8 papers
Diffusion Transformers with Representation Autoencoders
Boyang Zheng, Nanye Ma, Shengbang Tong +1
Latent generative modeling, where a pretrained autoencoder maps pixels into a latent space for the diffusion process, has become the standard strategy for Diffusion Transformers (D…
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Tianzhe Chu, Yuexiang Zhai, Jihan Yang +6
Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization…
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Xiang Yue, Tianyu Zheng, Yuansheng Ni +10
This paper introduces MMMU-Pro, a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark. MMMU-Pro rigorously assesses multimodal mo…
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
Chun-Hsiao Yeh, Chenyu Wang, Shengbang Tong +7
Multi-view understanding, the ability to reconcile visual information across diverse viewpoints for effective navigation, manipulation, and 3D scene comprehension, is a fundamental…
Scaling Language-Free Visual Representation Learning
David Fan, Shengbang Tong, Jiachen Zhu +8
Visual Self-Supervised Learning (SSL) currently underperforms Contrastive Language-Image Pretraining (CLIP) in multimodal settings such as Visual Question Answering (VQA). This mul…
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
Shengbang Tong, David Fan, Jiachen Zhu +7
In this work, we propose Visual-Predictive Instruction Tuning (VPiT) - a simple and effective extension to visual instruction tuning that enables a pretrained LLM to quickly morph…