9 papers
Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
Sichun Luo, Yi Huang, Guanzhi Deng +6
Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly.…
Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
Haochen Luo, Yi Huang, Sichun Luo +5
Self-evolving frameworks usually optimize task solutions while treating the surrounding harness as fixed. We introduce Harness-Aware Self-Evolving (HASE), an agentic reinforcement-…
Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation
Haocheng Luo, Jiahui Liu, Ruicheng Zhang +8
While Vision-Language Models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this limitation to a perception--reasoning mo…
SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution
Sichun Luo, Yi Huang, Haochen Luo +7
Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through execu…
PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks
Jingning Xu, Haochen Luo, Chen Liu
Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific adversarial examples are computa…
Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
Haocheng Luo, Zehang Deng, Thanh-Toan Do +3
Direct Preference Optimization (DPO) has emerged as a popular algorithm for aligning pretrained large language models with human preferences, owing to its simplicity and training s…