Skip to content

Author

Hayden Kwok-Hay So

University of Hong Kong

We have 5 of 173 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

Training-Free Predictive Spatio-Temporal Token Pruning for Few-Step Autoregressive Video Diffusion

Few-step autoregressive (AR) video diffusion models generate videos chunk by chunk and have made efficient video generation practical. However, further accelerating these models toward real-time generation remains challenging, as few-step distillation leaves little cross-step redundancy for existing training-free cachi...

Jia Li, Xu-Rui Peng, Xing Wang et al. · 0 citations
Preprint Nov 2026

A Per-Step Load-Balancing Engine for Expert-Parallel MoE Serving

In expert-parallel Mixture-of-Experts serving, a layer finishes only when the most loaded GPU of its group does. Token routing shifts at every decode step and concentrates on a few experts, so most of the group's reserved GPU time waits on stragglers. Recovering that time means re-deciding, at every layer of every deco...

Jing-Yuan Li, Mao-Lin Wang, Hayden Kwok-Hay So · 0 citations
Preprint Oct 2026

TriTD: Tri-Partite Trajectory-Distribution Distillation for Real-Time Autoregressive Video Generation

Autoregressive (AR) video diffusion has emerged as a leading paradigm for efficient video generation, yet its practical deployment remains bottlenecked by the trade-off between generation quality and inference efficiency. We attribute this bottleneck to three error sources in AR rollouts: the base model error, the trai...

Jia Li, Xu-Rui Peng, Hao-Wei Zhu et al. · 1 citation
#natural language process... Preprint Sep 2026

Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance

SPS is a training-free latent steering framework that constructs a state-conditioned Direction Bank containing multiple progress-guided steering vectors for different prefix-state regions and applies it at high-uncertainty transitions to guide the next reasoning step toward meaningful progress.

Hengyuan Zhang, Chenming Shang, Zun-Hai Su et al. · 0 citations
#machine learning Conference Oct 2025

Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation

PerSyn (Personalized data Synthesis), a novel synthesis strategy that operates under a new ``Route then Generate''paradigm to create data tailored to each student model, enabling it to learn more effectively, is proposed.

Hengyuan Zhang, Shi-Ping Yang, Xiao Liang et al. · 21 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.