127 citations · 129 across the 13 of their papers we have counts for
13 papers
Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models
In Chong Choi, Jiacheng Zhang, Feng Liu +1
Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. Howev…
SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification
Jiacheng Zhang, Feng Liu, Chao Du +1
A line of recent training-free methods for mitigating hallucinations in large vision-language models (LVLMs) operates by amplifying attention to visual tokens during autoregressive…
ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching
Guanbo Huang, Jingjia Mao, Fanding Huang +8
Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of…
Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
Shuhai Zhang, ZiHao Lian, Jiahao Yang +6
AI-generated videos have achieved near-perfect visual realism (e.g., Sora), urgently necessitating reliable detection mechanisms. However, detecting such videos faces significant c…
Vision Language Models Cannot Plan, but Can They Formalize?
Muyu He, Yuxi Zheng, Yuchen Liu +7
The advancement of vision language models (VLMs) has empowered embodied agents to accomplish simple multimodal planning tasks, but not long-horizon ones requiring long sequences of…
Dynamic-I2V: Exploring Image-to-Video Generation Models via Multimodal LLM
Peng Liu, Xiaoming Ren, Fengkai Liu +5
Recent advancements in image-to-video (I2V) generation have shown promising performance in conventional scenarios. However, these methods still encounter significant challenges whe…
EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse
Tianyu Guo, Hande Dong, Yichong Leng +4
Large language models (LLMs) are often used for infilling tasks, which involve predicting or generating missing information in a given text. These tasks typically require multiple…
ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models
Ozgur Kara, Krishna Kumar Singh, Feng Liu +3
Current diffusion-based text-to-video methods are limited to producing short video clips of a single shot and lack the capability to generate multi-shot videos with discrete transi…
Could AI Trace and Explain the Origins of AI-Generated Images and Text?
Hongchao Fang, Yixin Liu, Jiangshu Du +7
AI-generated content is becoming increasingly prevalent in the real world, leading to serious ethical and societal concerns. For instance, adversaries might exploit large multimoda…
Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding
Yun Li, Zhe Liu, Yajing Kong +6
Applying Multimodal Large Language Models (MLLMs) to video understanding presents significant challenges due to the need to model temporal relations across frames. Existing approac…
AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs
Lijia Lv, Weigang Zhang, Xuehai Tang +4
Jailbreak vulnerabilities in Large Language Models (LLMs) refer to methods that extract malicious content from the model by carefully crafting prompts or suffixes, which has garner…
Baichuan 2: Open Large-scale Language Models
Aiyuan Yang, Bin Xiao, Bingning Wang +52
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing…
MemeFaceGenerator: Adversarial Synthesis of Chinese Meme-face from Natural Sentences
Yifu Chen, Zongsheng Wang, Bowen Wu +6
Chinese meme-face is a special kind of internet subculture widely spread in Chinese Social Community Networks. It usually consists of a template image modified by some amusing deta…