Zeqi Xiao
@zeqi_xiao
Followers
356
Following
158
Statuses
38
Ph.D. student@MMLab, Nanyang Technological University .
Joined September 2022
Introducing 💡Trajectory Attention for Fine-grained Video Motion Control💡. By augmenting attention along predefined trajectories, our approach empowers tasks such as camera motion control in images and videos, as well as video editing.
1
10
62
RT @zhouyifan1107: Just published my new deep dive on NIPS 2024 Best Paper Visual Autoregressive Modeling (VAR)! I discuss: * Basic concept…
0
2
0
Wow, a promising direction for filmmaking!
Upon the release of Sora, I’m glad to share our 𝟑𝐃𝐓𝐫𝐚𝐣𝐌𝐚𝐬𝐭𝐞𝐫 with the Kling team @Kling_ai. It can control multiple entity motions in 3D space with entity-specific 3D trajectories for video generation. [1/3] 👉 Website: 👉 Code:
1
0
4
RT @_amirbar: Happy to share our new work on Navigation World Models! 🔥🔥 Navigation is a fundamental skill of agents with visual-motor ca…
0
56
0
RT @GoogleDeepMind: Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image.…
0
1K
0
RT @WinstonGu_: Imagine a future where you can ask humanoid robots to clean your room, but some items, like heavy sofas, are too challengin…
0
61
0
bro is the king of VLM
Excited to announce our new paper VILA^2, an awesome collaboration with @LigengZhu and my amazing mentors @Yao__Lu @yin_hongxu @songhan_mit. We demonstrate SOTA VLMs can keep evolving by augmenting their own pertaining data with self-augmentation and specialist-augmentation loops! More details will be released at
0
0
2
RT @_akhaliq: Google presents Genie Generative Interactive Environments introduce Genie, the first generative interactive environment tra…
0
516
0
RT @OpenAI: Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, comple…
0
31K
0