Show Detail » Timezone:
America/Los_Angeles
Filter Events:  

 

MON 25 APR
midnight
Remarks:
(ends 12:55 AM)
1 a.m.
Invited Talk:
Pushmeet Kohli
(ends 2:15 AM)
2:30 a.m.
(ends 4:30 AM)
10:30 a.m.
(ends 12:30 PM)
noon
Affinity Social:
(ends 4:59 PM)
Affinity Social:
(ends 2:00 PM)
5 p.m.
Orals 5:00-6:30
[5:00] Language modeling via stochastic processes
[5:15] MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling
[5:30] Real-Time Neural Voice Camouflage
[5:45] ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics
[6:00] Open-Set Recognition: A Good Closed-Set Classifier is All You Need
[6:15] Vision-Based Manipulators Need to Also See from Their Hands
(ends 6:30 PM)
Orals 5:00-6:30
[5:00] Hyperparameter Tuning with Renyi Differential Privacy
[5:15] PiCO: Contrastive Label Disambiguation for Partial Label Learning
[5:30] Poisoning and Backdooring Contrastive Learning
[5:45] Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
[6:00] The Information Geometry of Unsupervised Reinforcement Learning
[6:15] Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics
(ends 6:30 PM)
6:30 p.m.
(ends 8:30 PM)
8 p.m.
Affinity Social:
(duration 1.0 hr)
TUE 26 APR
1 a.m.
Orals 1:00-2:30
[1:00] Understanding over-squashing and bottlenecks on graphs via curvature
[1:15] Efficiently Modeling Long Sequences with Structured State Spaces
[1:30] Neural Structured Prediction for Inductive Node Classification
[1:45] A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?"
[2:00] CycleMLP: A MLP-like Architecture for Dense Prediction
[2:15] Variational Inference for Discriminative Learning with Generative Modeling of Feature Incompletion
(ends 2:30 AM)
Orals 1:00-2:45
[1:00] Expressiveness and Approximation Properties of Graph Neural Networks
[1:15] Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
[1:30] Learning Strides in Convolutional Neural Networks
[1:45] The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions
[2:00] Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond
[2:15] DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNS
[2:30] Representational Continuity for Unsupervised Continual Learning
(ends 2:45 AM)
Orals 1:00-2:30
[1:00] Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space
[1:15] Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization
[1:30] Data-Efficient Graph Grammar Learning for Molecular Generation
[1:45] iLQR-VAE : control-based learning of input-driven dynamics with applications to neural data
[2:00] Einops: Clear and Reliable Tensor Manipulations with Einstein-like Notation
[2:15] StyleAlign: Analysis and Applications of Aligned StyleGAN Models
(ends 2:30 AM)
2:30 a.m.
(ends 4:30 AM)
10:30 a.m.
(ends 12:30 PM)
noon
Affinity Social:
(duration 1.0 hr)
1 p.m.
3 p.m.
5 p.m.
Invited Talk:
Jenny Davis
(ends 6:15 PM)
6:30 p.m.
(ends 8:30 PM)
WED 27 APR
1 a.m.
Invited Talk:
Cordelia Schmid
(ends 2:15 AM)
2:30 a.m.
(ends 4:30 AM)
9 a.m.
Orals 9:00-10:30
[9:00] Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
[9:15] Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks
[9:30] A Fine-Grained Analysis on Distribution Shift
[9:45] Sparse Communication via Mixed Distributions
[10:00] Frame Averaging for Invariant and Equivariant Network Design
[10:15] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization
(ends 10:30 AM)
Orals 9:00-10:30
[9:00] Bootstrapped Meta-Learning
[9:15] Coordination Among Neural Modules Through a Shared Global Workspace
[9:30] Meta-Learning with Fewer Tasks through Task Interpolation
[9:45] Weighted Training for Cross-Task Learning
[10:00] Domino: Discovering Systematic Errors with Cross-Modal Embeddings
[10:15] Extending the WILDS Benchmark for Unsupervised Adaptation
(ends 10:30 AM)
10:30 a.m.
(ends 12:30 PM)
5 p.m.
Invited Talk:
Kunle Olukotun
(ends 6:15 PM)
6:30 p.m.
(ends 8:30 PM)
8 p.m.
THU 28 APR
1 a.m.
Orals 1:00-2:30
[1:00] Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
[1:15] Natural Language Descriptions of Deep Features
[1:30] Finetuned Language Models are Zero-Shot Learners
[1:45] Large Language Models Can Be Strong Differentially Private Learners
[2:00] GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation
[2:15] Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting
(ends 2:30 AM)
Orals 1:00-2:30
[1:00] Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
[1:15] Comparing Distributions by Measuring Differences that Affect Decision Making
[1:30] Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling
[1:45] RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation
[2:00] BEiT: BERT Pre-Training of Image Transformers
[2:15] Resolving Training Biases via Influence-based Data Relabeling
(ends 2:30 AM)
2:30 a.m.
(ends 4:30 AM)
4 a.m.
6 a.m.
9 a.m.
From Reinforcement Learning to AI:
Doina Precup
(ends 10:15 AM)
10:30 a.m.
(ends 12:30 PM)
12:30 p.m.
Town Hall:
(ends 1:30 PM)
2 p.m.
5 p.m.
Invited Talk:
H. Sebastian Seung
(ends 6:15 PM)
6:30 p.m.
(ends 8:30 PM)
FRI 29 APR
midnight
Remarks:
(ends 12:30 AM)
1:45 a.m.
2 a.m.
Workshop:
(ends 11:30 AM)
8 a.m.
Workshop:
(ends 2:00 PM)
Workshop:
(ends 4:35 PM)