papers

Publications (12)

cs.CV2023

LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model

Peng Gao, Jiaming Han, Renrui Zhang +9

How to efficiently transform large language models (LLMs) into instruction followers is recently a popular research direction, while training LLM for multi-modal reasoning remains…

cs.CV2023

SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models

Ziyi Lin, Chris Liu, Renrui Zhang +13

We present SPHINX, a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, tuning tasks, and visual embeddings. First, for stronger vision-languag…

cs.CV2025

TerDiT: Ternary Diffusion Models with Transformers

Xudong Lu, Aojun Zhou, Ziyi Lin +7

Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of…

cs.CV2022

ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning

Junting Pan, Ziyi Lin, Xiatian Zhu +2

Capitalizing on large pre-trained models for various downstream tasks of interest have recently emerged with promising performance. Due to the ever-growing model size, the standard…

cs.CV2022

Frozen CLIP Models are Efficient Video Learners

Ziyi Lin, Shijie Geng, Renrui Zhang +6

Video recognition has been dominated by the end-to-end learning paradigm -- first initializing a video recognition model with weights of a pretrained image model and then conductin…

cs.CV2022

ConvMAE: Masked Convolution Meets Masked Autoencoders

Peng Gao, Teli Ma, Hongsheng Li +3

Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer…

cs.CV2020

1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020

Siyu Chen, Junting Pan, Guanglu Song +6

This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020. Our entry is mainly b…

cs.CV2025

SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

Dongyang Liu, Renrui Zhang, Longtian Qiu +16

We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX…

cs.CR2025

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate

Senmao Qi, Yifei Zou, Peng Li +3

Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security im…

cs.CV2023

Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking

Peng Gao, Renrui Zhang, Rongyao Fang +4

Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decod…

cs.CV2018

Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration

Lu Sheng, Ziyi Lin, Jing Shao +1

Zero-shot artistic style transfer is an important image synthesis problem aiming at transferring arbitrary style into content images. However, the trade-off between the generalizat…

cs.CV2023

Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models

Junting Pan, Ziyi Lin, Yuying Ge +5

Video Question Answering (VideoQA) has been significantly advanced from the scaling of recent Large Language Models (LLMs). The key idea is to convert the visual information into t…