2025
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs.
CoRR, April, 2025
Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning.
CoRR, April, 2025
Task-Driven Semantic Quantization and Imitation Learning for Goal-Oriented Communications.
CoRR, February, 2025
PICO-RAM: A PVT-Insensitive Analog Compute-In-Memory SRAM Macro With In Situ Multi-Bit Charge Computing and 6T Thin-Cell-Compatible Layout.
IEEE J. Solid State Circuits, January, 2025
URLOST: Unsupervised Representation Learning without Stationarity or Topology.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
2024
Trajectory Regularization Enhances Self-Supervised Geometric Representation.
CoRR, 2024
Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition.
CoRR, 2024
Insight: A Multi-modal Diagnostic Pipeline Using LLMs for Ocular Surface Disease Diagnosis.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2024, 2024
Pose-Aware Self-supervised Learning with Viewpoint Trajectory Regularization.
Proceedings of the Computer Vision - ECCV 2024, 2024
Unsupervised Feature Learning with Emergent Data-Driven Prototypicality.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
2023
Learning Energy-Based Models in High-Dimensional Spaces with Multiscale Denoising-Score Matching.
Entropy, October, 2023
Bag of Image Patch Embedding Behind the Success of Self-Supervised Learning.
Trans. Mach. Learn. Res., 2023
URLOST: Unsupervised Representation Learning without Stationarity or Topology.
CoRR, 2023
Variance-Covariance Regularization Improves Representation Learning.
CoRR, 2023
EMP-SSL: Towards Self-Supervised Learning in One Training Epoch.
CoRR, 2023
Compact and Optimal Deep Learning with Recurrent Parameter Generators.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
Simple Emergent Action Representations from Multi-Task Policy Training.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
On the duality between contrastive and non-contrastive self-supervised learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
2022
RG-Flow: a hierarchical and explainable flow model based on renormalization group and sparse prior.
Mach. Learn. Sci. Technol., 2022
Unsupervised Learning of Structured Representations via Closed-Loop Transcription.
CoRR, 2022
Minimalistic Unsupervised Learning with the Sparse Manifold Transform.
CoRR, 2022
Joint Embedding Self-Supervised Learning in the Kernel Regime.
CoRR, 2022
Intra-Instance VICReg: Bag of Self-Supervised Image Patch Embedding.
CoRR, 2022
Neural Manifold Clustering and Embedding.
CoRR, 2022
Disentangling images with Lie group transformations and sparse coding.
Proceedings of the NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2022
Decoupled Contrastive Learning.
Proceedings of the Computer Vision - ECCV 2022, 2022
3D Shape Reconstruction from Free-Hand Sketches.
Proceedings of the Computer Vision - ECCV 2022 Workshops, 2022
Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
2021
A Neural Network MCMC Sampler That Maximizes Proposal Entropy.
Entropy, 2021
Free Hyperbolic Neural Networks with Limited Radii.
CoRR, 2021
Recurrent Parameter Generators.
CoRR, 2021
The 2020 Low-Power Computer Vision Challenge.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the 3rd IEEE International Conference on Artificial Intelligence Circuits and Systems, 2021
Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors.
Proceedings of Deep Learning Inside Out: The 2nd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, 2021
2020
The Sparse Manifold Transform and Unsupervised Learning for Signal Representation.
PhD thesis, 2020
Orthogonal Convolutional Neural Networks.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
2019
Annealed Denoising Score Matching: Learning Energy-Based Models in High-Dimensional Spaces.
CoRR, 2019
Word Embedding Visualization Via Dictionary Learning.
CoRR, 2019
Superposition of many models into one.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
2018
The Sparse Manifold Transform.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
2014
Orchestrating Cache Management and Memory Scheduling for GPGPU Applications.
IEEE Trans. Very Large Scale Integr. Syst., 2014
2013
Exploiting the Task-Pipelined Parallelism of Stream Programs on Many-Core GPUs.
IEICE Trans. Inf. Syst., 2013
2012
Providing Source Code Level Portability Between CPU and GPU with MapCG.
J. Comput. Sci. Technol., 2012
2011
Hermes: an integrated CPU/GPU microarchitecture for IP routing.
Proceedings of the 48th Design Automation Conference, 2011