69 citations · 127 across the 30 of their papers we have counts for
36 papers
Traffic State Prediction and Control Using a Koopman Operator Framework with Polynomial Observables
Shakib Mustavee, Arvind Singh, Shaurya Agarwal
In this paper, we develop a Koopman operator framework for modeling and control of traffic flow governed by the Lighthill--Whitham--Richards (LWR) conservation law. We show that th…
Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers
Qiao Li, Xiaomeng Fu, Yuanshu Zhao +3
Multimodal Diffusion Transformers (MM-DiTs) have demonstrated remarkable text-to-image generation performance, surpassing traditional U-Net-based diffusion models. Nevertheless, th…
Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors
Qiao Li, Xiaomeng Fu, Wangjia Yu +4
The exceptional generation capabilities of text-to-image diffusion models have raised copyright concerns, particularly the unauthorized reproduction of animation characters. Existi…
CogRec: Structure-Cognitive Fast-and-Slow Reasoning for Generative Recommendation
Xiang Liu, Jingsong Su, Shuqi Zhao +7
Semantic-ID-based generative recommendation represents each item as a hierarchical discrete token sequence and reformulates next-item prediction as constrained sequence generation.…
Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agents
Jiwen Zhou, Xiang Liu, Mingming Li +5
Recommender systems operate as Black-Boxes, leaving users and regulators unable to steer their outputs toward specific intentions or audit their behavior. This lack of controllabil…
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption
Xiaomeng Fu, Jia Li, Yiming Hu +5
Autoregressive (AR) streaming models have emerged as a powerful paradigm for long video generation. However, the linearly growing Key-Value (KV) cache poses a significant bottlenec…
HoloRec: Holistic Encoding and Interleaved Reasoning for Generative Recommendation
Shuqi Zhao, Jingsong Su, Xiang Liu +9
Generative recommendation models that formulate the task as sequence generation overcome the objective fragmentation problem of traditional cascade architectures, yet existing appr…
BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation
Xi Zhou, Famin Wu, Mingming Li +4
Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities loca…
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
Lijia Lv, Xuehai Tang, Jie Wen +2
Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering int…
RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents
Wenjie Xiao, Xuehai Tang, Biyu Zhou +2
Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions insi…
FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing
Peng Wang, Biyu Zhou, Xuehai Tang +2
Unstructured model editing aims to update models with real-world text, yet existing methods often memorize text holistically without reliable fine-grained fact access. To address t…
RecBundle: A Next-Generation Geometric Paradigm for Explainable Recommender Systems
Hui Wang, Tianzhu Hu, Mingming Li +6
Recommender systems are inherently dynamic feedback loops where prolonged local interactions accumulate into macroscopic structural degradation such as information cocoons. Existin…
A Cognitive Distribution and Behavior-Consistent Framework for Black-Box Attacks on Recommender Systems
Hongyue Zhang, Mingming Li, Dongqin Liu +6
With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extractio…
Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing
Runze He, Yiji Cheng, Tiankai Hang +11
In-context image generation and editing (ICGE) enables users to specify visual concepts through interleaved image-text prompts, demanding precise understanding and faithful executi…
Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
Liang Lin, Zhihao Xu, Xuehai Tang +5
The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensit…
Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
Xikang Yang, Biyu Zhou, Xuehai Tang +2
Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit co…
Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation
Wenchao Zhang, Jiahe Tian, Runze He +5
Recent text-to-image (T2I) generation models have advanced significantly, enabling the creation of high-fidelity images from textual prompts. However, existing evaluation benchmark…
LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
Peng Wang, Biyu Zhou, Xuehai Tang +2
Large Language Models often contain factually incorrect or outdated knowledge, giving rise to model editing methods for precise knowledge updates. However, current mainstream locat…
Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regression
Shaofei Huang, Zhenwei Shen, Zehao Huang +4
In this paper, we focus on the challenging task of monocular 3D lane detection. Previous methods typically adopt inverse perspective mapping (IPM) to transform the Front-Viewed (FV…
Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation
Baisen Wang, Le Zhuo, Zhaokai Wang +7
Multimodal music generation aims to produce music from diverse input modalities, including text, videos, and images. Existing methods use a common embedding space for multimodal fu…
The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models
Xikang Yang, Xuehai Tang, Jizhong Han +1
The widespread deployment of large language models (LLMs) across various domains has showcased their immense potential while exposing significant safety vulnerabilities. A major co…
FreeEdit: Mask-free Reference-based Image Editing with Multi-modal Instruction
Runze He, Kai Ma, Linjiang Huang +6
Introducing user-specified visual concepts in image editing is highly practical as these concepts convey the user's intent more precisely than text-based descriptions. We propose F…
Dynamic Prompting of Frozen Text-to-Image Diffusion Models for Panoptic Narrative Grounding
Hongyu Li, Tianrui Hui, Zihan Ding +5
Panoptic narrative grounding (PNG), whose core target is fine-grained image-text alignment, requires a panoptic segmentation of referred objects given a narrative caption. Previous…
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…