14 citations · 21 across the 26 of their papers we have counts for
28 papers
StreamErase: Towards Ultra-Fast Streaming Video Erasing
Zhuobai Dong, Xiaobing Tu, Xiantao Zhang +4
Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present StreamErase, enab…
Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents
AIMAE Team, Tianxiang Chen, Yan Cheng +39
Browser agents perform well on short, clean demonstrations, but real deployment is fundamentally different: agents must sustain dozens of decisions on live websites while recoverin…
STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion Models
Qingyan Wei, Guangzhao Li, Xiaobing Tu +5
On-policy distillation (OPD) has become an effective approach for consolidating multiple task-specialized image generation models into a single student. However, existing OPD metho…
EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPE
Zexuan Yan, Yuzhou Wu, Yue Ma +9
Egocentric video offers rich manipulation experience for embodied AI, yet collecting diverse egocentric data across scenes, objects, motions, and embodiments remains costly. We pre…
SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
Zhengan Yan, Shikang Zheng, Haoran Qin +9
Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dyna…
GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs
Wei Huang, Anda Cheng, Yinggui Wang
Fine-tuning Large Language Models (LLMs) with downstream data is often considered time-consuming and expensive. Structured pruning methods are primarily employed to improve the inf…
LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning
Wei Huang, Anda Cheng, Yinggui Wang +2
Large Language Models (LLMs) can be fine-tuned on domain-specific data to enhance their performance in specialized fields. However, such data often contains numerous low-quality sa…
Prefix Probing: Lightweight Harmful Content Detection for Large Language Models
Jirui Yang, Hengqi Guo, Zhihui Lu +6
Large language models often face a three-way trade-off among detection accuracy, inference latency, and deployment cost when used in real-world safety-sensitive applications. This…
Can LLM Infer Risk Information From MCP Server System Logs?
Jiayi Fu, Yuansen Zhang, Yinggui Wang
Large Language Models (LLMs) demonstrate strong capabilities in solving complex tasks when integrated with external tools. The Model Context Protocol (MCP) has become a standard in…
Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning
Wei Huang, Anda Cheng, Yinggui Wang
Recent advancements in large language models (LLMs) have shown impressive capabilities in various downstream tasks but typically face Catastrophic Forgetting (CF) during fine-tunin…
DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression
Wei Huang, Huang Wei, Yinggui Wang
Large language models (LLMs) excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data. With many open-source LLMs available, selectin…
DPF-CM: A Data Processing Framework with Privacy-Preserving Vector Databases for Chinese Medical LLMs Training and Deployment
Wei Huang, Anda Cheng, Zhao Zhang +1
Current open-source training pipelines for Chinese medical language models predominantly emphasize optimizing training methodologies to enhance the performance of large language mo…
AnchorSync: Global Consistency Optimization for Long Video Editing
Zichi Liu, Yinggui Wang, Tao Wei +1
Editing long videos remains a challenging task due to the need for maintaining both global consistency and temporal coherence across thousands of frames. Existing methods often suf…
GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models
Kai Yao, Zhaorui Tan, Penglei Gao +7
The rapid growth of large language models (LLMs) with traditional centralized fine-tuning emerges as a key technique for adapting these models to domain-specific challenges, yieldi…
On the Inference (In-)Security of Vertical Federated Learning: Efficient Auditing against Inference Tampering Attack
Chung-ju Huang, Ziqi Zhang, Yinggui Wang +3
Vertical Federated Learning (VFL) is an emerging distributed learning paradigm for cross-silo collaboration without accessing participants' data. However, existing VFL work lacks a…
Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley Value
Le Ma, Shirao Yang, Zihao Wang +4
The proliferation of large models has intensified the need for efficient data valuation methods to quantify the contribution of individual data providers. Traditional approaches, s…
CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept Rotation
Jirui Yang, Zheyu Lin, Zhihui Lu +6
Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerabil…
PRIV-QA: Privacy-Preserving Question Answering for Cloud Large Language Models
Guangwei Li, Yuansen Zhang, Yinggui Wang +3
The rapid development of large language models (LLMs) is redefining the landscape of human-computer interaction, and their integration into various user-service applications is bec…
Privacy Evaluation Benchmarks for NLP Models
Wei Huang, Yinggui Wang, Cen Chen
By inducing privacy attacks on NLP models, attackers can obtain sensitive information such as training data and model parameters, etc. Although researchers have studied, in-depth,…
Information Leakage from Embedding in Large Language Models
Zhipeng Wan, Anda Cheng, Yinggui Wang +1
The widespread adoption of large language models (LLMs) has raised concerns regarding data privacy. This study aims to investigate the potential for privacy invasion through input…
Ditto: Quantization-aware Secure Inference of Transformers upon MPC
Haoqi Wu, Wenjing Fang, Yancheng Zheng +4
Due to the rising privacy concerns on sensitive client data and trained models like Transformers, secure multi-party computation (MPC) techniques are employed to enable secure infe…
Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attack
Yinggui Wang, Yuanqing Huang, Jianshu Li +3
The utilization of personal sensitive data in training face recognition (FR) models poses significant privacy concerns, as adversaries can employ model inversion attacks (MIA) to i…
Inference Attacks Against Face Recognition Model without Classification Layers
Yuanqing Huang, Huilong Chen, Yinggui Wang +1
Face recognition (FR) has been applied to nearly every aspect of daily life, but it is always accompanied by the underlying risk of leaking private information. At present, almost…
A Fast, Performant, Secure Distributed Training Framework For Large Language Model
Wei Huang, Yinggui Wang, Anda Cheng +3
The distributed (federated) LLM is an important method for co-training the domain-specific LLM using siloed data. However, maliciously stealing model parameters and data from the s…