Singapore

Recent progress in text-to-image (T2I) generative models has led to significant improvements in generating high-quality images aligned with text prompts. However, these models still struggle with prompts involving multiple objects, often resulting in object neglect or object mixing. Through extensive studies, we identify four problematic scenarios, Similar Shapes, Similar Textures, Dissimilar Background Biases, and Many Objects, where inter-object relationships frequently lead to such failures. Motivated by two key observations about CLIP embeddings, we propose DOS (Directional Object Separation), a method that modifies three types of CLIP text embeddings before passing them into text-to-image models. Experimental results show that DOS consistently improves the success rate of multi-object image generation and reduces object mixing. In human evaluations, DOS significantly outperforms four competing methods, receiving 26.24%-43.04% more votes across four benchmarks. These results highlight DOS as a practical and effective solution for improving multi-object image generation.

AAAI 2026

DOS: Directional Object Separation in Text Embeddings for Multi-Object Image Generation

cv: diffusion models for vision

cv: language and vision

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

We propose BRIC, a novel test-time adaptation (TTA) framework that enables long-term human motion generation by resolving execution discrepancies between diffusion-based kinematic motion planners and reinforcement learning-based physics controllers. While diffusion models can generate diverse and expressive motions conditioned on text and scene context, they often produce physically implausible outputs, leading to execution drift during simulation. To address this, BRIC dynamically adapts the physics controller to noisy motion plans at test time, while preserving pre-trained skills via a loss function that mitigates catastrophic forgetting. In addition, BRIC introduces a lightweight test-time guidance mechanism that steers the diffusion model in the signal space without updating its parameters.
By combining both adaptation strategies, BRIC ensures consistent and physically plausible long-term executions across diverse environments in an effective and efficient manner. We validate the effectiveness of BRIC on a variety of long-term tasks, including motion composition, obstacle avoidance, and human-scene interaction, achieving state-of-the-art performance across all tasks.

BRIC: Bridging Kinematic Plans and Physical Control at Test Time

Accurate air quality forecasting is essential for public health and environmental sustainability, but remains challenging due to the complex pollutant dynamics.
Existing deep learning methods often model pollutant dynamics as an instantaneous process, overlooking the intrinsic delays in pollutant propagation. 
Thus, we propose AirDDE, the first neural delay differential equation framework in this task that integrates delay modeling into a continuous-time pollutant evolution under physical guidance.
Specifically, two novel components are introduced: (1) a memory-augmented attention module that retrieves globally and locally historical multimo features, which can adaptively capture delay effects modulated by multifactor data; and (2) a physics-guided delay evolving function, grounded in the continuity equation, that models diffusion, delayed advection, and source/sink terms, which can capture delay-aware pollutant accumulation patterns with physical plausibility. 
Extensive experiments on three real-world datasets demonstrate that AirDDE achieves the state-of-the-art forecasting performance with an average MAE reduction of 8.81\% over the best baselines.

AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting

The booming remote sensing (RS) technology is giving rise to a novel multimodality generalization task, which requires the model to overcome data heterogeneity while possessing powerful cross-scene generalization ability. Moreover, most vision-language models (VLMs) usually describe surface materials in RS images using universal texts, lacking proprietary linguistic prior knowledge specific to different RS vision modalities. In this work, we formalize RS multimodality generalization (RSMG) as a learning paradigm, and propose a frequency-aware vision-language multimodality generalization network (FVMGN) for RS image classification. Specifically, a diffusion-based training-test-time augmentation (DTAug) strategy is designed to reconstruct multimodal land-cover distributions, enriching input information for FVMGN. Following that, to overcome multimodal heterogeneity, a multimodal wavelet disentanglement (MWDis) module is developed to learn cross-domain invariant features by resampling low and high frequency components in the frequency domain. Considering the characteristics of RS vision modalities, shared and proprietary class texts is designed as linguistic inputs for the transformer-based text encoder to extract diverse text features. For multimodal vision inputs, a spatial-frequency-aware image encoder (SFIE) is constructed to realize local-global feature reconstruction and representation. Finally, a multiscale spatial-frequency feature alignment (MSFFA) module is suggested to construct a unified semantic space, ensuring refined multiscale alignment of different text and vision features in spatial and frequency domains. Extensive experiments show that FVMGN has the excellent multimodality generalization ability compared with state-of-the-art (SOTA) methods.

Frequency-Aware Vision-Language Multimodality Generalization Network for Remote Sensing Image Classification

The response behaviors observed in online user-generated content (UGC) frequently demonstrate non-linear characteristics, such as conditional branching and selective avoidance. These patterns present additional challenges for ensuring the trustworthiness of Large Language Models (LLMs) reasoning, particularly as their unidirectional, left-to-right inference mechanisms may not adequately capture such complex reasoning dynamics. To address this, we propose a Forest of Thought Explanation (FoTE), a novel prompting that models the selective avoidance in UGC while ensuring explanation consensus through reasoning paths across all decision sub-trees. The FoTE employs an Iterative Chain of Thought (ICoT) to generate diverse reasoning thoughts. The thoughts are then assessed via a cooperative contribution evaluator with a fair contribution. The top-$k$ highest-contribution thoughts are retained for subsequent reasoning iterations, while subsets are randomly sampled to simulate selective avoidance—thereby constructing the FoTE. Through extensive evaluations across three open-source LLMs and two established social science problems (spanning four benchmark datasets), the FoTE demonstrates superior success rates compared to competing prompting strategies. Notably, its performance gains increase with the strength of selective avoidance in social problems. The trustworthiness of our FoTE is enhanced by the incorporation of (1) a cooperative game theory-based thought evaluator and (2) a transparent reasoning path that converges toward consensus.

Exploring Selective Avoidance for Online User Behavior Analysis: A Forest of Thought Explanation

Large language models (LLMs) often suffer from hallucination, generating factually incorrect statements when handling questions beyond their knowledge and perception. Retrieval-augmented generation (RAG) addresses this by retrieving query-relevant contexts from knowledge bases to support LLM reasoning. Recent advances leverage pre-constructed graphs to capture the relational connections among distributed documents, showing remarkable performance in complex tasks. However, existing Graph-based RAG (GraphRAG) methods rely on a costly process to transform the corpus into a graph, introducing overwhelming token cost and update latency. Moreover, real-world queries vary in type and complexity, requiring different logic structures for accurate reasoning. The pre-built graph may not align with these required structures, resulting in ineffective knowledge retrieval. To this end, we propose a Logic-aware Retrieval Augmented Generation framework (LogicRAG) that dynamically extracts reasoning structures at inference time to guide adaptive retrieval without any pre-built graph. LogicRAG begins by decomposing the input query into a set of subproblems and constructing a directed acyclic graph (DAG) to model the logical dependencies among them. To support coherent multi-step reasoning, LogicRAG then linearizes the graph using topological sort, so that subproblems can be addressed in a logically consistent order. Besides, LogicRAG applies graph pruning to reduce redundant retrieval and uses context pruning to filter irrelevant context, significantly reducing the overall token cost. Extensive experiments demonstrate that LogicRAG achieves both superior performance and efficiency compared to state-of-the-art baselines.

You Don’t Need Pre-Built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures

Developing intelligent agents capable of operating a wide range of Graphical User Interfaces (GUIs) with human-level proficiency is a key milestone on the path toward Artificial General Intelligence. While most existing datasets and benchmarks for training and evaluating GUI agents are static and idealized, failing to reflect the complexity and unpredictability of real-world environments, particularly the presence of anomalies. To bridge this research gap, we propose D-GARA, a dynamic benchmarking framework, to evaluate Android GUI agent robustness in real-world anomalies. D-GARA introduces a diverse set of real-world anomalies that GUI agents commonly face in practice, including interruptions such as permission dialogs, battery warnings, and update prompts. Based on D-GARA framework, we construct and annotate a benchmark featuring commonly used Android applications with embedded anomalies to support broader community research. Comprehensive experiments and results demonstrate substantial performance degradation in state-of-the-art GUI agents when exposed to anomaly-rich environments, highlighting the need for robustness-aware learning. D-GARA is modular and extensible, supporting the seamless integration of new tasks, anomaly types, and interaction scenarios to meet specific evaluation goals. The codes and benchmark will be open source after the double-blind review.

D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies

Federated recommendation (FR) facilitates collaborative training by aggregating local models from massive devices, enabling client-specific personalization while ensuring privacy. However, we empirically and theoretically demonstrate that server-side aggregation can undermine client-side personalization, leading to suboptimal performance, which we term the aggregation bottleneck. This issue stems from the inherent heterogeneity across numerous clients in FR, which drives the globally aggregated model to deviate from local optima. To this end, we propose FedEM, which elastically merges the global and local models to compensate for impaired personalization. Unlike existing personalized federated recommendation (pFR) methods, FedEM (1) investigates the aggregation bottleneck in FR through theoretical insights, rather than relying on heuristic analysis; (2) leverages off-the-shelf local models rather than designing additional mechanisms to boost personalization. Extensive experiments on real-world datasets demonstrate that our method preserves client personalization during collaborative training, outperforming state-of-the-art baselines.

Breaking the Aggregation Bottleneck in Federated Recommendation: A Personalized Model Merging Approach

Graph-Level Anomaly Detection (GLAD) seeks to identify anomalous graphs within graph datasets, which has significant applications across diverse real-world fields. Most existing GLAD methods are trained in an unsupervised manner due to high costs for labeling, resulting in sub-optimal performance when compared to supervised methods. To fill this gap, we propose a $\textbf{D}$isentangled $\textbf{G}$eneration-Based $\textbf{P}$rototypical $\textbf{A}$lignment $\textbf{(DGPA)}$ method that extends graph-level anomaly detection to Few-Shot Unsupervised Domain Adaptation (FUDA) setting, aiming to identify anomalous graphs from a set of unlabeled graphs (target domain) by using partially labeled graphs from a different but related domain (source domain), which fulfills the practical requirement of transferring anomaly knowledge. This is specifically achieved through a dedicated Disentangled Sample Generation module, which addresses $\textbf{label scarcity}$ by generating faithful samples with disentangled representation learning grounded in Information Bottleneck principle, along with a Graph-based Prototypical Self-Supervision module, which alleviates $\textbf{domain shift}$ by encoding and aligning semantic structures in the shared latent space across domains in a self-supervised manner. Extensive experiments on five benchmark datasets reveal the effectiveness of our proposed DGPA.

Disentangled Generation-Based Prototypical Alignment for Few-Shot Unsupervised Domain Adaptation in Graph-Level Anomaly Detection

Scene Text Editing (STE) aims to naturally modify text in images while preserving visual consistency, the decisive factors of which can be divided into three parts, i.e., text style, text content, and background. Previous methods have struggled with incomplete disentanglement of editable attributes, typically addressing only one aspect—such as editing text content—thus limiting controllability and visual consistency. To overcome these limitations, we propose TripleFDS, a novel framework for STE with disentangled modular attributes, and an accompanying dataset called SCB Synthesis. 
SCB Synthesis provides robust training data for triple feature disentanglement by utilizing the "SCB Group", a novel construct that combines three attributes per image to generate diverse, disentangled training groups.
Leveraging this construct as a basic training unit, TripleFDS first disentangles triple features, ensuring semantic accuracy through inter-group contrastive regularization and preventing redundancy through intra-sample multi-feature orthogonality. In the synthesis phase, TripleFDS performs feature remapping to prevent "shortcut" phenomena during reconstruction and mitigate potential feature leakage.
Trained on 125,000 SCB Groups, TripleFDS achieves state-of-the-art image fidelity (SSIM of 44.54) and text accuracy (ACC of 93.58\%) on the mainstream STE benchmarks. Besides superior performance, the more flexible editing of TripleFDS supports new operations such as style replacement and background transfer.

TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing

Federated learning (FL) enables collaborative model training across distributed nodes without exposing raw data, but its decentralized nature makes it vulnerable in trust-deficient environments. Inference attacks may recover sensitive information from gradient updates, while poisoning attacks can degrade model performance or induce malicious behaviors. Existing defenses often suffer from high communication and computation costs, or limited detection precision. To address these issues, we propose LSHFed, a robust and communication-efficient FL framework that simultaneously enhances aggregation robustness and privacy preservation. At its core, LSHFed incorporates LSHGM, a novel gradient verification mechanism that projects high-dimensional gradients into compact binary representations via multi-hyperplane locality-sensitive hashing. This enables accurate detection and filtering of malicious gradients using only their irreversible hash forms, thus mitigating privacy leakage risks and substantially reducing transmission overhead. Extensive experiments demonstrate that LSHFed maintains high model performance even when up to 50% of participants are collusive adversaries, while achieving up to a 1000× reduction in gradient verification communication compared to full-gradient methods.

Downloads

Next from AAAI 2026

BRIC: Bridging Kinematic Plans and Physical Control at Test Time

Similar lecture

Object-Centric Data Synthesis for Category-level Object Detection (Student Abstract)