(intro)=
# Naresh Kumar Devulapally

<div class="nav-links">
  <a href="./intro.html">About Me</a>
  <a href="./publications.html">Publications</a>
  <a href="./course_notes/my-teaching-philosophy.html">My Teaching</a>
  <a href="./research_notes/intro.html">Research Notes</a>
</div>

---

I am a PhD candidate (chair's fellow) at UB's CVML Lab in the Computer Science Department at University at Buffalo. My research is advised by [Dr. Vishnu Lokhande](https://vlokhande-ub.github.io). 

```{admonition} My Research
:class: tip
My research focuses on **enhancing reliability, robustness and alignment in Generative AI models**. My goal is to build Responsible, Trustworthy AI models.
```

## Updates

<div class="news-scroll" role="region" aria-label="Recent news">
  <ul class="news-list">
    <li>
      👨🏻‍🏫 Invited <a href="./guest_lectures/spring_2026/intro.html">Guest Lectures</a> on Diffusion Models in CSE 555: Pattern Recognition course at UB.
      <ul>
        <li><em>Instructor: Prof. Ifeoma Nwogu.</em></li>
      </ul>
    </li>
    <li>
      🎉 <a href="#">Token-to-Token Similarity Reduction in dLLMs for Edit-Friendly Hard Prompt Inversion</a> is accepted to <strong>CVPR 2026</strong>!
      <ul>
        <!-- <li>(with: <a href="#">Adobe Research</a>). <strong><u>Accepted at CVPR 2026</u></strong> 🎉</li> -->
      </ul>
    </li>
    <li>
      👨🏻‍🏫 Invited <a href="#">Guest Lectures</a> on CNNs and Diffusion Models in CSE 573: Computer Vision course at UB. 
      <ul>
        <li><em>Instructor: Prof. Junsong Yuan.</em></li>
      </ul>
    </li>
    <li>
      🎉 Recipient of <a href="https://arc.net/l/quote/fxgsjydt">CSE Graduate Teaching Award</a> for my Summer CVIP course at UB.
      <ul>
        <!-- <li>(with: <a href="#">Adobe Research</a>). <strong><u>Accepted at CVPR 2026</u></strong> 🎉</li> -->
      </ul>
    </li>
    <li>
      🎉 Passed Oral Qualifying Examination at UB!
      <ul>
        <!-- <li>(with: <a href="#">Adobe Research</a>). <strong><u>Accepted at CVPR 2026</u></strong> 🎉</li> -->
      </ul>
    </li>
    <li>
      👨🏻‍🏫 Taught CSE 4/573: <a href="https://naresh-ub.github.io/cvip-summer25">Computer Vision and Image Processing</a> at UB, <strong>Summer 2025</strong>.
      <ul>
        <!-- <li>(with: <a href="#">Adobe Research</a>). <strong><u>Accepted at CVPR 2026</u></strong> 🎉</li> -->
      </ul>
    </li>
    <li>
      🎉 <a href="https://openaccess.thecvf.com/content/ICCV2025/html/Devulapally_Your_Text_Encoder_Can_Be_An_Object-Level_Watermarking_Controller_ICCV_2025_paper.html">Your Text Encoder can be an Object-Level Watermarking Controller</a> is accepted at <strong>ICCV 2025</strong>!
      <ul>
        <li>(with: <a href="https://research.adobe.com/publication/your-text-encoder-can-be-an-object-level-watermarking-controller/">Adobe Research</a>, <a href="https://arc.net/l/quote/zgjwmrzi">Prof. Siwei Lyu</a>).</li>
      </ul>
    </li>
    <li>
      🎉 <a href="https://dl.acm.org/doi/10.1145/3746027.3755112">Latent Diffusion Unlearning: Protecting Against Unauthorized Personalization Through Trajectory Shifted Perturbations</a> is accepted at <strong>ACM MM 2025</strong>!
      <ul>
        <li>(with: Adobe Research, <a href="https://arc.net/l/quote/sfgeqwly">CVG at UMBC</a>).</li>
      </ul>
    </li>
    <!-- <li>
      <a href="#">Hallucination Mitigation in Diffusion Models.</a>
      <ul>
        <li>(with: <a href="https://cse.buffalo.edu/~doermann/index.html">Dr. David Doermann</a>). <em>(Under Review)</em></li>
      </ul>
    </li> -->
  </ul>
</div>

---

**My collaborators**:

<div style="display: flex; justify-content: center; align-items: center;">
  <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(120px, 1fr)); gap: 10px; max-width: 500px;">
    <a href="https://contentauthenticity.org/" target="_blank" rel="noopener noreferrer">
      <img src="figures/images/adobe_logo.png" alt="Adobe" style="width:100%; border-radius:8px;">
    </a>
    <a href="https://arc.net/l/quote/agrivvzx" target="_blank" rel="noopener noreferrer">
      <img src="figures/images/cvg_horz.png" alt="CVG" style="width:100%; border-radius:8px;">
    </a>
  </div>
</div>


---

Before joining UB as a PhD Candidate, I completed my Masters (Thesis) in CS at UB. My thesis, [Towards Generalizable and Robust Multimodal ML models](https://cse.buffalo.edu/tech-reports/2024-11.pdf) for Video Emotion Recognition is co-supervised of [Dr. Junsong Yuan](https://cse.buffalo.edu/~jsyuan/) and [Dr. Sreyasee Das Bhattacharjee](https://cse.buffalo.edu/~sreyasee/). During my masters at UB, my research was published at venues such as `ACM Multimedia 2023, BigMM 2024, and ICME 2024`. My research project PRIMAL (Privacy Preserving Multimodal Emotion Recognition in conversation) received a honorable mention at <a href="https://web.archive.org/web/20240624133953/https://engineering.buffalo.edu/computer-science-engineering/news-and-events/events/russell-l-agrusa-cse-student-innovation-competition/agrusa-competition-2022.html" target="_blank">Agrusa L. Student Innovation Competition 2022</a>.

Before joining UB as a Master's student, I worked as a Data Scientist-III (for ~2.5 years). During this time, I led global-scale AI solutions for clients including Unilever, BOSCH, DOLE etc. I led the ideation and development of Trade Promotion Optimization at Carbynetech (India) which continues to generate ~$50k every year.

## My Teaching

```{admonition} I Love Teaching!!!
:class: tip

My PhD is immensely motivated by my extreme passion for teaching. I aim to impart the knowledge that I received over to the next generation of researchers.

- Check out my [RateMyProfessor Ratings](https://www.ratemyprofessors.com/professor/3113460).
```

I have been fortunate to teach:

- [Computer Vision and Generative AI course at UB.](https://naresh-ub.github.io/cvip-summer25) _(Summer 2025)._
<!-- - [Differential Equations and Diffusion Models](#) (soon). -->

## Contact Details

📍 **301C Davis Hall, Buffalo NY, 14260**   
✉️ **Email:** [devulapa@buffalo.edu](mailto:devulapa@buffalo.edu)  

<!-- ## **Links**
--- -->
<head>
  <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.2/css/all.min.css">
  <style>
    .social-icons a {
      text-decoration: none; /* Removes underlines */
      display: inline-block; /* Ensures proper spacing */
      margin: 15px; /* Increased spacing between icons */
    }
    .social-icons {
      text-align: center;
      font-size: 45px; /* Slightly bigger icons */
    }
  </style>
</head>

<div class="social-icons">
  <a href="mailto:devulapa@buffalo.edu" style="color: green;">
    <i class="fa-solid fa-envelope"></i>
  </a>
  <a href="https://scholar.google.com/citations?user=20vLrzMAAAAJ&hl=en" style="color: #4285F4;">
    <i class="fa-brands fa-google-scholar"></i>
  </a>
  <a href="https://github.com/naresh-ub" style="color: green;">
    <i class="fa-brands fa-github"></i>
  </a>
  <a href="https://www.linkedin.com/in/nareshdevulapally" style="color: #0A66C2;">
    <i class="fa-brands fa-linkedin"></i>
  </a>
  <!-- <a href="#" style="color: black;">
    <i class="fa-brands fa-x-twitter"></i>
  </a> -->
</div>