VideoPhy2
PulseAugur coverage of VideoPhy2 — every cluster mentioning VideoPhy2 across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New RoboJudge benchmark and model improve AI evaluation of embodied video generation
Researchers have developed RoboJudge, a new benchmark and a fine-tuned model for evaluating multimodal language models (MLLMs) as judges of embodied video generation. The benchmark, RoboJudge-Bench, assesses physical ad…
-
New RoboJudge benchmark evaluates LLMs as video generation judges
Researchers have developed RoboJudge-Bench, a new benchmark designed to evaluate how well multimodal large language models (MLLMs) can act as judges for embodied video generation. This benchmark assesses physical adhere…
-
New framework audits test-time scaling for video world models
A new research paper introduces the Compute-Value Audit (CVA) framework to evaluate the effectiveness of test-time scaling (TTS) in video world models. The study found that while increasing sampling can improve candidat…
-
New PhyS framework distills physical priors into streaming world models
Researchers have developed PhyS, a novel three-stage framework designed to imbue streaming world models with physical coherence. This framework addresses limitations in current methods by constructing a large dataset of…
-
New frameworks enhance physical realism in AI video generation
Researchers have developed two new frameworks, Proprio and LaMo, aimed at improving the physical realism of AI-generated videos. Proprio, a training-free method, enables existing video generators to self-assess and refi…