Useful resource-constrained picture technology and visible understanding: an interview with Aniket Roy

Within the newest in our collection of interviews assembly the AAAI/SIGAI Doctoral Consortium individuals, we caught up with Aniket Roy to search out out extra about his analysis on generative fashions for laptop imaginative and prescient duties.

Inform us a bit about your PhD – the place did you examine, and what was the subject of your analysis?

I not too long ago accomplished my PhD in Pc Science at Johns Hopkins College, the place I labored below the supervision of Bloomberg Distinguished Professor Rama Chellappa. My analysis primarily targeted on growing strategies for resource-constrained picture technology and visible understanding. Particularly, I explored how trendy generative fashions might be tailored to function effectively whereas sustaining robust efficiency.

Throughout my PhD, I labored broadly on the intersection of generative AI, multimodal studying, and few-shot studying. A lot of my work concerned designing methods that allow fashions to study new ideas or carry out complicated visible duties with restricted information or computational assets. This included analysis on diffusion fashions, personalised picture technology, and multimodal illustration studying. Total, my work goals to make superior imaginative and prescient and generative AI programs extra adaptable, environment friendly, and sensible for real-world functions.

Might you give us an outline of the analysis you carried out throughout your PhD?

Throughout my PhD, my analysis broadly targeted on enhancing the adaptability, effectivity, and high quality of contemporary generative fashions for laptop imaginative and prescient duties. The fast progress in generative AI–significantly diffusion fashions and imaginative and prescient–language fashions–has created new alternatives to handle long-standing challenges similar to information shortage, controllable technology, and personalised picture synthesis. My work aimed to develop strategies that enable these massive fashions to adapt successfully with restricted information and computational assets whereas sustaining excessive visible constancy.

One line of my analysis addressed studying in data-constrained settings. For instance, I proposed FeLMi, a few-shot studying framework that leverages uncertainty-guided exhausting mixup methods to enhance robustness and generalization when solely a small variety of labeled samples can be found. Constructing on this concept of enhancing coaching information high quality, I additionally developed Cap2Aug, which introduces caption-guided multimodal augmentation. This method makes use of textual descriptions to information artificial picture technology, enhancing visible variety whereas lowering the area hole between actual and generated information.

Overview of Cap2Aug.

One other side of my analysis targeted on enhancing the perceptual high quality of pictures generated by diffusion fashions. On this route, I proposed DiffNat, a plug-and-play regularization methodology primarily based on the kurtosis-concentration property noticed in pure pictures. By incorporating this precept into diffusion fashions by means of a KC loss, the generated pictures exhibit extra pure texture statistics and improved perceptual realism, which additionally advantages downstream imaginative and prescient duties.

A significant a part of my work explored personalization and environment friendly adaptation of huge generative fashions. I launched DuoLoRA, a parameter-efficient framework for composing low-rank adapters that permits fine-grained management over content material and elegance with out requiring full retraining of the bottom mannequin. I additional prolonged personalization to zero-shot settings utilizing a training-free textual inversion method that permits arbitrary objects to be personalized straight throughout technology. Lastly, I proposed MultiLFG, a frequency-guided multi-LoRA composition framework that makes use of wavelet-domain representations and timestep-aware weighting to allow correct and training-free fusion of a number of ideas in diffusion fashions.

Overview of DuoLoRA.

Total, my analysis contributes towards constructing generative programs which might be extra environment friendly, adaptable, and controllable, enabling high-quality picture technology and understanding even in data-limited or resource-constrained eventualities.

Was there a selected challenge or a side of your analysis that was significantly attention-grabbing?

One challenge that I discovered significantly attention-grabbing throughout my PhD is DiffNat, which was revealed in TMLR 2025. Diffusion fashions have turn into the spine of many trendy generative AI programs and have achieved spectacular ends in producing and enhancing real looking pictures. Nonetheless, enhancing the perceptual high quality and naturalness of generated pictures stays an essential problem.

Overview of DiffNat.

On this work, we launched a easy however efficient regularization approach known as the kurtosis focus (KC) loss, which might be built-in into customary diffusion mannequin pipelines as a plug-and-play part. The concept was impressed by a statistical property of pure pictures: when a picture is decomposed into totally different band-pass filtered variations–for instance utilizing the Discrete Wavelet Remodel–the kurtosis values throughout these frequency bands are typically comparatively constant. In distinction, generated pictures usually present massive discrepancies throughout these bands. Our methodology reduces the hole between the best and lowest kurtosis values throughout the frequency elements, encouraging the generated pictures to comply with extra pure picture statistics.

As well as, we launched a condition-agnostic perceptual steerage technique throughout inference that additional improves picture constancy with out requiring extra coaching alerts. We evaluated the method throughout a number of various duties, together with personalised few-shot finetuning with textual content steerage, unconditional picture technology, picture super-resolution, and blind face restoration. Throughout these duties, incorporating the KC loss and perceptual steerage persistently improved perceptual high quality, measured by means of metrics similar to FID and MUSIQ, in addition to by means of human analysis.

What I significantly preferred about this challenge is that it connects classical picture statistics with trendy diffusion fashions. It exhibits that comparatively easy statistical insights about pure pictures can nonetheless play a robust position in enhancing massive generative fashions.

What are your plans for constructing on the PhD – the place are you working now and what’s going to you be investigating subsequent?

Throughout my PhD, I found that I genuinely benefit from the means of analysis–particularly the second when an instinct or concept seems to work in observe. That means of exploring new concepts and pushing the boundaries of what we all know is one thing I discover very motivating.

To proceed pursuing this, I can be becoming a member of NEC Laboratories America as a Analysis Scientist. On this position, I hope to construct on my PhD work by growing new strategies for generative fashions and exploring how these fashions can work together with broader multimodal programs. Particularly, I’m fascinated by advancing analysis on the intersection of generative fashions, imaginative and prescient–language–motion fashions, and embodied AI. Extra broadly, my aim is to contribute to the event of clever programs that may perceive, generate, and work together with the visible world extra successfully, whereas additionally persevering with to push ahead the scientific understanding of those fashions.

I’m fascinated by how you bought into the sphere. What impressed you to check laptop imaginative and prescient and machine studying?

My curiosity in laptop imaginative and prescient and machine studying began throughout my undergraduate research, after I took programs in sign processing and picture processing. I discovered these topics significantly fascinating as a result of they allowed you to experiment with algorithms and instantly see their results on pictures. That visible and intuitive side made the sphere very partaking, and it helped me admire how mathematical ideas can straight translate into significant visible outcomes.

On the similar time, I used to be additionally interested by how the human mind processes visible data—how we’re capable of acknowledge objects, perceive scenes, and interpret complicated visible alerts so effortlessly. That curiosity led me to wonder if we may design computational fashions that mimic points of human notion and allow machines to know visible information in an identical approach.

A significant affect throughout this time was my professor, Dr. Kuntal Ghosh, who inspired me to assume extra deeply about these issues and method them with a scientific mindset. His mentorship performed an essential position in shaping my curiosity in analysis. Since then, that curiosity about visible notion and clever programs has continued to drive my work in laptop imaginative and prescient and machine studying.

What was your expertise of the Doctoral Consortium at AAAI?

Sadly, I used to be not capable of attend the AAAI Doctoral Consortium in particular person resulting from visa-related points. Nonetheless, a colleague kindly helped current my poster on my behalf throughout the occasion. Regardless that I couldn’t be there bodily, I used to be very inspired by the response my work acquired. A number of researchers reached out to me after seeing the poster, and we had some very insightful discussions concerning the concepts and potential future instructions of the analysis. In that sense, I nonetheless discovered the expertise fairly rewarding. The Doctoral Consortium is a good platform for sharing early-stage concepts, receiving suggestions from the group, and connecting with different researchers engaged on associated issues. I appreciated the chance to interact with individuals who had been within the work, and people interactions helped spark new views and collaborations.

Might you inform us an attention-grabbing (non-AI associated) truth about you?

Exterior of analysis, I’m an enormous fan of music and stand-up comedy, and I actually take pleasure in touring each time I get the prospect. Exploring new locations, cultures, and views is one thing I discover refreshing—it’s an effective way to recharge and keep curious concerning the world past work. I additionally take pleasure in writing poetic satire infrequently, and I often carry out it. It’s a enjoyable inventive outlet that permits me to combine humor and storytelling, which is kind of totally different from the analytical nature of the analysis work I often do.

About Aniket Roy

Aniket is at the moment a Analysis Scientist at NEC Labs America. He obtained his PhD from the Pc Science dept at Johns Hopkins College below the steerage of Bloomberg Distinguished Professor Prof. Rama Chellappa. Previous to that, he did a Grasp’s from Indian Institute of Know-how Kharagpur. He was acknowledged with the Greatest Paper Award at IWDW 2016 and the Markose Thomas Memorial Award for the very best analysis paper on the Grasp’s degree. Throughout PhD, he explored domains of few-shot studying, multimodal studying, diffusion fashions, LLMs, LoRA merging with publications in main venues similar to NeurIPS, ICCV, TMLR, WACV, CVPR and likewise 3 US patents filed. Throughout his PhD, he additionally gained industrial expertise by means of a number of internships in Amazon, Qualcomm, MERL, and SRI Worldwide. He was awarded as an Amazon Fellow (2023-24) at JHU and chosen to take part in ICCV’25 and AAAI’26 doctoral consortium.