12 papers
XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modeling
Jinxiu Liu, Xuanming Liu, Kangfu Mei +2
High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative sampling. Existing efficient method…
Open-Linguistic Concept Unified Learning for Cross-Site Interpretable Dermatology Image Diagnosis
Chengyu Wu, Junpeng Tan, Wanxiang Luo +3
Human-interpretable computer-aided diagnosis is crucial for clinical decision making. Concept-based models excel by providing transparent reasoning and enabling post-hoc, clinician…
SymbOmni: Evolving Agentic Omni Models via Symbolic Concept Learning
Jinxiu Liu, Jianru Li, Tanqing Kuang +4
Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation. Yet prevailing monolithic models remain fund…
Drifting Preference Optimization for One-Step Generative Models
Zhou Jiang, Yandong Wen, Zhen Liu
One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standar…
PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective
Yangyi Huang, Ruotian Peng, Zeju Qiu +4
Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstream accuracy while overlooking t…
Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
Kexuan Shi, Hanxuan Li, Zeju Qiu +3
We introduce Pion, a spectrum-preserving optimizer for large language model (LLM) training based on orthogonal equivalence transformation. Unlike additive optimizers such as Adam a…
Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance
Zhou Jiang, Yandong Wen, Zhen Liu
Aligning large-scale text-to-image diffusion models with nuanced human preferences remains challenging. While direct preference optimization (DPO) is simple and effective, large-sc…
Model Merging with Functional Dual Anchors
Kexuan Shi, Yandong Wen, Weiyang Liu
Model merging is an efficient post-training strategy for integrating knowledge from multiple finetuned checkpoints of a shared foundation model. Existing methods operate in the par…
Beyond the Sampled Token: Preserving Candidate Support in RLVR
Ruotian Peng, Yi Ren, Zhouliang Yu +2
We revisit exploration collapse in reinforcement learning with verifiable rewards (RLVR), from the perspective of the \emph{candidate distribution} for next-token prediction. We fo…
Symbolic Graphics Programming with Large Language Models
Yamei Chen, Haoquan Zhang, Yangyi Huang +4
Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplore…
FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models
Zhouliang Yu, Ruotian Peng, Keyi Ding +10
Formal mathematical reasoning remains a critical challenge for artificial intelligence, hindered by limitations of existing benchmarks in scope and scale. To address this, we prese…
Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception
Ruotian Peng, Haiying He, Yake Wei +2
High-quality image captions play a crucial role in improving the performance of cross-modal applications such as text-to-image generation, text-to-video generation, and text-image…