Facial Emotion Analysis (FEA) extends traditional facial emotion recognition by incorporating explainable, fine-grained reasoning. The task integrates three subtasks—emotion recognition, facial Action Unit (AU) recognition, and AU-based emotion reasoning—to jointly model affective states. While recent approaches leverage Vision-Language Models (VLMs) and achieve promising results, they face two critical limitations: (1) hallucinated reasoning, where VLMs generate plausible but inaccurate explanations due to insufficient emotion-specific knowledge; and (2) misalignment between emotion reasoning and recognition, caused by fragmented connections between observed facial features and final labels. We propose Facial-R1, a three-stage alignment framework that effectively addresses both challenges with minimal supervision. First, we employ instruction fine-tuning to establish basic emotional reasoning capability for reducing hallucinations. Second, we introduce reinforcement training guided by emotion and AU labels as reward signals, which explicitly aligns the generated reasoning process with the predicted emotion. Third, we design a data synthesis pipeline that iteratively leverages the prior stages to expand the training dataset, enabling scalable self-improvement of the model. Built upon this framework, we introduce FEA-20K, a benchmark dataset comprising 17,737 training and 1,688 test samples with fine-grained emotion analysis annotations. Extensive experiments across eight standard benchmarks demonstrate that Facial-R1 achieves state-of-the-art performance in FEA, with strong generalization and robust interpretability.

Large Visual Language Models (LVLMs) have demonstrated impressive capabilities across multiple tasks.However, their trustworthiness is often challenged by hallucinations, which can be attributed to the modality misalignment and the inherent hallucinations of their underlying Large Language Models (LLMs) backbone.Existing preference alignment methods focus on aligning model responses with human preferences while neglecting image-text modality alignment, resulting in over-reliance on LLMs and hallucinations.In this paper, we propose Entity-centric Multimodal Preference Optimization (EMPO), which achieves enhanced modality alignment than existing human preference alignment methods.Besides, to overcome the scarcity of high-quality multimodal preference data, we utilize open-source instruction datasets to automatically construct highquality preference data across three aspects: image, instruction, and response.Experiments on two human preference datasets and five multimodal hallucination benchmarks demonstrate the effectiveness of EMPO, e.g., reducing hallucination rates by 85.

Large Vision-Language Models (LVLMs) have shown impressive performance across diverse multimodal tasks. However, their trustworthiness is challenged by two types of hallucinations: over-reliance on the language priors of the underlying Large Language Model (LLM) and misalignment between visual and textual modalities. Most existing hallucination mitigation methods often require high training costs, limiting their effectiveness and robustness. To address this, we propose Dual Contrastive Decoding (DCD), which mitigates hallucinations stemming from language priors by subtracting image-irrelevant distributions and further aligns image-text modalities by enabling LVLMs to focus on correct image entities. This strategy requires no additional training and can be applied during the decoding phase of any LVLM, effectively improving the inference capability of LVLMs at minimal cost. Extensive experiments on discriminative (POPE, MME) benchmarks demonstrate that DCD significantly mitigates hallucinations at both the object and attribute levels, while also enhancing overall model performance on general vision-language perception and recognition tasks. The code and dataset will be made available.

This paper proposes a novel swarm intelligence optimization method which integrates bacterial foraging optimization (BFO) with quantum computing, called quantum bacterial foraging optimization (QBFO) algorithm. In QBFO, a multi-qubit which can represent a linear superposition of states in search space probabilistically is used to represent a bacterium, so that the quantum bacteria representation has a better characteristic of population diversity. A quantum rotation gate is designed to simulate the chemotactic step to drive the bacteria toward better solutions. Several tests are conducted based on benchmark functions including multi-peak function to evaluate optimization performance of the proposed algorithm. The numeric results show that the proposed QBFO has more powerful properties in convergence rate, stability and the ability of searching for the global optimal solution than the original BFO and quantum genetic algorithm. In addition, we applied our proposed QBFO to solve the traveling salesman problem, which is a well-known NP-hard problem in combinatorial optimization. The results indicate that the proposed QBFO shows better convergence behavior without premature convergence, and has more powerful properties in convergence rate, stability and the ability of searching for the global optimal solution, as compared to ant colony optimization algorithm and quantum genetic algorithm.