news | Xingchen Wan

Jul 21, 2026	Google DeepMind announced Gemini 3.6 Flash and Gemini 3.5 Flash Cyber in CodeMender!
Jun 15, 2026	Google Cloud launched Proxy Models in BigQuery and AlloyDB, powered by our UQE research!
Apr 30, 2026	Our paper Can Large Language Models Generalize Procedures Across Representations? has been accepted to ICML 2026!
Feb 20, 2026	Our paper VISTA: A Test-Time Self-Improving Video Generation Agent has been accepted to CVPR 2026!
Feb 05, 2026	Two papers have been accepted to ICLR 2026: Visual Planning with Reinforcement Learning (Oral) and MASS (Optimizing Agents with Better Prompts and Topologies).
Oct 17, 2025	We present VISTA and Maestro, two self-improving multimodal generation agents for text-to-video and text-to-image generation, respectively. 🚨 Google just dropped the most advanced self-improving video AI ever built. It’s called VISTA, and it literally rewrites its own prompts to make every new generation better than the last. No retraining. No fine-tuning. Just pure test-time self-reflection. Here’s how it works:… pic.twitter.com/WyhX9uur9l— Louis Gleeson (@aigleeson) October 24, 2025</blockquote> </td> </tr>
May 19, 2025	We present Visual Planning, where we apply reinforcement learning post-training on pure-vision models to achieve state-of-the-art performance in visual reasoning tasks. 🚀Let’s Think Only with Images. No language and No verbal thought.🤔 Let’s think through a sequence of images💭, like how humans picture steps in their minds🎨. We propose Visual Planning, a novel reasoning paradigm that enables models to reason purely through images. pic.twitter.com/ly9JtuEC33— Yi Xu (@_yixu) May 19, 2025</blockquote> </td> </tr> </table> </div> </div>