8 papers
Latent Visual States for Efficient Multimodal Reasoning
Xiuwei Chen, Wentao Hu, Yongxin Wang +8
The integration of visual evidence has significantly enhanced the capabilities of large multimodal models. However, this integration predominantly relies on generating discrete out…
DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling
Tengyao Tu, Yulin Li, Hui-Ling Zhen +6
Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from…
SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning
Kun Xiang, Terry Jingchen Zhang, Zirong Liu +15
We introduce SeePhys Pro, a fine-grained modality transfer benchmark that studies whether models preserve the same reasoning capability when critical information is progressively t…
FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
Zehua Pei, Hui-Ling Zhen, Xianzhi Yu +3
Large language models can now process increasingly long inputs, yet their ability to effectively use information spread across long contexts remains limited. We trace this gap to h…
MemDLM: Memory-Enhanced DLM Training
Zehua Pei, Hui-Ling Zhen, Weizhe Lin +4
Diffusion Language Models (DLMs) offer attractive advantages over Auto-Regressive (AR) models, such as full-attention parallel decoding and flexible generation. However, standard D…
DLLM Agent: See Farther, Run Faster
Huiling Zhen, Weizhe Lin, Renxi Liu +15
Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties, yet their implications for…
Top 10 Open Challenges Steering the Future of Diffusion Language Model and Its Variants
Yunhe Wang, Kai Han, Huiling Zhen +13
The paradigm of Large Language Models (LLMs) is currently defined by auto-regressive (AR) architectures, which generate text through a sequential ``brick-by-brick'' process. Despit…
Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs
Hanting Chen, Jiarui Qin, Jialong Guo +15
Large Language Models (LLMs) deliver state-of-the-art capabilities across numerous tasks, but their immense size and inference costs pose significant computational challenges for p…