Shuochen Chang, Tong Bai, Xiaofeng Zhang, Qianli Ma, Qingyang Liu, Zhaohe Liao, Yibo Miao, Li Niu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Video Question-Answering (VideoQA) enables machines to interpret and respond to complex video content, advancing human-computer interaction. However, existing multimodal large language models (MLLMs) often provide incomplete or opaque explanations and existing benchmarks mainly focus on the correction of final answers, limiting insight into their reasoning processes and hindering both transparency and verifiability. To address this gap, we propose the Question Parsing, Video Alignment and Answer Aggregation framework (QPVA$^{3}$3), which leverages a compositional graph to drive visual and logical reasoning in VideoQA. Specifically, QPVA$^{3}$3 consists of three core components, the planner, executor, and reasoner to generate the compositional graph and conduct graph-driven reasoning. For the original question, the planner parses it into the compositional graph, capturing the underlying reasoning logic and structuring it into a series of interconnected questions. For each question in compositional graph, the executor aligns the video by selecting relevant video clips and generates answers, ensuring accurate, context-specific responses. For each question with its first-order descents, the reasoner aggregates answers by integrating reasoning logic with visual evidence, resolving conflicts to produce a coherent and accurate response. Moreover, to assess the performance of existing MLLMs in the reasoning processes of VideoQA, we introduce novel compositional consistency metrics and construct a VideoQA benchmark (QPVA$^{3}$3 Bench) with 3,492 question-video tuples, each annotated with detailed compositional graphs and fine-grained answers. We evaluate the QPVA$^{3}$3 framework on QPVA$^{3}$3 Bench and 5 other VideoQA benchmarks. Experimental results demonstrate that our framework improves both consistency and accuracy compared to baselines, leading to a more transparent and verifiable VideoQA system. This approach has the potential to advance the field, as supported by our comprehensive evaluation and benchmarking efforts.

Video Question-Answering (VideoQA) remains challenging in achieving advanced cognitive reasoning due to the uncontrollable and opaque reasoning processes in existing Multimodal Large Language Models (MLLMs). To address this issue, we propose a novel Language-centric Tree Reasoning (LTR) framework that targets on enhancing the reasoning ability of models. In detail, it recursively divides the original question into logically manageable parts and conquers them piece by piece, enhancing the reasoning capabilities and interpretability of existing MLLMs. Specifically, in the first stage, the LTR focuses on language to recursively generate a language-centric logical tree, which gradually breaks down the complex cognitive question into simple perceptual ones and plans the reasoning path through a RAG-based few-shot approach. In the second stage, with the aid of video content, the LTR performs bottom-up logical reasoning within the tree to derive the final answer along with the traceable reasoning path. Experiments across 11 VideoQA benchmarks demonstrate that our LTR framework significantly improves both accuracy and interpretability compared to state-of-the-art MLLMs. To our knowledge, this is the first work to implement a language-centric logical tree to guide MLLM reasoning in VideoQA, paving the way for language-centric video understanding from perception to cognition.

Despite the recent progress made in Video Question-Answering (VideoQA), these methods typically function as black-boxes, making it difficult to understand their reasoning processes and perform consistent compositional reasoning. To address these challenges, we propose a model-agnostic Video Alignment and Answer Aggregation (VA3) framework, which is capable of enhancing both compositional consistency and accuracy of existing VidQA methods by integrating video aligner and answer aggregator modules. The video aligner hierarchically selects the relevant video clips based on the question, while the answer ag-gregator deduces the answer to the question based on its sub-questions, with compositional consistency ensured by the information flow along question decomposition graph and the contrastive learning strategy. We evaluate our framework on three settings of the AGQA-Decomp dataset with three baseline methods, and propose new metrics to measure the compositional consistency of VidQA methods more comprehensively. Moreover, we propose a large language model (LLM) based automatic question decomposition pipeline to apply our framework to any VidQA dataset. We extend MSVD and NExT-QA datasets with it to evaluate our VA3framework on broader scenarios. Extensive experiments show that our framework improves both compositional consistency and accuracy of existing methods, leading to more interpretable real-world VidQA models.

The last few years have seen the wide applications of ride-sharing, a transportation service that allows users to share their travel routes. A typical problem for ride-sharing is to find an optimal route for each worker to serve the dynamically arriving requests with different objectives. Previous studies focus on the route planning on a single platform. However, a single platform may have an uneven distribution of supply and demand, which causes the platform to lose requests from lack of available workers. Luckily, some ride-sharing platforms provide the same service, which enables their collaborations. The inter-platform collaborations on ride-sharing can ease the worker shortages and greatly improve the service quality, but have not been studied yet. In this paper, we propose a Cross Online Ride-sharing (CORS) problem, which allows a platform to borrow the available workers from other platforms to serve its own requests. We first design two algorithms to select the optimal available worker from other platforms, ROWS and DOWS. ROWS randomly picks an available worker, while DOWS selects the optimal worker with the minimum additional travel distance calculated based on his/er predicted destination direction. Then, we design an efficient CORS framework that embeds the proposed optimal worker selection algorithms for the CORS problem. Extensive experiments on real and synthetic datasets demonstrate the effectiveness and efficiency of our algorithms.