collaborators

11 papers

cs.RO2026

Keep the Future, Drop the Rollout: RIFT for World Action Models

Chushan Zhang, Jinguang Tong, Xuesong Li +2

World action models (WAMs) condition robot actions on predicted futures, but iterative video rollout increases deployment latency. We ask whether action generation requires the evo…

cs.CV2026

Maintain Plasticity in Long-timescale Continual Test-time Adaptation

Yanshuo Wang, Xuesong Li, Jinguang Tong +5

Continual test-time domain adaptation (CTTA) aims to adjust pre-trained source models to perform well over time across non-stationary target environments. While previous methods ha…

cs.CV2026

Label Shift Aware Adaptation for Online Zero-shot Learning with Contrastive Language-Image Pre-Training (CLIP)

Pengxiao Han, Changkun Ye, Yanshuo Wang +5

Vision-language models like Contrastive Language-Image Pre-Training (CLIP) have been extensively studied in data-scarce scenarios. A particularly challenging and realistic task in…

cs.CV2026

Structural Energy Guidance for View-Consistent Text-to-3D Generation

Qing Zhang, Jinguang Tong, Jing Zhang +2

Text-to-3D generation based on diffusion models often suffers from the Janus problem, leading to inconsistent geometry across viewpoints. This work identifies viewpoint bias in 2D…

cs.RO2026

EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control

Chushan Zhang, Ruihan Lu, Jinguang Tong +3

Chunked vision-language-action (VLA) policies predict multi-step robot controls, conditioning each update on the current visual observation alone. Yet robot actions cause contact,…

cs.CV2026

MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model

Jinguang Tong, Jinbo Wu, Kaisiyuan Wang +12

Human-Object Interaction (HOI) video reenactment aims to transfer the interaction dynamics of a source video to a novel target object while preserving realistic hand-object coordin…