Singapore

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as mathematical problem-solving. Previous works have focused on fine-tuning on specialized mathematical datasets. However, these datasets are typically distilled directly from teacher models, which capture only static reasoning patterns and leaving substantial gaps compared to student models. This reliance on fixed teacher-derived datasets not only restricts the model&#39;s ability to adapt to novel or more intricate questions that extend beyond the confines of the training data, but also lacks the iterative depth needed for robust generalization.
To overcome these limitations, we propose MathSE, a Mathematical Self-Evolving framework for MLLMs. In contrast to traditional one-shot fine-tuning paradigms, MathSE iteratively refines the model through cycles of inference, reflection, and reward-based feedback. Specifically, we leverage iterative fine-tuning by incorporating correct reasoning paths derived from previous-stage inference and integrating reflections from a specialized Outcome Reward Model (ORM). 
To verify the effectiveness of MathSE, we evaluate it on a suite of challenging benchmarks, demonstrating significant performance gains over backbone models. Notably, our experimental results on MathVL-test surpass the leading open-source multimodal mathematical reasoning model QVQ.

AAAI 2026

MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning

self-evolving

large multimodal models (lmms)

math reasoning

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as mathematical problem-solving. Previous works have focused on fine-tuning on specialized mathematical datasets. However, these datasets are typically distilled directly from teacher models, which capture only static reasoning patterns and leaving substantial gaps compared to student models. This reliance on fixed teacher-derived datasets not only restricts the model's ability to adapt to novel or more intricate questions that extend beyond the confines of the training data, but also lacks the iterative depth needed for robust generalization.
To overcome these limitations, we propose MathSE, a Mathematical Self-Evolving framework for MLLMs. In contrast to traditional one-shot fine-tuning paradigms, MathSE iteratively refines the model through cycles of inference, reflection, and reward-based feedback. Specifically, we leverage iterative fine-tuning by incorporating correct reasoning paths derived from previous-stage inference and integrating reflections from a specialized Outcome Reward Model (ORM). 
To verify the effectiveness of MathSE, we evaluate it on a suite of challenging benchmarks, demonstrating significant performance gains over backbone models. Notably, our experimental results on MathVL-test surpass the leading open-source multimodal mathematical reasoning model QVQ.

poster

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The Kolmogorov-Arnold Network (KAN) has been gaining popularity as an alternative to the multi-layer perceptron (MLP) with its increased expressiveness and interpretability. However, the KAN can be orders of magnitude slower due to its increased computational cost and training instability, limiting its applicability to larger-scale tasks. Recently, the Kolmogorov-Arnold Transformer (KAT) has been proposed, which can achieve FLOPs similar to the traditional Transformer with MLPs by leveraging Group-Rational KAN (GR-KAN). Unfortunately, despite the comparable FLOPs, our characterizations reveal that the KAT is still 123x slower in training speeds, indicating that there are other performance bottlenecks beyond FLOPs. In this paper, we conduct a series of experiments to understand the root cause of the slowdown in KAT. We uncover that the slowdown can be isolated to memory stalls and, more specifically, in the backward pass of GR-KAN caused by inefficient gradient accumulation. To address this memory bottleneck, we propose FlashKAT, which builds on our restructured kernel that minimizes gradient accumulation with atomic adds and accesses to slow memory. Evaluations demonstrate that FlashKAT can achieve a training speedup of 86.5x compared with the state-of-the-art KAT, while reducing rounding errors in the coefficient gradients. We plan to release our code upon acceptance.

FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer

Multi-Robot Motion Planning (MRMP) involves generating collision-free trajectories for multiple robots operating in a shared continuous workspace. While discrete multi-agent path finding (MAPF) methods are broadly adopted due to their scalability, their coarse discretization severely limits trajectory quality. In contrast, continuous optimization-based planners offer higher-quality paths but suffer from the curse of dimensionality, resulting in poor scalability with respect to the number of robots. This paper tackles the limitations of these two approaches by introducing a novel framework that integrates discrete MAPF solvers with constrained generative diffusion models. 
The resulting framework, called Discrete-Guided Diffusion (DGD), has three key characteristics: (1) it decomposes the original nonconvex MRMP problem into tractable subproblems with convex configuration spaces, (2) it combines discrete MAPF solutions with constrained optimization techniques to guide diffusion models capture complex spatiotemporal dependencies among robots, and (3) it incorporates a lightweight constraint repair mechanism to ensure trajectory feasibility. The proposed method sets a new state-of-the-art performance in large-scale, complex environments, scaling to 100 robots while achieving planning efficiency and high success rates.

Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning

Fine-tuning large pretrained vision-language models (VLMs) has emerged as a prevalent paradigm for downstream adaptation, yet it faces a critical trade-off between domain specificity and domain generalization (DG) ability. Current methods typically fine-tune a universal model on the entire dataset, which potentially compromises the ability to generalize to unseen domains. To fill this gap, we provide a theoretical understanding of the generalization ability for VLM fine-tuning, which reveals that training multiple parameter-efficient expert models on partitioned source domains leads to better generalization than fine-tuning a universal model. Inspired by this finding, we propose a two-step domain-expert-Guided DG (GuiDG) framework. GuiDG first employs prompt tuning to obtain source domain experts, then introduces a Cross-Modal Attention module to guide the fine-tuning of the vision encoder via adaptive expert integration. To better evaluate few-shot DG, we construct ImageNet-DG from ImageNet and its variants. Extensive experiments on standard DG benchmarks and ImageNet-DG demonstrate that GuiDG improves upon state-of-the-art fine-tuning methods while maintaining efficiency. Code and Appendix: https://github.com/TL-UESTC/GuiDG.

Generalizing Vision-Language Models with Dedicated Prompt Guidance

Graphical user interface (GUI) agents have recently emerged as an intriguing paradigm for human-computer interaction, capable of automatically executing user instructions to operate intelligent terminal devices. 
However, when encountering out-of-distribution (OOD) instructions that violate environmental constraints or exceed the current capabilities of agents, GUI agents may suffer task breakdowns or even pose security threats. Therefore, effective OOD detection for GUI agents is essential. Traditional OOD detection methods perform suboptimally in this domain due to the complex embedding space and evolving GUI environments. 
In this work, we observe that the in-distribution input semantic space of GUI agents exhibits a clustering pattern with respect to the distance from the centroid.
Based on the finding, we propose GEM, a novel method based on fitting a Gaussian mixture model over input embedding distances extracted from the GUI Agent that reflect its capability boundary. 
Evaluated on eight datasets spanning smartphones, computers, and web browsers, our method achieves an average accuracy improvement of 23.70\% over the best-performing baseline while only increasing training time by 4.9\% and testing time by 6.5\%.
We also experimentally demonstrate that GEM can improve the step-wise success rate by 9.40\% by requesting assistance from the cloud model when encountering OOD samples.
Analysis verifies the generalization ability of our method through experiments on nine different backbones.

GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents

Research in Machine Learning (ML) and AI evolves rapidly. Information Extraction (IE) from scientific publications enables to identify information about research concepts and resources on a large scale and therefore is a pathway to improve understanding and reproducibility of machine learning-related research. To extract and connect fine-grained information in ML related research, e.g. method training and data usage, we introduce a new dataset. It is a manually curated fine-grained dataset with 10 entity types and 18 semantically categorized relation types, containing mentions of 63K entities and 35K relations from the full text of 100 machine learning publications. We show that our dataset enables fine-tuned models to automatically extract information relevant for downstream tasks ranging from knowledge graph (KG) construction, to monitoring the computational reproducibility of AI research at scale. Additionally, we use our dataset as a test suite to explore prompting strategies for IE using Large Language Models (LLM). It is observed that the performance of the state-of-the-art LLM prompting methods is largely outperformed by our best fine-tuned baseline model (NER: 80.6%, RE: 54.0% for the fine-tuned model vs. NER: 44.4%, RE: 10.1% for the LLM). This disparity of performance between supervised models and unsupervised usage of LLMs suggests datasets like ours are needed to advance research in the domain of scholarly information extraction.

GSAP-ERE: Fine-Grained Scholarly Entity and Relation Extraction Focused on Machine Learning

Multi-view clustering (MVC) seeks to uncover the intrinsic group structures embedded in multi-view data, which has attracted considerable attention in recent years. Existing approaches predominantly concentrate on incorporating suitable model priors to capture consistency across views. However, these explicit constraints often fail to hold in scenarios involving significant modal differences between views or the presence of noise, thereby limiting the efficacy of these methods in more complex contexts. To address these issues, this paper introduces BONE, a lightweight and interpretable MVC framework that Bridges Optimization and Neural networks for Efficient MVC. By leveraging learnable parameters to extract high-level features from low-level features derived through classical optimization, BONE integrates the consistency information across views without the need for explicit prior constraints, while eliminating the necessity for pre-training or post-processing. Extensive experiments show that BONE achieves clustering performance comparable to or even better than existing deep MVC methods, while using only one-thousandth of the parameters, offering a new perspective for designing efficient MVC algorithms.

Bridging Optimization and Neural Networks for Efficient Multi-view Clustering

Multimodal 3D object detection for autonomous driving, a task for real-world application, poses substantial challenges in maintaining robust performance under various perturbations and complex environmental conditions. However, most existing approaches primarily focus on performance optimization under relatively ideal scenarios or focus on one or few disturbing conditions (interference or adverse conditions), lacking systematic exploration of robustness against real-world factors, including high class imbalance, adverse weather conditions, sensor jitter and failures, and significant scene variations. To address this issue, we propose a robust multimodal 3D detector, termed RobusTor3D, which integrates robustness at both the structural and supervisory levels by blending the knowledge from Vision-Language Models (VLMs). Structurally, textual descriptions are incorporated to enhance the semantic richness and diversity of rare classes. This novel semantic injection operation compensates for the inherent class imbalance and modality weakness in conventional visual features. Furthermore, semantic alignment capability and robust representation by Vision-Language Knowledge Extraction (V-LKE) serve as semantic priors to complement modality-specific representations, significantly improving model adaptability. At the supervisory level, we propose a Scene-level Multimodal Consistency Learning (SMCL) strategy, which jointly enforces global semantic constraints across modalities, encouraging the learning of stable and abundant semantic representations. This special design specifically reduces the impact of spatial alignment, while notably enabling semantic compensation under modality-loss conditions. Extensive robustness experiments conducted on KITTI, KITTI-C, and CADC benchmarks evaluate five robustness aspects, including long-tail problem, adverse weather (rain, snow, fog, strong sunlight), sensor spatial misalignment and motion blur, modality loss, and cross-domain scenarios. The results show that the proposed RobusTor3D demonstrates superior robustness across all five evaluated aspects. It consistently outperforms the state-of-the-art methods under various challenging conditions.

RobusTor3D: Robust Multimodal 3D Object Detector for Autonomous Driving by Vision-Language Knowledge Blending

Multi-Agent Debate (MAD) is an emerging paradigm that leverages the reasoning abilities of Large Language Models (LLMs) by encouraging them to collaboratively solve problems through human-like discussions. However, current MAD methods typically constrain agents to follow fixed discussion pipelines, repeatedly applying the same discussion act for a predetermined number of rounds, which limits their effectiveness and adaptability in complex and diverse tasks. To address this limitation, we propose Analyze–Compose–Execute (ACE), a novel debate framework in which agents dynamically execute the discussion actions according to the dialogue context. To enable truly dynamic discussions, By analyzing the current responses of agents, ACE selects appropriate acts from a predefined Atomic Dis-
cussion Acts Library (ADAL), which are composed into a discussion action to be executed in the next round, to enable truly dynamic debate. We conduct extensive experiments on the challenging benchmark Big-Bench Hard (BBH) benchmark. ACE achieves state-of-the- art results on 17 out of 23 tasks, with an average performance gain of 8.5% across all tasks, demonstrating the effectiveness and robustness of our approach.

Analyze–Compose–Execute: A Dynamic Dialogue Framework for Multi-Agent Debate

Few-shot detection-based counters estimate the number of instances in the image specified only by a few test-time exemplars. 
A common approach to localize objects across multiple sizes is to merge backbone features of different resolutions.
Furthermore, to enable small object detection in densely populated regions, the input image is commonly upsampled and tiling is applied to cope with the increased computational and memory requirements. Because of these ad-hoc solutions, existing counters struggle with images containing diverse-sized objects and densely populated regions of small objects.
We propose GeCo2, an end-to-end few-shot counting and detection method that explicitly addresses the object scale issues. 
A new dense query representation gradually aggregates exemplar-specific feature information across scales that leads to high-resolution dense queries that enable detection of large as well as small objects.
GeCo2 surpasses state-of-the-art few-shot counters in counting as well as detection accuracy by $\sim$10\% while running $\sim$3$\times$ faster at smaller GPU memory footprint.
Code will be released upon acceptance.

Generalized-Scale Object Counting with Gradual Query Aggregation

Multimodal large language models (MLLMs), which integrate language and visual cues for problem-solving, are crucial for advancing artificial general intelligence (AGI). However, current benchmarks for measuring the intelligence of MLLMs suffer from limited scale, narrow coverage, and unstructured knowledge, offering only static and undifferentiated evaluations. To bridge this gap, we introduce MDK12-Bench, a large-scale multidisciplinary benchmark built from real-world K–12 exams spanning six disciplines with 141K instances and 6,225 knowledge points organized in a six-layer taxonomy. Covering five question formats with difficulty and year annotations, it enables comprehensive evaluation to capture the extent to which MLLMs perform over four dimensions: 1) difficulty levels, 2) temporal (cross-year) shifts, 3) contextual shifts, and 4) knowledge-driven reasoning. We propose a novel dynamic evaluation framework that introduces unfamiliar visual, textual, and question form shifts to challenge model generalization while improving benchmark objectivity and longevity by mitigating data contamination. We further evaluate knowledge-point reference-augmented generation (KP-RAG) to examine the role of knowledge in problem-solving. Key findings reveal limitations in current MLLMs in multiple aspects and provide guidance for enhancing model robustness, interpretability, and AI-assisted education.

Content not yet available

Next from AAAI 2026

FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES