activity
20242026
collaborators

15 papers

cs.AI2026

Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders

Keito Kozaki, Keigo Sakurai, Ren Togo +2

Transformer-based sequential recommenders with causal self-attention often rely heavily on the most recent interaction at inference time, but how this behavior is structurally expr…

cs.CV2026

Beyond Pixel Histories: World Models with Persistent 3D State

Samuel Garcin, Thomas Walker, Steven McDonagh +5

Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D rep…

cs.CV2026

Foundation VAEs for 3D CT Reconstruction, Augmentation, and Generation

Qi Chen, Shuhan Ding, Yu Gu +5

Variational autoencoders (VAEs) compress high resolution CT volumes into compact latents while preserving clinically relevant structure. However, training CT-specific VAEs from scr…

cs.CV2026

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

Haoyu Wu, Diankun Wu, Tianyu He +4

Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw video data often fail to capture…

cs.CV2026

LIVE: Long-horizon Interactive Video World Modeling

Junchao Huang, Ziyang Ye, Xinting Hu +5

Autoregressive video world models predict future visual observations conditioned on actions. While effective over short horizons, these models often struggle with long-horizon gene…

cs.CV2025

Reinforcement Learning with Inverse Rewards for World Model Post-training

Yang Ye, Tianyu He, Shuo Yang +1

World models simulate dynamic environments, enabling agents to interact with diverse input modalities. Although recent advances have improved the visual quality and temporal consis…