15 papers
DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
ZhiYan Hou, Xinyu Tang, Hongyan An +9
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals…
Continual Learning in Transition
Zhiyan Hou, Dan Zhang, Tao Feng +11
Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architect…
Can Text-to-Image Models Draw from the Right Frame of Reference?
Zheyuan Gu, Ruihang Li, Yong Huang +5
Spatial instruction following has become a crucial requirement for text-to-image (T2I) generation. A common challenge arises when directional expressions are interpreted under diff…
Test-Time Curriculum for Open-Set AIGC Detection
Yiqian Zhang, Zheyuan Gu, Xiangzhao Hao +8
AI-generated image detectors deployed in open-world environments inevitably face distribution shifts as new and stronger generative models continue to emerge. Although existing met…
ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding
Shijie Wang, Xiangzhao Hao, Yueti Li +3
Universal multimodal embedding (UME) maps heterogeneous multimodal inputs into a shared embedding space. Existing UME models either form embeddings through single forward encoding…
PLUME: Latent Reasoning Based Universal Multimodal Embedding
Chenwei He, Xiangzhao Hao, Tianyu Yang +6
Universal multimodal embedding (UME) maps heterogeneous inputs into a shared retrieval space with a single model. Recent approaches improve UME by generating explicit chain-of-thou…