activity
20232026
most citedSwitch EMA: A Free Lunch for Better Flatness and Sharpness

3 citations · 5 across the 25 of their papers we have counts for

collaborators
Showing 2026Show all

11 papers · 1 filter

stat.ML2026

FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models

Yansen Han, Shengyi Liao, Peng Sun +4

Preference alignment for flow and diffusion models now spans online reinforcement learning and offline preference optimization, but the relation between these methods remains uncle…

cs.LG2026

When Can Conditional Flow Matching Replace Pointwise Negative Log-Likelihood?

Yansen Han, Hongxin Sun, Tao Lin

Flow matching enables likelihood-free training, yet alignment methods increasingly reuse conditional flow matching (CFM) losses as endpoint negative log-likelihoods (NLLs) and thei…

cs.CV2026

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Chuyan Chen, Haoxing Chen, Kun Chen +27

We introduce LLaDA-Image, a unified framework that pairs a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision-language understanding module built on the LLaDA…

cs.AI2026

Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking

Yansen Han, Shengyi Liao, Yuanxing Zhang +2

Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching, reward-driven upda…

cs.CV2026

Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs

Tao Lin, Gaojie Jin, Zongxin Liu +2

Existing vision-language model (VLM) backdoors are usually treated as static vulnerabilities: one-to-one and N-to-N attacks bind one or more triggers to a finite set of targets bef…

cs.LG2026

Three-Body Scattering for Generative Modeling

Peng Sun, Zhenglin Cheng, Deyuan Liu +3

Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressive factorization. Instead, we show that a proper distributional…