15 papers
When 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction
Yihang Huang, Peisong Wen, Chenhao Zhou +2
Visual token compression has emerged as a critical technique for reducing the inference cost of Vision-Language Models. Existing methods select tokens based on text relevance, visu…
Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment
Haoming Yang, Ke Ma, Yangbangyan Jiang +6
Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign context. We id…
The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video Generation
Peng Li, Qianqian Xu, Yangbangyan Jiang +2
The rapid evolution of video generation has shifted the paradigm from pure text-driven to multi-conditional controllable generation, with reference images now widely adopted as con…
ZenGen: Social Mind for LLMs
ZenGen Team, Ao Xiang, Bi Jingping +57
As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track…
Technical Report on the CVPR 2026@AdvML Workshop Challenge
Tianyuan Zhang, Zonglei Jing, Jiangfan Liu +47
Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Cha…
Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning
Yang Liu, Qianqian Xu, Peisong Wen +2
Recent advances in large vision-language models have expanded video retrieval from simple text-based search to more flexible scenarios, where users may specify the desired result t…
Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection
Boyu Han, Qianqian Xu, Shilong Bao +3
In this report, we address the problem of determining whether a user performs an action incorrectly from egocentric video data. To this end, we propose an Understanding-Enhanced Mo…
Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate
Huangyu Xu, Jingqin Yang, Qianqian Xu +1
Sparse optimization is a fundamental challenge in various practical applications. A popular approach to sparse optimization is regularization. However, it may encounter op…
The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works
Guanghui Wang, Kaiwen Lv Kacuila, Zhiyong Yang +5
Knowledge distillation (KD) transfers knowledge from a large teacher model to a smaller student. In language modeling, the student is trained either on tokens sampled from the teac…
The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?
Xingyu Lyu, Qianqian Xu, Zhiyong Yang +2
Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform their non-gated counterparts, ye…
Localize and Neutralize: Gradient-guided Token Suppression against Visual Prompt Injection Attack
Dongpeng Zhang, Ke Ma, Yangbangyan Jiang +4
Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the unde…
Learn Faster and Remember More: Balancing Exploration and Exploitation for Continual Test-time Adaptation
Pinci Yang, Peisong Wen, Ke Ma +1
Continual Test-Time Adaptation (CTTA) aims to adapt a source pre-trained model to continually changing target domains during inference. As a fundamental principle, an ideal CTTA me…
A Unified Framework for Stealthy Adversarial Generation via Latent Optimization and Transferability Enhancement
Gaozheng Pei, Ke Ma, Dongpeng Zhang +3
Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to re…
Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain
Gaozheng Pei, Ke Ma, Yingfei Sun +2
The diffusion-based adversarial purification methods attempt to drown adversarial perturbations into a part of isotropic noise through the forward process, and then recover the cle…
Exploring Query Efficient Data Generation towards Data-free Model Stealing in Hard Label Setting
Gaozheng Pei, Shaojie lyu, Ke Ma +3
Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training da…