7 citations · 17 across the 51 of their papers we have counts for
57 papers
MergeHEIR: Mitigating Multimodal Hallucinations as the Tax of Model Merging
Jinyu Li, Hao Fang, Zhiming Zhang +3
Model merging consolidates task-specialized experts into a single deployable model. However, we show that such capability consolidation incurs a merging tax of increased hallucinat…
PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding
Xiang Liu, Jinxiang Wang, Bin Chen +5
Implicit neural representation (INR) has achieved remarkable progress in novel view synthesis and image/video coding in recent years.Compared to conventional end-to-end image codec…
Weak Ties, Strong Signals: Efficient Training Data Detection in Diffusion LLMs via Independent Token Sampling
Hongyao Yu, Tianqu Zhuang, Ziyuan Xu +4
Diffusion large language models (dLLMs) offer a compelling alternative to autoregressive models, yet they may expose sensitive training data during denoising. Detecting such usage…
CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment
Wenbo Yu, Bohua Wang, Hao Fang +10
Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or multilin…
MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents
Yv Zhang, Hao Sun, Hao Fang +5
External memory has become a core component of modern web agents, enabling long-horizon reasoning through the retrieval of past experiences. However, this paradigm introduces a cri…
Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization
Ziang Xu, Wenbo Yu, Hongyao Yu +6
With the growing concerns over copyright infringement in diffusion-based customization, adversarial attacks have emerged as a prominent defense strategy to prevent malicious conten…
Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization
Jiawei Kong, Hao Fang, Shunxiang Liao +5
Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallu…
FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
Yi Sun, Zhiqi Zhang, Xinhao Zhong +5
Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or un…
C2P-VAR: Continual and Compositional Personalization in Visual Autoregressive Models
Junhao Li, Xinhao Zhong, Yi sun +4
Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation, yet their personalization capabilities remain largely limited to sta…
Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation
Sixu Chen, Xiang Chen, Hongyao Yu +5
The widespread deployment and redistribution of large language models (LLMs) have made model provenance tracking a critical challenge. While existing LLM fingerprinting methods, pa…
C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts
Chenxi Qing, Junxi Wu, Zheng Liu +5
Recently, large language models (LLMs) are capable of generating highly fluent textual content. While they offer significant convenience to humans, they also introduce various risk…
Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding
Shuoyang Sun, Chang Dai, Hao Fang +6
Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a tar…
Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy
Junxi Wu, Kailin Huang, Dongjian Hu +4
Detecting AI-generated text is an important but challenging problem. Existing likelihood-based detection methods are often sensitive to content complexity and may exhibit unstable…
NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)
Ya-nan Guan, Shaonan Zhang, Hang Guo +55
In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI Flash Portrait. Despite sign…
Seeing Through the Chain: Understanding and Mitigating Hallucinations in Multimodal Large Reasoning Models
Hao Fang, Jinyu Li, Jiawei Kong +4
While multimodal reasoning models (MLRMs) have exhibited impressive capabilities, they remain prone to hallucinations, and effective solutions are still underexplored. In this pape…
Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization
Hao Fang, Wenbo Yu, Bin Chen +4
Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a global model…
Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation
Xiaochen Yang, Hao Fang, Jiawei Kong +3
Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitatio…
Tail-Aware Post-Training Quantization for 3D Geometry Models
Sicheng Pan, Chen Tang, Shuzhao Xie +6
The burgeoning complexity and scale of 3D geometry models pose significant challenges for deployment on resource-constrained platforms. While Post-Training Quantization (PTQ) enabl…
Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective
Hao Fang, Tianyi Zhang, Tianqu Zhuang +6
Proprietary large language models (LLMs) embody substantial economic value and are generally exposed only as black-box APIs, yet adversaries can still exploit their outputs to extr…
Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
Zhiqi Zhang, Xinhao Zhong, Yi Sun +5
Text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images, yet their tendency to reproduce undesirable concepts, such as NSFW conte…
Generalization Bounds for Transformer Channel Decoders
Qinshan Zhang, Bin Chen, Yong Jiang +1
Transformer channel decoders, such as the Error Correction Code Transformer (ECCT), have shown strong empirical performance in channel decoding, yet their generalization behavior r…
Splatwizard: A Benchmark Toolkit for 3D Gaussian Splatting Compression
Xiang Liu, Yimin Zhou, Jinxiang Wang +9
The recent advent of 3D Gaussian Splatting (3DGS) has marked a significant breakthrough in real-time novel view synthesis. However, the rapid proliferation of 3DGS-based algorithms…
Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive Models
Xinhao Zhong, Yimin Zhou, Zhiqi Zhang +6
The rapid progress of visual autoregressive (VAR) models has brought new opportunities for text-to-image generation, but also heightened safety concerns. Existing concept erasure t…
Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization
Yixiang Qiu, Yanhan Liu, Hongyao Yu +4
The growing complexity of Deep Neural Networks (DNNs) has led to the adoption of Split Inference (SI), a collaborative paradigm that partitions computation between edge devices and…