activity
20242026
collaborators

9 papers

cs.CL2026

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs

Yuchuan Tian, Yuchen Liang, Shuo Zhang +10

Diffusion Language Models (DLMs) enable fast generation, yet training large DLMs from scratch is costly. As a practical shortcut, adapting off-the-shelf Auto-Regressive (AR) model…

cs.CL2026

Top 10 Open Challenges Steering the Future of Diffusion Language Model and Its Variants

Yunhe Wang, Kai Han, Huiling Zhen +13

The paradigm of Large Language Models (LLMs) is currently defined by auto-regressive (AR) architectures, which generate text through a sequential ``brick-by-brick'' process. Despit…

cs.CL2026

Deferred Commitment Decoding for Diffusion Language Models

Yingte Shu, Yuchuan Tian, Chao Xu +2

Diffusion language models (DLMs) have recently emerged as a strong alternative to autoregressive models by enabling parallel text generation. To improve inference efficiency and KV…

cs.CL2025

Nexus: Higher-Order Attention Mechanisms in Transformers

Hanting Chen, Chong Zhu, Kai Han +6

Transformers have achieved significant success across various domains, relying on self-attention to capture dependencies. However, the standard first-order attention mechanism is o…

astro-ph.HE2025

Revealing the Temporally Stable Bimodal Energy Distribution of FRB 20121102A with a Tripled Burst Set from AI Detections

Yidan Wang, Jing Han, Pei Wang +34

Active repeating Fast Radio Bursts (FRBs), with their large number of bursts, burst energy distribution, and their potential energy evolution, offer critical insights into the FRBs…

cs.CV2025

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping

Ning Ding, Jing Han, Yuchuan Tian +3

Diffusion Transformer (DiT) has now become the preferred choice for building image generation models due to its great generation capability. Unlike previous convolution-based UNet…