22 citations · 73 across the 29 of their papers we have counts for
34 papers
Looking Into The Past: The Impact of Context on Detecting Deceptive Statements
Alex Clay, Ernesto Jimenez-Ruiz, Pranava Madhyastha
Deception detection typically considers messages in isolation. Previous works in claim verification and role detection have displayed that additional information such as gameplay h…
In-Context Learning Can Help Vision-Language Models Overcome Training Priors
Kun Wang, Xindi Wu, Sanghyuk Chun +2
Vision-language models (VLMs) learn strong statistical regularities during training, which can make them fail to properly respond to visual evidence when input images violate those…
Depth as Time in One-Step Generative Models
Arnold Caleb Asiimwe, William Yang, Sanghyuk Chun +2
The recent wave of one-step generative models, which compress the multi-step trajectory of diffusion via either distillation or learned flow maps, has reached an inflection point w…
Addressable Memory for Video World Models
Xindi Wu, Sven Elflein, James Lucas +5
We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames.…
Personalized Generative Models for Contextual Debiasing
Xinran Liang, Esin Tureci, Prachi Sinha +3
Different visual patterns appear with different frequencies in the world: e.g., beach balls appear on sand more often than they do on a road. These statistics are reflected in visi…
Reinforced Fast Weights with Next-Sequence Prediction
Hee Seung Hwang, Xindi Wu, Sanghyuk Chun +1
Fast weight architectures offer a promising alternative to attention-based transformers for long-context modeling by maintaining constant memory overhead regardless of context leng…
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
Ye Zhu, Kaleb S. Newman, Johannes F. Lutzeyer +3
Despite high semantic alignment, modern text-to-image (T2I) generative models still struggle to synthesize diverse images from a given prompt. In this work, we enhance the T2I dive…
Motion Attribution for Video Generation
Xindi Wu, Despoina Paschalidou, Jun Gao +5
Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a m…
Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition
Ellie Zhou, Jihoon Chung, Olga Russakovsky
Human action recognition models often rely on background cues rather than human movement and pose to make predictions, a behavior known as background bias. We present a systematic…
Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
William Yang, Xindi Wu, Zhiwei Deng +2
Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating effective synthetic training data for classification remains challenging. Fine-tun…
Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
Asher J. Hancock, Xindi Wu, Lihan Zha +2
Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it…
Dynamic Diffusion Schrödinger Bridge in Astrophysical Observational Inversions
Ye Zhu, Duo Xu, Zhiwei Deng +2
We study Diffusion Schrödinger Bridge (DSB) models in the context of dynamical astrophysical systems, specifically tackling observational inverse prediction tasks within Giant Mole…
Visual Compositional Tuning
Xindi Wu, Hee Seung Hwang, Polina Kirichenko +2
Visual instruction tuning (VIT) datasets have grown rapidly in scale, yet the informativeness of individual training samples has largely been overlooked. Recent dataset selection m…
Unifying Specialized Visual Encoders for Video Language Models
Jihoon Chung, Tyler Zhu, Max Gonzalez Saez-Diez +3
The recent advent of Large Language Models (LLMs) has ushered sophisticated reasoning capabilities into the realm of video through Video Large Language Models (VideoLLMs). However,…
ICONS: Influence Consensus for Vision-Language Data Selection
Xindi Wu, Mengzhou Xia, Rulin Shao +3
Training vision-language models via instruction tuning relies on large data mixtures spanning diverse tasks and domains, yet these mixtures frequently include redundant information…
The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation
Ruoyu Wang, Huayang Huang, Ye Zhu +2
In this work, we introduce NoiseQuery as a novel method for enhanced noise initialization in versatile goal-driven text-to-image (T2I) generation. Specifically, we propose to lever…
SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation
Yuhan Pei, Ruoyu Wang, Yongqi Yang +3
Originating from the diffusion phenomenon in physics, which describes the random movement and collisions of particles, diffusion generative models simulate a random walk in the dat…
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
Xindi Wu, Dingli Yu, Yangsibo Huang +2
Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions. Existing e…
What is Dataset Distillation Learning?
William Yang, Ye Zhu, Zhiwei Deng +1
Dataset distillation has emerged as a strategy to overcome the hurdles associated with large datasets by learning a compact set of synthetic data that retains essential information…
Analyzing the Roles of Language and Vision in Learning from Limited Data
Allison Chen, Ilia Sucholutsky, Olga Russakovsky +1
Does language help make sense of the visual world? How important is it to actually see the world rather than having it described with words? These basic questions about the nature…
DETER: Detecting Edited Regions for Deterring Generative Manipulations
Sai Wang, Ye Zhu, Ruoyu Wang +3
Generative AI capabilities have grown substantially in recent years, raising renewed concerns about potential malicious use of generated data, or "deep fakes". However, deep fake d…
A Sampling-Based Domain Generalization Study with Diffusion Generative Models
Ye Zhu, Yu Wu, Duo Xu +3
In this work, we investigate the domain generalization capabilities of diffusion models in the context of synthesizing images that are distinct from the training data. Instead of f…
Vision-Language Dataset Distillation
Xindi Wu, Byron Zhang, Zhiwei Deng +1
Dataset distillation methods reduce large-scale datasets to smaller sets of synthetic data, preserving sufficient information to quickly train a new model from scratch. However, pr…
Boundary Guided Learning-Free Semantic Control with Diffusion Models
Ye Zhu, Yu Wu, Zhiwei Deng +2
Applying pre-trained generative denoising diffusion models (DDMs) for downstream tasks such as image semantic editing usually requires either fine-tuning DDMs or learning auxiliary…