BAIR/CPAR/BDD Internal Weekly Seminar

The Berkeley Artificial Intelligence Research Lab co-hosts a weekly internal seminar series with the CITRIS People and Robots Initiative and Berkeley DeepDrive. The seminars are every Tuesday morning, from 11:10A-12P, and are open to BAIR faculty, students, and sponsors. Talks will take place via Zoom. For any questions, please email

Spring 2021 Schedule

Date Speaker 1: 11:10 AM -12:00 PM or 11:10-11:30 AMSpeaker 2: N/A or  11:30-11:50 AM
Jan 26Hany Farid: Forensic Photographic IdentificationN/A
Feb 2Stephen Bates: Distribution-Free, Risk-Controlling Prediction SetsN/A
Feb 9Abhishek Gupta: Algorithms and Systems for Real World Robotic LearningN/A
Feb 16Glen Berseth: Developing Autonomous Agents to Learn and Plan in the Real WorldN/A
Feb 23Forrest Laine: Computing Feedback Nash Equilibria in Robotic GamesN/A
Mar 2Ellen Novoseller: Online Learning from Human Preference Feedback and Multi-Fidelity Models with Application to Assistive ExoskeletonsN/A
Mar 9Amir Gholami: Systematic Neural Network Pruning and QuantizationColorado Reed: Practical Self-Supervised Learning
Mar 16N/ATBD
Mar 23N/AN/A
Mar 30Adam Gleave: Understanding and Evaluating Learned Reward FunctionsN/A
Apr 6Jiachen Li: Relational Reasoning for Multi-Agent SystemsN/A
Apr 13Taesung Park: Machine Learning for Deep Image ManipulationN/A
Apr 20Samaneh Azadi: Towards Content-Creative AIN/A
Apr 27Daniel Seita: TBDN/A

Fall 2020 Schedule

DateSpeaker 1: 11:10 AM -12:00 PM or 11:10-11:30 AMSpeaker 2: N/A or  11:30-11:50 AM
Sep 1Alvin Wan: What Explainable AI Fails to Explain (and how we fix that)Amir GholamiZhewei Yao: ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning
Sep 8Nikita Kitaev: Is Unstructured Computation All You Need for Natural Language Processing?Lucy Li: Content Analysis of Textbooks via Natural Language Processing: Findings on Gender, Race, and Ethnicity in Texas U.S. History Textbooks
Sep 15Georgios Pavlakos: Learning to Reconstruct 3D HumansN/A
Sep 22Lerrel Pinto: Rich Robotic Supervision through Cheap Human DemonstrationsN/A
Sep 29Philippe Laban: Text Summarization Without The SummariesKatie Stasaski: More Diverse Dialogue Datasets via Diversity-Informed Data Collection
Oct 6Aldo Pacchiano:  Learning to Score Behaviors for Guided Policy OptimizationN/A
Oct 13Paria Rashidinejad: Learning to Predict in Unknown Dynamical Systems with Long-Term MemoryZhen Dong: Efficient Neural Networks Through Systematic Quantization
Oct 20Eugene Vinitsky: Optimizing Energy Efficiency of Traffic at Scale via Multi-agent Deep RL
Anastasios Angelopoulos: Uncertainty for Black Box Models
Oct 27Misha Laskin: Escaping the Simulator: Accelerating Real Robot Learning through Unsupervised LearningN/A
Nov 3Wei Zhan: Close-loop Evaluation of Prediction Algorithms with Complex Scenarios from Naturalistic Driving DataLiting Sun: Modeling Human Behaviors in Human-robot Interactions
Nov 10
Daniel Brown
: Safe and Efficient Imitation Learning
Nov 17Edward Kim: Scenic: Dynamic Scenario Description Language for Autonomous SystemsKimin Lee: Ensemble methods in reinforcement learning
Nov 24Xin Wang: Last-Mile Delivery of Computer Vision with Test-Time AdaptationN/A
Dec 1Huijuan Xu: Temporal Action Detection in Videos with Multi-Level SupervisionN/A

Spring 2020 Schedule

DateSpeaker 1: 3:10-4:00 or 3:10-3:30Speaker 2: N/A or 3:30-3:50
Jan. 24Dylan Hadfield-Menell: The Principal-Agent Value Alignment ProblemN/A
Jan. 31Somil Bansal: Safe and Data-efficient Learning for Physical SystemsN/A
Feb. 7Nick Antipa: Lensless Computational Imaging: Seeing More with LessN/A
Feb. 14Ruoxi Jia: Towards a Responsible Data Economy: Fairness, Privacy, and SecurityN/A
Feb. 21Chandan Singh: Interpreting and Improving Neural Networks via Disentangled AttributionsN/A
Feb. 28Alexei (Alyosha) Efros: Image Manipulation… And Ways to Detect ItN/A
Mar. 6Brijen Thananjeyan and Ashwin Balakrishna:  Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic TasksJeff Ichnowski: Fog-Robotics Serverless and Deep Grasp-Optimized Robot Motion Planning
Mar. 13Aravind Srinivas: Self-Supervised Visual Representation LearningN/A
Mar. 20Ronghang Hu: Structured Models for Vision-and-Language ReasoningN/A
Mar. 27No SeminarN/A
Apr. 3Misha Laskin: Improving Reinforcement Learning with Unsupervised and Self-Supervised LearningN/A
Apr. 10Dequan Wang: Object-Centric Representation for Perception, Prediction, and PlanningN/A
Apr. 17Coline Devin:Learning with Modularity and Compositionality for Robotics
Apr. 24Cecilia Zhang: Bringing Cinema Quality Rendering into Casual Photos and Videos.N/A
May 1Sylvia Herbert: Safe Real-World Autonomy in Uncertain and Unstructured EnvironmentsN/A
May 8Sasha Sax: Robust Learning Through Cross-Task ConsistencyN/A
May 15Carlos Florensa: What Supervision Scales? Practical Learning Through InteractionN/A

Spring 2019 Schedule

DateSpeaker 1: 3:10-4:00 or 3:10-3:30Speaker 2: N/A or 3:30-3:50
Jan. 18Eric Jonas: Structured Prediction via Machine Learning for Inverse ProblemsN/A
Jan. 25Dinesh Jayaraman: Towards Embodied Visual IntelligenceN/A
Feb. 1Ke Li: Advances in Machine Learning: Learning to Optimize, Generative Modelling and Nearest Neighbour SearchN/A
Feb. 8Deepak Pathak: Self-Directed LearningN/A
Feb. 15Samaneh Azadi: Rectify the GAN Generator Distribution by Rejecting Bad SamplesSasha Sax: On Perception for Robotics: Mid-level Visual Representations Improve Generalization and Sample Complexity for Learning Active Tasks
Feb. 22Jaime Fisac: Resilient Safety Assurance for Robotic Systems: Staying Safe Even When Models Are WrongN/A
Mar. 1Fisher Yu: Towards Human-Level Recognition via Contextual, Dynamic, and Predictive RepresentationsN/A
Mar. 8Andrew Owens: Sight and SoundN/A
Mar. 15Daniel Fried: Pragmatic Models for Generating and Following Grounded InstructionsNikita Kitaev: Syntactic Parsing with Self-Attention
Mar. 22**Oriol Vinyals: AlphaStar: Mastering the Real-Time Strategy Game StarCraft II (**This will be held 11am-12pm in 250 SDH**)N/A
Mar. 22Jacob Steinhardt: What Makes Neural Networks (Non-)Robust?N/A
Mar. 29HolidayHoliday
Apr. 5Alex Lee: Visual Dynamics Models for Robotic Planning and ControlN/A
Apr. 12Lisa Anne Hendricks: Visual Understanding through Natural LanguageN/A
Apr. 19Evan Shelhamer: Blurring the Line between Structure and Learning for Adaptive Local RecognitionN/A
Apr. 26Yian Ma: Bridging MCMC and OptimizationN/A
May 3Sandy Huang: Optimizing for Robot TransparencyN/A
May 10Jeffrey Regier: Statistical Inference for Cataloging the Visible UniverseN/A

Fall 2018 Schedule

DateSpeaker 1: 3:10-4:00 or 3:10-3:30Speaker 2: N/A or 3:30-3:50
Aug. 24Jaime FisacAndrea BajcsySylvia Herbert: Probabilistically Safe Robot Planning with Confidence-Based Human PredictionsN/A
Aug. 31Aviv Tamar: Learning Representations for PlanningN/A
Sept. 7Chi Jin: Is Q-learning Provably Efficient?N/A
Sept. 14Wojciech Zaremba: Learning dexterityN/A
Sept. 21Tuomas Haarnoja: Acquiring Diverse Robot Skills via Maximum Entropy Reinforcement LearningN/A
Sept. 28Professor Ruzena Bajcsy: Data Driven vs. Model Driven Analysis of Human Ability for Human Robot InteractionN/A
Oct. 5Ke Li: Implicit Maximum Likelihood EstimationN/A
Oct. 12Roy Fox: Multi-Task Hierarchical Imitation Learning of Robot SkillsN/A
Oct. 19Ankush Desai: DRONA: A Framework for Programming Safe Robotics SystemsN/A
Oct. 26Ajay Tanwani: A Fog Robotics Approach to Large Scale Robot LearningLaura Hallock: Human Muscle Force Modeling for Enhanced Assistive Device Control
Nov. 2Abhishek Gupta: Unsupervised (Meta) RLAnja Rohrbach: Diagnosing and correcting bias in captioning models
Nov. 9HolidayHoliday
Nov. 16Daniel Fried: Pragmatic Models for Generating and Following Grounded InstructionsNikita Kitaev: Syntactic Parsing with Self-Attention
Nov. 23HolidayHoliday
Dec. 7Jiantao Jiao: Deconstructing Generative Adversarial NetworksN/A

Spring 2018 Schedule

DateSpeaker 1: 3:10-4:00 or 3:10-3:30Speaker 2: N/A or 3:30-3:50
Jan. 19Pulkit Agrawal: Continually Evolving Machines: Learning by ExperimentingN/A
Jan. 26Sanjay Krishnan: Dirty Data, Robotics, and Artificial IntelligenceN/A
Feb. 2David Fouhey: Towards a 3D World of InteractionN/A
Feb. 9Saurabh Gupta: Visual Perception and Navigation in 3D ScenesN/A
Feb. 16Jacob Andreas: Learning from LanguageN/A
Feb. 23Chelsea Finn: Generalization and Self-Supervision in Deep Robotic LearningN/A
Mar. 2Jennifer Listgarten: Where genetics and biology meet machine learningN/A
Mar. 9Yi Ma: Low-dimensional Structures and Deep Models for High-dimensional DataTBD
Mar. 16Cathy Wu: Mixed-autonomy mobility: scalable learning and optimizationN/A
Mar. 23Xiang Cheng: Langevin MCMC as gradient flow over the probability spaceEric Tzeng and Andreea Bobu: Domain Adaptation for Fixed and Continuously Varying Domains
Apr. 6Shubham Tulsiani: Learning Single-view 3D Reconstruction of Objects and ScenesTBD
Apr. 13Tinghui Zhou: Beyond Direct Supervision: Visual Learning via Data-driven Consistency Consistency (Location: SWARM Lab 490 Cory)N/A
Apr. 20Richard Zhang: Image Synthesis for Self-Supervised Representation LearningN/A
Apr. 27Reza Abbasi-Asl: Structural compression of Convolutional Neural NetworksFereshteh Sadeghi: Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control

Fall 2017 Schedule

DateSpeaker 1: 3:10-3:40Speaker 2: 3:40-4:10
Aug. 25Jitendra Malik: What have we learned from datasets in computer vision?Angjoo Kanazawa: Single-View 3D Reconstruction of Deformable Objects like Animals and People
Sept. 1Chang Liu: Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity DetectionClaire Tomlin: Safe Learning
Sept. 8Andrew Critch: Open-source game theory is weirdAnna Rohrbach: Generation and grounding of natural language descriptions for visual data
Sept. 15Bo Li: Secure learning in adversarial environmentsChing-Yao Chan: Safety of Automated Driving Systems (ADS) and AI/ML – A Dialogue
Sept. 22Alex Anderson: The High-Dimensional Geometry of Binary Neural NetworksJeff Mahler: Learning Deep Policies for Robot Bin Picking using Discrete-Event Simulation of Robust Grasping Sequences
Sept. 29Fisher Yu: Towards Universal Representation for Image RecognitionMax Rabinovich: Abstract Syntax Networks for Code Generation and Semantic Parsing
Oct. 6Michael Laskey: Learning Home Robotics Manipulation Tasks from Remote SupervisionPulkit Agrawal: Continually Evolving Agents: Curiosity & Experimentation
Oct. 13Ron Fearing: Dextrous LocomotionSylvia Herbert and David Fridovich: Planning, Fast and Slow with FaSTrack: A Framework for Adaptive Real-Time Safe Trajectory Planning
Oct. 20Emrah Bostan: Learning Convex Regularizers for Optimal Bayesian DenoisingSomil Bansal: Overcoming Model Bias in Model-based Learning
Oct. 27Roberto CalandraAaditya Ramdas: Sequential testing and online false discovery rate control
Nov. 3Roy Fox: Discovery of Hierarchical Structures for Robot Learning and Neural ProgrammingLeila Wehbe: Modeling brain responses to natural language stimuli
Nov. 10HolidayHoliday
Nov. 17Jacob Andreas: Learning with Latent LanguageNiladri Chatterji: Alternating minimization for dictionary learning with random initialization
Nov. 24HolidayHoliday
Dec. 1Eric Jonas: Could a neuroscientist understand a microprocessorTuomas Haarnoja: Soft Q-Learning

Spring 2017 Schedule

DateSpeaker 1: 3:10-3:40Speaker 2: 3:40-4:10
Jan. 20Jack Gallant: Melding neuroscience and computer scienceJavad Lavaei: On optimization theory, numerical algorithms and machine learning for nationwide energy systems
Jan. 27Trevor Darrell: Adaptive Learning of Driving Models from Large-scale Video DatasetsColine Devin: Transfer learning for robotics
Feb. 3Phillip Isola: Image-to-Image Translation with Conditional Adversarial NetworksAnil Aswani: Human Modeling Using Inverse Optimization
Feb. 10Zeynep Akata: Generating Fine-Grained Visual Explanations and Realistic ImagesDeirdre Mulligan: Hand-offs in AI: Functional Fidelity, Values, and Governance
Feb. 17(3:10- 3:25) Jaime Fernandez Fisac: Generating plans that predict themselves/ (3:25-3:40) Aaron Bestick: Implicitly Assisting Humans to Choose Good Grasps in Robot to Human HandoversWilliam Guss: WaveLayers: Neural Topology Inspired by Topology
Feb. 24Laurent El Ghaoui: Safe feature elimination in sparse learningLaura Waller: Computational Microscopy with sparsity
Mar. 3Chi Jin: How to Escape Saddle Points EfficientlyHoria Mania: Universality of Mallows’ and degeneracy of Kendall’s kernels for rankings
Mar. 10Matthew Matl: Automated Grasp Transfer with Mesh Segmentation and Point Cloud RegistrationPaul Grigas: An Extended Frank-Wolfe Method with “In-Face” Directions, and its Application to Low-Rank Matrix Completion
Mar. 17Roy Fox: Multi-Level Discovery of Deep OptionsParvez Ahammad: Beyond navigation metrics: Teaching computers how users perceive web application performance
Mar. 24Ke Li: Learning to Optimize and Fast k-Nearest Neighbour SearchJessica Hamrick: Metacontrol for Imagination-Based Optimization
Apr. 7Deepak Pathak: Exploring Four Axes of Self-SupervisionSaurabh Gupta: Cognitive Mapping and Planning for Visual Navigation
Apr. 14Jeff Mahler: Dex-Net: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp MetricsJudy Hoffman: A General Framework for Domain Adversarial Learning
Apr. 21Fereshteh Sadeghi: Sim2Real Collision Avoidance for Indoor Navigation of Mobile Robots via Deep Reinforcement LearningEvan Shelhamer: Loss is its own Reward: Self-Supervision for Reinforcement Learning
Apr. 28Roberto Calandra: Robustness in Multi-objective Bayesian optimizationRichard Zhang: Cross-Channel Visual Prediction
May 5Abhishek Gupta: Imitation Learning for Dexterous Manipulation and Transfer in Reinforcement LearningTinghui Zhou: 3D Visual Synthesis and Understanding from 2D Views
May 12Karl Zipser: New Trajectories in the Autonomous Model Car ProjectDaniel Drew: Silent Swarms: Flying Microrobots Using Atmospheric Ion Thrusters

Fall 2016 Schedule

DateSpeaker 1: 3:10-3:40Speaker 2: 3:40-4:10
Aug. 26Ken Goldberg: Deep DexteritySanjay Krishnan: Inverse Reinforcement Learning For Sequential Robotic Tasks
Sep 2Anca Dragan: How Robots Influence Our ActionsJeff Donahue: Adversarial Feature Learning
Sep 9Robert Nishihara & Philipp Moritz: Distributed Machine Learning with RayJohn DeNero: Interactive machine translation
Sep 16Joseph Gonzalez: Prediction Serving and RISEKevin Jamieson: Bayesian Optimization and other bad ideas for hyperparameter tuning
Sep 23Stuart Russell: Human-Compatible AIMarcus Rohrbach: Explain and Answer: Intelligent systems which can communicate about what they see.
Sep 30Richard Zhang: Colorful Image ColorizationVirginia Smith: A General Framework for Communication-Efficient Distributed Optimization
Oct 7Gregory Kahn: Learning Control Policies for Partially Observable Safety-Critical SystemsJohn Canny: Accountable Deep Networks
Oct 14Ruzena Bajcsy: Individualized Human Models for Cyberphysical InteractionJacob Andreas: Neural module networks
Oct 21Dave Moore: Bayesian seismic monitoring from raw waveformsGreg Durrett: Data-Driven Text Analysis with Joint Models
Oct 28Jun-Yan Zhu: Visual Manipulation and Synthesis on the Natural Image ManifoldDylan Hadfield-Menell: The Off-Switch
Nov 4Bin Yu: Artificial neurons meet real neurons: building stable interpretations of V4 neurons from CNN+regression modelsPulkit Agrawal: Forecasting from Pixels: Intuitive Physics and Intuitive Behavior
Dec 02Chelsea Finn: Adversarial Inverse Reinforcement LearningAviv Tamar: Deep Policy Representations based on a Planning Computation
Dec 09Michael Laskey: A Human-Centric Approach to Deep Robotic Learning from Demonstrations.Michael Oliver: Using artificial neural networks to model visual neurons
Dec 16Lisa Anne Hendricks: Localizing Moments in Video with Natural LanguageAndrew Owens: Learning visual models from paired audio-visual examples