10 papers
Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models
Xingyu Mou, Zijin Huang, Tianze Zhang +5
Block diffusion is the dominant approach for scaling discrete diffusion language models (dLLMs), as fixed-size blocks preserve parallel decoding while keeping quadratic attention c…
MOVA: Towards Scalable and Synchronized Video-Audio Generation
OpenMOSS Team, Donghua Yu, Mingshu Chen +38
Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on casc…
SimpleTool: Parallel Decoding for Real-Time LLM Function Calling
Xiaoxin Shi, Jiaxin Wan, Linkang Dong +3
LLM-based function calling enables intelligent agents to interact with external tools and environments, yet autoregressive decoding imposes a fundamental latency bottleneck that li…
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…
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…
Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs
Xiaoran Liu, Yuerong Song, Zhigeng Liu +6
Rotary Position Embeddings (RoPE) have become a standard for encoding sequence order in Large Language Models (LLMs) by applying rotations to query and key vectors in the complex p…