Zeyu Feng(Ted) (@tedfeng_xd) profile picture

PhD student at UCSD

San Diego, CA
Joined May 2017
Photo by Zeyu Feng(Ted) (@tedfeng_xd)
Excited to finally share PAN 2! ๐Ÿš€ Pretrained on millions of hours of egocentric, robotic, and human-motion data, PAN 2 is a step toward foundation world models that can understand and predict the physical world.
Introducing PAN 2: an open foundation world model for physical intelligence. A language model predicts the next word. PAN 2 predicts the next world: what happens after each action, grounded in time, physics and space. Towards AI that simulates โ€œwhat if?โ€ before it acts. More details: ifm.ai/pan/
1
1
14
656
Zeyu Feng(Ted) retweeted
๐ŸŒ€ Introducing ๐„๐ช๐ฎ๐ข๐ฅ๐ข๐›๐ซ๐ข๐ฎ๐ฆ ๐‘๐ž๐š๐ฌ๐จ๐ง๐ž๐ซ๐ฌ (๐„๐ช๐‘) ! Feedforward models and weight-tied models behave very differently on hard reasoning generalization. EqR pushes this difference to the extreme by learning ๐ญ๐š๐ฌ๐ค-๐œ๐จ๐ง๐๐ข๐ญ๐ข๐จ๐ง๐ž๐ ๐ง๐ž๐ฎ๐ซ๐š๐ฅ ๐š๐ญ๐ญ๐ซ๐š๐œ๐ญ๐จ๐ซ๐ฌ . โ€ข Sudoku-Extreme: 99.8% โ€ข Maze: 93% #ICML2026
13
66
10
333
108,227
Zeyu Feng(Ted) retweeted
Agents can now live like humans in a virtual city built with Unreal Engine: exercising outdoors, strolling through parks, or even playing chess with friends! ๐ŸŒ Check out SimWorld: an open-ended simulator for LLM agents to act, perceive, and plan in richly embodied, endlessly diverse virtual worlds. SimWorld now supports plug-and-play integration with arbitrary UE environments. Deploy agents in your own scenes and build fully customizable simulations for autonomous driving, collaborative games, or social experiments! SimWorld is a strong testbed for evaluating embodied agents, as it provides: - โš™๏ธPhysical + social simulation: realistic physics (collision/friction/inertia) and social dynamics like traffic rules/flows. - ๐Ÿค– LLM/VLM-friendly interfaces: a Gym-style API with multimodal observations and grounded language actions. - ๐Ÿค” Long-horizon tasks + reasoning: diverse physical/social tasks for systematic training and evaluation. 1/ #LLM #Agent #UnrealEngine #simulation
2
20
6
44
10,005
Pretraining has scaling laws to guide compute allocation. But for RL on LLMs, we lack a practical guide on how to spend compute wisely. We show the optimal compute allocation in LLM RL scales predictably. โ†“ Key takeaways below
18
97
16
444
75,293
Zeyu Feng(Ted) retweeted
๐Ÿš€ Excited to announce the release of PAN, a general world model Iโ€™ve been working on for years. PAN can simulate physical, agentic, and nested worlds โ€” generating infinite interactive experiences to train and evaluate AI agents. Check out demo: ifm.mbzuai.ac.ae/pan/ ๐Ÿ‘‡
18
66
6
472
78,553
๐ŸŒ Introducing long-horizon, interactable PAN World Model that lets you step into coherent worlds and evolve them through language-guided actions. A world model is far more than visuals โ€” it understands world dynamics, enabling an agent to imagine scenarios, anticipate outcomes, and act with strategy.
2
6
30
6,869
Check out our website & paper ๐Ÿ‘‡ Website: ifm.mbzuai.ac.ae/pan/ Paper: arxiv.org/abs/2511.09057
1
1
2
161
Zeyu Feng(Ted) retweeted
๐Ÿ”ฅReally excited to see the release of PAN world model, a project I had been working over the past years. PAN is a general world model capable of simulating physical, agentic, and nested worlds, synthesizing infinite interactive experiences for training AI agents. Building on top of pretrained LLMs and video diffusion models, PAN connects language, perception, action, and latent thoughts, for long-horizon simulation and reasoning. PAN shows overwhelming performance gains over JEPA-2, Cosmos-2, and other prior models. More in the thread๐Ÿ‘‡ ... 1/
8
52
2
238
31,289
Zeyu Feng(Ted) retweeted
๐Ÿš€ Introducing PAN, our latest general world model. ๐Ÿ’ก Compared to traditional video generation models like Sora 2, PAN simulates worlds you can interact with, over long horizons, with natural-language actions.
1
10
27
2,790
Zeyu Feng(Ted) retweeted
Super excited to introduce Pandora, a generative video World Model interactively controllable by language. #Sora and #GPT4 are both powerful. How about fusing them in a single model? ๐Ÿ’ฅ Pandora gives a preview:๐Ÿ”ญ > Build a General World Model (GWM) super efficiently by integrating pretrained autoregressive LLM and diffusion Video Model, aligning them in the representation space. > Let the LLM control the VM on-the-fly. Instruction tuning maximizes the controllability. > Autoregressive LLM empowers VM to generate indefinitely long videos: Starting with a VM for 2-second videos, Pandora extends it for 8-second videos. Would #Sora+#GPT4 under Pandora produce hours-long videos? ๐Ÿ“ฝ๏ธ > World Model is beyond just video generation. Itโ€™s sensory-level information processing + concept-level reasoning and reflection. Pandora bridges both, with the concept- / language-level backbone (LLM) managing & steering the sensory-level VM functionalities. ๐Ÿ‘๏ธ๐Ÿง  Check out for a bunch of interesting results: world-model.ai
๐Ÿ”ฅIntroducing Pandora ๐ŸŒ ๐Ÿช a World Model that generates videos of world states with real-time language control ๐ŸŽฅ๐Ÿ•น๏ธ Simulate the world across domains in an _interactive_ way! check out more world-model.ai
9
58
8
307
63,564
I am excited to share the latest work from our group: ๐—ฃ๐—ฎ๐—ป๐—ฑ๐—ผ๐—ฟ๐—ฎ๐ŸŒ. It is a world model that predicts future states with real-time steerable control using natural language. It is a step towards General World Model.
๐Ÿ”ฅIntroducing Pandora ๐ŸŒ ๐Ÿช a World Model that generates videos of world states with real-time language control ๐ŸŽฅ๐Ÿ•น๏ธ Simulate the world across domains in an _interactive_ way! check out more world-model.ai
3
211
Zeyu Feng(Ted) retweeted
๐Ÿš€๐Ÿš€๐Ÿš€Today, we're thrilled to introduce ๐๐š๐ง๐๐จ๐ซ๐š: a ๐™ฌ๐™ค๐™ง๐™ก๐™™ ๐™ข๐™ค๐™™๐™š๐™ก๐ŸŒ that generates videos๐ŸŽฅ with ๐™ง๐™š๐™–๐™ก-๐™ฉ๐™ž๐™ข๐™š control with ๐™›๐™ง๐™š๐™š-๐™ฉ๐™š๐™ญ๐™ฉ actions๐ŸŽฌ!!! Check it out more world-model.ai ! @MaitrixOrg
1
3
9
490
Zeyu Feng(Ted) retweeted
๐Ÿ”ฅ We are excited to announce ๐—ฃ๐—ฎ๐—ป๐—ฑ๐—ผ๐—ฟ๐—ฎ, a world model with natural language actions and video states. ๐ŸŒ It is a step towards a General World Model that: 1. Simulates world states by generating videos across any domains 2. Allows any-time control with free-text actions
6
51
7
176
33,657
Zeyu Feng(Ted) retweeted
๐Ÿ”ฅIntroducing Pandora ๐ŸŒ ๐Ÿช a World Model that generates videos of world states with real-time language control ๐ŸŽฅ๐Ÿ•น๏ธ Simulate the world across domains in an _interactive_ way! check out more world-model.ai
6
73
37
224
102,232