TTIC Young Researcher Seminar Series

The TTIC Young Researcher Seminar Series features talks by Ph.D. students and postdocs whose research is of broad interest to the computer science community. The series provides an opportunity for early-career researchers to present recent work to and meet with students and faculty at TTIC and nearby universities.

Talks are typically held on Wednesdays at 11:00am in TTIC Room 530.

To receive announcements regarding the seminar series, please subscribe to the mailing list.

For additional information, please contact Shiry Ginosar(shiry@ttic.edu)

Upcoming Talks - (Past Talks)

Date: April 16, 2025
Speaker: Vihan Shah, University of Waterloo
Host: Ali Vakilian (vakilian@ttic.edu)

Date: May 7, 2025
Speaker: Ekdeep Lubana, Harvard

2024/2025 Academic Year

Title: Towards Intelligent Robots Beyond Human Capability
Date: October 8, 2024
Speaker: Ruoshi Liu, Columbia University
Host: Anand Bhattad (bhattad@ttic.edu)

Title: Comparing deep learning-based autonomous driving algorithms with the brain activity of human drivers
Date: October 23, 2024
Speaker: Kaylene Stocking, UC Berkeley
Host: Matt Walter (mwalter@ttic.edu)

Title: Reverse Engineering CLIP
Date: November 6, 2024
Speaker: Yossi Gandelsman, UC Berkeley
Host: Shiry Ginosar (shiry@ttic.edu)

Title: AI Safety Through Interpretable and Controllable Language Models
Date: November 20, 2024
Speaker: Peter Hase, University of North Carolina at Chapel Hill
Host: Karen Livescu (klivescu@ttic.edu)
Video Link: https://www.youtube.com/watch?v=Ao8Gprp9mC0

Title: Optimal Quantile Estimation: Beyond the Comparison Model
Date: December 4, 2024
Speaker: Meghal Gupta, Berkeley
Hosts: Avrim Blum (avrim@ttic.edu) and Siddharth Bhandari (siddharth@ttic.edu)
Video Link: https://www.youtube.com/watch?v=9FHbTfWwK4g

2023/2024 Academic Year

Title: A Journey on Interpretability Methods in NLP: Inside-Out and Back
Date: January 11, 2023
Speaker: Lena Voita, University of Edinburgh
Host: Karen Livescu (klivescu@ttic.edu)

Title: The staircase property and the leap complexity
Date: January 25, 2023
Speaker: Enric Boix, MIT
Host: Nathan Srebro (nati@ttic.edu)

Title: Statistical physics insights into the dynamics of learning algorithms
Date: May 24, 2023
Speaker: Francesca Mignacco, Princeton University
Host: Nathan Srebro (nati@ttic.edu)

Title: Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles
Date: October 25, 2023
Speaker: Noah Golowich, MIT
Host: Ali Vakilian (vakilian@ttic.edu)

Title: Feature Learning in Infinite-Depth Neural Networks
Date: December 6, 2023
Speaker: Dingli Yu, Princeton University
Host: Zhiyuan Li (zhiyuanli@ttic.edu)

2022/2023 Academic Year

Title: Optimal Sublinear Sampling of Spanning Trees and Determinantal Point Processes via Average-Case Entropic Independence
Date: November 7, 2022
Special Time: 3:00pm
Speaker: June Vuong, Stanford
Host: Madhur Tulsiani (madhurt@ttic.edu)

Title: Diffusion-LM Improves Controllable Text Generation
Date: November 16, 2022
Speaker: Lisa Li, Stanford
Host: David McAllester (mcallester@ttic.edu)

2021/2022 Academic Year

Title: Hypercontractivity and Small-Set Expansion on High Dimensional Expanders
Date: April 27, 2022
Speaker: Max Hopkins, UCSD
Host: Madhur Tulsiani (madhurt@ttic.edu)

Title: Efficient Convex Optimization Requires Superlinear Memory
Date: May 18, 2022
Speaker: Annie Marsden, Stanford University
Host: Nathan Srebro (nati@ttic.edu)

2019/2020 Academic Year

Title: Optimization Landscapes in Deep Learning
Date: November 6, 2019
Speaker: Kenji Kawaguchi, Massachusetts Institute of Technology
Host: Nathan Srebro (nati@ttic.edu)

Title: Exploring Surrogate Losses for Learning Neural Networks
Date: December 4, 2019
Speaker: Surbhi Goel, University of Texas
Host: Nathan Srebro (nati@ttic.edu)

Title: Making contextual bandits as easy as regression
Date: February 19, 2020
Speaker: Dylan Foster, Massachusetts Institute of Technology
Host: Nathan Srebro (nati@ttic.edu)

2018/2019 Academic Year

Title: Insights on Deep Representations with Applications to Healthcare
Date: October 17, 2018
Speaker: Maithra Raghu, Cornell
Host: Nathan Srebro (nati@ttic.edu)

Title: Learning From Sub-Optimal Data
Date: May 1, 2019
Speaker: Bradly Stadie, University of Toronto
Host: Gregory Shakhnarovich (gregory@ttic.edu)

Title: Non-Interactive Agreement and Dimension Reduction for Polynomials
Date: May 8, 2019
Speaker: Pritish Kamath, Massachusetts Institute of Technology
Host: Nathan Srebro (nati@ttic.edu)

Title: Image Synthesis for Self-Supervised Visual Representation Learning
Date: May 13, 2019
Speaker: Richard Zhang, Adobe
Host: Gregory Shakhnarovich (gregory@ttic.edu)

2017/2018 Academic Year

Title: A Dynamical View of Optimization Algorithms
Date: October 25, 2017
Speaker: Ashia Wilson
Host: Nathan Srebro (nati@ttic.edu)

Title: Learning Single-view 3D Reconstruction of Objects and Scenes
Date: January 24, 2018
Speaker: Shubham Tulsiani
Host: Gregory Shakhnarovich (gregory@ttic.edu)

Title: Look, Listen, and Speak: Vision Systems that Communicate with Natural Language
Date: February 14, 2018
Speaker: Lisa Anne Hendricks
Host: Gregory Shakhnarovich (gregory@ttic.edu)

Title: Generalization and Self-Supervision in Deep Robotic Learning
Date: February 28, 2018
Speaker: Chelsea Finn
Host: Matt Walter (mwalter@ttic.edu)

Title: Learning Sight from Sound
Date: March 28, 2018
Speaker: Andrew Owens
Host: Gregory Shakhnarovich (gregory@ttic.edu)

2016/2017 Academic Year

Title: Modular neural architectures for grounded language learning
Date: September 28, 2016
Speaker: Jacob Andreas
Host: Kevin Gimpel (kgimpel@ttic.edu)

Title: Understanding scenes over time with unlabeled video
Date: September 21, 2016
Speaker: Carl Vondrick
Host: Gregory Shakhnarovich (gregory@ttic.edu)

Title: Memory and Communication in Neural Networks
Date: October 5, 2016
Special Time: 10:00am
Speaker: Sainbayar Sukhbaatar
Host: David McAllester (mcallester@ttic.edu)

Title: Learning Spatial Priors for Text to 3D Scene Generation
Date: October 19, 2016
Speaker: Angel Chang
Host: Kevin Gimpel (kgimpel@ttic.edu)

Title: Conditional Quadratic Hardness for Data Analysis Problems
Date: October 26, 2016
Speaker: Arturs Backurs
Host: Yury Makarychev (yury@ttic.edu)

Title: A Task-Oriented Neural Dialogue System
Date: November 9, 2016
Speaker: Tsung-Hsien (Shawn) Wen
Host: Karen Livescu (klivescu@ttic.edu)

Title: Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks
Date: November 30, 2016
Speaker: Emily Denton
Host: Gregory Shakhnarovich (gregory@ttic.edu)

Title: Sample-Optimal Inference, the Method of Moments, and Community Detection
Date: May 17, 2017
Speaker: Samuel Hopkins
Host: Madhur Tulsiani (madhurt@ttic.edu)

Title: Towards Hierarchical Multiscale Recurrent Neural Networks and their Applications
Date: June 7, 2017
Speaker: Junyoung Chung
Host: David McAllester (mcallester@ttic.edu)

2015/2016 Academic Year

Title: End-to-End Speech Recognition using Deep LSTMs, CTC Training and WFST Decoding
Date: February 3, 2016
Speaker: Yajie Miao, CMU
Host: Karen Livescu (klivescu@ttic.edu)

Title: Locality-Sensitive Hashing and Beyond
Date: February 10, 2016
Speaker: Ilya Razenshteyn, MIT CSAIL
Host: Yury Makarychev (yury@ttic.edu)

Title: Machine Learning for Observational Studies
Date: February 17, 2016
Speaker: Uri Shalit, NYU
Host: Nathan Srebro (nati@ttic.edu)

Title: Using Motion to Understand Objects in the Real World
Date: March 2, 2016
Speaker: David Held, Stanford
Host: David McAllester (mcallester@ttic.edu)

Title: Initialization and Dual Expressivity of Neural Networks
Date: March 9, 2016
Speaker: Roy Frostig, Stanford
Host: Nathan Srebro (nati@ttic.edu)

Title: Neural Dialogue Generation
Date: April 20, 2016
Speaker: Jiwei Li, Stanford University
Host: Kevin Gimpel (kgimpel@ttic.edu)

Title: Scene Understanding from RGB-D Images
Date: May 11, 2016
Speaker: Saurabh Gupta, Berkeley
Host: Gregory Shakhnarovich (gregory@ttic.edu)