JHU Computer Science

Salzberg and Schatz among world’s most cited researchers for fifth consecutive year The annual list compiled by Clarivate Analytics recognizes researchers whose publications rank in the top 1% of citations.

Congratulations to @stevensalzberg.bsky.social and @mikeschatz.bsky.social on being named @clarivate.com Highly Cited Researchers for the 5th year in a row!

Wheel of Fortune logo. Can I buy an AI? Wheel of Fortune tournament: Do you think U can beat the bots? Friday, December 12th. Bloomberg Student Center 213. 6:00-8:00 pm. QR code. Register now.

Take a break from studying and test your Wordle skills with a Wheel of Fortune! tournament on Friday, Dec. 12 from 6–8 p.m. in Room 213 of the Bloomberg Student Center! Sign up now to play against other students & the AI bots they developed over the fall semester: docs.google.com/forms/d/e/1F...

Pedro R.A.S. Bassi, Zongwei Zhou, Wenxuan Li, Alan Yuille, Kuma Liu, and Xinran Li pose in front of a window showing the Chicago skyline.

Pedro R.A.S. Bassi, Zongwei Zhou, Wenxuan Li, and Kuma Liu stand behind a lectern with the RSNA logo.

Xinran Li, Kuma Liu, Alan Yuille, Zongwei Zhou, Wenxuan Li, and Pedro R.A.S. Bassi pose in front of Lake Michigan.

Xinran Li, Kuma Liu, Alan Yuille, Zongwei Zhou, Wenxuan Li, and Pedro R.A.S. Bassi pose in front of large block letters reading LEARN.

Our CCVL researchers had a blast at #RSNA2025 last week!

Congratulations! Rachel Wicks Successfully defended her dissertation “On the Path Towards Contextual Machine Translation” under the guidance of advisors Philipp Koehn and Matt Post. Rachel plans to join Bloomberg’s Artificial Intelligence Engineering group. We in the department are extremely proud of our students who have successfully completed their PhD. Congratulations on this achievement and best wishes as you begin an exciting new phase of life!

Congratulations, @rewicks.bsky.social!

Johns Hopkins researchers launch projects under Cancer AI Alliance The researchers are using AI to predict outcomes, individualize treatment, and protect patient privacy, transforming how cancer is understood and treated.

As part of the Cancer AI Alliance, researchers like @alexisbattle.bsky.social and @mathias-unberath.bsky.social are showcasing how #AI can transform #cancer research and patient care.

Congratulations to our fellows!

“The change in their feed was barely perceptible, yet they reported a significant difference in how they felt about other people,” says @tiziano.bsky.social. “Based on U.S. trends, that shift corresponds to roughly three years of polarization.”

Journal Club Alert! ‼️
We’re excited to invite you to our next RISE-MICCAI Journal Club session, led by Pedro Bassi (Johns Hopkins University).
📅 December 6th
🕒 12:00 pm EST / 06:00 pm CEST
🔗 us02web.zoom.us/webinar/regi...
#MICCAI

Congratulations to all @jhu.edu researchers participating in #NeurIPS2025! Check out all Johns Hopkins accepted papers, tutorials, and workshops at ai.jhu.edu/news/johns-h....

Augmented reality meets neuroendoscopy Hopkins researchers bring advanced 3D visualization techniques to neurosurgery.

Johns Hopkins researchers (including @imagingai.bsky.social) have improved their cutting-edge augmented endoscopy algorithm—which allows neurosurgeons to navigate the deep brain in real time without having to use invasive clamps or pins—for real-life operations by integrating #AI tracking.

The Human Side of Big Data: IDIES Symposium Highlights The Institute for Data-Intensive Engineering and Science (IDIES) hosted its annual symposium on Thursday, Oct. 16. The symposium opened with remarks from Alex Szalay – Bloomberg Distinguished Professo...

Check out the Johns Hopkins News-Letter’s recap of the Johns Hopkins Institute for Data Intensive Engineering and Science’s annual symposium, directed by JHU CS’ Alex Szalay:

Johns Hopkins Whiting School of Engineering Johns Hopkins engineers are makers and problem solvers. Hopkins engineers at all levels collaborate with recognized leaders in their fields to solve real-world problems.

Today at 4:30 - Join us in celebrating the Don P. Giddens Inaugural Professorial Lecture recognizing Joanne Selinski as a teaching professor in @jhucompsci.bsky.social. In the Rose Auditorium, Maxine F. Singer Building, Carnegie Institute and LIVE on YouTube: www.youtube.com/user/Hopkins...

Johns Hopkins among nine schools selected for Amazon AI fellowship program Two doctoral candidates from the Department of Computer Science received two-year fellowships through the new program.

Congratulations to our PhD students—both Amazon AI PhD Fellows and AI2AI Fellows! 🎉

@jhu.edu is 1 of 9 universities selected by Amazon for its new AI PhD Fellowship program, an initiative that will provide nearly $68 million in funding over 2 years to more than 100 doctoral students nationwide.

and “When Does Curriculum Learning Help? A Theoretical Perspective” by Kaibo Zhang, Yunjuan Wang, and Raman Arora develops a theoretical framework for curriculum learning 🎒 based on biased regularized empirical risk minimization: (17/17)

In “Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting,” @anandbhattad.bsky.social, Konpat Preechakul, and Alexei A. Efros propose a novel scene understanding task 🎲: (16/17)

Tiezheng Zhang, Yitong Li, Yu-Cheng Chou, @jienengchen.bsky.social, Alan Yuille, Chen Wei, and Junfei Xiao introduce a framework for building VLMs with strong captioning 💬 capabilities in “Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models”: (15/17)

“SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning” by Wufei Ma, Yu-Cheng Chou, Qihao Liu, Alan Yuille, Xingrui Wang, @celso-de-melo.bsky.social, Jianwen Xie introduces a novel LVLM that addresses 3D spatial reasoning with explicit 3D representations: (14/17)

In “SimWorld-Robotics: Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration,” @tianaiy.bsky.social, @marstin.bsky.social, @lianhui.bsky.social, @zhitinghu.bsky.social, & more present an #AI simulation platform for urban 🏙️ environments: (13/17)

Wenxuan Li, Xinze Zhou, Qi Chen, Tianyu Lin, Pedro R. A. S. Bassi, Alan Yuille, Zongwei Zhou, and more present a large-scale, multi-institutional dataset curated to advance research in pancreatic CT analysis in “PanTS: The Pancreatic Tumor Segmentation Dataset”: (12/17)

“OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions” by Yuanhao Cai, Alan Yuille, @zhanghesprinter.bsky.social, and more develops IVTM training with image 🖼️ editing data to enable instructive editing ✏️: (11/17)

In “Monitoring Risks in Test-Time Adaptation,” by @enalisnick.bsky.social, @monaschir.bsky.social, @metodjazbec.bsky.social, & @canaesseth.bsky.social propose pairing TTA w/ risk-monitoring frameworks that track predictive performance & raise alerts 🚨 when performance criteria are violated: (10/17)

@murat-kocaoglu.bsky.social, Jincheng Zhou, Mengbo Wang, Anqi He, Yumeng Zhou, Hessam Olya, and @brunofmr.bsky.social develop differentiable-separation scores obtained through a percolation ☕ theory in “Differentiable Constraint-Based Causal Discovery”: (9/17)

“Conformal Linguistic Calibration: Trading-off between Factuality and Specificity” by Zhengping Jiang, @aliu33.bsky.social, and Benjamin Van Durme proposes a unified view 👁️ that reinterprets linguistic calibration as answer set prediction: (8/17)

In “Characterization and Learning of Causal Graphs from Hard Interventions,” @murat-kocaoglu.bsky.social, Zihan Zhou, and Muhammed Qasim Elahi propose a set of graphical 📉 constraints that are fundamentally linked to Pearl's do-calculus 🧮: (7/17)

Tianyu Lin, Xinran Li, Chuntung Zhuang, Qi Chen, Yuanhao Cai, Kai Ding, Alan Yuille, and Zongwei Zhou propose a suite of novel anatomy-aware 🫁 evaluation metrics in “Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?”: (6/17)

“A Generalized Binary Tree Mechanism for Differentially Private Approximation of All-Pair Distances” by @mdinitz.bsky.social, @jalajupadhyay.bsky.social, and more studies the problem of approximating all-pair distances in a weighted undirected graph 📈 with differential privacy: (5/17)

In “SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds,” Tianmin Shu, @marstin.bsky.social, @zhitinghu.bsky.social, @lianhui.bsky.social, and more introduce a new simulator for developing and evaluating agents in rich, real-world-like settings 🌎: (4/17)

Jiani Huang, Mayank Keoliya, Matthew Kuo, Neelay Velingker, Amish Sethi, JungHo Jung, Ser-Nam Lim, Ziyang Li, and Mayur Naik propose a framework that contextualizes embodied agents by grounding their perception in “ESCA: Contextualizing Embodied Agents via Scene-Graph Generation”: (3/17)

“AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling” by Zhining Zhang, @chuanyang-jin.bsky.social, Mung Yao Jia, @zssc.tech, and Tianmin Shu introduces an automated agent 🤖 modeling method for scalable, robust, and interpretable mental inference: (2/17)

Johns Hopkins researchers to present work at NeurIPS 2025 NeurIPS is an interdisciplinary annual event that highlights advancements in machine learning, artificial intelligence, and computational neuroscience through talks, demonstrations, symposia, and oral...

Congratulations to all the researchers presenting work at @neuripsconf.bsky.social 2025! Check out the full list of accepted research below or keep scrolling in this thread 🧵 for the highlights (1/17):