Singapore

Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling.
However, controllable generation remains challenging for Visual Autoregressive (VAR) models due to their hierarchical, next-scale prediction style.
Existing VAR-based methods often suffer from inefficient control encoding and disruptive injection mechanisms that compromise both fidelity and efficiency. 
In this work, we present SCALAR, a controllable generation method based on VAR, incorporating a Scale-wise Conditional Decoding mechanism. 
SCALAR leverages a pretrained image encoder to extract semantic control signal encodings, which are projected into scale-specific representations and injected into the corresponding layers of the VAR backbone. 
This design provides persistent and structurally aligned guidance throughout the generation process.
Building on SCALAR, we develop SCALAR-Uni, a unified extension that aligns multiple control modalities into a shared latent space, supporting flexible multi-conditional guidance in a single model.
Extensive experiments show that SCALAR achieves superior generation quality and control precision across various tasks.
All the code will be released.

AAAI 2026

SCALAR: Scale-wise Controllable Visual Autoregressive Learning

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.

To identify objects beyond predefined categories, open-vocabulary aerial object detection(OVAD) leverages the zero-shot capabilities of visual-language models (VLMs) to generalize from base to novel categories. Existing approaches typically utilize self-learning mechanisms with weak text supervision to generate region-level pseudo-labels to align detectors with VLMs semantic spaces. However, text dependence induces semantic bias, restricting open-vocabulary expansion to text-specified concepts. We propose $\textbf{VK-Det}$, a $\textbf{V}$isual $\textbf{K}$nowledge-guided open-vocabulary object $\textbf{Det}$ection framework $\textit{without}$ extra supervision. First, we discover and leverage vision encoder's inherent informative region perception to attain fine-grained localization and adaptive distillation. Second, we introduce a novel prototype-aware pseudo-labeling strategy. It models inter-class decision boundaries through feature clustering and maps detection regions to latent categories via prototype matching. This enhances attention to novel objects while compensating for missing supervision. Extensive experiments show state-of-the-art performance, achieving 30.1 $\mathrm{mAP}^{N}$ on DIOR and 23.3 $\mathrm{mAP}^{N}$ on DOTA, outperforming even extra supervised methods.

VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection

Membership Inference Attack (MIA) aims to determine if a data sample is used in the training dataset of a target model. Traditional MIA obtains feature of target model via shadow models and uses the feature to train attack model, but the scale and complexity of training or fine-tuning data for large language model (LLM)-based recommendation systems make shadow models difficult to construct. Knowledge distillation as a method for extracting knowledge contributes to construct a stronger reference model. Knowledge distillation enables separate distillation for member and non-member data during the distillation process, enhancing the model's discriminative capability between the two in MIA. This paper propose a knowledge distillation-based MIA paradigm to improve the performance of membership inference attacks on LLM-based recommendation systems. Our paradigm introduces knowledge distillation to obtain a reference model, which enhances the reference model's ability to distinguish between member and non-member data. We obtain individual features from the reference model and train our attack model with fused feature. Our paradigm improves the attack performance of MIA compared to shadow model-based attack.

Membership Inference Attack Against Large Language Model-Based Recommendation Systems: A New Distillation-Based Paradigm

Large Language Models (LLMs) often falter at complex planning tasks that require exploration and self-correction, as their linear reasoning process struggles to recover from early mistakes. While search algorithms like Monte Carlo Tree Search (MCTS) can explore alternatives, they are often ineffective when guided by sparse rewards and fail to leverage the rich semantic capabilities of LLMs. We introduce SPIRAL (Symbolic LLM Planning via Grounded and Reflective Search), a novel framework that embeds a cognitive architecture of three specialized LLM agents into an MCTS loop. SPIRAL's key contribution is its integrated planning pipeline where a Planner proposes creative next steps, a Simulator grounds the search by predicting realistic outcomes, and a Critic provides dense reward signals through reflection. This synergy transforms MCTS from a brute-force search into a guided, self-correcting reasoning process. On the DailyLifeAPIs and HuggingFace datasets, SPIRAL consistently outperforms the default Chain-of-Thought planning method and other state-of-the-art agents. More importantly, it substantially surpasses other state-of-the-art agents; for example, SPIRAL achieves 83.6% overall accuracy on DailyLifeAPIs, an improvement of over 16 percentage points against the next-best search framework, while also demonstrating superior token efficiency. Our work demonstrates that structuring LLM reasoning as a guided, reflective, and grounded search process yields more robust and efficient autonomous planners. The source code for all experiments is available in the supplemental materials for reproducibility.

SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search

Unlike traditional object detection, moving infrared small target detection is highly challenging due to tiny target size and limited labeled samples. Currently, most existing methods mainly focus on the pure-vision features usually by fully-supervised learning, heavily relying on extensive high-cost manual annotations. Moreover, they almost have not concerned the potentials of multi-modal (e.g., vision and text) learning yet. To address these issues, inspired by prevalent vision-language models, we propose the first semi-supervised vision-language (SeViL) framework with adaptive text prompt guiding. Breaking through traditional pure-vision modality, it takes text prompts as prior knowledge to adaptively enhance target regions and then filter the low-quality pseudo-labels generated on unlabeled data. In the meanwhile, we employ an adaptive cross-modal masking strategy to align text and vision features, promoting cross-modal deep interactions. Remarkably, our extensive experiments on three public datasets (DAUB, ITSDT-15K and IRDST) verify that our new scheme could outperform other semi-supervised ones, and even achieve comparable performance to fully-supervised state-of-the-art (SOTA) methods, with only 10% labeled training samples. Source codes will be publicly available after acceptance.

SeViL: Semi-supervised Vision-Language Learning with Text Prompt Guiding for Moving Infrared Small Target Detection

High quality datasets are critical for training reliable machine learning models, yet data faults caused by insufficient annotation expertise or malicious poisoning attacks remain prevalent. Traditional classifier based methods rely on manually curated subsets for fault detection, but their limited scale frequently leads to model overfitting. While multimodal large language models (MLLMs) based methods offer promising detection capabilities, their few-shot learning limitations hinder generalization in domain specific tasks. To address these challenges, we propose MLLM Guided Iterative Sample Filtering (MISF), a novel framework that combines the strengths of MLLM based initialization and iterative data refinement. Our framework initializes the detection model with MLLM generated synthetic images and a curated clean subset, then iteratively refines it by progressively selecting high certainty clean samples, improving both domain adaptation and detection accuracy. Extensive experiments on RESISC45 and Oxford-IIIT Pets datasets demonstrate that MISF effectively identifies data faults, outperforming existing approaches. MISF provides a robust, scalable solution for improving dataset quality in specialized domains.

MISF: MLLM Guided Iterative Sample Filtering for Data Fault Detection

Appearance-based gaze estimation, aiming to predict accurate 3D gaze direction from a single facial image, has made promising progress in recent years. However, most methods suffer from heavy performance degradation when facing across-domain evaluation due to gaze-irrelevant factor interference, such as expressions, wearables, and image quality. To alleviate this problem, we present a novel Hybrid-domain Adaptative Representation Learning (shorted by HARL) framework that exploits multi-source hybrid datasets to learn robust gaze representation. More specifically, we propose to disentangle gaze-relevant representation from low-quality facial images by aligning features extracted from high-quality near-eye images in an unsupervised domain-adaptation manner, which hardly requires any computational or inference costs. Additionally, we also analyze the effect of head-pose and design a simple yet efficient sparse graph fusion module to explore the inner geometric constraint between gaze direction and head-pose, which leads to dense and robust gaze representation. Extensive experiments on EyeDiap, MPIIFaceGaze, and Gaze360 datasets demonstrate that our approach achieves state-of-the-art accuracy of $\textbf{5.02}^{\circ}$ and $\textbf{3.36}^{\circ}$, and $\textbf{9.26}^{\circ}$ respectively, and present completing performances through cross-datasets evaluation.

Hybrid-Domain Adaptative Representation Learning for Gaze Estimation

Sparse-view 3D Gaussian splatting seeks to render high-quality novel views of 3D scenes from a limited set of input images. While recent pose-free feed-forward methods leveraging pre-trained 3D priors have achieved impressive results, most of them rely on full fine-tuning of large Vision Transformer (ViT) backbones and incur substantial GPU costs.
In this work, we introduce MuSASplat, a novel framework that dramatically reduces the computational burden of training pose-free feed-forward 3D Gaussian splats models with little compromise of rendering quality. Central to our approach is a lightweight Multi-Scale Adapter that enables efficient fine-tuning of ViT-based architectures with only a small fraction of training parameters. This design avoids the prohibitive GPU overhead associated with previous full-model adaptation techniques while maintaining high fidelity in novel view synthesis, even with very sparse input views. In addition, we introduce a Feature Fusion Aggregator that integrates features across input views effectively and efficiently. Unlike widely adopted memory banks, the Feature Fusion Aggregator ensures consistent geometric integration across input views and meanwhile mitigates the memory usage, training complexity, and computational costs significantly.
Extensive experiments across diverse datasets show that MuSASplat achieves state-of-the-art rendering quality but has significantly reduced parameters and training resource requirements as compared with existing methods.

MuSASplat: Efficient Sparse-View 3D Gaussian Splats via Lightweight Multi-Scale Adaptation

Understanding multi-page documents poses a significant challenge for multimodal large language models (MLLMs), as it requires fine-grained visual comprehension and multi-hop reasoning across pages. While prior work has explored reinforcement learning (RL) for enhancing advanced reasoning in MLLMs, its application to multi-page document understanding remains underexplored. In this paper, we introduce DocR1, an MLLM trained with a novel RL framework, Evidence Page-Guided GRPO (EviGRPO). EviGRPO incorporates an evidence-aware reward mechanism that promotes a coarse-to-fine reasoning strategy, guiding the model to first retrieve relevant pages before generating answers. To support this, we design a rigorous two-stage annotation pipeline and a curriculum learning strategy that enables effective training with limited supervision. Using this pipeline, we construct two datasets: EviBench, a high-quality training set with 4.8k examples, and ArxivFullQA, a benchmark with 8.6k QA examples over full scientific papers. Extensive experiments across a wide range of benchmarks demonstrate that DocR1 achieves state-of-the-art performance on multi-page tasks while maintaining strong results on single-page benchmarks.

DocR1: Evidence Page-Guided GRPO for Multi-Page Document Understanding

Streaming free-viewpoint video (FVV) in real-time still faces significant challenges, particularly in training, rendering, and transmission efficiency. Harnessing superior performance of 3D Gaussian Splatting (3DGS), recent 3DGS-based FVV methods have achieved notable breakthroughs in both training and rendering. However, the storage requirements of these methods can reach up to $10$MB per frame, making stream FVV in real-time impossible. To address this problem, we propose a novel FVV representation, dubbed StreamSTGS, designed for real-time streaming. StreamSTGS represents a dynamic scene using canonical 3D Gaussians, temporal features, and a deformation field. For high compression efficiency, we encode canonical Gaussian attributes as 2D images and temporal features as a video. This design not only enables real-time streaming, but also inherently supports adaptive bitrate control based on network condition without any extra training. Moreover, we propose a sliding window scheme to aggregate adjacent temporal features to learn local motions, and then introduce a transformer-guided auxiliary training module to learn global motions. On diverse FVV benchmarks, StreamSTGS demonstrates competitive performance on all metrics compared to state-of-the-art methods. Notably, StreamSTGS increases the PSNR by an average of $1$dB while reducing the average frame size to just $170$KB.

StreamSTGS: Streaming Spatial and Temporal Gaussian Grids for Real-Time Free-Viewpoint Video

Graph Neural Networks (GNNs) have achieved impressive performance in semi-supervised graph anomaly detection (GAD). While many GNN variants have been developed for this task, they largely focus on advanced message aggregation schemes, leaving the message routing aspect underexplored. We argue that the commonly used broadcast-based routing can also hinder generalization, particularly in the presence of rare and structurally challenging (vertices with a high-degree) anomalies. To address this, we propose Binary Message Passing (BMP), a novel routing paradigm that models the message flow of each vertex as a binary tree (BMP tree), where vanilla graph convolution is decoupled by its left and right subtrees. Each vertex recursively gathers information from neighbors with higher anomaly probabilities within each subtree, thereby amplifying the propagation of anomaly information across the topology. The anomaly probabilities are estimated and updated by the model itself, enabling adaptive, self-supervised routing over iterations. Furthermore, combining multiple BMP trees into a BMP forest provides multi-scale structural context, enhancing the expressiveness of final vertex embeddings. Extensive experiments show that BMP improves detection performance under limited supervision while exhibiting better generalization across structurally diverse anomalies.

Premium content

Next from AAAI 2026

VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES