Hallucination continues to pose a major obstacle in the reasoning capabilities of large language models (LLMs). Although the Multi-Agent Debate (MAD) paradigm offers a promising solution by promoting consensus among multiple agents to enhance reliability, it relies on the unrealistic assumption that all debaters are rational and reflective, which is a condition that may not hold when agents themselves are prone to hallucinations. To address this gap, we introduce the Multi-agent Undercover Gaming (MUG) protocol, inspired by social deduction games like ''Who is Undercover?''. MUG reframes MAD as a process of detecting ''undercover'' agents (those suffering from hallucinations) by employing multimodal counterfactual tests. Specifically, we modify reference images to introduce counterfactual evidence and observe whether agents can accurately identify these changes, providing ground-truth for identifying hallucinating agents and enabling robust, crowd-powered multimodal reasoning. MUG advances MAD protocols along three key dimensions: (1) enabling factual verification beyond statistical consensus through counterfactual testing; (2) introducing cross-evidence reasoning via dynamically modified evidence sources instead of relying on static inputs; and (3) fostering active reasoning, where agents engage in probing discussions rather than passively answering questions. Collectively, these innovations offer a more reliable and effective framework for multimodal reasoning in LLMs.

Model Diagram-to-Code Generation aims to translate model diagrams from research papers into implementation code that reconstructs the model's architecture. This task plays a crucial role in accelerating scientific workflows and enhancing the efficiency of industrial model deployment. While recent studies have explored various Image-to-Code Generation tasks using Multimodal Large Language Models (MLLMs), these efforts have primarily focused on reconstructing the visual appearance depicted in input images, leaving this task largely underexplored. The complex structural elements and implicit relationships in model diagrams present greater challenges for MLLMs, particularly in terms of visual reasoning and semantic interpretation. To support this task, we introduce MDCDataset, a dataset designed to evaluate the ability of MLLMs to generate code from model diagrams. It comprises 1,008 instances spanning 16 research domains, each with a model diagram, structured textual content, and the ground-truth code implementation. Furthermore, to address the inherent challenges of this task, we propose MDCAgent, a collaborative multi-agent framework composed of Parsing, Generation, and Check Agents. These agents work in coordination to analyze, extract, and verify complex elements and implicit relationships within model diagrams, thereby enhancing the visual architecture-aware reasoning capabilities of MLLMs. Our extensive experiments confirm the effectiveness of the framework.

This paper presents a pilot study aimed at introducing multi-agent debate into multimodal reasoning. The study addresses two key challenges: the trivialization of opinions resulting from excessive summarization and the diversion of focus caused by distractor concepts introduced from images. These challenges stem from the inductive (bottom-up) nature of existing debating schemes. To address the issue, we propose a deductive (top-down) debating approach called Blueprint Debate on Graphs (BDoG). In BDoG, debates are confined to a blueprint graph to prevent opinion trivialization through world-level summarization. Moreover, by storing evidence in branches within the graph, BDoG mitigates distractions caused by frequent but irrelevant concepts. Extensive experiments validate that BDoG is able to achieve state-of-the-art results in ScienceQA and MMBench with significant improvements over previous methods. The source code can be accessed at https://github.com/thecharm/BDoG.

Learning manipulations from videos is an inspiriting way for robots to acquire new skills. In this paper, we propose a framework that can generate robotic manipulation plans by observing human demonstration videos without special marks or unnatural demonstrated behaviors. More specifically, the framework contains a video parsing module and a robot execution module. The first module recognizes the demonstrator's actions using two-stream convolution neural networks, and classifies the operated objects by adopting a Mask R-CNN. After that, two XGBoost classifiers are applied to further classify the objects into subject object and patient object respectively, according to the demonstrator's actions. In the second module, a grammar-based parser is used to summarize the videos and generate the common instructions for robot execution. Extensive experiments are conducted on a publicly available video datasets consisting of 273 videos and manifest that our approach is able to learn manipulation plans from demonstration videos with high accuracy (73.36%). Furthermore, we integrate our framework with a humanoid robot Baxter to perform the manipulation learning from demonstration videos, which effectively verifies the performance of our framework.

Popularity prediction for social media is an efficient way for scientists to explore advanced predictive trend and make better strategic decisions for future. In this paper, we propose a framework that uses visual-textual features combined with XGBoost for popularity prediction. More specifically, the framework contains three procedures, including visual-textual features extraction, features fusion and XGBoost regression. In order to extract the visual-textual data, on the one hand, we first adopt one-hot encoder to encode the metadata of the posts, and then apply a word2vec model to produce word embeddings. On the other hand, we adopt a shape descriptor called Hu moment to extract the visual features from the images. What's more, we exploit user's information, e.g. users' followings and users' followers, for providing extra social features to the regression. After that, we fuse the multi-modal features and input them to the XGBoost directly for popularity prediction. Extensive experiments conducted on the SMPD2019 dataset manifest the effectiveness of our system. Furthermore, our approach achieves the 3nd place on the leader board of the Grand Challenge in ACM Multimedia 2019.