1 citations · 3 across the 12 of their papers we have counts for
13 papers
Budgeted Attack Scheduling for LLM Red-Teaming: The Roles of Static Priors, Semantic Guidance, and Online Feedback
Zhicheng Fang, Han Sun, Jiachen Lei +5
As jailbreak attacks against large language models (LLMs) become increasingly diverse, red-teaming has come to rely on large libraries of jailbreak prompts and attack strategies to…
DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
Jiashu Zhu, Yanhao Zheng, Ruitian Tian +7
Recent video generators often omit audio or synthesize it in a separate stage, limiting reciprocal modeling of visual dynamics and acoustic events. We present DreamX-Creator 1.0, a…
FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding
Fufangchen Zhao, Jinhu Fu, Jiachen Lei +3
Counterfactual video understanding evaluates whether models grasp physical and commonsense regularities. However, existing multiple-choice question (MCQ) benchmarks inadvertently l…
DreamX-World 1.0: A General-Purpose Interactive World Model
DreamX Team, Yancheng Bai, Rui Chen +20
DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model for controllable long-horizon generation. It supports camera navigation, revisits to previously ob…
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
Chenxi Zhao, Chen Zhu, Xiaokun Feng +6
Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow prima…
MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
Xiaoxiao Ma, Jiachen Lei, Tianfei Ren +6
Reinforcement learning (RL) has been successfully applied to autoregressive (AR) and diffusion models. However, extending RL to hybrid AR-diffusion frameworks remains challenging d…
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
Meiqi Wu, Zhixin Cai, Fufangchen Zhao +13
Video--based world models have emerged along two dominant paradigms: video generation and 3D reconstruction. However, existing evaluation benchmarks either focus narrowly on visual…
There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training
Jiachen Lei, Keli Liu, Julius Berner +4
Pixel-space generative models are often more difficult to train and generally underperform compared to their latent-space counterparts, leaving a persistent performance and efficie…
Robust Representation Consistency Model via Contrastive Denoising
Jiachen Lei, Julius Berner, Jiongxiao Wang +5
Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying ro…
Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
Yiquan Li, Zhongzhu Chen, Kun Jin +3
Diffusion Purification, purifying noised images with diffusion models, has been widely used for enhancing certified robustness via randomized smoothing. However, existing framework…
SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution
Zhongjie Ba, Jieming Zhong, Jiachen Lei +5
Advanced text-to-image models such as DALLE 2 and Midjourney possess the capacity to generate highly realistic images, raising significant concerns regarding the potential p…
Masked Diffusion Models Are Fast Distribution Learners
Jiachen Lei, Qinglong Wang, Peng Cheng +5
Diffusion model has emerged as the \emph{de-facto} model for image generation, yet the heavy training overhead hinders its broader adoption in the research community. We observe th…
Masked Autoencoders for Egocentric Video Understanding @ Ego4D Challenge 2022
Jiachen Lei, Shuang Ma, Zhongjie Ba +3
In this report, we present our approach and empirical results of applying masked autoencoders in two egocentric video understanding tasks, namely, Object State Change Classificatio…