103 citations · 278 across the 43 of their papers we have counts for
8 papers · 1 filter
DMax: Aggressive Parallel Decoding for dLLMs
Zigeng Chen, Gongfan Fang, Xinyin Ma +2
We present DMax, a new paradigm for efficient diffusion language models (dLLMs). It mitigates error accumulation in parallel decoding, enabling aggressive decoding parallelism whil…
Invisible Safety Threat: Malicious Finetuning for LLM via Steganography
Guangnian Wan, Xinyin Ma, Gongfan Fang +1
Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we high…
VeriThinker: Learning to Verify Makes Reasoning Model Efficient
Zigeng Chen, Xinyin Ma, Gongfan Fang +2
Large Reasoning Models (LRMs) excel at complex tasks using Chain-of-Thought (CoT) reasoning. However, their tendency to overthinking leads to unnecessarily lengthy reasoning chains…
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
Xinyin Ma, Gongfan Fang, Michael Bi Mi +1
Diffusion Transformers have recently demonstrated unprecedented generative capabilities for various tasks. The encouraging results, however, come with the cost of slow inference, s…
Structural Pruning for Diffusion Models
Gongfan Fang, Xinyin Ma, Xinchao Wang
Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive…
Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data
Gongfan Fang, Yifan Bao, Jie Song +4
Knowledge distillation~(KD) aims to craft a compact student model that imitates the behavior of a pre-trained teacher in a target domain. Prior KD approaches, despite their gratify…
Data-Free Adversarial Distillation
Gongfan Fang, Jie Song, Chengchao Shen +3
Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer. However, almost all exist…
Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning
Sihui Luo, Xinchao Wang, Gongfan Fang +3
An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without acce…