Pulkit

CS PhD student @umdcs

[Prateksha Udhayanan @Prateksha_03]

Looking forward to presenting Scale Space Diffusion at #CVPR2026!

📍Poster 675 - Poster Session 5, Exhibit Hall F
📅 June 7 (Sunday)
🕒 11:45 AM - 1:45 PM MDT

Joint work with @soumikkanad* and @abhi2610.

Project webpage: https://t.co/XigNUwobaK

[Matthew Walmer @MatthewWalmer]

We’re looking forward to presenting UPLiFT at #CVPR2026! Efficiently extract pixel-dense features from pretrained backbones like DINOv3.

We’ll be at the final poster session on Sunday (6/7) from 3:30-5:30pm at Poster 474, so please come by!

Website: https://t.co/Wng5ZfzjGA

[Soumik Mukhopadhyay @ CVPR26 @soumikkanad]

Come visit our poster "Scale Space Diffusion" at #CVPR2026!

We reformulate diffusion using scale space theory to enable progressive information flow for efficient pixel diffusion!

📍Main Conference: ExHall F 675; Sun, Jun 7, 2026 • 11:45 AM – 1:45 PM MDT

[Connor Dilgren @ConnorDilgren]

Excited to announce my first preprint in LM interpretability!

Latent reasoning models are not monitorable by default, since they don't reason in human-readable, natural language text. But can we make progress in understanding their intermediate reasoning steps using mech interp?

[Soumik Mukhopadhyay @ CVPR26 @soumikkanad]

Diffusion models be like:
“this image is 97% noise… better process all 256×256 pixels anyway”
If very noisy diffusion states contain no more useful information than a tiny downsampled image,
Then why run expensive full-res computation on them?
🧵

[Matthew Walmer @MatthewWalmer]

Excited to announce that UPLiFT has been accepted to #CVPR2026!

You can also try out UPLiFT right now to extract pixel-dense DINOv3 features with our pretrained models linked below!

Code: https://t.co/slgetOBNPO
Paper: https://t.co/9IqMewyZeG
Website: https://t.co/MJ78gJpXAJ

[Matthew Walmer @MatthewWalmer]

We’re excited to announce UPLiFT, our lightweight, pixel-dense feature upsampler. UPLiFT boosts feature density, preserves semantics, and has better efficiency scaling than recent SOTA methods. See all links in the thread below.
Coauthors: @_sakshams_ @AnirudAgg @abhi2610
🧵[1/6]

[Roni Sengupta @SenguptRoni]

🚨 PhD Opening: 3D/4D SLAM & Inverse Rendering for Endoscopy (NIH funded) at @UNC_CS! 🚨

The Project:
🟩 Ideal for students with a strong background in 3D Computer Vision & interested in medical robotics & visualization.
🟩 Highly collaborative work with roboticists, medical imaging researchers, and clinicians (GI, ENT, Pulmonology).
🟩Aim to publish in top-tier CV/ML/Robotics/Medical Imaging venues.
🟩 Build on our prior works:
1⃣Endoscopy depth estimator: PPSNet [ECCV'24 - https://t.co/THubw1c68K]
2⃣ 3D SLAM for endoscopy: NFL-BA [NeurIPS'25 -https://t.co/63iME90LnU]

Apply now! 📧 Email CV to [email protected] 📝 Formal UNC CS application required (Deadline soon!)

RTs appreciated! 🙏

[Pulkit @pulkitkumar95]

Aloha #ICCV2025! 🌺

Join @ShuaiyiH, @abhi2610 and me today (21 Oct) at poster #334, 11 AM–1 PM!

We will be presenting Trokens — our work on point tracking for action recognition.

Details of the paper are below 👇

[Pulkit @pulkitkumar95]

🎉 Excited to share our paper "Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition" has been accepted to #ICCV2025!

Equally co-led with @ShuaiyiH — we advance few-shot action recognition via smart point tracking.

🔗 https://t.co/449JI1WiL4
🧵👇

[Ruoshi Liu @ruoshi_liu]

Everyone says they want general-purpose robots.

We actually mean it — and we’ll make it weird, creative, and fun along the way 😎

Recruiting PhD students to work on Computer Vision and Robotics @umdcs for Fall 2026 in the beautiful city of Washington DC!

[Pulkit @pulkitkumar95]

Looking forward to presenting this work and discussing it with fellow researchers. See you in Hawaii! 🌺🌺
#ICCV25 #ICCV2025 #ICCV

[Pulkit @pulkitkumar95]

🎉 Excited to share our paper "Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition" has been accepted to #ICCV2025!

Equally co-led with @ShuaiyiH — we advance few-shot action recognition via smart point tracking.

🔗 https://t.co/449JI1WiL4
🧵👇

[Pulkit @pulkitkumar95]

👥 This work was co-led with @ShuaiyiH in collaboration with @MatthewWalmer, @rssaketh , and @abhi2610

🔗 All code and data are released:
🌐 Webpage: https://t.co/449JI1WiL4
📄 ArXiv: https://t.co/73Xj6vm8jt
💻 Code: https://t.co/NJoiV0JgPw
🤗 Data: https://t.co/TZhzE8CX8R

[Pulkit @pulkitkumar95]

@zenwill_ai @ICCVConference From the instructions

[Ani Aggarwal @AnirudAgg]

🧵 Your DiT, faster
Introducing ECAD: we reframe diffusion model caching as multi-objective optimization and evolve Pareto-optimal schedules via a genetic algorithm—achieving 4.47 FID gain at 2.58× speedup, with no retraining or tuning.
🔗 https://t.co/RBF5SuguTd
#MachineLearning