1 citations · 1 across the 14 of their papers we have counts for
7 papers · 1 filter
COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detection
Zhan Yang, Tiancheng Shen, Weijie Lyu +4
Generalizable AI-generated image (AIGI) and deepfake detection remain challenging due to the asymmetry phenomenon, where adaptation to limited training distributions can degrade th…
The Thinking Leakage in Reinforcement Learning for LLMs
Wenxuan Zhu, Shuming Liu, Bang An +4
Hybrid reasoning models such as the Qwen3 series switch between a THINK mode and a NO-THINK mode through a few chat-template tokens. A popular recipe trains such models with reinfo…
SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity
Liyang Yuan, Yibo Yang, Dandan Guo +2
Federated Learning (FL) is fundamentally challenged by statistical heterogeneity, where non-identically distributed (non-IID) data induces client drift that severely hampers global…
Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner
Jieke Wang, Tiancheng Shen, Yibo Yang +1
Frontier multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning. Parameter-level adaptation is unavailable…
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models
Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey +3
Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two dire…
Defending Against Harmful Supervision Hidden in Benign Samples
Bang An, Yibo Yang, Dandan Guo +3
Existing defenses are effective when harmful content is explicitly mixed into downstream fine-tuning data, but crafted samples can instead hide harmful supervision inside benign ta…
CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
Zhongzhu Zhou, Fengxiang Bie, Ziyan Chen +6
Converting pretrained attention modules such as grouped-query attention (GQA) into multi-head latent attention (MLA) can improve expressivity without increasing KV-cache cost, maki…