activity
20242026
collaborators

9 papers

cs.LG2026

CSyMR: Benchmarking Compositional Music Information Retrieval in Symbolic Music Reasoning

Boyang Wang, Yash Vishe, Xin Xu +4

Natural language information needs over symbolic music scores rarely reduce to a single step lookup. Many queries require compositional Music Information Retrieval (MIR) that extra…

cs.LG2026

CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models

Zhenghao He, Guangzhi Xiong, Boyang Wang +2

Internal activations of diffusion models encode rich semantic information, but interpreting such representations remains challenging. While Sparse Autoencoders (SAEs) have shown pr…

cs.CV2026

RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation

Boyang Wang, Haoran Zhang, Shujie Zhang +8

The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constraints, collecting la…

cs.CV2025

Frame In-N-Out: Unbounded Controllable Image-to-Video Generation

Boyang Wang, Xuweiyi Chen, Matheus Gadelha +1

Controllability, temporal coherence, and detail synthesis remain the most critical challenges in video generation. In this paper, we focus on a commonly used yet underexplored cine…

eess.IV2025

DPC-QA Net: A No-Reference Dual-Stream Perceptual and Cellular Quality Assessment Network for Histopathology Images

Qijun Yang, Boyang Wang, Hujun Yin

Reliable whole slide imaging (WSI) hinges on image quality,yet staining artefacts, defocus, and cellular degradations are common. We present DPC-QA Net, a no-reference dual-stream…

cs.RO2025

This&That: Language-Gesture Controlled Video Generation for Robot Planning

Boyang Wang, Nikhil Sridhar, Chao Feng +4

Clear, interpretable instructions are invaluable when attempting any complex task. Good instructions help to clarify the task and even anticipate the steps needed to solve it. In t…