14 papers
Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?
Tianyi Zhang, Mahtab Bigverdi, Ranjay Krishna
Vision-language models (VLMs) are increasingly augmented with continuous or latent non-textual tokens intended to support "visual thinking." Despite improved task accuracy, this al…
RefDecoder: Enhancing Visual Generation with Conditional Video Decoding
Xiang Fan, Yuheng Wang, Bohan Fang +2
Video generation powers a vast array of downstream applications. However, while the de facto standard, i.e., latent diffusion models, typically employ heavily conditioned denoising…
Posterior Augmented Flow Matching
George Stoica, Sayak Paul, Matthew Wallingford +6
Flow matching (FM) trains a time-dependent vector field that transports samples from a simple prior to a complex data distribution. However, for high-dimensional images, each train…
NVILA: Efficient Frontier Visual Language Models
Zhijian Liu, Ligeng Zhu, Baifeng Shi +24
Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a…
ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
Jiawei Gu, Yunzhuo Hao, Huichen Will Wang +5
Multimodal reasoning requires iterative coordination between language and vision, yet it remains unclear what constitutes a meaningful interleaved chain of thought. We posit that t…
AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
Mingyang Song, Haoyu Sun, Jiawei Gu +4
When humans face problems beyond their immediate capabilities, they rely on tools, providing a promising paradigm for improving visual reasoning in multimodal large language models…