← Search

Shengzhi Wang

7 accepted papers

2026

Group-wise Data Ordering: Enhancing Instruction Tuning of Large Language Models via Embedding Proximity

ICML 2026poster

Instruction tuning (IT) is a central mechanism for aligning large language models (LLMs) with user intent. In practice, randomly shuffling the training set is a simple yet surprisingly strong baseline. However, it overlooks latent structure, such as domain and reasoning depth, and thus interleaves h…

Cited by 0SourceScholar
2026

MedLesionVQA: A Multimodal Benchmark Emulating Clinical Visual Diagnosis for Body Surface Health

ICLR 2026poster

Body-surface health conditions, spanning diverse clinical departments, represent some of the most frequent diagnostic scenarios and a primary target for medical multimodal large language models (MLLMs). Yet existing medical benchmarks are either built from publicly available sources with limited ex…

Cited by 0SourceScholar
2025

Align-A-Video: Deterministic Reward Tuning of Image Diffusion Models for Consistent Video Editing

CVPR 2025poster

Due to control limitations in the denoising process and the lack of training, zero-shot video editing methods often struggle to meet user instructions, resulting in generated videos that are visually unappealing and fail to fully satisfy expectations. To address this problem, we propose Align-A-Vide…

Cited by 0SourcePDFScholar
2025

Bio-Inspired Soft Variable-Stiffness Prehensile Tail Enabling Versatile Grasping and Enhancing Dynamic Mobility

RA-L 2025

In nature, prehensile tails serve as versatile and essential appendages for animals, facilitating both grasping and enhanced mobility. Although existing robotic tails effectively contribute to mobility across a range of behaviors, they lack versatile object-grasping capabilities. Inspired by these b

Cited by 2SourceScholar
2023

Combining Tail and Reaction Wheel for Underactuated Spatial Reorientation in Robot Falling With Quadratic Programming

RA-L 2023

Inertial appendages (e.g., tails and reaction wheels) have shown their reorientation capability to enhance robots' mobility while airborne or improve robots' safety in falling. The tail, especially with two Degrees of Freedom (DoFs), is normally subject to its limited Range of Motion (RoM). Although

Cited by 10SourceScholar
2023

Towards Exact Interaction Force Control for Underactuated Quadrupedal Systems with Orthogonal Projection and Quadratic Programming

ICRA 2023poster

Projected Inverse Dynamics Control (PIDC) is commonly used in robots subject to contact, especially in quadrupedal systems. Many methods based on such dynamics have been developed for quadrupedal locomotion tasks, and only a few works studied simple interactions between the robot and environment, su…

Cited by 2SourceScholar
2023

Towards Safe Landing of Falling Quadruped Robots Using a 3-DoF Morphable Inertial Tail

ICRA 2023poster

Falling cat problem is well-known where cats show their super aerial reorientation capability and can land safely. For their robotic counterparts, a similar falling quadruped robot problem, has not been fully addressed, although achieving safe landing as the cats has been increasingly investigated.…

Cited by 19SourceScholar