12 papers
EgoSafe: A First-Person Mobile-Captured Benchmark for Visual Safety Understanding
Yuyun Chen, Tianao Li, TianQuan Feng +4
The paper introduces EgoSafe-Bench, a first‑person video dataset and evaluation protocol designed to test causal and forensic reasoning for visual safety understanding, highlightin…
FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization
Jianwei Wang, Guoyang Shen, Yanhong Wu +5
Stream guardrails enable token-level safety detection before full responses are generated. However, they often make overly conservative judgements and block those sensitive but saf…
ProCache: Constraint-Aware Feature Caching with Selective Computation for Diffusion Transformer Acceleration
Fanpu Cao, Yaofo Chen, Zeng You +1
Diffusion Transformers (DiTs) have achieved state-of-the-art performance in generative modeling, yet their high computational cost hinders real-time deployment. While feature cachi…
RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior
Junyao Yang, Jianwei Wang, Huiping Zhuang +2
Large Language Models (LLMs) with long chain-of-thought (CoT) capability, termed Reasoning Models, demonstrate superior intricate problem-solving abilities through multi-step long…
REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning
Run He, Di Fang, Yizhu Chen +5
Exemplar-free class-incremental learning (EFCIL) aims to mitigate catastrophic forgetting in class-incremental learning (CIL) without available historical training samples as exemp…
ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior
Weikai Lu, Ziqian Zeng, Kehua Zhang +5
Multimodal Large Language Models (MLLMs) are increasingly vulnerable to multimodal Indirect Prompt Injection (IPI) attacks, which embed malicious instructions in images, videos, or…