May 2025 - talks - lists.cs.princeton.edu

Yunyun Wang will present her FPO "Generative Universal Models for Speech" on Friday, May 30, 2025 at 2:00 PM in CS 302.
by gradinfo＠cs.princeton.edu 28 May '25

28 May '25

Yunyun Wang will present her FPO "Generative Universal Models for Speech" on Friday, May 30, 2025 at 2:00 PM in CS 302. Location: CS 302 The members of Yunyun's committee are as follows: Examiners: Adam Finkelstein (Adviser), Szymon Rusinkiewicz, Felix Heide Readers: Danqi Chen, Zeyu Jin (Adobe Research) A copy of her thesis is available upon request. Please email gradinfo(a)cs.princeton.edu <mailto:gradinfo@cs.princeton.edu> if you would like a copy of the thesis. Everyone is invited to attend her talk. Abstract follows below: This thesis presents a comprehensive framework for controllable speech synthesis through self-supervised generative modeling. We propose Generative Universal Models for Speech (GUMS), a system that decomposes speech into disentangled representations-speaker embeddings, acoustic embeddings, and content representations, and reconstructs it using a synthesis model. Our approach enables detailed control over speaker voice, environmental acoustics, speech content, and speaking rate. We introduce three key representation models. First, GR0 learns global speaker embeddings by disentangling them from time-varying local content without requiring speaker labels. Second, we develop content representation models AIC and GUMS Codec that capture speech content in continuous and quantized forms, respectively. The AIC model enforces speaker and pitch invariance through the alteration invariant content loss. GUMS Codec builds on the speech codec model DAC, incorporating residual vector quantization along with speaker and pitch conditioning. The result is a highly compact, discrete, and language-independent representation that is well-suited for manipulation, control, and efficient transmission. We then integrate these representations into a high-fidelity speech synthesis model, DiTVC, based on a Diffusion Transformer architecture. DiTVC enables direct prompting using target speaker audio instead of relying on fixed embeddings, allowing for more expressive voice conversion and robust prosody control. By combining these models, we achieve controllable, high-quality speech synthesis using unlabeled, in-the-wild data. The unified framework advances both representation learning and generation, offering an interpretable, and editable approach to speech synthesis.

1 1

Tim Kosfeld will present his General Exam "Advances in Supervised Interpretation and Preprocessing of ATAC-seq" on Tuesday, May 27, 2025 at 12:00 PM in Icahn 101.
by CS Grad Department 22 May '25

22 May '25

Tim Kosfeld will present his General Exam "Advances in Supervised Interpretation and Preprocessing of ATAC-seq" on Tuesday, May 27, 2025 at 12:00 PM in Icahn 101. Committee Members: Yuri Pritykin (advisor), Mona Singh, Ben Raphael Abstract: Single-cell assay for transposase-accessible chromatin with sequencing (scATAC-seq) has been widely used to profile chromatin accessibility and explore the epigenomic properties in heterogeneous cell populations. Furthermore, transcription factors (TFs) bind to accessible sites, and scATAC-seq analysis could associate TF binding specificities, typically available as sequence motifs, with variance in chromatin accessibility. Here we present a new supervised TF motif regression method, MotifReg, for computational analysis and interpretation of scATAC-seq data. MotifReg can efficiently analyze large-scale scATAC-seq datasets and learn interpretable associations between TF motifs and accessible peaks. The resultant low-dimensional cell representations in the TF activity space facilitate downstream cell type-specific analyses of scATAC-seq data. The supervised formulation in MotifReg enables ranking TF motifs by significance of their association with chromatin accessibility, implicating cell type-specific TFs. Furthermore, by comparing MotifReg performance across data analysis settings, we develop guidelines and best practices for scATAC-seq peak calling, data preprocessing and normalization. We leverage these best practices to show that aggregation of biologically similar ATAC data allows for the discovery of chromosomal regions enriched for chromatin interaction, known motif binding, or ATAC co-accessibility. We provide an automated methodology to quickly and efficiently scrape, compile, and preprocess this data from online sources and illustrate how construction of these high-quality atlases can complement existing analyses. Reading List: https://docs.google.com/document/d/1gnqGszJkHUIQisI3UL_mw-w_pCR2hD0dmL5N5OA… Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0

Yuqi Zhang will present her General Exam "Linking Genomic Alterations to Cancer Pathway Expression Changes via Canonical Correlation Analysis" on Wednesday, May 21, 2025 at 2:30 PM in Icahn Lab 280.
by CS Grad Department 16 May '25

16 May '25

Yuqi Zhang will present her General Exam "Linking Genomic Alterations to Cancer Pathway Expression Changes via Canonical Correlation Analysis" on Wednesday, May 21, 2025 at 2:30 PM in Icahn Lab 280. Committee Members: Mona Singh (advisor), Olga Troyanskaya, Yuri Pritykin Abstract: Cancer is a disease where numerous genomic alterations are acquired and cause widespread disruption to cellular function. Understanding how these alterations impact biological pathways is essential for uncovering the underlying mechanisms of complex diseases. We propose a framework based on Canonical Correlation Analysis (CCA) to uncover relationships between genes frequently altered in cancer and dysregulated pathway expression. Specifically, we jointly consider the multi-omic alterations affecting a known cancer-relevant gene—including its copy number alteration (CNA), mutation, and methylation status—and model their joint relationship with the expression of genes within specific biological pathways. A key contribution of our framework is a novel sampling-based hypothesis test for CCA that mitigates random signals often observed in high-dimensional datasets. Additionally, we adapt existing visualization methods to uncover relationships between specific types of genomic alterations and gene expression. Our model inherently accounts for correlation between molecular alterations and gene expression, improving sensitivity in detecting biologically meaningful associations. We apply our method across multiple driver genes and pathways, revealing significant associations that traditional gene-level approaches miss. Our framework also reveals the directionality of genomic alterations' regulatory effects on pathway expression while accounting for correlation and joint effects in high-dimensional data. By capturing the joint influence of genomic alterations on pathway activity while reducing statistical noise, our method offers a powerful approach for discovering key regulatory mechanisms in cancer. Reading List: https://docs.google.com/document/d/1edX-ARuzaajncovwykvHNW8GUXdYFqiw83vb_AY… Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0

Zhiyue Zhang will present her General Exam "Best practices of multiome data analysis and application to anti-tumor immunology in obesity" on Monday, May 19, 2025 at 2:30 PM in Icahn 200.
by CS Grad Department 14 May '25

14 May '25

Zhiyue Zhang will present her General Exam "Best practices of multiome data analysis and application to anti-tumor immunology in obesity" on Monday, May 19, 2025 at 2:30 PM in Icahn 200. Committee Members: Yuri Pritykin (advisor), Lydia Lynch (advisor), Mona Singh, Olga Troyanskaya Abstract: Technological advances in single-cell sequencing have expanded the detection of cell phenotype beyond the transcriptome, allowing for more refined characterization of cell types and discovery of novel therapeutic targets. Notably, paired scRNA-seq and scATAC-seq, called multiome data, facilitates inference of how variation in chromatin accessibility regulates gene expression and cell identity. However, unlike scRNA analysis, procedures of scATAC analysis lack consensus, mainly due to the high sparsity and the unfixed feature set of the original data. In this talk, we first present evaluating differential representations of scATAC by integrating with scRNA and validating against the pairing information of multiome data. We show that several decisions in current scATAC processing tools result in loss of information and recommend best practices of featurization and downstream analysis. Next, we demonstrate the power of multiome through an analysis of new multiome data from tumor-infiltrating CD8+ T cells in obesity. We find an enrichment of progenitor exhausted CD8+ T cells in obese tumors, and generate a new hypothesis for "the obesity paradox", namely why certain obese patients have improved response to immune checkpoint inhibitors despite displaying impaired anti-tumor immunity. Reading List: https://docs.google.com/document/d/1Pl6x0mOhhlj8NIXbllube2f11S-JnxglPgM0kOT… Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0

Jimmy Wu will present his FPO "Spatial Representations for Learning Robotic Mobile Manipulation" on Tuesday, May 20, 2025 at 1:30 PM in CS 401 and Zoom.
by CS Grad Department 13 May '25

13 May '25

Jimmy Wu will present his FPO "Spatial Representations for Learning Robotic Mobile Manipulation" on Tuesday, May 20, 2025 at 1:30 PM in CS 401 and Zoom. Location: Zoom link: https://princeton.zoom.us/j/96975727674 The members of Jimmy’s committee are as follows: Examiners: Szymon Rusinkiewicz (Adviser), Thomas Funkhouser (Adviser), Anirudha Majumdar Readers: Jia Deng, Jeannette Bohg (Stanford University) A copy of his thesis is available upon request. Please email gradinfo(a)cs.princeton.edu if you would like a copy of the thesis. Everyone is invited to attend his talk. Abstract follows below: The development of intelligent mobile manipulators has long been a goal of robotics research, promising transformative applications. However, enabling robots to operate outside of controlled laboratory settings remains a formidable challenge. This dissertation explores the role of spatial representations in learning-based systems for mobile manipulation. We develop a sequence of spatially grounded frameworks that progressively increase robot capabilities. First, we introduce spatial action maps, an action representation that is spatially aligned with the robot’s state representation, allowing a policy to predict actions on a 2D map of possible target locations. This approach simplifies the perception-to-control mapping, yielding more sample-efficient reinforcement learning and improved task performance. We then extend this idea to multi-robot systems with spatial intention maps, in which the intentions of other robots are spatially encoded in the state representation. This enables implicit coordination between robots, leading to improved multi-agent task success and emergent cooperative strategies such as collision avoidance and task specialization. Next, we tackle dynamic manipulation tasks with multi-frequency spatial action maps, which operate on multiple temporal scales, allowing a single policy to exhibit both high-level deliberative planning and low-level reactive behaviors. Finally, we present TidyBot, a mobile manipulation system for open-world household cleanup that leverages foundation models in vision and language. We show that spatial grounding allows the robot to tap into the broad semantic understanding embedded in foundation models, enabling generalization to novel objects and scenarios. Together, these contributions demonstrate that spatially grounded learning is a powerful paradigm for robotic mobile manipulation, bringing us closer to practical, intelligent robotic systems capable of operating in the real world.

1 0

Andrew Sheinberg will present his General Exam "Laying Down the Sequence Train(ing) Tracks: Minimizing Communication and Reducing HBM Footprint via Local Computations and Orchestrated Dataflow" on 5/14/25 at 10:00am in CS 302.
by Gradinfo 12 May '25

12 May '25

Andrew Sheinberg will present his General Exam "Laying Down the Sequence Train(ing) Tracks: Minimizing Communication and Reducing HBM Footprint via Local Computations and Orchestrated Dataflow" on 5/14/25 at 10:00am in CS 302. Committee: Kai Li (adviser), Tri Dao, Ravi Netravali Abstract and Reading List: [ https://docs.google.com/document/d/1ARxwBp59w7Azys4_dZHU2noUUUGWUbCtlLeIUM4… | https://docs.google.com/document/d/1ARxwBp59w7Azys4_dZHU2noUUUGWUbCtlLeIUM4… ]

1 0

Anushri Arora will present her General Exam "Efficient Training of Maximal and Minimal Low-Rank RNNs" on Monday, May 12, 2025 at 11:00 AM in FC 008 and via zoom.
by gradinfo＠cs.princeton.edu 12 May '25

12 May '25

Anushri Arora will present her General Exam "Efficient Training of Maximal and Minimal Low-Rank RNNs" on Monday, May 12, 2025 at 11:00 AM in FC 008 and via zoom. Zoom link: https://princeton.zoom.us/j/94357119848 Committee Members: Jonathan Pillow (advisor), Ben Eysenbach, Adji Bousso Dieng Abstract: Low-rank recurrent neural networks (RNNs) have recently gained prominence as a framework for understanding how neural systems solve complex cognitive tasks. However, fitting and interpreting these networks remains an important open problem. In this talk, I will introduce an alternative, yet mathematically equivalent perspective on low-rank RNNs that addresses these challenges. Specifically, we view individual neurons as nonlinear basis functions for representing an ordinary differential equation (ODE) of interest. Leveraging this perspective, we demonstrate how to embed arbitrary ODEs into the network using least-squares and recursive least-squares regression. First, this view provides geometric and algebraic insight highlighting how the choice of neuronal nonlinearity (e.g. tanh, ReLU) affects the network's universal approximation capacity. Second, we show that this construction is mathematically equivalent to performing kernel regression in a high-dimensional feature space, thereby connecting our approach to a Gaussian Process in the infinite width limit. Third, by applying a variant of orthogonal matching pursuit, we derive the minimal network size required to implement any target ODE. Fourth, using active learning, we systematically select the smallest set of dynamical trajectories needed for training. Finally, we benchmark our approach against FORCE and Backpropagation through time (BPTT) demonstrating that our approach learns significantly faster and achieves higher accuracy with substantially smaller networks. Reading List: https://docs.google.com/document/d/19cgCy1iOIE3ckuIzXgEVZ3dEFrWJ20-ieyklysyH DTE/edit?usp=sharing Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following

1 1

CS Colloquium speakers: week of February 26
by Emily C. Lawrence 12 May '25

12 May '25

CS Colloquium speakers Speaker: Jialin Ding, Amazon Web Services Date: Monday, February 26 Time: 12:30pm EST Location: CS 105 Host: Wyatt Lloyd Event page: https://www.cs.princeton.edu/events/26578 Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_10z_l8MYRr21ZOuPqA8Odw Title: Instance-Optimization: Rethinking Database Design for the Next 1000X Abstract: Modern database systems aim to support a large class of different use cases while simultaneously achieving high performance. However, as a result of their generality, databases often achieve adequate performance for the average use case but do not achieve the best performance for any individual use case. In this talk, I will describe my work on designing databases that use machine learning and optimization techniques to automatically achieve performance much closer to the optimal for each individual use case. In particular, I will present my work on instance-optimized database storage layouts, in which the co-design of data structures and optimization policies improves query performance in analytic databases by orders of magnitude. I will highlight how these instance-optimized data layouts address various challenges posed by real-world database workloads and how I implemented and deployed them in production within Amazon Redshift, a widely-used commercial database system. Bio: Jialin Ding is an Applied Scientist at AWS. Before that, he received his PhD in computer science from MIT, advised by Tim Kraska. He works broadly on applying machine learning and optimization techniques to improve data management systems, with a focus on building databases that automatically self-optimize to achieve high performance for any specific application. His work has appeared in top conferences such as SIGMOD, VLDB, and CIDR, and has been recognized by a Meta Research PhD Fellowship. To learn more about Jialin’s work, please visit [ https://jialinding.github.io/ | https://jialinding.github.io/ ] . CSML/CS/PSY Colloquium Speaker: Brenden Lake, New York University Date: Tuesday, February 27 Time: 12:30pm EST Location: CS 105 Host: Tom Griffiths Event page: https://csml.princeton.edu/events/csmlpsycs-seminar Register for live-stream online here: https://princeton.zoom.us/webinar/register/WN_aUfLfVQFSIqV2RDSYu4big Title: Towards more human-like learning in machines: Bridging the data and generalization gaps Abstract: There is an enormous data gap between how AI systems and children learn: The best LLMs now learn language from text with a word count in the trillions, whereas it would take a child roughly 100K years to reach those numbers through speech (Frank, 2023, "Bridging the data gap"). There is also a clear generalization gap: whereas machines struggle with systematic generalization, children can excel. For instance, once a child learns how to "skip," they immediately know how to "skip twice" or "skip around the room with their hands up" due to their compositional skills. In this talk, I'll describe two case studies in addressing these gaps. 1) The data gap: We train deep neural networks from scratch (using DINO, CLIP, etc.), not on large-scale data from the web, but through the eyes and ears of a single child. Using head-mounted video recordings from a child as training data (<200 hours of video slices over 26 months), we show how deep neural networks can perform challenging visual tasks, acquire many word-referent mappings, generalize to novel visual referents, and achieve multi-modal alignment. Our results demonstrate how today's AI models are capable of learning key aspects of children's early knowledge from realistic input. 2) The generalization gap: Can neural networks capture human-like systematic generalization? We address a 35-year-old debate catalyzed by Fodor and Pylyshyn's classic article, which argued that standard neural networks are not viable models of the mind because they lack systematic compositionality -- the algebraic ability to understand and produce novel combinations from known components. We'll show how neural networks can achieve human-like systematic generalization when trained through meta-learning for compositionality (MLC), a new method for optimizing the compositional skills of neural networks through practice. With MLC, neural networks can match human performance and solve several machine learning benchmarks. Given these findings, we'll discuss the paths forward for building machines that learn, generalize, and interact in more human-like ways based on more natural input. Related articles: Vong, W. K., Wang, W., Orhan, A. E., and Lake, B. M (2024). Grounded language acquisition through the eyes and ears of a single child. Science, 383, 504-511. Orhan, A. E., and Lake, B. M. (in press). Learning high-level visual representations from a child’s perspective without strong inductive biases. Nature Machine Intelligence. Lake, B. M. and Baroni, M. (2023). Human-like systematic generalization through a meta-learning neural network. Nature, 623, 115-121. Bio: Brenden M. Lake is an Assistant Professor of Data Science and Psychology at New York University. He received his M.S. and B.S. in Symbolic Systems from Stanford University in 2009, and his Ph.D. in Cognitive Science from MIT in 2014. He was a postdoctoral Data Science Fellow at NYU from 2014-2017. Brenden is a recipient of the Robert J. Glushko Prize for Outstanding Doctoral Dissertation in Cognitive Science and the MIT Technology Review 35 Innovators Under 35. His research was also selected by Scientific American as one of the 10 most important advances of 2016. Brenden's research focuses on computational problems that are easier for people than they are for machines, such as learning new concepts from just a few examples, learning by asking questions, learning by generating new goals, and learning by producing novel combinations of known components. CS Colloquium Speaker: Eric Mitchell, Stanford University Date: Thursday, February 29 Time: 12:30pm EST Location: CS 105 Host: Karthik Narasimhan Event page: https://www.cs.princeton.edu/events/26587 Register for live-stream online here: TBA Talk info TBA

1 24

[alg-ml-reading-group] Alg-ML Talk by Akshay Krishnamurthy on May 12, Monday, from 3pm - 4pm ET
by Emily C. Lawrence 09 May '25

09 May '25

Dr. Akshay Krishnamurthy from Microsoft Research will present his recent work on Understanding Inference Time Compute: Self-Improvement and Scaling . The talk is scheduled on on May 12, Monday. Bio: Akshay Krishnamurthy is a senior principal research manager at Microsoft Research, New York City. He previously spent two years as an assistant professor in the College of Information and Computer Sciences at the University of Massachusetts, Amherst and a year as a postdoctoral researcher at Microsoft Research, NYC. He completed my PhD in the Computer Science Department at Carnegie Mellon University, advised by Aarti Singh and received his undergraduate degree in EECS at UC Berkeley. His research interests are broadly in the areas of machine learning and statistics. He is most excited about interactive learning and decision making, including reinforcement learning, and recently has been thinking about how reinforcement learning can be used to improve modern generative AI systems. Feel free to grab a slot [ https://docs.google.com/spreadsheets/d/10LQsvqhbxw36MDLcxpnDPcG12nsrDl33yG0… | here ] to meet with our speaker! The talk will start at 3.00 pm ET. ____________________________________________________________________________ Time: 3 .00 PM ET on May 12 , Monday Physical Location: COS 402 ____________________________________________________________________________ Title: Understanding Inference Time Compute: Self-Improvement and Scaling Abstract: Inference-time compute has emerged as a new axis for scaling large language models, leading to breakthroughs in AI reasoning. Broadly speaking, inference-time compute methods involve allowing the language model to interact with a verifier to search for desirable, high-quality, or correct responses. While recent breakthroughs involve using a ground-truth verifier of correctness, it is also possible to invoke the language model itself or an otherwise learned model as verifiers. These latter protocols raise the possibility of self-improvement, whereby the AI system evaluates and refines its own generations to achieve higher performance. This talk presents new understanding of and new algorithms for language model self-improvement. The first part of the talk focuses on a new perspective on self-improvement that we refer to as sharpening, whereby we "sharpen" the model toward one placing large probability mass on high-quality sequence, as measured by the language model itself. We show how the sharpening process can be done purely at inference time or amortized into the model via post-training, thereby avoiding expensive inference-time computation. In the second part of the talk, we consider the more general setting of a learned reward model, show that the performance of naive-but-widely-used inference-time compute strategies does not improve monotonically with compute, and develop a new compute-monotone algorithm with optimal statistical performance. Based on joint works with Audrey Huang, Dhruv Rohatgi, Adam Block, Qinghua Liu, Jordan T. Ash, Cyril Zhang, Max Simchowitz, Dylan J. Foster and Nan Jiang. We hope to see you there! ____________________________________________________________________________ (Useful links: [ https://princeton-alg-ml.github.io/ | alg-ml-website ] , [ https://calendar.google.com/calendar/u/1?cid=Y185ZWQxMzVmOGMxN2JjZmNhYjAyOT… | alg-ml-calendar ] , [ https://lists.cs.princeton.edu/mailman/listinfo/alg-ml-reading-group | alg-ml-mailing-list ] ) Best, Zixuan , Gon, and Catherine _______________________________________________ alg-ml-reading-group mailing list [ mailto:alg-ml-reading-group@lists.cs.princeton.edu | alg-ml-reading-group(a)lists.cs.princeton.edu ] [ https://lists.cs.princeton.edu/mailman/listinfo/alg-ml-reading-group | https://lists.cs.princeton.edu/mailman/listinfo/alg-ml-reading-group ]

1 0

Elizabeth Mieczkowski will present her General Exam "Quantifying Collaborative Trade-offs with Insights from Distributed Systems" on Tuesday, May 13, 2025 at 12:00 PM in FC 008.
by CS Grad Department 08 May '25

08 May '25

Elizabeth Mieczkowski will present her General Exam "Quantifying Collaborative Trade-offs with Insights from Distributed Systems" on Tuesday, May 13, 2025 at 12:00 PM in FC 008. Zoom Link: https://princeton.zoom.us/j/6756891992 Committee Members: Tom Griffiths (advisor), Benjamin Eysenbach, Wyatt Lloyd, Natalia Velez Abstract: Collaboration enables multi-agent systems to achieve goals beyond the capabilities of any single agent. However, coordination is inherently complex and dynamic. How can we identify the underlying principles that should guide the division of labor and resources in multi-agent teams, and formalize the trade-offs that emerge during collaboration? I argue that research from distributed computing systems provides a powerful interpretability framework for multi-agent collaboration. This literature focuses on building efficient, scalable, and fault-tolerant systems, while exposing fundamental constraints—such as communication overhead and consistency—when computation is shared across machines. I first extend Amdahl’s Law, which predicts how serial bottlenecks constrain parallel speedup, to naturalistic multi-agent tasks and confirm its validity in a set of human experiments. I then apply this model to large-scale MARL simulations in Overcooked, SMAC, and MPE, demonstrating that specialized policies emerge as a function of task parallelizability. Finally, I demonstrate how the model can benchmark existing algorithms and human collaborative strategies. Reading List: https://docs.google.com/document/d/12GKMv_n99TcUJvj8iua44eHGkUbQAz2hwX_zUYj… Everyone is invited to attend the talk, and those faculty wishing to remain for the oral exam following are welcome to do so.

1 0