kaichen_zhou

Working on 3D computer vision, Robotic and Generative Models
Researh Fellow @MIT
PhD @UniofOxford

[kaichen_zhou @alex_kai2020]

Congrats to VGGT-Omega and D4TR! 🎉

Great to see 4D reconstruction gaining more attention.

VGGT-Omage sets a strong benchmark.

Page-4D (ICLR 2026) uses the same inference backbone as VGGT, with open-source code, and still performs reasonably well in indoor scenarios. ✨
https://t.co/xY1i0IQXVA

[Ao Qu @ao_qu18465]

(1/n)🚀 We’re excited to introduce CORAL, an extensible infrastructure for autonomous multi-agent evolution.

You can think of CORAL as a system for running something close to @karpathy’s AutoResearch on arbitrary tasks — but more robustly and safely, with multi-agent communication and persistent knowledge accumulation.

Even the first results are already striking:

🏆 4 agents pushed Anthropic’s kernel engineering take-home score from 1363 (the previous best public score) to 1103 clock cycles
⚡ With the same base model (Opus 4.6), single-agent CORAL achieves 2.5× higher improvement rate and 10× faster evolution than OpenEvolve on Erdős Minimum Overlap, reaching 0.3808878 and surpassing the best score reported in AlphaEvolve (0.380924)
👥 When agents evolve together, we observe emergent organizational behaviors: independent research, cross-referencing, and spontaneous consensus-building

We now believe we are at a critical intersection: between increasingly capable self-evolving agents and a still-unclear science of how they should collaborate, organize, and co-evolve with humans. We wrote this blog (https://t.co/QArf9dv7aF) to document the early signals, surface the open questions, and invite the community to help shape this emerging frontier.

The code for our infra is fully open-source: https://t.co/5fCTnqDzct

#AI #Agents #SelfEvolvingAgents #MultiAgentSystems #LLM #OpenSource #AlphaEvolve #AutoResearch

[kaichen_zhou @alex_kai2020]

@ao_qu18465 @pliang279 @karpathy @ZijianZhou524 @bryanklow @hanzheng_7 nice

[kaichen_zhou @alex_kai2020]

🚀 PAGE-4D is out! (ICLR 2026)

We bring VGGT into the dynamic world 🌍
— disentangling pose & geometry for 4D perception

📈 SOTA across dynamic scene benchmarks
💻 Training + evaluation code fully released

📃 https://t.co/rUSzgLJqsW

@MIT @Harvard @medialab

#AI #ComputerVision #4D

[kaichen_zhou @alex_kai2020]

https://t.co/cJMzaeeg0v

[Rao Fu @RaoFu79761158]

🚨 Embodied AI still lacks a true “Sense of Space” — 🖐️touch, 💪 force, 🧠 proprioception, 🔊 audio, 👃 smell, ❤️ bio-signals, 🌡️ thermal.

Submit & join the 1st Sense of Space Workshop @CVPR 2026 🏔️✨
🔗 https://t.co/4DmVK1peb7

We tackle it from two directions:
⬆️ Bottom-up: 🧩 emergent new sensors & systems
⬇️ Top-down: 🤖🖐️ dexterous hand–object manipulation from multisensory inputs

📣 Call for Papers: proceedings + non-proceedings
Accepted papers can apply for ✈️ travel grants + 🏆 sponsored paper awards.

Powered by an amazing organizing team 💥🤝
@RaoFu79761158 @LiGuankfd2 @alex_kai2020 Kun He @tomhodan Ergys Ristani Jessica Yin @AntheaYLi @yining_hong Devin Murphy Ray Song @xyz2maureen @ericyi0124 Qi Ye @YunzhuLiYZ @haoshu_fang @ruoshi_liu Vatsal Mehta @LuoYiyue @MengyuLearner @wojmatusik

[Rao Fu @RaoFu79761158]

🚨 Embodied AI still lacks a true “Sense of Space” — 🖐️touch, 💪 force, 🧠 proprioception, 🔊 audio, 👃 smell, ❤️ bio-signals, 🌡️ thermal.

Submit & join the 1st Sense of Space Workshop @CVPR 2026 🏔️✨
🔗 https://t.co/4DmVK1peb7

We tackle it from two directions:
⬆️ Bottom-up: 🧩 emergent new sensors & systems
⬇️ Top-down: 🤖🖐️ dexterous hand–object manipulation from multisensory inputs

📣 Call for Papers: proceedings + non-proceedings
Accepted papers can apply for ✈️ travel grants + 🏆 sponsored paper awards.

Powered by an amazing organizing team 💥🤝
@RaoFu79761158 @LiGuankfd2 @alex_kai2020 Kun He @tomhodan Ergys Ristani Jessica Yin @AntheaYLi @yining_hong Devin Murphy Ray Song @xyz2maureen @ericyi0124 Qi Ye @YunzhuLiYZ @haoshu_fang @ruoshi_liu Vatsal Mehta @LuoYiyue @MengyuLearner @wojmatusik