Tag
HappyWorld-Bench is a comprehensive benchmark that evaluates the reliability of world models under interaction and modification across video, spatial, and embodied tracks.
Marc Lou shares his achievement in a Hyrox race, finishing 1st in his age group, and expresses gratitude to his AI sponsors including Higgsfield AI for their support.
ActionSplice introduces counterfactual state transport to splice revised actions into chunk-autoregressive video world models without replaying completed evaluations, improving fidelity and inference speed.
Principia is a benchmark that evaluates video models on Newtonian physics using relational consistency between paired objects, revealing significant gaps in current models' physical reasoning.
A tweet from the Coors Light CEO asserts that video models in AI are fully solved, presenting a bold claim about the current state of AI development.
Visual prompt engineering (VIPE) automatically modifies task images to improve video model reasoning performance, often more effective than text-based prompting or test-time scaling.
This paper introduces Visual Prompt Engineering (VIPE), a method that automatically modifies task images to improve video model performance, showing it can be more effective than text-based prompt engineering or test-time scaling.
The author launches a weekly Video Model Journal Club covering video generation, world models, physical reasoning, diffusion, flow matching, etc. The first in-person talk will be by Yilun Du on Embodied Reasoning with World Models.
LongCat released WBench, a benchmark for video world models that tests control, memory, instruction-following, and physical plausibility across 289 cases and 20 models, finding that no model excels in all dimensions, highlighting the gap between video quality and true world simulation.
A tweet thread reveals that Google's Omni is distinct from video models like Veo and Seedance, with DeepMind's Jeff Dean clarifying its unique input/output capabilities, described as a transformative AR filter for video.