Singapore

We introduce OSVBench, a new benchmark for evaluating Large Language Models (LLMs) in generating complete specification code pertaining to operating system kernel verification tasks. The benchmark first defines the specification generation problem into a program synthesis problem within a confined scope of syntax and semantics by providing LLMs with the programming model. The LLMs are required to understand the provided verification assumption and the potential syntax and semantics space to search for, then generate the complete specification for the potentially buggy operating system code implementation under the guidance of the high-level functional description of the operating system. This benchmark is built upon a real-world operating system kernel, Hyperkernel, and consists of 245 complex specification generation tasks in total, each is a long context task of about 20k-30k tokens. Our comprehensive evaluation of 12 LLMs exhibits the limited performance of the current LLMs on the specification generation tasks for operating system verification. Significant disparities in their performance on the benchmark highlight differences in their ability to handle long-context code generation tasks. The evaluation toolkit and benchmark are available at https://anonymous.4open.science/r/OSVBench.

AAAI 2026

OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification

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.

Deformable medical image registration is essential in medical image analyses. Recent transformer-based registration methods have achieved high registration accuracy. However, these methods often rely on patch embedding at the beginning of encoding, resulting in limited ability to capture detailed anatomical structural information in the images and explore local semantic relationships within individual patches. Here, we proposed a novel Dual-feet Encoder (DFEnc) to asynchronously model semantic information from moving and fixed images at various scales through two separate branches in three steps. For each step, features from adjacent resolution levels were processed by a Single Step Hybrid Extractor (SSHExt), which performed patch convolution to preserve local information, followed by several transformer blocks to capture global context. Dense connections were employed to enhance semantic awareness across adjacent feature resolution levels. Additionally, we introduced a Feature Fusion-based Decoder (FFDec) to progressively fuse features related to the fixed and moving images and to generate intermediate deformation fields at each stage, enabling accurate image alignment through stepwise warping and alignment refinement. Extensive ablation studies demonstrated the effectiveness of the proposed DFEnc, SSHExt, and FFDec. Compared to a state-of-the-art AutoFuse-Trans method, our approach yielded improvements in Dice of 1.41\%, 2.21\%, and 7.80\% on the ACDC, OASIS, and Abdomen CT datasets, respectively, while maintaining relatively low computational cost. These results suggest the utility of the proposed approach for broad research and clinical applications.

DFMN: A Dual-feet Matching Network with Hybrid Transformer-based Feature Extractor for Unsupervised Deformable Medical Image Registration

Due to its expressiveness and unambiguous nature, First-Order Logic (FOL) is a powerful formalism for representing concepts expressed in natural language (NL). This is useful, e.g., for specifying and verifying desired system properties. While translating FOL into human-readable English is relatively straightforward, the inverse problem, converting NL to FOL (NL-FOL translation), has remained a longstanding challenge, for both humans and machines. Although the emergence of Large Language Models (LLMs) promised a breakthrough, recent literature provides contrasting results on their ability to perform NL-FOL translation. In this work, we provide a threefold contribution. First, we critically examine existing datasets and protocols for evaluating NL-FOL translation performance, revealing key limitations that may cause a misrepresentation of LLMs' actual capabilities. Second, to overcome these shortcomings, we propose a novel evaluation protocol explicitly designed to distinguish genuine semantic-level logical understanding from superficial pattern recognition, memorization, and dataset contamination. Third, using this new approach, we show that state-of-the-art, dialogue-oriented LLMs demonstrate strong NL-FOL translation skills and a genuine grasp of sentence-level logic, whereas embedding-centric models perform markedly worse.

Do LLMs Really Struggle at NL-FOL Translation? Revealing Their Strengths via a Novel Benchmarking Strategy

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, while they remain prone to generating hallucinated or outdated responses due to their static internal knowledge. 
Recent advancements in Retrieval-Augmented Generation (RAG) methods have aimed to enhance models' search and reasoning capabilities through reinforcement learning (RL).
Although these methods demonstrate promising results, they face challenges in training stability and encounter issues such as substantial inference time and restricted capabilities due to reliance on single-query mode.
In this paper, we propose RAG-R1, a novel training framework designed to enable LLMs to adaptively leverage internal and external knowledge during the reasoning process. 
We further expand the generation and retrieval processes within the framework from single-query mode to multi-query parallelism, with the aim of reducing inference time and enhancing the model's capabilities.
Extensive experiments on seven question-answering benchmarks demonstrate that our method outperforms the strongest baseline by up to 13.2% and decreases inference time by 11.1%.
The code and model checkpoints will be available soon.

RAG-R1:Incentivizing the Search and Reasoning Capabilities of LLMs Through Multi-Query Parallelism

Multimodal fake news detection plays a crucial role in combating online misinformation. The inherent domain diversity of news in the real world has driven the development of cross-domain detection methods. However, these detection methods either suffer from significant performance degradation due to semantic and deception pattern shifts between the training (source) and test (target) domains or heavily rely on annotated labels. To address the problems, we propose ADOSE, an active multi-source domain adaptation framework for multimodal fake news detection which actively annotates a small subset of target samples to improve detection performance. Specifically, for domain shifts, we design a multi-expert classifier network based on refined features to comprehensively capture and adapt to the semantic space and deception patterns of news across different domains. To maximize adaptation performance with limited annotation cost, we propose a least-disagree uncertainty selector equipped with a diversity calculator for selecting the most informative samples. The selector leverages the uncertainty of inconsistent predictions before and after perturbations by multiple classifiers as an indicator of unfamiliar samples. It further incorporates diversity scores derived from multi-view features to ensure the chosen samples achieve maximal coverage of target domain features. The extensive experiments on multiple datasets show that ADOSE outperforms existing domain adaptation methods by 2.45\% $\sim$ 9.1\%, indicating the superiority of our model.

Active Multi-source Domain Adaptation for Multimodal Fake News Detection

Recent advances in stochastic differential equations (SDEs) have enabled robust modeling of real-world dynamical processes across diverse domains, such as finance, health, and systems biology. However, parameter estimation for SDEs typically relies on accurately time-stamped observational data. When temporal ordering information is corrupted, missing, or deliberately hidden (e.g., for privacy), existing estimation methods often fail. In this paper, we investigate the conditions under which temporal order can be recovered and introduce a novel framework that simultaneously reconstructs temporal information and estimates SDE parameters. Our approach exploits asymmetries between forward and backward processes, deriving a score-matching criterion to infer the correct temporal order between pairs of observations. We then recover the total order via a sorting procedure and estimate SDE parameters from the reconstructed sequence using maximum likelihood. Finally, we conduct extensive experiments on synthetic and real-world datasets to demonstrate the effectiveness of our method, extending parameter estimation to settings with missing temporal order and broadening applicability in sensitive domains.

Robust SDE Parameter Estimation Under Missing Time Information Setting

Deep networks have achieved remarkable success in image compressed sensing (CS) task, namely reconstructing a high-fidelity image from its compressed measurement. However, existing works are deficient in incoherent compressed measurement at sensing phase and implicit measurement representations at reconstruction phase, limiting the overall performance. In this work, we answer two questions: i) how to improve the measurement incoherence for decreasing the ill-posedness; ii) how to learn informative representations from measurements. To this end, we propose a novel asymmetric Kronecker CS (AKCS) model and theoretically present its better incoherence than previous Kronecker CS with minimal complexity increase. Moreover, we reveal that the unfolding networks' superiority over non-unfolding ones result from sufficient gradient descents, called explicit measurement representations. We propose a measurement-aware cross attention (MACA) mechanism to learn implicit measurement representations. We integrate AKCS and MACA into widely-used unfolding architecture to get a measurement-enhanced unfolding network (MEUNet). Extensive experiences demonstrate that our MEUNet achieve the state-of-the-art performance in reconstruction accuracy and inference speed.

Breaking Measurement Barriers: From Compressed Sensing to Deep Reconstruction

Generating realistic and coordinated 3D human motion for multiple individuals within complex environments remains a significant challenge. Existing text-to-motion methods are often ``blind'' to the physical scene, leading to implausible motions, while scene-conditioned (HSI) approaches demand cumbersome full 3D data and largely neglect multi-person dynamics. To address these limitations, we introduce the **VL2Motion** paradigm and its embodiment, **MMG-VL**, a hierarchical framework that generates coordinated multi-person motions from the most accessible inputs: a single 2D image and natural language. MMG-VL first employs a **Scene-Aware Intent Planner (SAIP)** to interpret the visual context and decompose the user's command into a set of spatially-grounded, multi-person action blueprints. Subsequently, a **Coordinated Motion Synthesizer (CMS)** translates these blueprints into high-fidelity 3D motion sequences. The synergy between these stages is driven by two novel loss functions: a **Spatial-Semantic Grounding Loss** to ensure the planner's output is grounded in visual reality, and a **Coordinated Environmental Realism Loss** that enforces physical constraints and coherent group dynamics during synthesis. To facilitate this research, we introduce **HumanVL**, the first large-scale dataset featuring multi-person activities in multi-room scenes, providing aligned images, text, blueprints, 3D motions, and scene geometry. Extensive experiments demonstrate that MMG-VL significantly outperforms existing methods in generating spatially coherent, physically realistic, and coordinated multi-person motions, paving the way for more scalable and intuitive creation of dynamic virtual worlds.

MMG-VL: A Vision-Language Driven Approach for Multi-Person Motion Generation

Recently, self‑supervised representation learning relying on vast amounts of unlabeled data has been explored as a pre‑training method for autonomous driving. However, directly applying popular contrastive or generative methods to this problem is insufficient and may even lead to negative transfer. In this paper, we present $\textbf{AD‑L‑JEPA}$, a novel self‑supervised pre‑training framework with a joint embedding predictive architecture (JEPA) for automotive LiDAR object detection. Unlike existing methods, AD‑L‑JEPA is neither generative nor contrastive. Instead of explicitly generating masked regions, our method predicts Bird’s‑Eye‑View embeddings to capture the diverse nature of driving scenes. Furthermore, our approach eliminates the need to manually form contrastive pairs by employing explicit variance regularization to avoid representation collapse. Experimental results demonstrate consistent improvements on the LiDAR 3D object detection downstream task across the KITTI3D, Waymo, and ONCE datasets, while reducing GPU hours by $1.9\times$-$2.7\times$ and GPU memory by $2.8\times$-$4\times$ compared with the state-of-the-art method Occupancy-MAE. Notably, on the largest ONCE dataset, pre‑training on 100K frames yields a 1.61 mAP gain, better than in case of all the other methods pre‑trained on either 100K or 500K frames, and pre‑training on 500K frames yields a 2.98 mAP gain, better than in case of all the other methods pre‑trained on either 500K or 1M frames. AD‑L‑JEPA constitutes the first JEPA‑based pre‑training method for autonomous driving. It offers $\textit{better quality}$, $\textit{faster}$, and more $\textit{GPU‑memory‑efficient}$ self‑supervised representation learning. The source code of AD-L-JEPA is ready to be released.

Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object Detection

Planar quadrilateral (PQ) mesh generation is a key process in computer-aided design, particularly for architectural applications where the goal is to discretize a freeform surface using planar quad faces. The conjugate direction field (CDF) defined on the freeform surface plays a significant role in generating a PQ mesh, as it largely determines the PQ mesh layout. Conventionally, a CDF is obtained by solving a complex non-linear optimization problem that incorporates user preferences, i.e., aligning the CDF with user-specified strokes on the surface. This often requires a large number of iterations for the optimization solver, which is a time-consuming process. To address this challenge, we propose a data-driven approach based on neural networks for controlled CDF generation. Our approach can effectively learn and fuse features from the freeform surface and the user strokes, and efficiently generate quality CDF respecting user guidance. To enable training and testing, we also present a dataset composed of 50000+ freeform surfaces with ground-truth CDFs, as well as a set of metrics for quantitative evaluation. The effectiveness and efficiency of our work are demonstrated by extensive experiments using testing data, architectural surfaces, and general 3D shapes. Our codes and dataset will be made publicly available upon acceptance.

Learning Conjugate Direction Fields for Planar Quadrilateral Mesh Generation

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.

Content not yet available

Downloads

Next from AAAI 2026

DFMN: A Dual-feet Matching Network with Hybrid Transformer-based Feature Extractor for Unsupervised Deformable Medical Image Registration

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

DFMN: A Dual-feet Matching Network with Hybrid Transformer-based Feature Extractor for Unsupervised Deformable Medical Image Registration

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads