DSP group member Sina Alemohammad successfully defended his PhD thesis entitled "Generative AI in the Age of Synthetic Data: Challenges and Solutions" in May 2025.

A pioneer in the study of "MADness" and "model collapse" that occur when generative AI systems are trained using self-synthesized data, Sina has also been a leader in developing methods for safely self-improving genAI models. His work has been written up in the New York Times and a host of other media outlets.

Sina's next position is as a postdoc in Atlas Wang's group at UT-Austin.

On 28 April 2025, we celebrated Professor Don Johnson and his remarkable 50 years of excellence at Rice University. His unwavering dedication to education, his innovative research, and his transformative contributions to the ECE community have made a lasting impact.

DoJo50 commemorated and celebrated the past, present, and future of one of the longest-running successful research and education programs at Rice with a variety of speakers, panel sessions, and discussions.

 

DSP group member Imtiaz Humayun successfully defended his PhD thesis entitled "Analyzing and Visualizing Emergent Structures in Deep Network Geometry" in April 2025. A leader in the interpreting deep networks in terms of continuous piecewise affine splines, Imtiaz is the founder of the SplineCam project that provides powerful visualization tools for the inner workings of deep networks.

Imtiaz’s next position is as a Research Scientist at Google Research, where he will be working on ways to make foundation models more adherent to human preferences and decision making processes.

DSP group member Paul Mayer successfully defended his PhD thesis entitled "Rethinking Maximum Likelihood Estimation" in April 2025.

Signal processing engineer by day, DJ and producer by night, Paul loves everything music and audio, from the science and mathematics behind it to producing and performing live. In addition to his research on statistical parameter estimation and machine learning, Paul is interested in the intersection of epistemology and artificial intelligence and has written a book that teaches mathematical logic alongside programming to STEM students. You can see samples of his teaching and radio-ready banter on his YouTube channel.

Paul's next position is R&D engineer at BASSBOSS in Austin, Texas, where he will be designing loudspeakers for nightclubs, festivals, and mobile DJs.

On the Geometry of Deep Learning
Randall Balestriero, Ahmed Imtiaz Humayun, Richard G. Baraniuk
Notices of the American Mathematical Society
April 2025

In this paper, we overview one promising avenue of progress at the mathematical foundation of deep learning: the connection between deep networks and function approximation by affine splines (continuous piecewise linear functions in multiple dimensions). In particular, we overview work over the past decade on understanding certain geometrical properties of a deep network’s affine spline mapping, in particular how it tessellates its input space. The affine spline connection and geometrical viewpoint provide a powerful portal through which to view, analyze, and improve the inner workings of deep networks.

Arxiv version

Richard Baraniuk, Rice University's C. Sidney Burrus Professor of Electrical and Computer Engineering and founder and director of OpenStax and SafeInsights, has been named the recipient of the 2025 IEEE Jack S. Kilby Signal Processing Medal.

The medal, presented annually since 1995, is given for outstanding achievements in signal processing. Baraniuk was specifically cited for his "contributions to multiscale and sparse signal processing."  The medal will be presented at the IEEE VIC Summit & Honors Gala in Tokyo in April 2025.

Rice Engineering News story | Rice News story | IEEE News story

 

 

DSP alum and University of Chicago professor Rebecca Willett is the inaugural recipient of the 2024 SIAM Activity Group on Data Science Career Prize. Becca received the prize for her work in physics-informed machine learning and data science and for her service and leadership in the data science community. From her pioneering work on photon-limited imaging to her analysis of generalization in overparameterized neural networks, Becca's work encompasses both the mathematical and statistical foundations of data science and the structure and context of problems from the natural sciences. Her research in physics-informed machine learning has contributed to bridging the gap between theoretical research and practical applications.

Becca is a professor of statistics and computer science and the Director of AI in the Data Science Institute at the University of Chicago.

Three DSP group papers have been accepted by The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP) Findings 2024 in Miami, Florida:

  1. MalAlgoQA: A Pedagogical Approach for Evaluating Counterfactual Reasoning Abilities by Naiming Liu, Shashank Sonkar, MyCo Le, and Richard G. Baraniuk
  2. Pedagogical Alignment of Large Language Models by Shashank Sonkar, Kangqi Ni, Sapana Chaudhary, and Richard G. Baraniuk
  3. The Student Data Paradox: Examining the Regressive Side Effects of Training LLMs for Personalized Learning by Shashank Sonkar, Naiming Liu, and Richard G. Baraniuk

To help organize the growing literature on AI self-consuming feedback loops, we have launched a "Self-Consuming AI Resources" archive at dsp.rice.edu/ai-loops.

In the 2000s, the Rice DSP group managed a similar archive for the field of compressive sensing, and it grew to several thousand papers that were used by a large community of researchers. We're hoping that this archive can be similarly useful.

We are currently in the process of refining the materials on the page. We would greatly appreciate it if you would recommend missing or new literature. There is also a ton of missing media coverage, and we are slowly working toward gathering it all.

Email us at selfconsumingAI@gmail.com to add your latest work or that of others in this fast-moving area!