6 papers
WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark
Yida Yin, Harish Krishnakumar, Chung Peng Lee +9
In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types without capturing the visual…
VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
Guanyu Zhou, Yida Yin, Wenhao Chai +3
Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition. One plausible contributing factor is that natural…
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
Shengbang Tong, Boyang Zheng, Ziteng Wang +7
Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet by training in high-dimensional semantic latent spaces. In this work, we investi…
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.…
AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy
Jinghang Shi, Xiaoyu Tang, Yang Huang +4
Astronomical image interpretation presents a significant challenge for applying multimodal large language models (MLLMs) to specialized scientific tasks. Existing benchmarks focus…
Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
Junhong Shen, Hao Bai, Lunjun Zhang +8
The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this…