1 citations · 1 across the 12 of their papers we have counts for
12 papers
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…
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…
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…
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…
Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives
Zecheng Wang, Deyuan Liu, Chunshan Li +5
Standard negative log-likelihood (NLL) for Supervised Fine-Tuning (SFT) applies uniform token-level weighting. This rigidity creates a two-fold failure mode: (i) overemphasizing lo…
Beyond Confidence: The Rhythms of Reasoning in Generative Models
Deyuan Liu, Zecheng Wang, Zhanyue Qin +3
Large Language Models (LLMs) exhibit impressive capabilities yet suffer from sensitivity to slight input context variations, hampering reliability. Conventional metrics like accura…
LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models
Zhanyue Qin, Yue Ding, Deyuan Liu +7
Nowadays, Large Language Models (LLMs) have attracted widespread attention due to their powerful performance. However, due to the unavoidable exposure to socially biased data durin…
Efficient Generative Model Training via Embedded Representation Warmup
Deyuan Liu, Peng Sun, Xufeng Li +1
Generative models face a fundamental challenge: they must simultaneously learn high-level semantic concepts (what to generate) and low-level synthesis details (how to generate it).…
Mitigating Gender Bias in Code Large Language Models via Model Editing
Zhanyue Qin, Haochuan Wang, Zecheng Wang +6
In recent years, with the maturation of large language model (LLM) technology and the emergence of high-quality programming code datasets, researchers have become increasingly conf…
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models
Zhanyue Qin, Haochuan Wang, Deyuan Liu +9
Sequential decision-making refers to algorithms that take into account the dynamics of the environment, where early decisions affect subsequent decisions. With large language model…
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
Deyuan Liu, Zhanyue Qin, Hairu Wang +12
While large language models (LLMs) excel in many domains, their complexity and scale challenge deployment in resource-limited environments. Current compression techniques, such as…
Checkpoint Merging via Bayesian Optimization in LLM Pretraining
Deyuan Liu, Zecheng Wang, Bingning Wang +6
The rapid proliferation of large language models (LLMs) such as GPT-4 and Gemini underscores the intense demand for resources during their training processes, posing significant ch…