NextStep-1
— AK (@_akhaliq) 15 août 2025
Toward Autoregressive Image Generation with Continuous Tokens at Scale pic.twitter.com/WXY2cukV9d
NextStep-1 Toward Autoregressive Image Generation with Continuous Tokens at Scale
By
–
NextStep-1
— AK (@_akhaliq) 15 août 2025
Toward Autoregressive Image Generation with Continuous Tokens at Scale pic.twitter.com/WXY2cukV9d
NextStep-1 Toward Autoregressive Image Generation with Continuous Tokens at Scale
By
–
Seeing, Listening, Remembering, and Reasoning
— AK (@_akhaliq) 14 août 2025
A Multimodal Agent with Long-Term Memory pic.twitter.com/stSrINaYLN
Seeing, Listening, Remembering, and Reasoning A Multimodal Agent with Long-Term Memory

By
–
Mol-R1 Towards Explicit Long-CoT Reasoning in Molecule Discovery

By
–
Story2Board A Training-Free Approach for Expressive Storyboard Generation
By
–
Decentralized Aerial Manipulation of a Cable-Suspended Load using Multi-Agent Reinforcement Learning pic.twitter.com/izRATDkpnU
— AK (@_akhaliq) 14 août 2025
Decentralized Aerial Manipulation of a Cable-Suspended Load using Multi-Agent Reinforcement Learning
By
–
AimBot
— AK (@_akhaliq) 14 août 2025
A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies pic.twitter.com/SmCkrzohlF
AimBot A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies
By
–
VertexRegen
— AK (@_akhaliq) 14 août 2025
Mesh Generation with Continuous Level of Detail pic.twitter.com/Mypcq20o7c
VertexRegen Mesh Generation with Continuous Level of Detail

By
–
Anycoder model list will continue to get bigger and you can use it for vibe coding on your phone

By
–
Beyond Ten Turns Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
By
–
Matrix-3D
— AK (@_akhaliq) 13 août 2025
Omnidirectional Explorable 3D World Generation pic.twitter.com/1YDZuQmKII
Matrix-3D Omnidirectional Explorable 3D World Generation