22 citations · 86 across the 30 of their papers we have counts for
31 papers
Improved Baselines with Representation Autoencoders
Jaskirat Singh, Boyang Zheng, Zongze Wu +3
Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this paper, we systematically investigate several design choices and find three insigh…
RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space
Xichen Pan, Aashu Singh, Satya Narayan Shukla +3
Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically limited to text encoding, while denoising is handled by newly trained generative…
Benchmarking Visual State Tracking in Multimodal Video Understanding
Sihyun Yu, Nanye Ma, Pinzhi Huang +8
Understanding a video requires more than recognizing isolated moments, as humans continuously track entities, states, and events over time. This capacity for visual state tracking…
PaintBench: Deterministic Evaluation of Precise Visual Editing
Kai Xu, Ellis Brown, Shrikar Madhu +3
While current multimodal models are proficient at open-ended visual editing, executing precise single-answer edits remains an important obstacle. To probe this challenge, we introd…
Cambrian-P: Pose-Grounded Video Understanding
Jihan Yang, Zifan Zhao, Xichen Pan +6
Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet this signal is large…
Image Generators are Generalist Vision Learners
Valentin Gabeur, Shangbang Long, Songyou Peng +22
Recent works show that image and video generators exhibit zero-shot visual understanding behaviors, in a way reminiscent of how LLMs develop emergent capabilities of language under…
Self-Refining Video Sampling
Sangwon Jang, Taekyung Ki, Jaehyeong Jo +3
Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additio…
Transition Matching Distillation for Fast Video Generation
Weili Nie, Julius Berner, Nanye Ma +3
Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to…
SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding
Ellis Brown, Arijit Ray, Ranjay Krishna +3
Despite impressive high-level video comprehension, multimodal language models struggle with spatial reasoning across time and space. While current spatial training approaches rely…
Cambrian-S: Towards Spatial Supersensing in Video
Shusheng Yang, Jihan Yang, Pinzhi Huang +12
We argue that progress in true multimodal intelligence calls for a shift from reactive, task-driven systems and brute-force long context towards a broader paradigm of supersensing.…
Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts
Ellis Brown, Jihan Yang, Shusheng Yang +2
Multimodal LLMs can answer many questions in vision-centric benchmarks without looking at the image, using linguistic priors and skewed answer distributions. Blind evaluation shows…
DASIP: Dynamic Test-Time Compute Scaling for Robot Control with Stochastic Interpolant Policies
Inkook Chun, Seungjae Lee, Michael S. Albergo +2
Diffusion- and flow-based policies deliver state-of-the-art performance on long-horizon robotic manipulation and imitation learning tasks. However, these controllers employ a fixed…
MindCube: Spatial Mental Modeling from Limited Views
Qineng Wang, Baiqiao Yin, Pingyue Zhang +11
Can Vision-Language Models (VLMs) imagine the full scene from just a few views, like humans do? Humans form spatial mental models naturally, internal representations of unseen spac…
Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
Bingda Tang, Boyang Zheng, Xichen Pan +2
This paper does not describe a new method; instead, it provides a thorough exploration of an important yet understudied design space related to recent advances in text-to-image syn…
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
Jiuhai Chen, Zhiyang Xu, Xichen Pan +10
Unifying image understanding and generation has gained growing attention in recent research on multimodal models. Although design choices for image understanding have been extensiv…
Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs
Hao Wang, Pinzhi Huang, Jihan Yang +2
The rapid evolution of multimodal large language models (MLLMs) has significantly enhanced their real-world applications. However, achieving consistent performance across languages…
Transfer between Modalities with MetaQueries
Xichen Pan, Satya Narayan Shukla, Aashu Singh +9
Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often dem…
PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop
Chenyu Li, Oscar Michel, Xichen Pan +3
Large-scale pre-trained video generation models excel in content creation but are not reliable as physically accurate world simulators out of the box. This work studies the process…
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…
Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
Jihan Yang, Shusheng Yang, Anjali W. Gupta +3
Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scal…
On Scaling Up 3D Gaussian Splatting Training
Hexu Zhao, Haoyang Weng, Daohan Lu +4
3D Gaussian Splatting (3DGS) is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed. However, 3DGS training currently occurs on a sing…
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Shengbang Tong, Ellis Brown, Penghao Wu +11
We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. While stronger language models can enhance multimodal capabilities, the design…
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
Yuexiang Zhai, Hao Bai, Zipeng Lin +8
Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios.…
MoDE: CLIP Data Experts via Clustering
Jiawei Ma, Po-Yao Huang, Saining Xie +5
The success of contrastive language-image pretraining (CLIP) relies on the supervision from the pairing between images and captions, which tends to be noisy in web-crawled data. We…