Toggle Poster Visibility
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Optimization inspired Multi-Branch Equilibrium Models
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Neural Networks as Kernel Learners: The Silent Alignment Effect
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
A Theory of Tournament Representations
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
TRGP: Trust Region Gradient Projection for Continual Learning
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
$\beta$-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Half-Inverse Gradients for Physical Deep Learning
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Context-Aware Sparse Deep Coordination Graphs
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Stein Latent Optimization for Generative Adversarial Networks
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Charformer: Fast Character Transformers via Gradient-based Subword Tokenization
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT) @ Virtual
EViT: Expediting Vision Transformers via Token Reorganizations
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT) @ Virtual
RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Information Gain Propagation: a New Way to Graph Active Learning with Soft Labels
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Learning Weakly-supervised Contrastive Representations
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Generalizing Few-Shot NAS with Gradient Matching
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT) @ Virtual
Know Thyself: Transferable Visual Control Policies Through Robot-Awareness
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT) @ Virtual
Bridging Recommendation and Marketing via Recurrent Intensity Modeling
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Gradient Information Matters in Policy Optimization by Back-propagating through Model
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
BEiT: BERT Pre-Training of Image Transformers
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Benchmarking the Spectrum of Agent Capabilities
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Coherence-based Label Propagation over Time Series for Accelerated Active Learning
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Efficient Sharpness-aware Minimization for Improved Training of Neural Networks
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Path Auxiliary Proposal for MCMC in Discrete Space
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Tracking the risk of a deployed model and detecting harmful distribution shifts
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Responsible Disclosure of Generative Models Using Scalable Fingerprinting
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Pre-training Molecular Graph Representation with 3D Geometry
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT) @ Virtual
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Convergent and Efficient Deep Q Learning Algorithm
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Exploring extreme parameter compression for pre-trained language models
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Scale Efficiently: Insights from Pretraining and Finetuning Transformers
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Pretrained Language Model in Continual Learning: A Comparative Study
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Large Language Models Can Be Strong Differentially Private Learners
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
How Low Can We Go: Trading Memory for Error in Low-Precision Training
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Learned Simulators for Turbulence
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Learning Continuous Environment Fields via Implicit Functions
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT) @ Virtual
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Learning Versatile Neural Architectures by Propagating Network Codes
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Convergent Graph Solvers
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Concurrent Adversarial Learning for Large-Batch Training
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Symbolic Learning to Optimize: Towards Interpretability and Scalability
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Neural Solvers for Fast and Accurate Numerical Optimal Control
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
SGD Can Converge to Local Maxima
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Meta-Imitation Learning by Watching Video Demonstrations
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT) @ Virtual
Online Hyperparameter Meta-Learning with Hypergradient Distillation
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
AdaAug: Learning Class- and Instance-adaptive Data Augmentation Policies
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Zero-Shot Self-Supervised Learning for MRI Reconstruction
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Mention Memory: incorporating textual knowledge into Transformers through entity mention attention
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
Declarative nets that are equilibrium models
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODEL
Poster
Wed Apr 27 06:30 PM -- 08:30 PM (PDT)
On the Convergence of Certified Robust Training with Interval Bound Propagation