papers

Publications (8)

cs.CV2026

A Very Big Video Reasoning Suite

Maijunxian Wang, Ruisi Wang, Juyi Lin +53

Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally c…

cs.CV2025

ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation

Xiaomeng Yang, Lei Lu, Qihui Fan +5

Diffusion models have demonstrated exceptional capabilities in generating high-fidelity images. However, their iterative denoising process results in significant computational over…

cs.CV2026

PhyGround: Benchmarking Physical Reasoning in Generative World Models

Juyi Lin, Arash Akbari, Yumei He +13

Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, ev…

cs.CV2025

Open-Source Acceleration of Stable-Diffusion.cpp Deployable on All Devices

Jingxu Ng, Cheng Lv, Pu Zhao +5

Stable diffusion plays a crucial role in generating high-quality images. However, image generation is time-consuming and memory-intensive. To address this, stable-diffusion.cpp (Sd…

cs.RO2026

Human Cognition in Machines: A Unified Perspective of World Models

Timothy Rupprecht, Pu Zhao, Amir Taherin +20

This report of world models distinguishes prior works by the cognitive functions they innovate. Many works claim an almost human-like cognitive capability in their world models. To…

cs.CV2026

VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting

Juyi Lin, Amir Taherin, Arash Akbari +11

Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language. However, current VLA models suffer…

cs.AI2026

Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs

Amir Taherin, Juyi Lin, Arash Akbari +5

Vision-Language-Action (VLA) models have emerged as powerful generalist policies for robotic control, yet their performance scaling across model architectures and hardware platform…

cs.CV2026

PhyWorld: Physics-Faithful World Model for Video Generation

Pu Zhao, Juyi Lin, Timothy Rupprecht +10

World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising…