activity
20242026
collaborators

8 papers

q-bio.GN2026

Improving scDiffusion with Sparsity-Biased Classifier-Free Guidance

Yu Song, Hao Sun, Ikuko Nishikawa +1

Single-cell RNA sequencing (scRNA-seq) has become an essential tool in modern cellular biology, and generating accurate synthetic scRNA-seq data is becoming increasingly important.…

cs.CV2026

SAM+D: Parameter-Efficient Dimensional Lifting of SAM-Family Models via Depth-Routed LoRA and Depth Shifting

Yu Song, Hao Sun, Shiyu Teng +2

Existing methods for adapting 2D foundation models such as SAM to 3D volumes either process slices independently---ignoring inter-slice context---or require substantial architectur…

cs.RO2026

MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents

Hao Sun, Yu Song, Shiyu Teng +2

VLA models have emerged as a powerful paradigm for transferring semantic knowledge from web-scale data to physical robotic control. However, current single-frame architectures suff…

cs.CV2026

Drag within Prior Distribution: Text-Conditioned Point-Based Image Editing within Distribution Constraints

Haoyang Hu, Masataka Seo, Yen-Wei Chen

Diffusion-based point editing methods have gained significant traction in image editing tasks due to their ability to manipulate image semantics and fine details by applying locali…

cs.CV2025

One Framework to Rule Them All: Unifying Multimodal Tasks with LLM Neural-Tuning

Hao Sun, Yu Song, Jiaqing Liu +3

Large-scale models have exhibited remarkable capabilities across diverse domains, including automated medical services and intelligent customer support. However, as most large mode…

cs.CV2025

EPIC: Efficient Prompt Interaction for Text-Image Classification

Xinyao Yu, Hao Sun, Zeyu Ling +5

In recent years, large-scale pre-trained multimodal models (LMMs) generally emerge to integrate the vision and language modalities, achieving considerable success in multimodal tas…