3 citations · 5 across the 20 of their papers we have counts for
23 papers
SPIDER: Multi-Layer Semantic Token Pruning and Adaptive Sub-Layer Skipping in Multimodal Large Language Models
Tianxiang Chen, Zhentao Tan, Zi Ye +9
Multimodal Large Language Models face significant efficiency challenges that stem from two distinct yet coupled sources: data redundancy and computational redundancy. While most me…
PlanGuard: A Guardrail for Multi-Step Plan Safety in Embodied Agents
Junchi Chen, Changtao Miao, Yuxiao Xiang +9
Embodied task planners may produce multi-step plans whose subtask dependencies and interactions with the environment create physical risks during execution. Yet existing safeguards…
EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders
Xinghao Wang, Dong Li, Wei Yu +5
Recent advances in text-to-video (T2V) diffusion models have demonstrated remarkable generative capabilities, yet their reliance on loosely curated training data raises pressing sa…
TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models
Chao Zhou, Yiling Chen, Qi Chu +3
Although pretrained joint audio-visual diffusion models offer rich control over \emph{what} to generate, they provide no explicit control over \emph{when} an utterance should occur…
Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation
Kaichao Jiang, Changtao Miao, Baiqi Wu +9
Recent audio-video generators increasingly support joint conditioning on text, images, audio, and video. These capabilities also enable attacks that exploit cross-modal interaction…
Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production
Cong Ming, Jingyi Chen, Bin Liu +4
Deployed LLM safety guardrails are predominantly static: trained once and frozen at release, while new jailbreak techniques and previously un-addressed harmful categories emerge wi…
ANFI: Rethinking Neighbor Feature Interaction in Person Re-ID
Xulin Li, Yan Lu, Bin Liu +5
In person re-identification, neighbor-based methods have achieved significant success by interacting with neighbor samples to obtain more robust representations. However, existing…
MFEN:Multi-Frequency Expert Network for Visible-Infrared Person Re-ID
Xulin Li, Yan Lu, Bin Liu +4
Visible-infrared person re-identification (VI-ReID) is challenging due to the large modality discrepancy between visible and infrared images. We contend that this discrepancy is la…
TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images
Yuning Zhang, Changtao Miao, Mingyu Liao +5
Recent AI-generated image (AIGI) detectors perform well on natural-image benchmarks, but their behavior on text-rich forgeries, such as fabricated screenshots, documents, and news…
Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs
Xuanpu Zhao, Zhentao Tan, Dianmo Sheng +6
To enhance the perception and reasoning capabilities of multimodal large language models in complex visual scenes, recent research has introduced agent-based workflows. In these wo…
SAPL: Semantic-Agnostic Prompt Learning in CLIP for Weakly Supervised Image Manipulation Localization
Xinghao Wang, Changtao Miao, Dianmo Sheng +6
Malicious image manipulation threatens public safety and requires efficient localization methods. Existing approaches depend on costly pixel-level annotations which make training e…
GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision
Yuxiao Xiang, Junchi Chen, Zhenchao Jin +5
Multimodal large reasoning models (MLRMs) are increasingly deployed for vision-language tasks that produce explicit intermediate rationales. However, reasoning traces can contain u…
Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization
Rui Chen, Bin Liu, Changtao Miao +5
Advances in image tampering pose serious security threats, underscoring the need for effective image manipulation localization (IML). While supervised IML achieves strong performan…
Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification
Xulin Li, Yan Lu, Bin Liu +6
In real applications, person re-identification (ReID) is expected to retrieve the target person at any time, including both daytime and nighttime, ranging from short-term to long-t…
Flora: Effortless Context Construction to Arbitrary Length and Scale
Tianxiang Chen, Zhentao Tan, Xiaofan Bo +5
Effectively handling long contexts is challenging for Large Language Models (LLMs) due to the rarity of long texts, high computational demands, and substantial forgetting of short-…
MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation
Chenghao Yang, Yinbo Luo, Zhoufutu Wen +8
Large Language Models (\textbf{LLMs}), e.g. ChatGPT, have been widely adopted in real-world dialogue applications. However, LLMs' robustness, especially in handling long complex di…
Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement
Xinghao Wang, Tao Gong, Qi Chu +2
Malicious image manipulation poses societal risks, increasing the importance of effective image manipulation detection methods. Recent approaches in image manipulation detection ha…
Inclusion 2024 Global Multimedia Deepfake Detection Challenge: Towards Multi-dimensional Face Forgery Detection
Yi Zhang, Weize Gao, Changtao Miao +10
In this paper, we present the Global Multimedia Deepfake Detection held concurrently with the Inclusion 2024. Our Multimedia Deepfake Detection aims to detect automatic image and a…
Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
Tianxiang Chen, Zhentao Tan, Tao Gong +5
As a manner to augment pre-trained large language models (LLM), knowledge injection is critical to develop vertical domain large models and has been widely studied. Although most c…
Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization
Changtao Miao, Qi Chu, Tao Gong +6
With the advancement of face manipulation technology, forgery images in multi-face scenarios are gradually becoming a more complex and realistic challenge. Despite this, detection…
MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection
Tianxiang Chen, Zi Ye, Zhentao Tan +6
Recently, infrared small target detection (ISTD) has made significant progress, thanks to the development of basic models. Specifically, the models combining CNNs with transformers…
Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues
Tianxiang Chen, Zhentao Tan, Tao Gong +6
How to effectively interact audio with vision has garnered considerable interest within the multi-modality research field. Recently, a novel audio-visual segmentation (AVS) task ha…
Towards More Unified In-context Visual Understanding
Dianmo Sheng, Dongdong Chen, Zhentao Tan +7
The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domai…