30 citations · 90 across the 24 of their papers we have counts for
25 papers
Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation
Deepak Sridhar, Yi Li, Kartikeya Bhardwaj +7
Prompt learning is a popular method for adapting foundation models, but learned prompts are typically task-specific and fail to generalize to new classes, domains, or compositions…
PipeFlow: Pipelined Processing and Motion-Aware Frame Selection for Long-Form Video Editing
Mustafa Munir, Md Mostafijur Rahman, Kartikeya Bhardwaj +2
Long-form video editing poses unique challenges due to the exponential increase in the computational cost from joint editing and Denoising Diffusion Implicit Models (DDIM) inversio…
ObjectAlign: Neuro-Symbolic Object Consistency Verification and Correction
Mustafa Munir, Harsh Goel, Xiwen Wei +6
Video editing and synthesis often introduce object inconsistencies, such as frame flicker and identity drift that degrade perceptual quality. To address these issues, we introduce…
Video Reasoning without Training
Deepak Sridhar, Kartikeya Bhardwaj, Jeya Pradha Jeyaraj +3
Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought, resulting in substantial computational overhead duri…
SubZero: Composing Subject, Style, and Action via Zero-Shot Personalization
Shubhankar Borse, Kartikeya Bhardwaj, Mohammad Reza Karimi Dastjerdi +8
Diffusion models are increasingly popular for generative tasks, including personalized composition of subjects and styles. While diffusion models can generate user-specified subjec…
Rapid Switching and Multi-Adapter Fusion via Sparse High Rank Adapters
Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi +9
In this paper, we propose Sparse High Rank Adapters (SHiRA) that directly finetune 1-2% of the base model weights while leaving others unchanged, thus, resulting in a highly sparse…
FouRA: Fourier Low Rank Adaptation
Shubhankar Borse, Shreya Kadambi, Nilesh Prasad Pandey +7
While Low-Rank Adaptation (LoRA) has proven beneficial for efficiently fine-tuning large models, LoRA fine-tuned text-to-image diffusion models lack diversity in the generated imag…
Sparse High Rank Adapters
Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi +9
Low Rank Adaptation (LoRA) has gained massive attention in the recent generative AI research. One of the main advantages of LoRA is its ability to be fused with pretrained models,…
Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models
Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi +3
Large generative models such as large language models (LLMs) and diffusion models have revolutionized the fields of NLP and computer vision respectively. However, their slow infere…
ZiCo-BC: A Bias Corrected Zero-Shot NAS for Vision Tasks
Kartikeya Bhardwaj, Hsin-Pai Cheng, Sweta Priyadarshi +1
Zero-Shot Neural Architecture Search (NAS) approaches propose novel training-free metrics called zero-shot proxies to substantially reduce the search time compared to the tradition…
Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities
Guihong Li, Duc Hoang, Kartikeya Bhardwaj +3
Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process. The key idea behind zero-…
TIPS: Topologically Important Path Sampling for Anytime Neural Networks
Guihong Li, Kartikeya Bhardwaj, Yuedong Yang +1
Anytime neural networks (AnytimeNNs) are a promising solution to adaptively adjust the model complexity at runtime under various hardware resource constraints. However, the manuall…
ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients
Guihong Li, Yuedong Yang, Kartikeya Bhardwaj +1
Neural Architecture Search (NAS) is widely used to automatically obtain the neural network with the best performance among a large number of candidate architectures. To reduce the…
Restructurable Activation Networks
Kartikeya Bhardwaj, James Ward, Caleb Tung +6
Is it possible to restructure the non-linear activation functions in a deep network to create hardware-efficient models? To address this question, we propose a new paradigm called…
Super-Efficient Super Resolution for Fast Adversarial Defense at the Edge
Kartikeya Bhardwaj, Dibakar Gope, James Ward +2
Autonomous systems are highly vulnerable to a variety of adversarial attacks on Deep Neural Networks (DNNs). Training-free model-agnostic defenses have recently gained popularity d…
Collapsible Linear Blocks for Super-Efficient Super Resolution
Kartikeya Bhardwaj, Milos Milosavljevic, Liam O'Neil +6
With the advent of smart devices that support 4K and 8K resolution, Single Image Super Resolution (SISR) has become an important computer vision problem. However, most super resolu…
New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design
Kartikeya Bhardwaj, Wei Chen, Radu Marculescu
In this paper, we first highlight three major challenges to large-scale adoption of deep learning at the edge: (i) Hardware-constrained IoT devices, (ii) Data security and privacy…
FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning
Wei Chen, Kartikeya Bhardwaj, Radu Marculescu
In this paper, we identify a new phenomenon called activation-divergence which occurs in Federated Learning (FL) due to data heterogeneity (i.e., data being non-IID) across multipl…
EdgeAI: A Vision for Deep Learning in IoT Era
Kartikeya Bhardwaj, Naveen Suda, Radu Marculescu
The significant computational requirements of deep learning present a major bottleneck for its large-scale adoption on hardware-constrained IoT-devices. Here, we envision a new par…
How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections?
Kartikeya Bhardwaj, Guihong Li, Radu Marculescu
DenseNets introduce concatenation-type skip connections that achieve state-of-the-art accuracy in several computer vision tasks. In this paper, we reveal that the topology of the c…
Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT
Kartikeya Bhardwaj, Chingyi Lin, Anderson Sartor +1
Model compression has emerged as an important area of research for deploying deep learning models on Internet-of-Things (IoT). However, for extremely memory-constrained scenarios,…
Dream Distillation: A Data-Independent Model Compression Framework
Kartikeya Bhardwaj, Naveen Suda, Radu Marculescu
Model compression is eminently suited for deploying deep learning on IoT-devices. However, existing model compression techniques rely on access to the original or some alternate da…
On Network Science and Mutual Information for Explaining Deep Neural Networks
Brian Davis, Umang Bhatt, Kartikeya Bhardwaj +2
In this paper, we present a new approach to interpret deep learning models. By coupling mutual information with network science, we explore how information flows through feedforwar…
Climate Anomalies vs Air Pollution: Carbon Emissions and Anomaly Networks
Anshul Goyal, Kartikeya Bhardwaj, Radu Marculescu
This project aims to shed light on how man-made carbon emissions are affecting global wind patterns by looking for temporal and geographical correlations between carbon emissions,…