Selected work

Representative Papers

Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection

Jul 28, 2026

This work proposes a novel representation learning framework that addresses the limited representational capacity of existing methods in complex scenarios by integrating adaptive multi-scale fusion with contrastive learning. The approach dynamically aggregates multi-level semantic information and introduces a structure-aware contrastive loss, thereby significantly enhancing the model’s ability to discriminate fine-grained differences. Extensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art methods across multiple benchmark datasets, exhibiting particularly strong robustness under low-resource settings and in the presence of noise. Beyond advancing the theoretical foundations of representation learning, this study also delivers an efficient and scalable solution with practical applicability.

0 citationsRead paper

Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models

Dec 08, 2025

Visual language models (VLMs) suffer from hallucination—generating factually inconsistent or image-ungrounded statements. To address this, we propose a training-free, parameter-free self-correction framework that iteratively refines model outputs via uncertainty-guided visual re-attention. Specifically, it quantifies token-level uncertainty across four dimensions—token entropy, attention dispersion, semantic consistency, and claim confidence—to dynamically identify and crop unreliable image regions, followed by response revision. The method requires no fine-tuning, external data, or architectural modifications. Evaluated on Qwen2.5-VL-7B, it reduces hallucination rate by 9.8 percentage points and improves object existence accuracy by 4.7 percentage points, outperforming existing training-free baselines. Our core contribution lies in the tight coupling of multi-dimensional uncertainty modeling with dynamic visual attention, enabling interpretable, lightweight, and reliable VLM inference without parameter updates.

0 citationsRead paper

Recent publications

Latest Papers

Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection

Jul 28, 2026

This work proposes a novel representation learning framework that addresses the limited representational capacity of existing methods in complex scenarios by integrating adaptive multi-scale fusion with contrastive learning. The approach dynamically aggregates multi-level semantic information and introduces a structure-aware contrastive loss, thereby significantly enhancing the model’s ability to discriminate fine-grained differences. Extensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art methods across multiple benchmark datasets, exhibiting particularly strong robustness under low-resource settings and in the presence of noise. Beyond advancing the theoretical foundations of representation learning, this study also delivers an efficient and scalable solution with practical applicability.

0 citationsRead paper

Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models

Dec 08, 2025

Visual language models (VLMs) suffer from hallucination—generating factually inconsistent or image-ungrounded statements. To address this, we propose a training-free, parameter-free self-correction framework that iteratively refines model outputs via uncertainty-guided visual re-attention. Specifically, it quantifies token-level uncertainty across four dimensions—token entropy, attention dispersion, semantic consistency, and claim confidence—to dynamically identify and crop unreliable image regions, followed by response revision. The method requires no fine-tuning, external data, or architectural modifications. Evaluated on Qwen2.5-VL-7B, it reduces hallucination rate by 9.8 percentage points and improves object existence accuracy by 4.7 percentage points, outperforming existing training-free baselines. Our core contribution lies in the tight coupling of multi-dimensional uncertainty modeling with dynamic visual attention, enabling interpretable, lightweight, and reliable VLM inference without parameter updates.

0 citationsRead paper