activity
20242026
most citedGMem: A Modular Approach for Ultra-Efficient Generative Models

1 citations · 1 across the 8 of their papers we have counts for

collaborators

12 papers

cs.CV2026

Self-Adversarial One Step Generation via Condition Shifting

Deyuan Liu, Peng Sun, Yansen Han +3

The push for efficient text to image synthesis has moved the field toward one step sampling, yet existing methods still face a three way tradeoff among fidelity, inference speed, a…

cs.LG2026

Duality Models: An Embarrassingly Simple One-step Generation Paradigm

Peng Sun, Xinyi Shang, Tao Lin +1

Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such m…

cs.CV2026

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Zhenglin Cheng, Peng Sun, Jianguo Li +1

Recent advances in large multi-modal generative models have demonstrated impressive capabilities in multi-modal generation, including image and video generation. These models are t…

cs.LG2026

A Collision-Free Hot-Tier Extension for Engram-Style Conditional Memory: A Controlled Study of Training Dynamics

Tao Lin

We investigate whether high-frequency key collisions are a primary bottleneck in Engram-style conditional memory. To isolate the effect of collisions, we introduce Engram-Nine, a c…

cs.CL2025

Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertainty

Ziyu Chen, Xinbei Jiang, Peng Sun +1

Masked Diffusion Models (MDMs) offer flexible, non-autoregressive generation, but this freedom introduces a challenge: final output quality is highly sensitive to the decoding orde…

cs.LG2025

Fast and Stable Diffusion Planning through Variational Adaptive Weighting

Zhiying Qiu, Tao Lin

Diffusion models have recently shown promise in offline RL. However, these methods often suffer from high training costs and slow convergence, particularly when using transformer-b…