9 papers
Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees
Zhongnian Li, Shi Xu, Mengting Xu +2
Reflective language agents reuse feedback and memory to adapt across tasks without updating model weights. However, existing guarantees for policy selection and action generation d…
Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems
Zhongnian Li, Shi Xu, Peng Ying +3
Optimization by PROmpting (OPRO) directly leverages Large Language Models (LLMs) to generate candidate solutions through natural-language prompting. However, OPRO's optimization pr…
Learning from Uncertain Similarity and Unlabeled Data
Meng Wei, Zhongnian Li, Peng Ying +1
Existing similarity-based weakly supervised learning approaches often rely on precise similarity annotations between data pairs, which may inadvertently expose sensitive label info…
ESA: Example Sieve Approach for Multi-Positive and Unlabeled Learning
Zhongnian Li, Meng Wei, Peng Ying +1
Learning from Multi-Positive and Unlabeled (MPU) data has gradually attracted significant attention from practical applications. Unfortunately, the risk of MPU also suffer from the…
Learning from Concealed Labels
Zhongnian Li, Meng Wei, Peng Ying +2
Annotating data for sensitive labels (e.g., disease, smoking) poses a potential threats to individual privacy in many real-world scenarios. To cope with this problem, we propose a…
Seeing the Undefined: Chain-of-Action for Generative Semantic Labels
Meng Wei, Zhongnian Li, Peng Ying +1
Recent advances in vision-language models (VLMs) have demonstrated remarkable capabilities in image classification by leveraging predefined sets of labels to construct text prompts…
Learning from True-False Labels via Multi-modal Prompt Retrieving
Zhongnian Li, Jinghao Xu, Peng Ying +2
Pre-trained Vision-Language Models (VLMs) exhibit strong zero-shot classification abilities, demonstrating great potential for generating weakly supervised labels. Unfortunately, e…
Determined Multi-Label Learning via Similarity-Based Prompt
Meng Wei, Zhongnian Li, Peng Ying +2
In multi-label classification, each training instance is associated with multiple class labels simultaneously. Unfortunately, collecting the fully precise class labels for each tra…
Learning from Stochastic Labels
Meng Wei, Zhongnian Li, Yong Zhou +2
Annotating multi-class instances is a crucial task in the field of machine learning. Unfortunately, identifying the correct class label from a long sequence of candidate labels is…