Ding-Ming Li

Explicit 3D geometry, rendered as text, unlocks superior spatial reasoning in RGB-only VLMs by guiding trajectory correction during distillation.

Visual-native skill cards, directly accessible to VLMs, unlock a self-reinforcing loop of policy improvement and skill accumulation, drastically boosting sample efficiency.

Even the best vision-language models struggle with predictive spatial reasoning, scoring less than 60% on a new benchmark designed to test anticipating unseen outcomes.

Standard translation metrics and 235B-parameter LLM judges actively reward the worst social media translations due to cultural blindness, but progressively decaying masked cultural scaffolding enables an 8B model to rival Gemini-3.1-Pro.

Decoupling perception from reasoning in visual tasks leads to a remarkable 93.2% accuracy on V-Star, showcasing a new paradigm for fine-grained visual reasoning.

Multimodal LLMs still struggle to faithfully recreate webpages from videos, particularly in capturing fine-grained style and motion, despite advances in other areas.

Forget fuzzy language – CoCo uses executable code as Chain-of-Thought to generate images with unprecedented control and precision, blowing away existing methods on complex scenes.