraded accuracy. Deploying smaller cloud-based big LLMs preserves performance, but at the cost of expensive per-token computation. We present a distributed inference framework, \our{}, that integrates speculative decoding (SD) across edge and cloud. A compact draft model deployed on the edge generates candidate tokens rapidly, and a large verifier model on the cloud validates these tokens in parallel. Accepted tokens are retained, while only rejections trigger verifier correction, substantially reducing the number of cloud queries. Our plug-and-play design shifts the bulk of computation to the edge, significantly lowers inference time and cloud cost, and preserves the accuracy of the big model without any retraining requirement. Our approach demonstrates a practical path toward scalable, cost-efficient, and accurate deployment of LLMs in real-world environments. Experimental results across multiple Natural Language Processing tasks using SpecBench and CNN/Dailymail datasets demonstrate that \our{} reduces the cloud model calls by $76\%$ with zero loss in accuracy as compared to the full model.

cs.AI↗

arXiv2026

Stochastic Multi-Armed Bandits with Limited Control Variates

Motivated by wireless networks where interference or channel state estimates provide partial insight into throughput, we study a variant of the classical stochastic multi-armed bandit problem in which the learner has limited access to auxiliary information. Recent work has shown that such auxiliary information, when available as control variates, can be used to get tighter confidence bounds, leading to lower regret. However, existing works assume that control variates are available in every round, which may not be realistic in several real-life scenarios. To address this, we propose UCB-LCV, an upper confidence bound (UCB) based algorithm that effectively combines the estimators obtained from rewards and control variates. When there is no control variate, UCB-LCV leads to a novel algorithm that we call UCB-NORMAL, outperforming its existing algorithms for the standard MAB setting with normally distributed rewards. Finally, we discuss variants of the proposed UCB-LCV that apply to general distributions and experimentally demonstrate that UCB-LCV outperforms existing bandit algorithms.

cs.LG↗

arXiv2026

FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference

Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration methods like distillation, trajectory truncation, and consistency approaches are static, require retraining, and often fail to generalize across tasks. We propose FastFlow, a plug-and-play adaptive inference framework that accelerates generation in flow matching models. FastFlow identifies denoising steps that produce only minor adjustments to the denoising path and approximates them without using the full neural network models used for velocity predictions. The approximation utilizes finite-difference velocity estimates from prior predictions to efficiently extrapolate future states, enabling faster advancements along the denoising path at zero compute cost. This enables skipping computation at intermediary steps. We model the decision of how many steps to safely skip before requiring a full model computation as a multi-armed bandit problem. The bandit learns the optimal skips to balance speed with performance. FastFlow integrates seamlessly with existing pipelines and generalizes across image generation, video generation, and editing tasks. Experiments demonstrate a speedup of over 2.6x while maintaining high-quality outputs. The source code for this work can be found at https://github.com/Div290/FastFlow.

cs.CV↗

arXiv2026

FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching

Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due to a large number of denoising steps limits their potential use in real-time or interactive applications. Existing acceleration methods, like distillation, truncation, or consistency training, either degrade quality, incur costly retraining, or lack generalization. We propose FlowCast, a training-free speculative generation framework that accelerates inference by exploiting the fact that FM models are trained to preserve constant velocity. FlowCast speculates future velocity by extrapolating current velocity without incurring additional time cost, and accepts it if it is within a mean-squared error threshold. This constant-velocity forecasting allows redundant steps in stable regions to be aggressively skipped while retaining precision in complex ones. FlowCast is a plug-and-play framework that integrates seamlessly with any FM model and requires no auxiliary networks. We also present a theoretical analysis and bound the worst-case deviation between speculative and full FM trajectories. Empirical evaluations demonstrate that FlowCast achieves $>2.5\times$ speedup in image generation, video generation, and editing tasks, outperforming existing baselines with no quality loss as compared to standard full generation.

cs.CV↗

arXiv2025

FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference

Vision-language Models (VLMs) have made significant strides in visual understanding and query response generation, but often face challenges of high computational cost and inference latency due to autoregressive decoding. In this work, we introduce an imitation-learning-based Self-Speculative Decoding (SSD) framework, named FastVLM, to address these limitations. Our approach employs a lightweight draft model for token generation in an autoregressive manner, while a full model verifies these tokens non-autoregressively. Accepted tokens proceed seamlessly, while rejected tokens are corrected by the full model and used to guide the draft model's refinement. Through an imitation network, FastVLM enhances the draft model by integrating deeper level insights from the full model's architecture. Also, it maintains the performance integrity of the full model while training the draft model, achieving a balance between efficiency and accuracy. Our method speeds up the inference process by 1.55-1.85x as compared to the final layer with minimal loss in performance.

cs.LG↗

arXiv2025

Cyber Warfare During Operation Sindoor: Malware Campaign Analysis and Detection Framework

Rapid digitization of critical infrastructure has made cyberwarfare one of the important dimensions of modern conflicts. Attacking the critical infrastructure is an attractive pre-emptive proposition for adversaries as it can be done remotely without crossing borders. Such attacks disturb the support systems of the opponents to launch any offensive activities, crippling their fighting capabilities. Cyberattacks during cyberwarfare can not only be used to steal information, but also to spread disinformation to bring down the morale of the opponents. Recent wars in Europe, Africa, and Asia have demonstrated the scale and sophistication that the warring nations have deployed to take the early upper hand. In this work, we focus on the military action launched by India, code-named Operation Sindoor, to dismantle terror infrastructure emanating from Pakistan and the cyberattacks launched by Pakistan. In particular, we study the malware used by Pakistan APT groups to deploy Remote Access Trojans in Indian systems. We provide details of the tactics and techniques used in the RAT deployment and develop a telemetry framework to collect necessary event logs using Osquery with a custom extension. Finally, we develop a detection rule that can be readily deployed to detect the presence of the RAT or any exploitation performed by the malware.

cs.CR↗

arXiv2025

Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability

Early-Exit Deep Neural Networks enable adaptive inference by allowing prediction at intermediary layers, significantly reducing computational costs and latency. Most of the early exit strategies greedily exit a sample at an intermediary layer if the confidence in class prediction exceeds a predefined threshold that is set using a static validation set. This is problematic as the model might be overconfident in a wrong class. Also, they are not robust to distribution shifts encountered in deployment, which can undermine model trustworthiness and accuracy. To address these challenges, we propose UAT that adapts the threshold for exit decisions using a Multi-Armed Bandit framework, enabling online, unsupervised adjustment of exit decisions. UAT makes decisions based on a new reward function that assesses predictive certainty and its reliability to balance computational efficiency and prediction quality while penalizing unnecessary late exits. We provide guarantees on risk achieved by UAT and validate its performance on diverse tasks spanning vision-language understanding, text generation, and classification. Our framework demonstrates consistent improvements in speedup (1.70-2.10x) with a minimal performance drop (<2%) as compared to full model performance. Our source code is available at https://github.com/Div290/UAT.

cs.LG↗

arXiv2025

Know What You Don't Know: Selective Prediction for Early Exit DNNs

Inference latency and trustworthiness of Deep Neural Networks (DNNs) are the bottlenecks in deploying them in critical applications like sensitive tasks. Early Exit (EE) DNNs overcome the latency issues by allowing samples to exit from intermediary layers if they attain `high' confidence scores on the predicted class. However, the DNNs are known to exhibit overconfidence, which can lead to many samples exiting early and render EE strategies untrustworthy. We use Selective Prediction (SP) to overcome this issue by checking the `hardness' of the samples rather than just relying on the confidence score alone. We propose SPEED, a novel approach that uses Deferral Classifiers (DCs) at each layer to check the hardness of samples before performing EEs. Specifically, the DCs identify if a sample is hard to predict at an intermediary layer, leading to hallucination, and defer it to an expert. Early detection of hard samples for inference prevents the wastage of computational resources and improves trust by deferring the hard samples to the expert. We demonstrate that EE aided with SP improves both accuracy and latency. Our method minimizes the risk of wrong prediction by $50\%$ with a speedup of $2.05\times$ as compared to the final layer. The anonymized source code is available at https://github.com/Div290/SPEED

cs.LG↗

arXiv2025

FREE: Fast and Robust Vision Language Models with Early Exits

In recent years, Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-Language tasks. However, their large size poses challenges for real-world applications where inference latency is a concern. To tackle this issue, we propose employing Early Exit (EE) strategies in VLMs. However, training exit classifiers in VLMs is challenging, particularly with limited labeled training data. To address this, we introduce FREE, an adversarial training approach within a GAN-based framework. Here, each exit consists of a transformer layer and a classifier. The transformer layer is adversarially trained to produce feature representations similar to the final layer, while a feature classifier serves as the discriminator. Our method focuses on performing input-adaptive inference that increases inference speed with minimal drop in performance. Experimental results demonstrate the effectiveness of our approach in enhancing accuracy and model robustness by mitigating overthinking and the phenomenon of mid-crisis that we highlight. We experimentally validate that our method speeds up the inference process by more than 1.51x while retaining comparable performance. The source code is available at https://github.com/Div290/FREE.

cs.LG↗

arXiv2025

BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts

Early Exit (EE) techniques have emerged as a means to reduce inference latency in Deep Neural Networks (DNNs). The latency improvement and accuracy in these techniques crucially depend on the criteria used to make exit decisions. We propose a new decision criterion where exit classifiers are treated as experts BEEM and aggregate their confidence scores. The confidence scores are aggregated only if neighbouring experts are consistent in prediction as the samples pass through them, thus capturing their ensemble effect. A sample exits when the aggregated confidence value exceeds a threshold. The threshold is set using the error rates of the intermediate exits aiming to surpass the performance of conventional DNN inference. Experimental results on the COCO dataset for Image captioning and GLUE datasets for various language tasks demonstrate that our method enhances the performance of state-of-the-art EE methods, achieving improvements in speed-up by a factor 1.5x to 2.1x. When compared to the final layer, its accuracy is comparable in harder Image Captioning and improves in the easier language tasks. The source code for this work is publicly available at https://github.com/Div290/BEEM1/tree/main

cs.LG↗

arXiv2025

A Survey of Early Exit Deep Neural Networks in NLP

Deep Neural Networks (DNNs) have grown increasingly large in size to achieve state of the art performance across a wide range of tasks. However, their high computational requirements make them less suitable for resource-constrained applications. Also, real-world datasets often consist of a mixture of easy and complex samples, necessitating adaptive inference mechanisms that account for sample difficulty. Early exit strategies offer a promising solution by enabling adaptive inference, where simpler samples are classified using the initial layers of the DNN, thereby accelerating the overall inference process. By attaching classifiers at different layers, early exit methods not only reduce inference latency but also improve the model robustness against adversarial attacks. This paper presents a comprehensive survey of early exit methods and their applications in NLP.

cs.LG↗

arXiv2024

Distributed Inference on Mobile Edge and Cloud: A Data-Cartography based Clustering Approach

The large size of DNNs poses a significant challenge for deployment on devices with limited resources, such as mobile, edge, and IoT platforms. To address this issue, a distributed inference framework can be utilized. In this framework, a small-scale DNN (initial layers) is deployed on mobile devices, a larger version on edge devices, and the full DNN on the cloud. Samples with low complexity (easy) can be processed on mobile, those with moderate complexity (medium) on edge devices, and high complexity (hard) samples on the cloud. Given that the complexity of each sample is unknown in advance, the crucial question in distributed inference is determining the sample complexity for appropriate DNN processing. We introduce a novel method named \our{}, which leverages the Data Cartography approach initially proposed for enhancing DNN generalization. By employing data cartography, we assess sample complexity. \our{} aims to boost accuracy while considering the offloading costs from mobile to edge/cloud. Our experimental results on GLUE datasets, covering a variety of NLP tasks, indicate that our approach significantly lowers inference costs by more than 43\% while maintaining a minimal accuracy drop of less than 0.5\% compared to performing all inferences on the cloud. The source code is available at https://anonymous.4open.science/r/DIMEC-1B04.

cs.DC↗

arXiv2024

DAdEE: Unsupervised Domain Adaptation in Early Exit PLMs

Pre-trained Language Models (PLMs) exhibit good accuracy and generalization ability across various tasks using self-supervision, but their large size results in high inference latency. Early Exit (EE) strategies handle the issue by allowing the samples to exit from classifiers attached to the intermediary layers, but they do not generalize well, as exit classifiers can be sensitive to domain changes. To address this, we propose Unsupervised Domain Adaptation in EE framework (DADEE) that employs multi-level adaptation using knowledge distillation. DADEE utilizes GAN-based adversarial adaptation at each layer to achieve domain-invariant representations, reducing the domain gap between the source and target domain across all layers. The attached exits not only speed up inference but also enhance domain adaptation by reducing catastrophic forgetting and mode collapse, making it more suitable for real-world scenarios. Experiments on tasks such as sentiment analysis, entailment classification, and natural language inference demonstrate that DADEE consistently outperforms not only early exit methods but also various domain adaptation methods under domain shift scenarios. The anonymized source code is available at https://github.com/Div290/DAdEE.

cs.CL↗

arXiv2024

CAPEEN: Image Captioning with Early Exits and Knowledge Distillation

Deep neural networks (DNNs) have made significant progress in recognizing visual elements and generating descriptive text in image-captioning tasks. However, their improved performance comes from increased computational burden and inference latency. Early Exit (EE) strategies can be used to enhance their efficiency, but their adaptation presents challenges in image captioning as it requires varying levels of semantic information for accurate predictions. To overcome this, we introduce CAPEEN to improve the performance of EE strategies using knowledge distillation. Inference in CAPEEN is completed at intermediary layers if prediction confidence exceeds a predefined value learned from the training data. To account for real-world deployments, where target distributions could drift from that of training samples, we introduce a variant A-CAPEEN to adapt the thresholds on the fly using Multiarmed bandits framework. Experiments on the MS COCO and Flickr30k datasets show that CAPEEN gains speedup of 1.77x while maintaining competitive performance compared to the final layer, and A-CAPEEN additionally offers robustness against distortions. The source code is available at https://github.com/Div290/CapEEN

cs.CV↗

arXiv2024

Distributed Inference on Mobile Edge and Cloud: An Early Exit based Clustering Approach

Recent advances in Deep Neural Networks (DNNs) have demonstrated outstanding performance across various domains. However, their large size is a challenge for deployment on resource-constrained devices such as mobile, edge, and IoT platforms. To overcome this, a distributed inference setup can be used where a small-sized DNN (initial few layers) can be deployed on mobile, a bigger version on the edge, and the full-fledged, on the cloud. A sample that has low complexity (easy) could be then inferred on mobile, that has moderate complexity (medium) on edge, and higher complexity (hard) on the cloud. As the complexity of each sample is not known beforehand, the following question arises in distributed inference: how to decide complexity so that it is processed by enough layers of DNNs. We develop a novel approach named DIMEE that utilizes Early Exit (EE) strategies developed to minimize inference latency in DNNs. DIMEE aims to improve the accuracy, taking into account the offloading cost from mobile to edge/cloud. Experimental validation on GLUE datasets, encompassing various NLP tasks, shows that our method significantly reduces the inference cost (> 43%) while maintaining a minimal drop in accuracy (< 0.3%) compared to the case where all the inference is made in cloud.

cs.LG↗

arXiv2024

FAIR: Filtering of Automatically Induced Rules

The availability of large annotated data can be a critical bottleneck in training machine learning algorithms successfully, especially when applied to diverse domains. Weak supervision offers a promising alternative by accelerating the creation of labeled training data using domain-specific rules. However, it requires users to write a diverse set of high-quality rules to assign labels to the unlabeled data. Automatic Rule Induction (ARI) approaches circumvent this problem by automatically creating rules from features on a small labeled set and filtering a final set of rules from them. In the ARI approach, the crucial step is to filter out a set of a high-quality useful subset of rules from the large set of automatically created rules. In this paper, we propose an algorithm (Filtering of Automatically Induced Rules) to filter rules from a large number of automatically induced rules using submodular objective functions that account for the collective precision, coverage, and conflicts of the rule set. We experiment with three ARI approaches and five text classification datasets to validate the superior performance of our algorithm with respect to several semi-supervised label aggregation approaches. Further, we show that achieves statistically significant results in comparison to existing rule-filtering approaches.

cs.LG↗

arXiv2024

CEEBERT: Cross-Domain Inference in Early Exit BERT

Pre-trained Language Models (PLMs), like BERT, with self-supervision objectives exhibit remarkable performance and generalization across various tasks. However, they suffer in inference latency due to their large size. To address this issue, side branches are attached at intermediate layers, enabling early inference of samples without requiring them to pass through all layers. However, the challenge is to decide which layer to infer and exit each sample so that the accuracy and latency are balanced. Moreover, the distribution of the samples to be inferred may differ from that used for training necessitating cross-domain adaptation. We propose an online learning algorithm named Cross-Domain Inference in Early Exit BERT (CeeBERT) that dynamically determines early exits of samples based on the level of confidence at each exit point. CeeBERT learns optimal thresholds from domain-specific confidence observed at intermediate layers on the fly, eliminating the need for labeled data. Experimental results on five distinct datasets with BERT and ALBERT models demonstrate CeeBERT's ability to improve latency by reducing unnecessary computations with minimal drop in performance. By adapting to the threshold values, CeeBERT can speed up the BERT/ALBERT models by $2\times$ - $3.5\times$ with minimal drop in accuracy.

cs.CL↗

arXiv2024

I-SplitEE: Image classification in Split Computing DNNs with Early Exits

The recent advances in Deep Neural Networks (DNNs) stem from their exceptional performance across various domains. However, their inherent large size hinders deploying these networks on resource-constrained devices like edge, mobile, and IoT platforms. Strategies have emerged, from partial cloud computation offloading (split computing) to integrating early exits within DNN layers. Our work presents an innovative unified approach merging early exits and split computing. We determine the 'splitting layer', the optimal depth in the DNN for edge device computations, and whether to infer on edge device or be offloaded to the cloud for inference considering accuracy, computational efficiency, and communication costs. Also, Image classification faces diverse environmental distortions, influenced by factors like time of day, lighting, and weather. To adapt to these distortions, we introduce I-SplitEE, an online unsupervised algorithm ideal for scenarios lacking ground truths and with sequential data. Experimental validation using Caltech-256 and Cifar-10 datasets subjected to varied distortions showcases I-SplitEE's ability to reduce costs by a minimum of 55% with marginal performance degradation of at most 5%.

cs.LG↗