Search Results for author:
Found 15 papers, 6 papers with code
PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization
Data augmentation is a popular tool for single source domain generalization, which expands the source domain by generating simulated ones, improving generalization on unseen target domains.
SceneMI: Motion In-betweening for Modeling Human-Scene Interactions
Modeling human-scene interactions (HSI) is essential for understanding and simulating everyday human behaviors.
Less is More: Improving Motion Diffusion Models with Sparse Keyframes
This severely limits the performance of generative motion models for downstream tasks.
Motion Synthesis with Sparse and Flexible Keyjoint Control
To process high-level intent and intuitive control in diverse scenarios, we propose a practical controllable motions synthesis framework that respects sparse and flexible keyjoint signals.
Versatile Physics-based Character Control with Hybrid Latent Representation
We present a versatile latent representation that enables physically simulated character to efficiently utilize motion priors.
A Survey on Human Interaction Motion Generation
Humans inhabit a world defined by interactions -- with other humans, objects, and environments.
Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning
Causal dynamics learning has recently emerged as a promising approach to enhancing robustness in reinforcement learning (RL).
Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction
Monte Carlo Tree Search (MCTS) has showcased its efficacy across a broad spectrum of decision-making problems.
On Discovery of Local Independence over Continuous Variables via Neural Contextual Decomposition
Conditional independence provides a way to understand causal relationships among the variables of interest.
Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details
We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects.
Learning Geometry-aware Representations by Sketching
Our method, coined Learning by Sketching (LBS), learns to convert an image into a set of colored strokes that explicitly incorporate the geometric information of the scene in a single inference step without requiring a sketch dataset.
SelecMix: Debiased Learning by Contradicting-pair Sampling
Experiments on standard benchmarks demonstrate the effectiveness of the method, in particular when label noise complicates the identification of bias-conflicting examples.
On the Importance of Critical Period in Multi-stage Reinforcement Learning
The initial years of an infant's life are known as the critical period, during which the overall development of learning performance is significantly impacted due to neural plasticity.
Ev-NeRF: Event Based Neural Radiance Field
We present Ev-NeRF, a Neural Radiance Field derived from event data.
Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition
We introduce Ev-TTA, a simple, effective test-time adaptation algorithm for event-based object recognition.
Ranked #1 on
Robust classification
on N-ImageNet
