Singapore

Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible to generate code from natural language, opening new opportunities for automating parametric 3D modeling. However, directly translating human design intent into executable CAD code remains highly challenging, due to the need for logical reasoning, syntactic correctness, and numerical precision. In this work, we propose CAD-RL, a multimodal Chain-of-Thought (CoT) guided reinforcement learning post training framework for CAD modeling code generation. Our method combines CoT-based Cold Start with goal-driven reinforcement learning post training using three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward. To ensure stable policy learning under sparse and high-variance reward conditions, we introduce three targeted optimization strategies: Trust Region Stretch for improved exploration, Precision Token Loss for enhanced dimensions parameter accuracy, and Overlong Filtering to reduce noisy supervision. To support training and benchmarking, we release ExeCAD, a noval dataset comprising 16,540 real-world CAD examples with paired natural language and structured design language descriptions, executable CADQuery scripts, and rendered 3D models. Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing VLMs.

AAAI 2026

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

cad;vlm;code generation

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.

poster

Recent advances in Multimodal Large Language Models (MLLMs) have spurred significant progress in Chain-of-Thought (CoT) reasoning. Building on the success of Deepseek-R1, researchers extended multimodal reasoning to post-training paradigms based on reinforcement learning (RL), focusing predominantly on mathematical datasets. However, existing post-training paradigms tend to neglect two critical aspects: (1) The lack of quantifiable difficulty metrics capable of strategically screening samples for post-training optimization. (2) Suboptimal post-training paradigms that fail to jointly optimize perception and reasoning capabilities. To address this gap, we propose two novel difficulty-aware sampling strategies: Progressive Image Semantic Masking (PISM) quantifies sample hardness through systematic image degradation, while Cross-Modality Attention Balance (CMAB) assesses cross-modal interaction complexity via attention distribution analysis. Leveraging these metrics, we design a hierarchical training framework that incorporates both GRPO-only and SFT+GRPO hybrid training paradigms, and evaluate them across six benchmark datasets. Experiments demonstrate consistent superiority of GRPO applied to difficulty-stratified samples compared to conventional SFT+GRPO pipelines, indicating that strategic data sampling can obviate the need for supervised fine-tuning while improving model accuracy.

Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View

Deep Reinforcement Learning (DRL) systems are increasingly used in safety-critical applications, yet their security remains severely underexplored. This work investigates backdoor attacks, which implant hidden triggers that cause malicious actions only when specific inputs appear in the observation space. Existing DRL backdoor research focuses solely on training-time attacks requiring full adversarial access to the training pipeline. In contrast, we reveal critical vulnerabilities across the DRL supply chain where backdoors can be embedded with significantly reduced adversarial privileges. We introduce two novel attacks: (1) TrojanentRL, which exploits component-level flaws to implant a persistent backdoor that survives full model retraining; and (2) InfrectroRL, a post-training backdoor attack which requires no access to training, validation, or test data. Empirical and analytical evaluations across six Atari environments show our attacks rival state-of-the-art training-time backdoor attacks while operating under much stricter adversarial constraints. We also demonstrate that InfrectroRL further evades two leading DRL backdoor defenses. These findings challenge the current research focus and highlight the urgent need for robust defenses.

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning

Curvilinear structure segmentation (CSS) plays a vital role in industrial applications, including medical imaging and structural health monitoring. Recently, the strong capacity of the Segment Anything Model (SAM) has inspired its downstream application in CSS tasks. To adapt SAM to CSS tasks, previous methods heavily rely on a certain number of samples and costly pixel-level annotation, which are hard to access for a new scenario. Considering this, the goal of our work is to adapt SAM in a very cost-effective setting where only a single unlabeled image is given. This is far more challenging than the typical supervised, unsupervised, or self-supervised learning manner that needs a large number of training samples. To tackle this problem, we propose a finetuning-free SAM for curvilinear structure segmentation, called \textbf{c}urvilinear-\textbf{a}ware \textbf{pro}mpt learning (\emph{CaPro}), which aims to automatically learn visual prompts via a single unlabeled image. In the first stage, we generate extensive curvilinear structures and oriented sub-curvilinear box annotations. To increase the realism of generated curvilinear structures, we adapt these structures into real image domains via the Fourier Transform using a single real-world unlabeled image. Now, these adapted images can be used to train our oriented sub-curvilinear detector. In the second stage, we propose the curvilinear-aware discrete representation matching to filter those unreliable detection results. Afterward, these reliable detection results can be converted into informative prompts, contributing to the cost-effective SAM adaptation to CSS tasks. Experiments demonstrate the effectiveness of \emph{CaPro} on medical image and crack segmentation tasks. Code and dataset will be publicly available.

CaPro: Curvilinear-aware Prompt Learning with Single Unlabeled Image for Cost-effective Curvilinear Structure Segmentation

The ability of Large Language Models (LLMs) to precisely follow complex and fine-grained lexical instructions is a cornerstone of their utility and controllability. However, evaluating this capability remains a significant challenge. Current methods either rely on subjective and costly human evaluation or on automated ``LLM-as-a-judge'' systems, which suffer from inherent biases and unreliability. Existing programmatic benchmarks, while objective, often lack the expressiveness to test intricate, compositional constraints at a granular level. To address these limitations, we introduce \textbf{LexInstructEvaL}, a new benchmark and evaluation framework for fine-grained lexical instruction following. Our framework is built upon a formal, rule-based grammar that deconstructs complex instructions into a canonical $\langle \texttt{Procedure, Relation, Value} \rangle$ triplet. This grammar enables the systematic generation of a diverse dataset through a multi-stage, human-in-the-loop pipeline and facilitates objective verification via a transparent, programmatic engine. Crucially, our engine is not only low-cost and fast but also highly reliable, achieving \textbf{97\% agreement} with expert human judgment. We release our dataset and open-source evaluation tools to facilitate further research into the controllability and reliability of LLMs.

LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models

Compositional Zero-Shot Learning (CZSL) addresses the challenge of recognizing unseen attribute-object compositions in images, representing a fundamental challenge in artificial intelligence. Current approaches, which primarily focus on semantic alignment or distribution independence of primitives, have not achieved effective state-object decoupling and causal interventional invariance, limiting their performance on unseen compositions. To tackle this challenge, this study introduces I2CD (Invertible Causal framework via Disentangle-Compose-Disentangle), a novel framework that integrates invertible neural networks with causal intervention techniques to achieve state-object disentanglement. The framework employs a disentangle-compose-disentangle mechanism for counterfactual generation within the disentangled representation space, ensuring that modifications to one primitive (attribute or object) maintain independence from the other, thus enabling robust causal disentanglement. Representational consistency is maintained through semantic alignment between initial disentangled representations and their recomposed-then-disentangled counterparts with corresponding textual concepts. Comprehensive evaluations on three benchmark datasets—MIT-States, UT-Zappos, and C-GQA—demonstrate the framework's effectiveness in achieving both disentanglement and compositional generalization in CZSL tasks.

I2CD: An Invertible Causal Framework for Compositional Zero-Shot Learning via Disentangle-Compose-Disentangle

Camera-based 3D semantic scene completion (SSC) plays a crucial role in autonomous driving, enabling voxelized 3D scene understanding for effective scene perception and decision-making. Existing SSC methods have shown efficacy in improving 3D scene representations, but suffer from the inherent input-output dimension gap and annotation-reality density gap, where the 2D planner view from input images with sparse annotated labels leads to inferior prediction of real-world dense occupancy with a 3D stereoscopic view. In light of this, we propose the corresponding High-Dimension High-Density Semantic Scene Completion (HD²-SSC) framework with expanded pixel semantics and refined voxel occupancies. To bridge the dimension gap, a High-dimension Semantic Decoupling module is designed to expand 2D image features along a pseudo third dimension, decoupling coarse pixel semantics from occlusions, and then identify focal regions with fine semantics to enrich image features. To mitigate the density gap, a High-density Occupancy Refinement module is devised with a “detect-and-refine" architecture to leverage contextual geometric and semantic structures for enhanced semantic density with the completion of missing voxels and correction of erroneous ones. Extensive experiments and analyses on the SemanticKITTI and SSCBench-KITTI-360 datasets validate the effectiveness of our HD²-SSC framework.

HD²-SSC: High-Dimension High-Density Semantic Scene Completion for Autonomous Driving

Large Multimodal Models (LMMs) often face a modality representation gap during pretraining: while language embeddings remain stable, visual representations are highly sensitive to contextual noise (e.g., background clutter). To address this issue, we introduce a visual comprehension stage, which we call \textbf{ViCToR}~(\textbf{Vi}sual \textbf{C}omprehension via \textbf{To}ken \textbf{R}econstruction), a novel pretraining framework for LMMs. ViCToR employs a learnable visual token pool and utilizes the Hungarian matching algorithm to select semantically relevant tokens from this pool for visual token replacement. Furthermore, by integrating a visual token reconstruction loss with dense semantic supervision, ViCToR can learn tokens which retain high visual detail, thereby enhancing the large language model’s (LLM’s) understanding of visual information.
After pretraining on 3 million publicly accessible images and captions, \textbf{ViCToR} achieves state-of-the-art results, improving over LLaVA-NeXT-8B by $10.4\%$, $3.2\%$, and $7.2\%$ on the MMStar, SEED$^{I}$, and RealWorldQA benchmarks, respectively. We will release the code and model weights to facilitate reproducibility.

ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs

Pan-sharpening aims to generate high-resolution multispectral (HRMS) images by integrating the spectral richness of low-resolution multispectral (MS) images with the spatial details of high-resolution panchromatic (PAN) images. Although frequency-domain modeling shows great potential in this field, most existing methods are still limited to spatial-domain processing or fail to effectively capture the contextual interactions between frequency and spatial features. To address these issues, we propose a novel multi-scale frequency-spatial collaborative fusion approach. A Frequency-Spatial U-Net (FS-UNet) is introduced as the backbone network, in which frequency-spatial modeling blocks are embedded to progressively enhance the frequency-guided spatial contextual modeling capability across layers. To this end, we design a Dual Branch Frequency Attention (DBFA) module that adaptively enhances high- and low-frequency information. In addition, we introduce fine-mid-coarse resolution branches and devise a main-auxiliary multi-scale reconstruction loss to facilitate collaborative optimization. The effectiveness of the proposed model is validated through extensive experiments, demonstrating superior performance in both qualitative and quantitative evaluations. Moreover, our model achieves the fastest inference time among all compared methods, striking an excellent balance between accuracy and efficiency.

Hierarchical Dual-Domain Fusion with Frequency-Guided Spatial Modeling for Pan-Sharpening

Video-based human pose estimation has vast applications such as action recognition, sports analytics, and crime detection. However, this task is challenging as it involves interpreting both spatial context and temporal dynamics to accurately localize human anatomical keypoints in video sequences. Current approaches, often based on attention mechanisms, perform well but struggle in challenging scenarios like rapid motion and pose occlusion. We attribute these failures to two fundamental limitations: spatial uniformity, where models indiscriminately assign attention to both joint-relevant features and background clutter, thereby introducing spatial noise; and temporal rigidity, an inability to adapt to large joint displacements, resulting in severe feature misalignment during rapid motion. To overcome these challenges, we introduce PSTPose, a novel progressive spatiotemporal refinement framework. Specifically, to address the spatial uniformity problem, we propose a Discriminative Feature Enhancement (DFE) module that emphasizes joint-relevant features and a Feature Cluster Grouping (FCG) module that forms compact, semantically meaningful regions. For the temporal rigidity problem, we introduce a Deformable Spatiotemporal Fusion (DSF) module that adaptively aligns features across consecutive frames via deformation-aware sampling. This design ensures robust keypoint localization, particularly in cluttered and dynamic scenes. Extensive experiments on four large-scale benchmarks, PoseTrack2017, PoseTrack2018, PoseTrack21, and Sub-JHMDB, demonstrate that PSTPose establishes a new state-of-the-art. The implementation is anonymously released and available in the supplementary material.

Attentive Keypoint Identification: Progressive Spatiotemporal Refinement for Video-based Human Pose Estimation

We present MoBGS, a novel motion deblurring 3D Gaussian Splatting (3DGS) framework capable of reconstructing sharp and high-quality novel spatio-temporal views from blurry monocular videos in an end-to-end manner. Existing dynamic novel view synthesis (NVS) methods are highly sensitive to motion blur in casually captured videos, resulting in significant degradation of rendering quality. While recent approaches address motion-blurred inputs for NVS, they primarily focus on static scene reconstruction and lack dedicated motion modeling for dynamic objects. To overcome these limitations, our MoBGS introduces a novel Blur-adaptive Latent Camera Estimation (BLCE) method using a proposed Blur-adaptive Neural Ordinary Differential Equation (ODE) solver for effective latent camera trajectory estimation, improving global camera motion deblurring. In addition, we propose a Latent Camera-induced Exposure Estimation (LCEE) method to ensure consistent deblurring of both a global camera and local object motions. Extensive experiments on the Stereo Blur dataset and real-world blurry videos show that our MoBGS significantly outperforms the very recent methods, achieving state-of-the-art performance for dynamic NVS under motion blur.

Downloads

Next from AAAI 2026

Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View

Similar lecture

ReACT: Reward-informed Autoregressive Decision CAD Transformer

.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

Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View

Similar lecture

ReACT: Reward-informed Autoregressive Decision CAD Transformer

Downloads