1 citations · 4 across the 17 of their papers we have counts for
18 papers
Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision
Shravan Venkatraman, Wenshuai Zhao, Mohammad Hassan Vali +1
We introduce ST (Self-Supervised Self-Distillation over Time), which, to the best of our knowledge, is the first fully self-contained framework for continuous video state track…
AV-JEPA: Extending LeJEPA to Audio-Visual Self-Supervised Learning
Benjamin Robson, Santeri Mentu, Wenshuai Zhao +1
We present AV-JEPA, an elegant multimodal extension of LeJEPA to audio-visual self-supervised learning. Using an early-fusion Vision Transformer and modality dropout as masking, th…
Point Tracking Improves World Action Models
Jiarui Guan, Wenshuai Zhao, Yue Pei +3
Robot policy learning benefits from world-action models that capture environment dynamics, but pixel-level prediction entangles dynamics with nuisance factors such as lighting and…
Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence
Zhiyuan Li, Rongzhen Zhao, Wenyan Yang +3
The de facto approach in video object-centric learning maintains temporal consistency through learned dynamics modules that predict future object representations, called slots. We…
Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing
Zhiyuan Li, Wenyan Yang, Wenshuai Zhao +4
Learning robotic manipulation from human videos is a promising solution to the data bottleneck in robotics, but the distribution shift between humans and robots remains a critical…
Latent-Compressed Variational Autoencoder for Video Diffusion Models
Jiarui Guan, Wenshuai Zhao, Zhengtao Zou +2
Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction.…
PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos
Yihao Wang, Yang Miao, Wenshuai Zhao +8
Articulation perception aims to recover the motion and structure of articulated objects (e.g., drawers and cupboards), and is fundamental to 3D scene understanding in robotics, sim…
Sparsely Supervised Diffusion
Wenshuai Zhao, Zhiyuan Li, Yi Zhao +5
Diffusion models have shown remarkable success across a wide range of generative tasks. However, they often suffer from spatially inconsistent generation, arguably due to excessive…
Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
Yi Zhao, Aidan Scannell, Wenshuai Zhao +7
Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online…
Closed-Loop Vision-Language Planning for Multi-Agent Coordination
Zhiyuan Li, Wenshuai Zhao, Joni Pajarinen
Cooperative multi-agent reinforcement learning (MARL) struggles with sample efficiency, interpretability, and generalization. While Large Language Models (LLMs) offer powerful plan…
Bi-Level Motion Imitation for Humanoid Robots
Wenshuai Zhao, Yi Zhao, Joni Pajarinen +1
Imitation learning from human motion capture (MoCap) data provides a promising way to train humanoid robots. However, due to differences in morphology, such as varying degrees of j…
Backpropagation Through Agents
Zhiyuan Li, Wenshuai Zhao, Lijun Wu +1
A fundamental challenge in multi-agent reinforcement learning (MARL) is to learn the joint policy in an extremely large search space, which grows exponentially with the number of a…
AgentMixer: Multi-Agent Correlated Policy Factorization
Zhiyuan Li, Wenshuai Zhao, Lijun Wu +1
In multi-agent reinforcement learning, centralized training with decentralized execution (CTDE) methods typically assume that agents make decisions based on their local observation…
Optimistic Multi-Agent Policy Gradient
Wenshuai Zhao, Yi Zhao, Zhiyuan Li +2
*Relative overgeneralization* (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behavior…
Exploiting Local Observations for Robust Robot Learning
Wenshuai Zhao, Eetu-Aleksi Rantala, Sahar Salimpour +3
While many robotic tasks can be addressed using either centralized single-agent control with full state observation or decentralized multi-agent control, clear criteria for choosin…
Simplified Temporal Consistency Reinforcement Learning
Yi Zhao, Wenshuai Zhao, Rinu Boney +2
Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficienc…
Learning Progress Driven Multi-Agent Curriculum
Wenshuai Zhao, Zhiyuan Li, Joni Pajarinen
The number of agents can be an effective curriculum variable for controlling the difficulty of multi-agent reinforcement learning (MARL) tasks. Existing work typically uses manuall…
Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey
Wenshuai Zhao, Jorge Peña Queralta, Tomi Westerlund
Deep reinforcement learning has recently seen huge success across multiple areas in the robotics domain. Owing to the limitations of gathering real-world data, i.e., sample ineffic…