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 bair-admin@berkeley.edu .
Spring 2021 Schedule
Date Speaker 1: 11:10 AM -12:00 PM or 11:10-11:30 AM Speaker 2: N/A or 11:30-11:50 AM Jan 26 Hany Farid : Forensic Photographic IdentificationN/A Feb 2 Stephen Bates : Distribution-Free, Risk-Controlling Prediction SetsN/A Feb 9 Abhishek Gupta : Algorithms and Systems for Real World Robotic LearningN/A Feb 16 Glen Berseth : Developing Autonomous Agents to Learn and Plan in the Real WorldN/A Feb 23 Forrest Laine : Computing Feedback Nash Equilibria in Robotic GamesN/A Mar 2 Ellen Novoseller : Online Learning from Human Preference Feedback and Multi-Fidelity Models with Application to Assistive ExoskeletonsN/A Mar 9 Amir Gholami : Systematic Neural Network Pruning and QuantizationColorado Reed : Practical Self-Supervised LearningMar 16 N/A TBD Mar 23 N/A N/A Mar 30 Adam Gleave : Understanding and Evaluating Learned Reward FunctionsN/A Apr 6 Jiachen Li : Relational Reasoning for Multi-Agent SystemsN/A Apr 13 Taesung Park : Machine Learning for Deep Image ManipulationN/A Apr 20 Samaneh Azadi : Towards Content-Creative AIN/A Apr 27 Daniel Seita : TBDN/A
Fall 2020 Schedule
Date Speaker 1: 11:10 AM -12:00 PM or 11:10-11:30 AM Speaker 2: N/A or 11:30-11:50 AM Sep 1 Alvin Wan : What Explainable AI Fails to Explain (and how we fix that)Amir Gholami , Zhewei Yao : ADAHESSIAN: An Adaptive Second Order Optimizer for Machine LearningSep 8 Nikita 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 TextbooksSep 15 Georgios Pavlakos: Learning to Reconstruct 3D Humans N/A Sep 22 Lerrel Pinto : Rich Robotic Supervision through Cheap Human DemonstrationsN/A Sep 29 Philippe Laban : Text Summarization Without The SummariesKatie Stasaski : More Diverse Dialogue Datasets via Diversity-Informed Data CollectionOct 6 Aldo Pacchiano : Learning to Score Behaviors for Guided Policy OptimizationN/A Oct 13 Paria Rashidinejad: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory Zhen Dong : Efficient Neural Networks Through Systematic QuantizationOct 20 Eugene Vinitsky : Optimizing Energy Efficiency of Traffic at Scale via Multi-agent Deep RLAnastasios Angelopoulos: Uncertainty for Black Box Models Oct 27 Misha Laskin : Escaping the Simulator: Accelerating Real Robot Learning through Unsupervised LearningN/A Nov 3 Wei Zhan : Close-loop Evaluation of Prediction Algorithms with Complex Scenarios from Naturalistic Driving DataLiting Sun : Modeling Human Behaviors in Human-robot InteractionsNov 10 Daniel Brown : Safe and Efficient Imitation LearningN/A Nov 17 Edward Kim: Scenic: Dynamic Scenario Description Language for Autonomous Systems Kimin Lee : Ensemble methods in reinforcement learningNov 24 Xin Wang : Last-Mile Delivery of Computer Vision with Test-Time AdaptationN/A Dec 1 Huijuan Xu : Temporal Action Detection in Videos with Multi-Level SupervisionN/A
Spring 2020 Schedule
Date Speaker 1: 3:10-4:00 or 3:10-3:30 Speaker 2: N/A or 3:30-3:50 Jan. 24 Dylan Hadfield-Menell : The Principal-Agent Value Alignment ProblemN/A Jan. 31 Somil Bansal : Safe and Data-efficient Learning for Physical SystemsN/A Feb. 7 Nick Antipa : Lensless Computational Imaging: Seeing More with LessN/A Feb. 14 Ruoxi Jia : Towards a Responsible Data Economy: Fairness, Privacy, and SecurityN/A Feb. 21 Chandan Singh : Interpreting and Improving Neural Networks via Disentangled AttributionsN/A Feb. 28 Alexei (Alyosha) Efros : Image Manipulation… And Ways to Detect ItN/A Mar. 6 Brijen 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 PlanningMar. 13 Aravind Srinivas : Self-Supervised Visual Representation LearningN/A Mar. 20 Ronghang Hu : Structured Models for Vision-and-Language ReasoningN/A Mar. 27 No Seminar N/A Apr. 3 Misha Laskin: Improving Reinforcement Learning with Unsupervised and Self-Supervised Learning N/A Apr. 10 Dequan Wang : Object-Centric Representation for Perception, Prediction, and PlanningN/A Apr. 17 Coline Devin: Learning with Modularity and Compositionality for Robotics Apr. 24 Cecilia Zhang : Bringing Cinema Quality Rendering into Casual Photos and Videos.N/A May 1 Sylvia Herbert : Safe Real-World Autonomy in Uncertain and Unstructured EnvironmentsN/A May 8 Sasha Sax: Robust Learning Through Cross-Task Consistency N/A May 15 Carlos Florensa : What Supervision Scales? Practical Learning Through InteractionN/A
Spring 2019 Schedule
Date Speaker 1: 3:10-4:00 or 3:10-3:30 Speaker 2: N/A or 3:30-3:50 Jan. 18 Eric Jonas : Structured Prediction via Machine Learning for Inverse ProblemsN/A Jan. 25 Dinesh Jayaraman: Towards Embodied Visual Intelligence N/A Feb. 1 Ke Li : Advances in Machine Learning: Learning to Optimize, Generative Modelling and Nearest Neighbour SearchN/A Feb. 8 Deepak Pathak : Self-Directed LearningN/A Feb. 15 Samaneh 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. 22 Jaime Fisac : Resilient Safety Assurance for Robotic Systems: Staying Safe Even When Models Are WrongN/A Mar. 1 Fisher Yu : Towards Human-Level Recognition via Contextual, Dynamic, and Predictive RepresentationsN/A Mar. 8 Andrew Owens : Sight and SoundN/A Mar. 15 Daniel Fried : Pragmatic Models for Generating and Following Grounded InstructionsNikita Kitaev : Syntactic Parsing with Self-AttentionMar. 22 **Oriol Vinyals : AlphaStar: Mastering the Real-Time Strategy Game StarCraft II (**This will be held 11am-12pm in 250 SDH**) N/A Mar. 22 Jacob Steinhardt : What Makes Neural Networks (Non-)Robust?N/A Mar. 29 Holiday Holiday Apr. 5 Alex Lee : Visual Dynamics Models for Robotic Planning and ControlN/A Apr. 12 Lisa Anne Hendricks: Visual Understanding through Natural LanguageN/A Apr. 19 Evan Shelhamer : Blurring the Line between Structure and Learning for Adaptive Local RecognitionN/A Apr. 26 Yian Ma : Bridging MCMC and OptimizationN/A May 3 Sandy Huang : Optimizing for Robot TransparencyN/A May 10 Jeffrey Regier: Statistical Inference for Cataloging the Visible Universe N/A
Fall 2018 Schedule
Date Speaker 1: 3:10-4:00 or 3:10-3:30 Speaker 2: N/A or 3:30-3:50 Aug. 24 Jaime Fisac , Andrea Bajcsy , Sylvia Herbert : Probabilistically Safe Robot Planning with Confidence-Based Human PredictionsN/A Aug. 31 Aviv Tamar : Learning Representations for PlanningN/A Sept. 7 Chi Jin: Is Q-learning Provably Efficient? N/A Sept. 14 Wojciech Zaremba : Learning dexterityN/A Sept. 21 Tuomas Haarnoja: Acquiring Diverse Robot Skills via Maximum Entropy Reinforcement Learning N/A Sept. 28 Professor Ruzena Bajcsy : Data Driven vs. Model Driven Analysis of Human Ability for Human Robot InteractionN/A Oct. 5 Ke Li : Implicit Maximum Likelihood EstimationN/A Oct. 12 Roy Fox : Multi-Task Hierarchical Imitation Learning of Robot SkillsN/A Oct. 19 Ankush Desai: DRONA: A Framework for Programming Safe Robotics Systems N/A Oct. 26 Ajay Tanwani : A Fog Robotics Approach to Large Scale Robot LearningLaura Hallock : Human Muscle Force Modeling for Enhanced Assistive Device ControlNov. 2 Abhishek Gupta : Unsupervised (Meta) RLAnja Rohrbach : Diagnosing and correcting bias in captioning modelsNov. 9 Holiday Holiday Nov. 16 Daniel Fried : Pragmatic Models for Generating and Following Grounded InstructionsNikita Kitaev : Syntactic Parsing with Self-AttentionNov. 23 Holiday Holiday Dec. 7 Jiantao Jiao : Deconstructing Generative Adversarial NetworksN/A
Spring 2018 Schedule
Date Speaker 1: 3:10-4:00 or 3:10-3:30 Speaker 2: N/A or 3:30-3:50 Jan. 19 Pulkit Agrawal : Continually Evolving Machines: Learning by ExperimentingN/A Jan. 26 Sanjay Krishnan: Dirty Data, Robotics, and Artificial IntelligenceN/A Feb. 2 David Fouhey : Towards a 3D World of InteractionN/A Feb. 9 Saurabh Gupta : Visual Perception and Navigation in 3D ScenesN/A Feb. 16 Jacob Andreas: Learning from Language N/A Feb. 23 Chelsea Finn: Generalization and Self-Supervision in Deep Robotic Learning N/A Mar. 2 Jennifer Listgarten : Where genetics and biology meet machine learningN/A Mar. 9 Yi Ma: Low-dimensional Structures and Deep Models for High-dimensional Data TBD Mar. 16 Cathy Wu : Mixed-autonomy mobility: scalable learning and optimizationN/A Mar. 23 Xiang Cheng: Langevin MCMC as gradient flow over the probability space Eric Tzeng and Andreea Bobu : Domain Adaptation for Fixed and Continuously Varying DomainsApr. 6 Shubham Tulsiani: Learning Single-view 3D Reconstruction of Objects and ScenesTBD Apr. 13 Tinghui Zhou: Beyond Direct Supervision: Visual Learning via Data-driven Consistency Consistency (Location: SWARM Lab 490 Cory)N/A Apr. 20 Richard Zhang : Image Synthesis for Self-Supervised Representation LearningN/A Apr. 27 Reza Abbasi-Asl: Structural compression of Convolutional Neural Networks Fereshteh Sadeghi : Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control
Fall 2017 Schedule
Date Speaker 1: 3:10-3:40 Speaker 2: 3:40-4:10 Aug. 25 Jitendra Malik : What have we learned from datasets in computer vision?Angjoo Kanazawa : Single-View 3D Reconstruction of Deformable Objects like Animals and PeopleSept. 1 Chang Liu: Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection Claire Tomlin : Safe LearningSept. 8 Andrew Critch : Open-source game theory is weirdAnna Rohrbach : Generation and grounding of natural language descriptions for visual dataSept. 15 Bo Li : Secure learning in adversarial environmentsChing-Yao Chan: Safety of Automated Driving Systems (ADS) and AI/ML – A DialogueSept. 22 Alex 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. 29 Fisher Yu : Towards Universal Representation for Image RecognitionMax Rabinovich: Abstract Syntax Networks for Code Generation and Semantic Parsing Oct. 6 Michael Laskey: Learning Home Robotics Manipulation Tasks from Remote Supervision Pulkit Agrawal: Continually Evolving Agents: Curiosity & Experimentation Oct. 13 Ron Fearing : Dextrous LocomotionSylvia Herbert and David Fridovich : Planning, Fast and Slow with FaSTrack: A Framework for Adaptive Real-Time Safe Trajectory PlanningOct. 20 Emrah Bostan : Learning Convex Regularizers for Optimal Bayesian DenoisingSomil Bansal : Overcoming Model Bias in Model-based LearningOct. 27 Roberto Calandra Aaditya Ramdas: Sequential testing and online false discovery rate control Nov. 3 Roy Fox : Discovery of Hierarchical Structures for Robot Learning and Neural ProgrammingLeila Wehbe : Modeling brain responses to natural language stimuliNov. 10 Holiday Holiday Nov. 17 Jacob Andreas: Learning with Latent Language Niladri Chatterji: Alternating minimization for dictionary learning with random initialization Nov. 24 Holiday Holiday Dec. 1 Eric Jonas : Could a neuroscientist understand a microprocessorTuomas Haarnoja: Soft Q-Learning
Spring 2017 Schedule
Date Speaker 1: 3:10-3:40 Speaker 2: 3:40-4:10 Jan. 20 Jack Gallant: Melding neuroscience and computer scienceJavad Lavaei: On optimization theory, numerical algorithms and machine learning for nationwide energy systemsJan. 27 Trevor Darrell: Adaptive Learning of Driving Models from Large-scale Video DatasetsColine Devin: Transfer learning for robotics Feb. 3 Phillip Isola: Image-to-Image Translation with Conditional Adversarial NetworksAnil Aswani: Human Modeling Using Inverse OptimizationFeb. 10 Zeynep Akata: Generating Fine-Grained Visual Explanations and Realistic ImagesDeirdre Mulligan: Hand-offs in AI: Functional Fidelity, Values, and GovernanceFeb. 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 Handovers William Guss: WaveLayers: Neural Topology Inspired by TopologyFeb. 24 Laurent El Ghaoui: Safe feature elimination in sparse learningLaura Waller: Computational Microscopy with sparsityMar. 3 Chi Jin: How to Escape Saddle Points Efficiently Horia Mania: Universality of Mallows’ and degeneracy of Kendall’s kernels for rankings Mar. 10 Matthew 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 CompletionMar. 17 Roy Fox : Multi-Level Discovery of Deep OptionsParvez Ahammad : Beyond navigation metrics: Teaching computers how users perceive web application performanceMar. 24 Ke Li : Learning to Optimize and Fast k-Nearest Neighbour SearchJessica Hamrick: Metacontrol for Imagination-Based OptimizationApr. 7 Deepak Pathak : Exploring Four Axes of Self-SupervisionSaurabh Gupta : Cognitive Mapping and Planning for Visual NavigationApr. 14 Jeff Mahler : Dex-Net: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp MetricsJudy Hoffman : A General Framework for Domain Adversarial LearningApr. 21 Fereshteh Sadeghi : Sim2Real Collision Avoidance for Indoor Navigation of Mobile Robots via Deep Reinforcement LearningEvan Shelhamer : Loss is its own Reward: Self-Supervision for Reinforcement LearningApr. 28 Roberto Calandra : Robustness in Multi-objective Bayesian optimizationRichard Zhang: Cross-Channel Visual PredictionMay 5 Abhishek Gupta : Imitation Learning for Dexterous Manipulation and Transfer in Reinforcement LearningTinghui Zhou : 3D Visual Synthesis and Understanding from 2D ViewsMay 12 Karl Zipser : New Trajectories in the Autonomous Model Car ProjectDaniel Drew : Silent Swarms: Flying Microrobots Using Atmospheric Ion Thrusters
Fall 2016 Schedule
Date Speaker 1: 3:10-3:40 Speaker 2: 3:40-4:10 Aug. 26 Ken Goldberg: Deep Dexterity Sanjay Krishnan: Inverse Reinforcement Learning For Sequential Robotic Tasks Sep 2 Anca Dragan: How Robots Influence Our Actions Jeff Donahue: Adversarial Feature Learning Sep 9 Robert Nishihara & Philipp Moritz: Distributed Machine Learning with Ray John DeNero: Interactive machine translation Sep 16 Joseph Gonzalez: Prediction Serving and RISE Kevin Jamieson: Bayesian Optimization and other bad ideas for hyperparameter tuning Sep 23 Stuart Russell: Human-Compatible AI Marcus Rohrbach: Explain and Answer: Intelligent systems which can communicate about what they see. Sep 30 Richard Zhang: Colorful Image Colorization Virginia Smith: A General Framework for Communication-Efficient Distributed Optimization Oct 7 Gregory Kahn: Learning Control Policies for Partially Observable Safety-Critical Systems John Canny: Accountable Deep Networks Oct 14 Ruzena Bajcsy: Individualized Human Models for Cyberphysical Interaction Jacob Andreas: Neural module networks Oct 21 Dave Moore: Bayesian seismic monitoring from raw waveforms Greg Durrett: Data-Driven Text Analysis with Joint Models Oct 28 Jun-Yan Zhu: Visual Manipulation and Synthesis on the Natural Image Manifold Dylan Hadfield-Menell: The Off-Switch Nov 4 Bin Yu: Artificial neurons meet real neurons: building stable interpretations of V4 neurons from CNN+regression models Pulkit Agrawal: Forecasting from Pixels: Intuitive Physics and Intuitive Behavior Dec 02 Chelsea Finn: Adversarial Inverse Reinforcement Learning Aviv Tamar: Deep Policy Representations based on a Planning Computation Dec 09 Michael Laskey: A Human-Centric Approach to Deep Robotic Learning from Demonstrations. Michael Oliver : Using artificial neural networks to model visual neuronsDec 16 Lisa Anne Hendricks: Localizing Moments in Video with Natural Language Andrew Owens: Learning visual models from paired audio-visual examples