21 papers
STRATA: Self-Maintaining Structured Experience Graphs for Self-Evolving Language Agents
Guanhua Zhu, Hanwen Li, Zhi Wei +2
Large language model (LLM) agents can self-evolve at test time by accumulating experience: retrieving relevant memories before acting and writing new lessons back afterwards. Yet m…
Grounding with Confidence: Controllable Generative Video Temporal Grounding
Jinhao Chen, Benlei Cui, Ruijian Jia +7
Video temporal grounding supports applications such as video search, content review, and automated editing by localizing events described in natural language. Yet existing generati…
Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models
Benlei Cui, Shen Pang, Yuke Wang +7
The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the meta level: template-based atta…
EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion
Ruijie Jian, Benlei Cui, Ting Ma +8
Existing evaluations of harmful content detection rely predominantly on static benchmarks, which struggle to reflect the interactive adversarial ecosystem of real-world content pla…
MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding
Benlei Cui, Ruize Wang, Junjie Li +9
Long-form video understanding requires locating sparse, question-relevant evidence in long, multimodal videos. Real-world video distributions differ in modality-specific informatio…
Pass the Baton: Trajectory-Relayed On-Policy Distillation
Haolei Xu, Xiaowen Xu, Haiwen Hong +5
On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning directi…
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Hongxing Li, Xiufeng Huang, Dingming Li +11
Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visual cues are buried in high-resolution images. Existing approach…
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
Ting Ma, Xiufeng Huang, Benlei Cui +43
As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safet…
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety
Shikai Qiu, Xiaowen Xu, Benlei Cui +55
General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI s…
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
Ziwen Xu, Haiwen Hong, Linsong Yu +4
Large Language Models (LLMs) must continuously learn and update knowledge to remain effective in dynamic real-world environments. While Low-Rank Adaptation (LoRA) is widely used fo…
simpleposter: A simple baseline for product poster generation
Benlei Cui, Fangao Zeng, Weitao Jiang +6
Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise control over dense, multi-l…
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
Ziwen Xu, Kewei Xu, Haoming Xu +8
Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality,…
Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
Haolei Xu, Haiwen Hong, Hongxing Li +7
Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon termed Seeing but Not Thinking:…
TC-Padé: Trajectory-Consistent Padé Approximation for Diffusion Acceleration
Benlei Cui, Shaoxuan He, Bukun Huang +8
Despite achieving state-of-the-art generation quality, diffusion models are hindered by the substantial computational burden of their iterative sampling process. While feature cach…
Diffusion Probe: Generated Image Result Prediction Using CNN Probes
Benlei Cui, Bukun Huang, Zhizeng Ye +7
Text-to-image (T2I) diffusion models lack an efficient mechanism for early quality assessment, leading to costly trial-and-error in multi-generation scenarios such as prompt iterat…
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
Ziwen Xu, Chenyan Wu, Hengyu Sun +9
Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation,…
YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models
Junyu Lin, Meizhen Liu, Xiufeng Huang +12
As large language models (LLMs) are increasingly deployed in real-world applications, safety guardrails are required to go beyond coarse-grained filtering and support fine-grained,…
AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset
Bingxiang He, Wenbin Zhang, Jiaxi Song +11
Preference learning is critical for aligning large language models (LLMs) with human values, yet its success hinges on high-quality datasets comprising three core components: Prefe…
One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications
Mengyao Lyu, Yuhong Yang, Haiwen Hong +6
The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing…
Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition
Yunqing Hu, Xuan Jin, Yin Zhang +5
Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base…
DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework
Haiwen Hong, Xuan Jin, Yin Zhang +4
In multimodal tasks, we find that the importance of text and image modal information is different for different input cases, and for this motivation, we propose a high-performance…