Code of "Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion"

SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects

🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

🎥 [Awesome] Egocentric / First-Person Video Datasets 📚 Papers, Benchmarks & Resources for Ego Vision

[CVPR 2026] Scaling Spatial Intelligence with Multimodal Foundation Models

[CVPR 2026 Highlight] U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences

[Roadmap] Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Modular SenseNova skills for building AI-powered office assistants and productivity workflows

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Your behavior is the signal. Not your words. — Behavioral intelligence for AI agents, built into your MacBook notch.

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

[ICLR 2026] 🦅 FALCON: an effective vision-language-action model injects rich 3D spatial tokens into the action head, enabling robust spatial understanding and SOTA performance across diverse manipu…

A simple video streaming baseline that outperforms SOTAs.

A benchmark for evaluating contextual agents on realistic multimodal personal-computer environments with profiling and factual-retention tasks.

Implementation for Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer.

The official implementation of “MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction”

Official Implementation of "Kinema4D: Kinematic4D World Modeling for Spatiotemporal Embodied Simulation"

An inference-time, plug-and-play method for temporal control in multi-event generation

Toy-scale unified multimodal model experiments — encoder-free understanding & generation with Mixture-of-Transformers on MLX/Apple Silicon

[ICML 2026 Oral] Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence

[ArXiv 26] The official repository of "ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors".

Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition