activity
20242026
collaborators

10 papers

cs.AI2026

MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agents

Zhiyuan Liu, Tinghong Ye, Chenghao Liu +2

Long-horizon agents accumulate growing contexts during interaction, impairing performance and stability. Compact memory mitigates this problem by compressing and rewriting the hist…

cs.CV2026

Making Foresight Actionable: Repurposing Representation Alignment in World Action Models

Lu Qiu, Yizhuo Li, Yi Chen +3

World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution before producing control actions. However…

cs.CV2026

Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

Zhixuan Liang, Yizhuo Li, Tianshuo Yang +9

Vision-Language-Action (VLA) models adapt large vision-language backbones to map images and instructions into robot actions. However, prevailing VLAs either generate actions autore…

cs.CV2026

End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer

Wenda Chu, Bingliang Zhang, Jiaqi Han +4

Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes r…

cs.LG2026

Aligning Latent Spaces with Flow Priors

Yizhuo Li, Yuying Ge, Yixiao Ge +2

This paper presents a novel framework for aligning learnable latent spaces to arbitrary target distributions by leveraging flow-based generative models as priors. Our method first…

cs.CV2026

DiCoDe: Diffusion-Compressed Deep Tokens for Autoregressive Video Generation with Language Models

Yizhuo Li, Yuying Ge, Yixiao Ge +2

Videos are inherently temporal sequences by their very nature. In this work, we explore the potential of modeling videos in a chronological and scalable manner with autoregressive…