#world models

437 stories · 37 in 7 days · 124 in 30 days
Oct 1
Sep 30
ModelsBuildersSelected01:05
Microsoft launches Quine biology model

Quine represents a shift toward more integrated biological research approaches, potentially accelerating scientific discovery by connecting previously siloed biological data. Researchers in life sciences can use this tool to explore complex biological relationships more efficiently, though its current early-stage status means practical applications are still developing.

Official accountMicrosoft Research@MSFTResearchSource
Sep 29
Sep 28
PapersBuildersSelected09:04
StarWM Routes Attention for Robust World Model Training

The technique targets a real failure mode: reconstruction-based world models waste capacity on pixel area instead of dynamics relevance, so agents get distracted by background video. Builders training RL agents or world models can borrow the attention-routed reconstruction pattern to keep representations focused on task-relevant content. It is a paper-level method benchmarked on DeepMind Control, comparable against both reconstruction-based and reconstruction-free baselines.

arXiv: Google DeepMind@Zeqiang Zhang et al. (7)Source
Sep 27
Sep 26
PapersBuildersSelected10:35
Paper Trains Object Permanence in World Models

Occlusion breaks scene consistency in generated video and embodied simulations, and object permanence offers a cognitive-science-grounded fix. Researchers working on world models, video generation or embodied agents can use the method to reduce object flicker and disappearance during occlusion. Compared with purely data-driven fixes, this frames the problem as a learnable cognitive capacity.

AK@_akhaliqSource
Sep 25
ProductsBuildersSelected10:53
Runway's WorldPrompt Shapes Real-Time Worlds in GWM Worlds 2

The key detail is that WorldPrompt separates world steering into persistent context and timed actions, turning prompting from a static instruction into ongoing state management — a different mental model from prompt-per-clip video tools like Sora or Veo. Builders working on interactive agents or generative media should study the interview for how latency and intervention are handled in production. The mechanics described apply directly to anyone prototyping live generative experiences.

Official accountLatent Space (swyx)@Richard MacManusSource
Sep 24
Sep 23
ModelsUS vs ChinaSelected72°15:46
PixVerse R2 Combines Real-Time Generation and General World Modelling

Putting real-time generation and general world-modelling tasks in one model could cut the latency and engineering cost of running separate specialised systems. Teams building interactive video, simulation or embodied applications should track how R2 performs against pipelines that bolt a world model onto a streaming engine. PixVerse competes with video generation tools like Runway and Kling in the same product space.

量子位@梦瑶Source
Sep 22
Sep 21
Sep 17
Sep 16
Sep 14