6 papers
Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers
Ligong Han, Kai Xu, Hao Wang +3
Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequential composition of many nonlin…
SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing
Ruikang Zhao, Zhenting Wang, Han Gao +1
Reinforcement learning for diffusion large language models (dLLMs) has largely moved to trajectory-aware methods. The current state of the art, TraceRL, holds that random masking i…
SNLP: Layer-Parallel Inference via Structured Newton Corrections
Ligong Han, Kai Xu, Hao Wang +1
Autoregressive language models execute Transformer layers sequentially, creating a latency bottleneck that is not removed by conventional tensor or pipeline parallelism. We study w…
S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation
Ligong Han, Hao Wang, Han Gao +2
Block-diffusion language models offer a promising path toward faster-than-autoregressive generation by combining block-wise autoregressive decoding with within-block parallel denoi…
Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention
Jiaqian Li, Yanshu Li, Ligong Han +2
Implicit in-context learning (ICL) has newly emerged as a promising paradigm that simulates ICL behaviors in the representation space of large language models (LLMs), aiming to att…
CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning
Yanshu Li, Jianjiang Yang, Zhennan Shen +3
Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it als…