AML Course Project, 2025
We apply Test-Time Training (TTT) to transductive models for the ARC-AGI benchmark, showing that small transformers trained from scratch with TTT can match SOTA LLMs, highlighting the power of specialized models for reasoning.
ICRA, 2025
We introduce Robust Robot Walker, a novel approach that enables quadruped robots to pass various invisible small obstacles.
ICRA, 2025
We introduce SARO (Space Aware Robot System for Terrain Crossing), an innovative system composed of a high-level reasoning module and a low-level control policy, enabling the robot to navigate across complex 3D terrains and reach the goal position.
In Submission, 2024
TBA
Arxiv, 2023
In this work, we first represent the emotion in the text prompt, which could inherit rich semantics from the CLIP, allowing flexible and generalized emotion control. We further reorganize these tasks as the target-oriented texture transfer and adopt the Diffusion Models.