Demo Data from EDBT 2026 / reviewers in the wild / expert
Kyle Hsu
dblp:217/3841
· DBLP profile ↗
12ranked-venue papers
6as first author
8since 2021 · last 2025
—ORCID · none
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 10 · 4 first-author · 8 since 2021Systems, architecture and hardware · 1 · 1 since 2021Software engineering, systems software and programming languages · 1 · 1 first-authorGraphics, computer vision, multimedia, augmented reality and games · 1 · 1 since 2021Theory of computation · 1 · 1 first-author
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
9 papers |
Representation and self-supervised learning · 22% Probabilistic and Bayesian machine learning · 19% Generative modeling · 14% | |
| Computer graphics and multimedia
1 paper |
Image and video coding · 100% |
Topics — the 19 heaviest of 23, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Deep learning architectures and training
autoencoder |
1.4 | 2 | 2024 | Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning · ICML 2024 Disentanglement via Latent Quantization · NeurIPS 2023 |
Machine learning › Representation and self-supervised learning › representation learning
disentangled representation learning |
1.4 | 2 | 2024 | Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning · ICML 2024 Disentanglement via Latent Quantization · NeurIPS 2023 |
Machine learning › Generative modeling › diffusion model › diffusion-based representation learning
diffusion autoencoder |
0.9 | 1 | 2025 | Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization · ICCV 2025 |
Machine learning › Generative modeling
diffusion model |
0.9 | 1 | 2025 | Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization · ICCV 2025 |
Machine learning › Probabilistic and Bayesian machine learning › structured models › latent variable model
latent generative model |
0.9 | 1 | 2025 | Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization · ICCV 2025 |
Machine learning › Representation and self-supervised learning › representation learning
modular representation learning |
0.9 | 1 | 2025 | Range, not Independence, Drives Modularity in Biologically Inspired Representations · ICLR 2025 |
Image and video coding
image tokenization |
0.9 | 1 | 2025 | Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization · ICCV 2025 |
Image and video coding › image compression
learned image compression |
0.9 | 1 | 2025 | Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization · ICCV 2025 |
Robotics › Motion planning and robot control › robot learning › robot policy learning
generalist robot policy |
0.8 | 1 | 2024 | Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration · ICRA 2024 |
Robotics › Motion planning and robot control
robot learning |
0.8 | 1 | 2024 | Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration · ICRA 2024 |
Robotics › Robot manipulation › robot vision
vision-based manipulation |
0.6 | 1 | 2022 | Vision-Based Manipulators Need to Also See from Their Hands · ICLR 2022 |
Machine learning › Probabilistic and Bayesian machine learning › monte carlo methods › importance sampling
annealed importance sampling |
0.5 | 1 | 2021 | Differentiable Annealed Importance Sampling and the Perils of Gradient Noise · NeurIPS 2021 |
Machine learning › Probabilistic and Bayesian machine learning › statistical inference › bayesian inference › bayesian model selection
marginal likelihood estimation |
0.5 | 1 | 2021 | Differentiable Annealed Importance Sampling and the Perils of Gradient Noise · NeurIPS 2021 |
Machine learning › Probabilistic and Bayesian machine learning › probabilistic inference › approximate inference
variational inference |
0.5 | 1 | 2021 | Differentiable Annealed Importance Sampling and the Perils of Gradient Noise · NeurIPS 2021 |
Machine learning › Reinforcement learning › reinforcement learning environment › environment design
automatic curriculum learning |
0.4 | 1 | 2019 | Unsupervised Curricula for Visual Meta-Reinforcement Learning · NeurIPS 2019 |
Machine learning › Reinforcement learning
meta-reinforcement learning |
0.4 | 1 | 2019 | Unsupervised Curricula for Visual Meta-Reinforcement Learning · NeurIPS 2019 |
Machine learning › Transfer learning and domain adaptation › meta-learning
unsupervised meta-learning |
0.4 | 1 | 2019 | Unsupervised Learning via Meta-Learning · ICLR (Poster) 2019 |
Machine learning › Representation and self-supervised learning › representation learning
unsupervised representation learning |
0.4 | 1 | 2019 | Unsupervised Learning via Meta-Learning · ICLR (Poster) 2019 |
Machine learning › Representation and self-supervised learning › representation learning
visual representation learning |
0.1 | 1 | 2019 | Unsupervised Curricula for Visual Meta-Reinforcement Learning · NeurIPS 2019 |
Methods — techniques the papers use, named apart from their topics
transformer · 1.7mode-seeking training · 1.7mode-matching pretraining · 1.7unsupervised learning · 0.9supervised learning · 0.9linear autoencoder theory · 0.9quantization · 0.8large-scale pretraining · 0.8independence regularization · 0.8functional influence regularization · 0.8
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image TokenizationabstractSince the advent of popular visual generation frameworks like VQGAN and latent diffusion models, state-of-the-art image generation systems have generally been two-stage systems that first tokenize or compress visual data into a lower-dimensional latent space before learning a generative model. Tokenizer training typically follows a standard recipe in which images are compressed and reconstructed subject to a combination of MSE, perceptual, and adversarial losses. Diffusion autoencoders have been proposed in prior work as a way to learn end-to-end perceptually-oriented image compression, but have not yet shown state-of-the-art performance on the competitive task of ImageNet-1K reconstruction. We propose FlowMo, a transformer-based diffusion autoencoder that achieves a new state-of-the-art for image tokenization at multiple compression rates without using convolutions, adversarial losses, spatially-aligned two-dimensional latent codes, or distilling from other tokenizers. Our key insight is that FlowMo training should be broken into a mode-matching pre-training stage and a mode-seeking post-training stage. In addition, we conduct extensive analyses and explore the training of generative models atop the FlowMo tokenizer. Our code and models will be available at http://kylesargent.github.io/flowmo . Kyle Sargent, Kyle Hsu, Justin Johnson 0001, Li Fei-Fei 0001, Jiajun Wu 0001 |
ICCV | 2 |
| 2025 | Range, not Independence, Drives Modularity in Biologically Inspired RepresentationsabstractWhy do biological and artificial neurons sometimes modularise, each encoding a single meaningful variable, and sometimes entangle their representation of many variables? In this work, we develop a theory of when biologically inspired networks---those that are nonnegative and energy efficient---modularise their representation of source variables (sources). We derive necessary and sufficient conditions on a sample of sources that determine whether the neurons in an optimal biologically-inspired linear autoencoder modularise. Our theory applies to any dataset, extending far beyond the case of statistical independence studied in previous work. Rather we show that sources modularise if their support is ``sufficiently spread''. From this theory, we extract and validate predictions in a variety of empirical studies on how data distribution affects modularisation in nonlinear feedforward and recurrent neural networks trained on supervised and unsupervised tasks. Furthermore, we apply these ideas to neuroscience data, showing that range independence can be used to understand the mixing or modularising of spatial and reward information in entorhinal recordings in seemingly conflicting experiments. Further, we use these results to suggest alternate origins of mixed-selectivity, beyond the predominant theory of flexible nonlinear classification. In sum, our theory prescribes precise conditions on when neural activities modularise, providing tools for inducing and elucidating modular representations in brains and machines. William Dorrell, Kyle Hsu, Luke Hollingsworth, Jin Hwa Lee, Jiajun Wu 0001, Chelsea Finn, Peter E. Latham, Timothy Edward John Behrens, James C. R. Whittington |
ICLR | 2 |
| 2024 | Tripod: Three Complementary Inductive Biases for Disentangled Representation LearningabstractInductive biases are crucial in disentangled representation learning for narrowing down an underspecified solution set. In this work, we consider endowing a neural network autoencoder with three select inductive biases from the literature: data compression into a grid-like latent space via quantization, collective independence amongst latents, and minimal functional influence of any latent on how other latents determine data generation. In principle, these inductive biases are deeply complementary: they most directly specify properties of the latent space, encoder, and decoder, respectively. In practice, however, naively combining existing techniques instantiating these inductive biases fails to yield significant benefits. To address this, we propose adaptations to the three techniques that simplify the learning problem, equip key regularization terms with stabilizing invariances, and quash degenerate incentives. The resulting model, Tripod, achieves state-of-the-art results on a suite of four image disentanglement benchmarks. We also verify that Tripod significantly improves upon its naive incarnation and that all three of its "legs" are necessary for best performance. Kyle Hsu, Jubayer Ibn Hamid, Kaylee Burns, Chelsea Finn, Jiajun Wu 0001 |
ICML | 1 |
| 2024 | Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment CollaborationabstractLarge, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io. Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin |
ICRA | 140 |
| 2023 | Disentanglement via Latent QuantizationabstractIn disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these sources, inductive biases take a paramount role in enabling disentanglement. In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. Concretely, we do this by (i) quantizing the latent space into discrete code vectors with a separate learnable scalar codebook per dimension and (ii) applying strong model regularization via an unusually high weight decay. Intuitively, the latent space design forces the encoder to combinatorially construct codes from a small number of distinct scalar values, which in turn enables the decoder to assign a consistent meaning to each value. Regularization then serves to drive the model towards this parsimonious strategy. We demonstrate the broad applicability of this approach by adding it to both basic data-reconstructing (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models. For reliable evaluation, we also propose InfoMEC, a new set of metrics for disentanglement that is cohesively grounded in information theory and fixes well-established shortcomings in previous metrics. Together with regularization, latent quantization dramatically improves the modularity and explicitness of learned representations on a representative suite of benchmark datasets. In particular, our quantized-latent autoencoder (QLAE) consistently outperforms strong methods from prior work in these key disentanglement properties without compromising data reconstruction. Kyle Hsu, William Dorrell, James C. R. Whittington, Jiajun Wu 0001, Chelsea Finn |
NeurIPS | 1 |
| 2022 | Vision-Based Manipulators Need to Also See from Their Hands
Kyle Hsu, Moo Jin Kim, Rafael Rafailov, Jiajun Wu 0001, Chelsea Finn |
ICLR | 1 |
| 2021 | On the role of data in PAC-Bayes
Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Gabriel Arpino, Daniel M. Roy 0001 |
AISTATS | 2 |
| 2021 | Differentiable Annealed Importance Sampling and the Perils of Gradient NoiseabstractAnnealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation, but are not fully differentiable due to the use of Metropolis-Hastings correction steps. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective using gradient-based methods. To this end, we propose Differentiable AIS (DAIS), a variant of AIS which ensures differentiability by abandoning the Metropolis-Hastings corrections. As a further advantage, DAIS allows for mini-batch gradients. We provide a detailed convergence analysis for Bayesian linear regression which goes beyond previous analyses by explicitly accounting for the sampler not having reached equilibrium. Using this analysis, we prove that DAIS is consistent in the full-batch setting and provide a sublinear convergence rate. Furthermore, motivated by the problem of learning from large-scale datasets, we study a stochastic variant of DAIS that uses mini-batch gradients. Surprisingly, stochastic DAIS can be arbitrarily bad due to a fundamental incompatibility between the goals of last-iterate convergence to the posterior and elimination of the accumulated stochastic error. This is in stark contrast with other settings such as gradient-based optimization and Langevin dynamics, where the effect of gradient noise can be washed out by taking smaller steps. This indicates that annealing-based marginal likelihood estimation with stochastic gradients may require new ideas. Guodong Zhang 0006, Kyle Hsu, Chelsea Finn, Roger B. Grosse |
NeurIPS | 2 |
| 2019 | Lazy Abstraction-Based Controller Synthesis
Kyle Hsu, Rupak Majumdar, Kaushik Mallik, Anne-Kathrin Schmuck |
ATVA | 1 |
| 2019 | Unsupervised Learning via Meta-Learning
Kyle Hsu, Sergey Levine, Chelsea Finn |
ICLR (Poster) | 1 |
| 2019 | Unsupervised Curricula for Visual Meta-Reinforcement LearningabstractIn principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast and effective reinforcement learning (RL) strategies. However, current meta-RL approaches rely on manually-defined distributions of training tasks, and hand-crafting these task distributions can be challenging and time-consuming. Can ``useful'' pre-training tasks be discovered in an unsupervised manner? We develop an unsupervised algorithm for inducing an adaptive meta-training task distribution, i.e. an automatic curriculum, by modeling unsupervised interaction in a visual environment. The task distribution is scaffolded by a parametric density model of the meta-learner's trajectory distribution. We formulate unsupervised meta-RL as information maximization between a latent task variable and the meta-learner’s data distribution, and describe a practical instantiation which alternates between integration of recent experience into the task distribution and meta-learning of the updated tasks. Repeating this procedure leads to iterative reorganization such that the curriculum adapts as the meta-learner's data distribution shifts. Moreover, we show how discriminative clustering frameworks for visual representations can support trajectory-level task acquisition and exploration in domains with pixel observations, avoiding the pitfalls of alternatives. In experiments on vision-based navigation and manipulation domains, we show that the algorithm allows for unsupervised meta-learning that both transfers to downstream tasks specified by hand-crafted reward functions and serves as pre-training for more efficient meta-learning of test task distributions. Allan Jabri, Kyle Hsu, Abhishek Gupta 0004, Benjamin Eysenbach, Sergey Levine, Chelsea Finn |
NeurIPS | 2 |
| 2018 | Multi-Layered Abstraction-Based Controller Synthesis for Continuous-Time SystemsabstractWe present multi-layered abstraction-based controller synthesis, which extends standard abstraction-based controller synthesis (ABCS) algorithms for continuous-time control systems by simultaneously maintaining several "layers" of abstract systems with decreasing precision. The resulting abstract multi-layered controller uses the coarsest abstraction whenever this is feasible, and dynamically adjusts the precision---by moving to a more precise abstraction and back to a coarser abstraction---based on the structure of the given control problem. Abstract multi-layered controllers can be refined to controllers with non-uniform resolution using feedback refinement relations established between each abstract layer and the concrete system, resulting in a sound ABCS method. We provide multi-layered controller synthesis algorithms for reachability, safety, and generalized Büchi specifications; our approach can be generalized to any ω-regular objective. Our algorithms are complete relative to single-layered synthesis on the finest layer. We empirically demonstrate that multi-layered synthesis can outperform standard (single-layer) ABCS algorithms on a number of examples, despite the additional cost of constructing multiple abstract systems. Kyle Hsu, Rupak Majumdar, Kaushik Mallik, Anne-Kathrin Schmuck |
HSCC | 1 |