Publications (18)
Adapting Feature Attenuation to NLP
Tianshuo Yang, Ryan Rabinowitz, Terrance E. Boult +1
Transformer classifiers such as BERT deliver impressive closed-set accuracy, yet they remain brittle when confronted with inputs from unseen categories--a common scenario for deplo…
AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratory
Zhiqian Lan, Yuxuan Jiang, Ruiqi Wang +12
Vision-language-action (VLA) models have shown promise as generalist robotic policies by jointly leveraging visual, linguistic, and proprioceptive modalities to generate action tra…
Matrix Kloosterman Sums, Random Matrix Statistics, and Cryptography
Tianshuo Yang
This paper presents a comprehensive study of matrix Kloosterman sums, including their computational aspects, distributional behavior, and applications in cryptographic analysis. Bu…
Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers
Peng Gao, Le Zhuo, Dongyang Liu +17
Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lac…
InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
Nianchen Deng, Lixin Gu, Shenglong Ye +17
Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversi…
AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
Yutian Chen, Shi Guo, Renbiao Jin +7
Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing diffusion-based approaches m…
LemmaHead: RAG Assisted Proof Generation Using Large Language Models
Tianbo Yang, Mingqi Yan, Hongyi Zhao +1
Developing the logic necessary to solve mathematical problems or write mathematical proofs is one of the more difficult objectives for large language models (LLMS). Currently, the…
RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination
Haotian Liang, Mingkang Chen, Yufei Huang +27
The paper introduces RxBrain, a foundation model that jointly reasons over language and visual inputs to create embodied plans, using a multimodal Mixture-of-Transformers architect…
Classified as unknown: A novel Bayesian neural network
Tianbo Yang, Tianshuo Yang
We establish estimations for the parameters of the output distribution for the softmax activation function using the probit function. As an application, we develop a new efficient…
4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture
Yutian Chen, Shi Guo, Tianshuo Yang +4
Reconstructing fast-dynamic scenes from multi-view videos is crucial for high-speed motion analysis and realistic 4D reconstruction. However, the majority of 4D capture systems are…
Finding the minimum distance and decoding linear codes with Gaussian Elimination Method
Tianshuo Yang
We propose an algorithm using the Gaussian elimination method to find the minimal Hamming distance and decode received messages of linear codes. This algorithm is easy to implement…
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models
Dehui Wang, Rong Wei, Yue Shi +9
The growing demand for Embodied AI and VR applications has highlighted the need for synthesizing high-quality 3D indoor scenes from sparse inputs. However, existing approaches stru…
Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
Zhixuan Liang, Yizhuo Li, Tianshuo Yang +9
Vision-Language-Action (VLA) models adapt large vision-language backbones to map images and instructions into robot actions. However, prevailing VLAs either generate actions autore…
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
Tianshuo Yang, Guanyu Chen, Yutian Chen +8
While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often compromises the profound rea…
Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop
Tianxing Chen, Kaixuan Wang, Zhaohui Yang +96
Embodied Artificial Intelligence (Embodied AI) is an emerging frontier in robotics, driven by the need for autonomous systems that can perceive, reason, and act in complex physical…
PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models
Fanqing Meng, Wenqi Shao, Lixin Luo +8
Text-to-image (T2I) models have made substantial progress in generating images from textual prompts. However, they frequently fail to produce images consistent with physical common…
Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model
Lirui Zhao, Tianshuo Yang, Wenqi Shao +5
This paper addresses an important problem of object addition for images with only text guidance. It is challenging because the new object must be integrated seamlessly into the ima…
MM-ACT: Learn from Multimodal Parallel Generation to Act
Haotian Liang, Xinyi Chen, Bin Wang +12
A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we…