[2601.14251] LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention

Space-Time Text-to-Video diffusion model by Google Research.

We present a simple yet effective technique to estimate lighting in a single input image. Our research uncovers a surprising relationship between the appearance of chrome balls and the initial diffusion noise map, which we utilize to consistently generate high-quality chrome balls. We further fine-tune an LDR diffusion model (Stable Diffusion XL) with LoRA, enabling it to perform exposure bracketing for HDR light estimation. Our method produces convincing light estimates across diverse settings and demonstrates superior generalization to in-the-wild scenarios.

Kimi K2 Thinking, Moonshot's best open-source thinking model.

Abstract page for arXiv paper 2602.07120: Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model

Abstract page for arXiv paper 2602.03510: Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers

DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance.

Abstract page for arXiv paper 2601.13976: FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation