|
arxiv.org
|
<papertitle>
Unified Noise Steering for Efficient Human-Guided VLA Adaptation
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
arxiv.org
|
<papertitle>
Reinforcing VLAs in Task-Agnostic World Models
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
arxiv.org
|
<papertitle>
Beyond Pixel Histories: World Models with Persistent 3D State
</papertitle>
|
|
francelico.github.io
|
<span class="iconify-inline" data-icon="ant-design:home-outlined"></span>
site
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
arxiv.org
|
<papertitle>
Co-Evolving Latent Action World Models
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
openreview.net
|
<papertitle>
Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
openreview.net
|
<papertitle>
villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
</papertitle>
|
|
microsoft.github.io
|
<span class="iconify-inline" data-icon="ant-design:home-outlined"></span>
site
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
papers.nips.cc
|
<papertitle>
Dyn-O: Building Structured World Models with Object-Centric Representations
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
arxiv.org
|
<papertitle>
What Do Latent Action Models Actually Learn?
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
arxiv.org
|
<papertitle>
Uncovering Untapped Potential in Sample-Efficient World Model Agents
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
arxiv.org
|
<papertitle>
How Far is Video Generation from World Model: A Physical Law Perspective
</papertitle>
|
|
phyworld.github.io
|
<span class="iconify-inline" data-icon="ant-design:home-outlined"></span>
site
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
openreview.net
|
<papertitle>
Implicit Curriculum in Procgen Made Explicit
</papertitle>
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
arxiv.org
|
<papertitle>
Improving Token-Based World Models with Parallel Observation Prediction
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
arxiv.org
|
<papertitle>
Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
arxiv.org
|
<papertitle>
Efficient Value Iteration for s-rectangular Robust Markov Decision Processes
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
proceedings.mlr.press
|
<papertitle>
PPG Reloaded: An Empirical Study on What Matters in Phasic Policy Gradient
</papertitle>
|
|
proceedings.mlr.press
|
<papertitle>
Reachability-Aware Laplacian Representation in Reinforcement Learning
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
openreview.net
|
<papertitle>
Revisiting Intrinsic Reward for Exploration in Procedurally Generated Environments
</papertitle>
|
|
proceedings.mlr.press
|
<papertitle>Jointly Modelling Uncertainty and Diversity for Active Molecular Property Prediction
</papertitle>
|
|
openreview.net
|
<papertitle>Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
arxiv.org
|
<papertitle>Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
arxiv.org
|
<papertitle>Policy Gradient for Reinforcement Learning with General Utilities
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
proceedings.mlr.press
|
<papertitle>
The Geometry of Robust Value Functions
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
slideslive.com
|
<span class="iconify-inline" data-icon="heroicons-outline:presentation-chart-line"></span>
presentation
|
|
dl.acm.org
|
<papertitle>Understanding and Resolving Performance Degradation in Graph
Convolutional Networks
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
dl.acm.org
|
<span class="iconify-inline" data-icon="heroicons-outline:presentation-chart-line"></span>
presentation
|
|
proceedings.mlr.press
|
<papertitle>Towards Better Laplacian Representation in Reinforcement Learning
with Generalized Graph Drawing
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
slideslive.com
|
<span class="iconify-inline" data-icon="heroicons-outline:presentation-chart-line"></span>
presentation
|
|
papers.nips.cc
|
<papertitle>Improving Generalization in Reinforcement Learning with Mixture
Regularization
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
slideslive.com
|
<span class="iconify-inline" data-icon="heroicons-outline:presentation-chart-line"></span>
presentation
|
|
openreview.net
|
<papertitle>Neural Epitome Search for Architecture-Agnostic Network Compression
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
iclr.cc
|
<span class="iconify-inline" data-icon="heroicons-outline:presentation-chart-line"></span>
presentation
|
|
openaccess.thecvf.com
|
<papertitle>PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
</papertitle>
|
|
arxiv.org
|
<span class="iconify-inline" data-icon="academicons:arxiv"></span>
arXiv
|
|
github.com
|
<span class="iconify-inline" data-icon="eva:github-outline"></span>
code
|
|
youtube.com
|
<span class="iconify-inline" data-icon="heroicons-outline:presentation-chart-line"></span>
presentation
|