10 papers
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
Pingchen Lu, Xiangyi Wang, Xiang Li +6
Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience, yet existing skill optimization methods often rely on costly execution-base…
PosterReward: Unlocking Accurate Evaluation for High-Quality Graphic Design Generation
Jianyu Lai, Sixiang Chen, Jialin Gao +7
Recent advancements in the text-rendering capabilities of image generation models have made the end-to-end creation of graphic design content, such as posters, increasingly feasibl…
PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback
Sixiang Chen, Jianyu Lai, Jialin Gao +6
Image-to-poster generation is a high-demand task requiring not only local adjustments but also high-level design understanding. Models must generate text, layout, style, and visual…
Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models
Tianyang Han, Junhao Su, Junjie Hu +4
Text-to-image (T2I) models today are capable of producing photorealistic, instruction-following images, yet they still frequently fail on prompts that require implicit world knowle…
Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions
Junhao Su, Yuanliang Wan, Junwei Yang +4
Tool-augmented large language models (LLMs) are usually trained with supervised imitation or coarse-grained reinforcement learning that optimizes single tool calls. Current self-re…
MAN++: Scaling Momentum Auxiliary Network for Supervised Local Learning in Vision Tasks
Junhao Su, Feiyu Zhu, Hengyu Shi +5
Deep learning typically relies on end-to-end backpropagation for training, a method that inherently suffers from issues such as update locking during parameter optimization, high G…
PositionIC: Unified Position and Identity Consistency for Image Customization
Junjie Hu, Tianyang Han, Kai Ma +6
Recent subject-driven image customization excels in fidelity, yet fine-grained instance-level spatial control remains an elusive challenge, hindering real-world applications. This…
PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
SiXiang Chen, Jianyu Lai, Jialin Gao +11
Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic conte…
Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
Hongyu Li, Songhao Han, Yue Liao +4
Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large langua…
Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank
Feiyu Zhu, Yuming Zhang, Xiuyuan Guo +4
Local learning offers an alternative to traditional end-to-end back-propagation in deep neural networks, significantly reducing GPU memory consumption. Although it has shown promis…