13 citations · 13 across the 6 of their papers we have counts for
8 papers
DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation
Siyang He, Qiqi Wang, Fan Liu +5
The rapid growth of microdramas has increased demand for high-quality script production. Long-form microdrama script generation with LLMs requires both diverse plot progression and…
Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position
Xiaoran Liu, Ziwei He, Xipeng Qiu
The architectural design of Large Language Models (LLMs) is shifting from traditional full-attention-only models to hybrid models, which combine different attention modules to impr…
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding
Zhigeng Liu, Zhiyuan Ning, Ruixiao Li +5
The development of long-context Large Language Models (LLMs) is constrained by the memory bandwidth bottleneck and quadratic complexity of the attention mechanism during decoding.…
DiRL: An Efficient Post-Training Framework for Diffusion Language Models
Ying Zhu, Jiaxin Wan, Xiaoran Liu +7
Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models. While recent efforts have validated their pre-training potential and accele…
FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation
Siyang He, Qiqi Wang, Xiaoran Liu +8
Despite the non-autoregressive potential of diffusion language models (dLLMs), existing decoding strategies demonstrate positional bias, failing to fully unlock the potential of ar…
SIM-CoT: Supervised Implicit Chain-of-Thought
Xilin Wei, Xiaoran Liu, Yuhang Zang +5
Implicit Chain-of-Thought (CoT) methods offer a token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited…
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
Xilin Wei, Xiaoran Liu, Yuhang Zang +9
While Rotary Position Embedding (RoPE) and its variants are widely adopted for their long-context capabilities, the extension of the 1D RoPE to video, with its complex spatio-tempo…
Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder
Jiaqi Wang, Zhenxi Song, Zhengyu Ma +3
Reconstructing natural language from non-invasive electroencephalography (EEG) holds great promise as a language decoding technology for brain-computer interfaces (BCIs). However,…