Jaemin Cho

LLMs often prefer compromise solutions over binary choices, reshaping our understanding of moral decision-making in AI.

MLLMs struggle with artistic intent, scoring only 48.29% on a benchmark designed to evaluate nuanced understanding in audiovisual arts.

PQSG reveals that state-of-the-art video generation models often misrepresent physical laws, with significant implications for the realism of generated content.

Open-sourcing a VLA model that beats closed-source giants on embodied reasoning tasks could finally make real-world robot deployment practical.

Forget training on closed sets: WildDet3D leverages geometric cues and diverse prompts to achieve SOTA 3D object detection across 13.5K categories in the wild.

Forget redrawing diagrams by hand: VFIG, a new vision-language model, can automatically convert rasterized figures into editable SVGs with near GPT-5.2 quality.

Pixel-space diffusion models get a serious boost: V-Co reveals a simple recipe for visual co-denoising that outperforms existing methods on ImageNet-256 with fewer training epochs.

Finally, AI can generate hour-long videos with consistent characters and backgrounds, thanks to a new framework that nails seamless transitions between shots.

Ditch the messy global 3D scene reconstruction: AnchorWeave weaves together clean, local geometric memories for camera-controllable video generation, boosting long-term consistency and visual quality.