9 papers
PaDoc: Layout-Grounded Parallel Decoding for Document Parsing
Hao Yu, Jiabo Zhan, Kang Liu +8
End-to-end document parsers provide a unified interface, but serialize page layouts and regional contents into one autoregressive sequence. This formulation forces independent regi…
Enhancing Geometric Perception in VLMs via Translator-Guided Reinforcement Learning
Hao Yu, Shuning Jia, Guanghao Li +2
Vision-language models (VLMs) often struggle with geometric reasoning due to their limited perception of fundamental diagram elements. To tackle this challenge, we introduce GeoPer…
ContextRL: Enhancing MLLM's Knowledge Discovery Efficiency with Context-Augmented RL
Xingyu Lu, Jinpeng Wang, YiFan Zhang +12
We propose ContextRL, a novel framework that leverages context augmentation to overcome these bottlenecks. Specifically, to enhance Identifiability, we provide the reward model wit…
DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
Guanghao Li, Zhihui Fu, Min Fang +4
As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Specu…
Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation
Xinrui Chen, Hongxing Zhang, Fanyi Zeng +5
Layer pruning has emerged as a promising technique for compressing large language models (LLMs) while achieving acceleration proportional to the pruning ratio. In this work, we ide…
ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
Hao Yu, Tangyu Jiang, Shuning Jia +7
The Transformer architecture has revolutionized various regions since it was proposed, and its effectiveness largely depends on the ability to encode positional information. Tradit…