norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers2 hours ago
ResearchDaily Papers

Modality-Autoregressive World-Action Models

The paper introduces ModAR, a world-action model that autoregressively denoises multiple future modalities before predicting actions, allowing each prediction to condition on previously generated modalities. Evaluations show that ModAR outperforms existing WAM formulations, achieving higher success rates with fewer training FLOPs and no pretraining.

Open original
SIGNAL FROM THE SOURCE
1
source votes
Tracking sinceSeptember 16, 20261 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedSeptember 15, 2026Adam Hung, Bardienus P. Duisterhof, Deva Ramanan
BEHIND THE NUMBERS

How interest changes

Daily Papers

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

1 source votes

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

This approach enables more efficient and effective prediction of future states by leveraging multiple visual modalities in a sequential manner, potentially improving performance in tasks requiring understanding of geometric, semantic, and motion features.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

PhysBrain 1.5 is a unified model for understanding physical environments, generating actions, and predicting future states. It uses a vision-language foundation, encodes language responses and motion as sequences, and is pre-trained on human interaction videos. The model achieves strong performance on embodied understanding benchmarks.

2 days agoDaily Papers

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

The paper discusses recursive self-improvement (RSI) in AI systems, outlining its development roadmap from autonomy in improvement execution to recursive meta-improvement. It examines RSI across various scenarios like scientific discovery and software engineering, highlighting different requirements and development speeds.

6 days agoDaily Papers

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

The paper introduces Vidu S2, a system with two components: Vidu S2-Avatar for real-time interactive digital characters and Vidu S2-Editing for real-time video editing. It also explores real-time spatial video generation for both components. Compared to its predecessor, Vidu S2-Avatar offers improved real-time 720p video generation, dynamic reference updates, and enhanced instruction following. Vidu S2-Editing enables real-time video stream editing with features like style rendering and background replacement.

6 days agoDaily Papers

LynnReal-Omni: Native Multi-Modal Video Generation for Agentic Visual Workflows

LynnReal-Omni is a native multimodal video generation framework that combines text-to-video, image-conditioned generation, and structural control into a single model. It includes a 32B shared multimodal diffusion transformer and a 27B Flash version for real-time rendering, with a data pipeline and evaluation method designed for video generation tasks.

2 days agoDaily Papers

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

ZGCM-1 is a 7B parameter foundation model designed for math and agentic search, emphasizing efficiency through architectural and system co-design, progressive curriculum learning, and an AI-native R&D workflow. It demonstrates competitive performance against larger models on mathematical and search tasks, with improvements in training efficiency and open-source availability of training materials.

5 days agoDaily Papers

Atria Dawn: The Dawn of Agentic Superintelligence

Atria Dawn Preview is a foundation agentic language model designed for scientific research and engineering workflows, trained via a Verifiable Experience Pipeline that connects tool-mediated interactions to executable environments and externally verified outcomes. It achieves competitive performance across 16 benchmarks and shows potential for human-AI collaboration in research and development.

2 days ago