Kaixin Ma

TMLR Journal 2026 Journal Article

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models

• Ce Zhang
• Kaixin Ma
• Tianqing Fang
• Wenhao Yu
• Hongming Zhang
• Zhisong Zhang
• Haitao Mi
• Dong Yu

Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur significant computational costs due to longer visual token sequences, posing challenges for real-time deployment. To mitigate this, prior studies have explored pruning unimportant visual tokens either at the output layer of the visual encoder or at the early layers of the language model. In this work, we revisit these design choices and reassess their effectiveness through comprehensive empirical studies of how visual tokens are processed throughout the visual encoding and language decoding stages. Guided by these insights, we propose VScan, a two-stage visual token reduction framework that addresses token redundancy by: (1) integrating complementary global and local scans with token merging during visual encoding, and (2) introducing pruning at intermediate layers of the language model. Extensive experimental results across four LVLMs validate the effectiveness of VScan in accelerating inference and demonstrate its superior performance over current state-of-the-arts on sixteen benchmarks. Notably, when applied to LLaVA-NeXT-7B, VScan achieves a 2.91$\times$ speedup in prefilling and a 10$\times$ reduction in FLOPs, while retaining 95.4\% of the original performance. Code will be made publicly available upon acceptance.

AAAI Conference 2025 Conference Paper

COLUMBUS: Evaluating COgnitive Lateral Understanding Through Multiple-Choice reBUSes

• Koen Kraaijveld
• Yifan Jiang
• Kaixin Ma
• Filip Ilievski

While visual question-answering (VQA) benchmarks have catalyzed the development of reasoning techniques, they have focused on vertical thinking. Effective problem-solving also necessitates lateral thinking, which remains understudied in AI and has not been used to test visual perception systems. To bridge this gap, we formulate visual lateral thinking as a multiple-choice question-answering task and describe a three-step taxonomy-driven methodology for instantiating task examples. Then, we develop COLUMBUS, a synthetic benchmark that applies the task pipeline to create QA sets with text and icon rebus puzzles based on publicly available collections of compounds and common phrases. COLUMBUS comprises over 1,000 puzzles, each with four answer candidates. While the SotA vision language models (VLMs) achieve decent performance, our evaluation demonstrates a substantial gap between humans and models. VLMs benefit from human-curated descriptions but struggle to self-generate such representations at the right level of abstraction.

ICLR Conference 2025 Conference Paper

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

• Liqiang Jing
• Zhehui Huang
• Xiaoyang Wang 0001
• Wenlin Yao
• Wenhao Yu 0002
• Kaixin Ma
• Hongming Zhang 0009
• Xinya Du

Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) have demonstrated impressive language/vision reasoning abilities, igniting the recent trend of building agents for targeted applications such as shopping assistants or AI software engineers. Recently, many data science benchmarks have been proposed to investigate their performance in the data science domain. However, existing data science benchmarks still fall short when compared to real-world data science applications due to their simplified settings. To bridge this gap, we introduce DSBench, a comprehensive benchmark designed to evaluate data science agents with realistic tasks. This benchmark includes 466 data analysis tasks and 74 data modeling tasks, sourced from Eloquence and Kaggle competitions. DSBench offers a realistic setting by encompassing long contexts, multimodal task backgrounds, reasoning with large data files and multi-table structures, and performing end-to-end data modeling tasks. Our evaluation of state-of-the-art LLMs, LVLMs, and agents shows that they struggle with most tasks, with the best agent solving only 34.12% of data analysis tasks and achieving a 34.74% Relative Performance Gap (RPG). These findings underscore the need for further advancements in developing more practical, intelligent, and autonomous data science agents.

TMLR Journal 2025 Journal Article

Leopard: A Vision Language Model for Text-Rich Multi- Image Tasks

• Mengzhao Jia
• Wenhao Yu
• Kaixin Ma
• Tianqing Fang
• Zhihan Zhang
• Siru Ouyang
• Hongming Zhang
• Dong Yu

Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots. Tasks involving multiple text-rich images are especially challenging, as they require not only understanding the content of individual images but reasoning about inter-relationships and logical flows across multiple visual inputs. Despite the importance of these scenarios, current multimodal large language models (MLLMs) struggle to handle such tasks due to two key challenges: (1) the scarcity of high-quality instruction tuning datasets for text-rich multi-image scenarios, and (2) the difficulty in balancing image resolution with visual feature sequence length. To address these challenges, we propose Leopard, a MLLM designed specifically for handling vision-language tasks involving multiple text-rich images. First, we curated about one million high-quality multimodal instruction-tuning data, tailored to text-rich, multi-image scenarios. Second, we proposed an adaptive high-resolution multi-image encoding module to dynamically optimize the allocation of visual sequence length based on the original aspect ratios and resolutions of images. Experiments on a diverse set of benchmarks reveal that our model consistently outperforms state-of-the-art systems, such as Llama-3.2 and Qwen2-VL, in challenging text-rich, multi-image evaluations. Remarkably, our approach achieves outstanding performance using only 1.2M fully open-sourced training instances, outperforming models that rely on large-scale in-house data, highlighting its efficiency and effectiveness. Our code and data are available at https://anonymous.4open.science/r/Leopard-908F.

ICLR Conference 2025 Conference Paper

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

• Siru Ouyang
• Wenhao Yu 0002
• Kaixin Ma
• Zilin Xiao
• Zhihan Zhang 0001
• Mengzhao Jia
• Jiawei Han 0001
• Hongming Zhang 0009

Large Language Models (LLMs) excel in code generation yet struggle with modern AI software engineering tasks. Unlike traditional function-level or file-level coding tasks, AI software engineering requires not only basic coding proficiency but also advanced skills in managing and interacting with code repositories. However, existing methods often overlook the need for repository-level code understanding, which is crucial for accurately grasping the broader context and developing effective solutions. On this basis, we present RepoGraph, a plug-in module that manages a repository-level structure for modern AI software engineering solutions. RepoGraph offers the desired guidance and serves as a repository-wide navigation for AI software engineers. We evaluate RepoGraph on the SWE-bench by plugging it into four different methods of two lines of approaches, where RepoGraph substantially boosts the performance of all systems, leading to a new state-of-the-art among open-source frameworks. Our analyses also demonstrate the extensibility and flexibility of RepoGraph by testing on another repo-level coding benchmark, CrossCodeEval. Our code is available at https://github.com/ozyyshr/RepoGraph.

NeurIPS Conference 2024 Conference Paper

MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning

• Yifan Jiang
• Jiarui Zhang
• Kexuan Sun
• Zhivar Sourati
• Kian Ahrabian
• Kaixin Ma
• Filip Ilievski
• Jay Pujara

While multi-modal large language models (MLLMs) have shown significant progress across popular visual reasoning benchmarks, whether they possess abstract visual reasoning abilities remains an open question. Similar to the Sudoku puzzles, abstract visual reasoning (AVR) problems require finding high-level patterns (e. g. , repetition constraints on numbers) that control the input shapes (e. g. , digits) in a specific task configuration (e. g. , matrix). However, existing AVR benchmarks only consider a limited set of patterns (addition, conjunction), input shapes (rectangle, square), and task configurations (3 × 3 matrices). And they fail to capture all abstract reasoning patterns in human cognition necessary for addressing real-world tasks, such as geometric properties and object boundary understanding in real-world navigation. To evaluate MLLMs’ AVR abilities systematically, we introduce MARVEL founded on the core knowledge system in human cognition, a multi-dimensional AVR benchmark with 770 puzzles composed of six core knowledge patterns, geometric and abstract shapes, and five different task configurations. To inspect whether the model performance is grounded in perception or reasoning, MARVEL complements the standard AVR question with perception questions in a hierarchical evaluation framework. We conduct comprehensive experiments on MARVEL with ten representative MLLMs in zero-shot and few-shot settings. Our experiments reveal that all MLLMs show near-random performance on MARVEL, with significant performance gaps (40%) compared to humans across all patterns and task configurations. Further analysis of perception questions reveals that MLLMs struggle to comprehend the visual features (near-random performance). Although closed-source MLLMs, such as GPT-4V, show a promising understanding of reasoning patterns (on par with humans) after adding textual descriptions, this advantage is hindered by their weak perception abilities. We release our entirecode and dataset at https: //github. com/1171-jpg/MARVEL_AVR.

NeSy Conference 2023 Conference Paper

Generalizable Neuro-Symbolic Systems for Commonsense Question Answering

• Alessandro Oltramari
• Jonathan Francis
• Filip Ilievski
• Kaixin Ma
• Roshanak Mirzaee

ECAI Conference 2023 Conference Paper

Transferring Procedural Knowledge Across Commonsense Tasks

• Yifan Jiang 0001
• Filip Ilievski
• Kaixin Ma

Stories about everyday situations are an essential part of human communication, motivating the need to develop AI agents that can reliably understand these stories. Despite the long list of supervised methods for story completion and procedural understanding, current AI fails to generalize its procedural reasoning to unseen stories. This paper is based on the hypothesis that the generalization can be improved by associating downstream prediction with fine-grained modeling and the abstraction of procedural knowledge in stories. To test this hypothesis, we design LEAP: a comprehensive framework that reasons over stories by jointly considering their (1) overall plausibility, (2) conflict sentence pairs, and (3) participant physical states. LEAP integrates state-of-the-art modeling architectures, training regimes, and augmentation strategies based on natural and synthetic stories. To address the lack of densely annotated training data on participants and their physical states, we devise a robust automatic labeler based on semantic parsing and few-shot prompting with large language models. Our experiments with in- and out-of-domain tasks reveal insights into the interplay of architectures, training regimes, and augmentation strategies. LEAP’s labeler consistently improves performance on out-of-domain datasets, while our case studies show that the dense annotation supports explainability.

AAAI Conference 2021 Conference Paper

Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering

• Kaixin Ma
• Filip Ilievski
• Jonathan Francis
• Yonatan Bisk
• Eric Nyberg
• Alessandro Oltramari

Recent developments in pre-trained neural language modeling have led to leaps in accuracy on commonsense question-answering benchmarks. However, there is increasing concern that models overfit to specific tasks, without learning to utilize external knowledge or perform general semantic reasoning. In contrast, zeroshot evaluations have shown promise as a more robust measure of a model’s general reasoning abilities. In this paper, we propose a novel neuro-symbolic framework for zero-shot question answering across commonsense tasks. Guided by a set of hypotheses, the framework studies how to transform various pre-existing knowledge resources into a form that is most effective for pretraining models. We vary the set of language models, training regimes, knowledge sources, and data generation strategies, and measure their impact across tasks. Extending on prior work, we devise and compare four constrained distractor-sampling strategies. We provide empirical results across five commonsense questionanswering tasks with data generated from five external knowledge resources. We show that, while an individual knowledge graph is better suited for specific tasks, a global knowledge graph brings consistent gains across different tasks. In addition, both preserving the structure of the task as well as generating fair and informative questions help language models learn more effectively.