4 citations · 11 across the 17 of their papers we have counts for
20 papers
JUICE: Unified Multimodal Modeling in Pretrained Representation Spaces
Jiahan Li, Huangyuan Su, Shengbang Tong +9
Most unified multimodal models treat images and text asymmetrically: a pretrained language model generates text, an attached diffusion head generates images, and outputs that conta…
Purify Before You Align: Improving Representation Alignment for Diffusion Models
Yingheng Wang, Yaoqiang Li, Yaqin Wu +4
Representation alignment improves and accelerates diffusion training by encouraging intermediate features to match a pretrained visual encoder. However, standard alignment matches…
Latent Reasoning with Normalizing Flows
Guancheng Tu, Xiangjun Fu, Suhao Yu +5
Large language models often improve reasoning by generating explicit chain-of-thought (CoT), demonstrating the importance of intermediate computation. However, textual CoT forces t…
Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
Yao Tang, Li Dong, Yaru Hao +3
Large language models often solve complex reasoning tasks more effectively with Chain-of-Thought (CoT), but at the cost of long, low-bandwidth token sequences. Humans, by contrast,…
DenseAnnotate: Enabling Scalable Dense Caption Collection for Images and 3D Scenes via Spoken Descriptions
Xiaoyu Lin, Aniket Ghorpade, Hansheng Zhu +9
With the rapid adoption of multimodal large language models (MLLMs) across diverse applications, there is a pressing need for task-centered, high-quality training data. A key limit…
Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
Huangjie Zheng, Shansan Gong, Ruixiang Zhang +5
Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token. This creates an 'information void' where semantic informati…
Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
Ruixiang Zhang, Shuangfei Zhai, Jiatao Gu +6
Autoregressive models have driven remarkable progress in language modeling. Their foundational reliance on discrete tokens, unidirectional context, and single-pass decoding, while…
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
Shansan Gong, Ruixiang Zhang, Huangjie Zheng +4
Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence. The global planni…
TADA: Improved Diffusion Sampling with Training-free Augmented Dynamics
Tianrong Chen, Huangjie Zheng, David Berthelot +3
Diffusion models have demonstrated exceptional capabilities in generating high-fidelity images but typically suffer from inefficient sampling. Many solver designs and noise schedul…
What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?
Yizhe Zhang, Richard Bai, Zijin Gu +5
Language models usually use left-to-right (L2R) autoregressive factorization. However, L2R factorization may not always be the best inductive bias. Therefore, we investigate whethe…
World-consistent Video Diffusion with Explicit 3D Modeling
Qihang Zhang, Shuangfei Zhai, Miguel Angel Bautista +4
Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However,…
Normalizing Flows are Capable Generative Models
Shuangfei Zhai, Ruixiang Zhang, Preetum Nakkiran +7
Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density estimation and generative modeling tasks, but ha…
TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models
Georgia Gabriela Sampaio, Ruixiang Zhang, Shuangfei Zhai +4
Evaluating text-to-image generative models remains a challenge, despite the remarkable progress being made in their overall performances. While existing metrics like CLIPScore work…
DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation
Jiatao Gu, Yuyang Wang, Yizhe Zhang +5
Diffusion models have become the dominant approach for visual generation. They are trained by denoising a Markovian process which gradually adds noise to the input. We argue that t…
Improving GFlowNets for Text-to-Image Diffusion Alignment
Dinghuai Zhang, Yizhe Zhang, Jiatao Gu +4
Diffusion models have become the de-facto approach for generating visual data, which are trained to match the distribution of the training dataset. In addition, we also want to con…
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
Jiatao Gu, Ying Shen, Shuangfei Zhai +3
Diffusion models have emerged as a powerful tool for generating high-quality images from textual descriptions. Despite their successes, these models often exhibit limited diversity…
Many-to-many Image Generation with Auto-regressive Diffusion Models
Ying Shen, Yizhe Zhang, Shuangfei Zhai +3
Recent advancements in image generation have made significant progress, yet existing models present limitations in perceiving and generating an arbitrary number of interrelated ima…
How Far Are We from Intelligent Visual Deductive Reasoning?
Yizhe Zhang, He Bai, Ruixiang Zhang +4
Vision-Language Models (VLMs) have recently demonstrated incredible strides on diverse vision language tasks. We dig into vision-based deductive reasoning, a more sophisticated but…
Divide-or-Conquer? Which Part Should You Distill Your LLM?
Zhuofeng Wu, He Bai, Aonan Zhang +4
Recent methods have demonstrated that Large Language Models (LLMs) can solve reasoning tasks better when they are encouraged to solve subtasks of the main task first. In this paper…
Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Models
Liangchen Song, Liangliang Cao, Jiatao Gu +3
The advancement of text-driven 3D content editing has been blessed by the progress from 2D generative diffusion models. However, a major obstacle hindering the widespread adoption…