· ai
[Paper] LitePT: Lighter Yet Stronger Point Transformer
Modern neural architectures for 3D point cloud processing contain both convolutional layers and attention blocks, but the best way to assemble them remains uncl...
-
- · ai
[Paper] Towards Scalable Pre-training of Visual Tokenizers for Generation
The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training p...
- · ai
[Paper] Recurrent Video Masked Autoencoders
We present Recurrent Video Masked-Autoencoders (RVM): a novel video representation learning approach that uses a transformer-based recurrent neural network to a...
- · ai
[Paper] I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners
Generalization remains the central challenge for interactive 3D scene generation. Existing learning-based approaches ground spatial understanding in limited sce...
- · ai
[Paper] LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction
Recent feed-forward reconstruction models like VGGT and π^3 achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memor...
- · ai
[Paper] Feedforward 3D Editing via Text-Steerable Image-to-3D
Recent progress in image-to-3D has opened up immense possibilities for design, AR/VR, and robotics. However, to use AI-generated 3D assets in real applications,...
- · ai
[Paper] JoVA: Unified Multimodal Learning for Joint Video-Audio Generation
In this paper, we present JoVA, a unified framework for joint video-audio generation. Despite recent encouraging advances, existing methods face two critical li...
- · ai
[Paper] Towards Interactive Intelligence for Digital Humans
We introduce Interactive Intelligence, a novel paradigm of digital human that is capable of personality-aligned expression, adaptive interaction, and self-evolu...
- · ai
[Paper] Directional Textual Inversion for Personalized Text-to-Image Generation
Textual Inversion (TI) is an efficient approach to text-to-image personalization but often fails on complex prompts. We trace these failures to embedding norm i...
- · ai
[Paper] World Models Can Leverage Human Videos for Dexterous Manipulation
Dexterous manipulation is challenging because it requires understanding how subtle hand motion influences the environment through contact with objects. We intro...
- · ai
[Paper] From Code to Field: Evaluating the Robustness of Convolutional Neural Networks for Disease Diagnosis in Mango Leaves
The validation and verification of artificial intelligence (AI) models through robustness assessment are essential to guarantee the reliable performance of inte...
- · ai
[Paper] Do-Undo: Generating and Reversing Physical Actions in Vision-Language Models
We introduce the Do-Undo task and benchmark to address a critical gap in vision-language models: understanding and generating physically plausible scene transfo...