10 papers
C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks
Xueshu Chen, Yan Wang, Zihao Xue +5
Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained visual c…
Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning
Zhen Bi, Xueshu Chen, Yan Wang +6
Scientific reasoning requires language models to retrieve specialized knowledge and incorporate it reliably into multi-step computation. Conditional memory provides an explicit loo…
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
Yan Wang, Zhixuan Chu, Zihao Xue +9
Reasoning-based LLM guardrails improve safety moderation by generating explicit rationales before issuing final decisions. However, their rationales do not always lead to faithful…
Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers
Zihao Xue, Yan Wang, Zhen Bi +7
Diffusion Transformers have become a powerful backbone for text-to-image generation, but their layered and cross-modal generation process makes safety control fundamentally differe…
Make LLM Learn to Synthesize from Streaming Experiences through Feedback
Zhenlin Hu, Yan Wang, Zhen Bi +7
Large language models (LLMs) have been widely adopted for synthetic data generation, significantly reducing annotation costs. However, most existing studies treat synthesis as a se…
RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis
Zhen Bi, Xueshu Chen, Luoyang Sun +4
The transition toward localized intelligence through Small Language Models (SLMs) has intensified the need for rigorous performance characterization on resource-constrained edge ha…
Your One-Stop Solution for AI-Generated Video Detection
Long Ma, Zihao Xue, Yan Wang +6
Recent advances in generative modeling can create remarkably realistic synthetic videos, making it increasingly difficult for humans to distinguish them from real ones and necessit…
Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
Xianya Fang, Feiyang Ren, Xiang Chen +4
Multimodal LLMs are powerful but prone to object hallucinations, which describe non-existent entities and harm reliability. While recent unlearning methods attempt to mitigate this…
Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation
Zhen Bi, Zhenlin Hu, Xueshu Chen +7
The reasoning capabilities of Large Language Models (LLMs) are increasingly attributed to training data quality rather than mere parameter scaling. However, existing data-centric p…
Thought Purity: A Defense Framework For Chain-of-Thought Attack
Zihao Xue, Zhen Bi, Long Ma +7
Large Reasoning Models (LRMs) leverage Chain-of-Thought (CoT) reasoning to solve complex tasks, but this explicit reasoning process introduces a critical vulnerability: adversarial…