Singapore

In the era of large-scale visual data, understanding collections of images is a challenging yet important task. To this end, we introduce ImageSet2Text, a novel method to automatically generate natural language descriptions of image sets. Based on large language models, visual-question answering chains, an external lexical graph, and CLIP-based verification, ImageSet2Text iteratively extracts key concepts from image subsets and organizes them into a structured concept graph. We conduct extensive experiments evaluating the quality of the generated descriptions in terms of accuracy, completeness, and user satisfaction. We also examine the method&#39;s behavior through ablation studies, scalability assessments, and failure analyses. Results demonstrate that ImageSet2Text combines data-driven AI and symbolic representations to reliably summarize large image collections for a wide range of applications.

AAAI 2026

ImageSet2Text: Describing Sets of Images Through Text

In the era of large-scale visual data, understanding collections of images is a challenging yet important task. To this end, we introduce ImageSet2Text, a novel method to automatically generate natural language descriptions of image sets. Based on large language models, visual-question answering chains, an external lexical graph, and CLIP-based verification, ImageSet2Text iteratively extracts key concepts from image subsets and organizes them into a structured concept graph. We conduct extensive experiments evaluating the quality of the generated descriptions in terms of accuracy, completeness, and user satisfaction. We also examine the method's behavior through ablation studies, scalability assessments, and failure analyses. Results demonstrate that ImageSet2Text combines data-driven AI and symbolic representations to reliably summarize large image collections for a wide range of applications.

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.

Graph Transformers (GTs), which simultaneously integrate message passing and self-attention mechanisms, have achieved promising empirical results in graph prediction tasks. However, the design of scalable and structure-aware node tokenization strategies has lagged behind other modalities. This gap becomes critical as the quadratic complexity of full attention renders GTs impractical on large-scale graphs. Recently, Spiking Neural Networks (SNNs), as brain-inspired models, provided an energy-saving scheme to convert changes of sequential input intensity into discrete spike-based representations through event-driven spiking neurons. Inspired by these characteristics, we propose **GT-SNT**, a linear-time Graph Transformer with Spiking Node Tokenization. By integrating random feature-based positional encoding with SNNs, the spiking node tokenizer extracts compact, structure-aware spike count embeddings as node tokens and mitigates the issue of *codebook collapse*. These tokens are used to dynamically reconstruct the codebook within a codebook-guided self-attention mechanism, enabling efficient global context aggregation with linear complexity. In experiments, we compare GT-SNT with other state-of-the-art baselines on node classification datasets ranging from small to large. Experimental results show that GT-SNT has achieved competitive performances on most datasets while maintaining up to **130×** faster inference speed compared to other GTs.

GT-SNT: A Linear-Time Transformer for Large-Scale Graphs via Spiking Node Tokenization

Accurately grounding regions of interest (ROIs) is critical for diagnosis and treatment planning in medical imaging. While multimodal large language models (MLLMs) combine visual perception with natural language, current medical-grounding pipelines still rely on supervised fine-tuning with explicit spatial hints, making them ill-equipped to handle the implicit queries common in clinical practice.
This work makes three core contributions. We first define **Unified Medical Reasoning Grounding (UMRG)**, a novel vision–language task that demands clinical reasoning and pixel-level grounding. Second, we release **U-MRG-14K**, a dataset of 14K samples featuring pixel-level masks alongside implicit clinical queries and reasoning traces, spanning 10 modalities, 15 super-categories, and 108 specific categories. Finally, we introduce **MedReasoner**, a modular framework that distinctly separates reasoning from segmentation: an MLLM reasoner is optimized with reinforcement learning, while a frozen segmentation expert converts spatial prompts into masks, with alignment achieved through format and accuracy rewards. MedReasoner achieves state-of-the-art performance on U-MRG-14K and demonstrates strong generalization to unseen clinical queries, underscoring the significant promise of reinforcement learning for interpretable medical grounding.

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision

In this work, we present EchoGen, a unified framework for layout-to-image generation and image grounding, capable of generating images with both accurate layout and high fidelity to the text description.(e.g., spatial relationship), and grounding the image robustly at the same time. We believe that image grounding possesses strong text and layout understanding abilities, which can compensate for the corresponding limitations in layout-to-image generation. At the same time, images generated from layouts exhibit high diversity in content, thereby enhancing the robustness of image grounding. Jointly training both tasks within a unified model can promote performance improvements for each. However, we identify that this joint training paradigm encounters several optimization challenges and results in restricted performance. To address these issues, we propose progressive training strategies. First, the Parallel Multi-Task Pre-training (PMTP) stage equips the model with basic abilities for both tasks, leveraging shared tokens to accelerate training. Next, the Dual Joint Optimization (DJO) stage exploits task duality to sequentially integrate the two tasks, enabling unified optimization. Finally, the Cycle RL stage eliminates reliance on visual supervision by using consistency constraints as rewards, significantly enhancing the model’s unified capabilities via the GRPO strategy. Extensive experiments demonstrate state-of-the-art results on both layout-to-image generation and image grounding benchmarks, and reveal clear synergistic gains from optimizing the two tasks together.

EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding

The Dense Audio-Visual Event Localization (DAVEL) task aims to temporally localize events in untrimmed videos that occur simultaneously in both the audio and visual modalities. This paper explores DAVEL under a new and more challenging weakly-supervised setting (W-DAVEL task), where only video-level event labels are provided and the temporal boundaries of each event are unknown. We address W-DAVEL by exploiting \textit{cross-modal salient anchors}, which are defined as reliable timestamps that are well predicted under weak supervision and exhibit highly consistent event semantics across audio and visual modalities. Specifically, we propose a \textit{Mutual Event Agreement Evaluation} module, which generates an agreement score by measuring the discrepancy between the predicted audio and visual event classes. Then, the agreement score is utilized in a \textit{Cross-modal Salient Anchor Identification} module, which identifies the audio and visual anchor features through global-video and local temporal window identification mechanisms. The anchor features after multimodal integration are fed into an \textit{Anchor-based Temporal Propagation} module to enhance event semantic encoding in the original temporal audio and visual features, facilitating better temporal localization under weak supervision. We establish benchmarks for W-DAVEL on both the UnAV-100 and ActivityNet1.3 datasets. Extensive experiments demonstrate that our method achieves state-of-the-art performance.

CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization

Universal medical image segmentation models have emerged as a promising paradigm due to their strong generalizability across diverse tasks, showing great potential for a wide range of clinical applications. This potential has been partly driven by the success of general-purpose vision models such as the Segment Anything Model (SAM), which has inspired the development of various fine-tuned variants for medical segmentation tasks. However, fine-tuned variants like MedSAM are trained on comparatively limited medical imaging data that often suffers from heterogeneity, scarce annotations, and distributional shifts. These challenges limit their ability to generalize across a wide range of medical segmentation tasks. In this regard, we propose MedSAMix, a training-free model merging method that integrates the strengths of both generalist models (e.g., SAM) and specialist models (e.g., MedSAM) for medical image segmentation.
In contrast to traditional model merging approaches that rely on manual configuration and often result in suboptimal outcomes, we propose a zero-order optimization method to automatically discover optimal layer-wise merging solutions. Furthermore, for clinical applications, we develop two regimes to meet the demand of domain-specificity and generalizability in different scenarios by single-task optimization and multi-objective optimization respectively. Extensive evaluations on 25 medical segmentation tasks demonstrate that MedSAMix effectively mitigates model bias and consistently improves performance in both domain-specific accuracy and generalization, achieving improvements of 6.67% on specialized tasks and 4.37% on multi-task evaluations.

MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation

Classifier-free guidance has become a staple for conditional generation with denoising diffusion models. However, a comprehensive understanding of classifier-free guidance is still missing. In this work, we carry out an empirical study to provide a fresh perspective on classifier-free guidance. Concretely, instead of solely focusing on classifier-free guidance, we trace back to the root, i.e., classifier guidance, pinpoint the key assumption for the derivation, and conduct a systematic study to understand the role of the classifier. On 1D data, we find that both classifier guidance and classifier-free guidance achieve conditional generation by pushing the denoising diffusion trajectories away from decision boundaries, i.e., areas where conditional information is usually entangled and is hard to learn. To validate this classifier-centric perspective on high-dimensional data, we assess whether a flow-matching postprocessing step that is designed to narrow the gap between a pre-trained diffusion model’s learned distribution and the real data distribution, especially near decision boundaries, can improve the performance. Experiments on various datasets verify our classifier-centric understanding.

Studying Classifier(-Free) Guidance from a Classifier-Centric Perspective

Wide-angle cameras, despite their popularity for con-
tent creation, suffer from distortion-induced facial stretch-
ing—especially at the edge of the lens—which degrades vi-
sual appeal. To address this issue, we propose a structure-
to-detail portrait correction model named ImagePC. It in-
tegrates the long-range awareness of transformer and multi-
step denoising of diffusion models into a unified framework,
achieving global structural robustness and local detail refine-
ment. Besides, considering the high cost of obtaining video
labels, we then repurpose ImagePC for unlabeled wide-angle
videos (termed VideoPC), by spatiotemporal diffusion adap-
tion with spatial consistency and temporal smoothness con-
straints. For the former, we encourage the denoised image to
approximate pseudo labels following the wide-angle distor-
tion distribution pattern, while for the latter, we derive rectifi-
cation trajectories with backward optical flows and smooth
them. Compared with ImagePC, VideoPC maintains high-
quality facial corrections in space and mitigates the potential
temporal shakes sequentially in blind scenarios. Finally, to
establish an evaluation benchmark and train the framework,
we establish a video portrait dataset with a large diversity in
people number, lighting conditions, and background. Experi-
ments demonstrate that the proposed methods outperform ex-
isting solutions quantitatively and qualitatively, contributing
to high-fidelity wide-angle videos with stable and natural por-
traits. The codes and dataset will be available.

Beyond Wide-Angle Images: Structure-to-Detail Video Portrait Correction via Unsupervised Spatiotemporal Adaptation

Visual Speech Recognition (VSR), commonly known as lipreading, enables the recognition of spoken text by analyzing lip visual features. Due to the subtlety of lip movements, its recognition is much harder than other motion recognition tasks. Existing VSR models face the challenge of viseme ambiguity when processing phonemes with similar pronunciations—multiple phonemes share similar viseme features, leading to a notable drop in lipreading accuracy. To address this issue, this study proposes a Linguistics-Knowledge Guided Progressive Disambiguation Network for Visual Speech Recognition(LinProVSR) framework. First, an ambiguous sample set is constructed based on linguistic knowledge to provide supervisory signals for the model's training. Then, a Progressive Contrastive Disambiguation Network (PCDN) is designed, which progressively enhances the model's ability to capture the subtle viseme differences corresponding to similar phonemes through viseme-phoneme contrastive disambiguation in the encoding stage and text contrastive disambiguation in the decoding stage. Furthermore, we pioneer the Ambiguous Word Error Rate (AWER) metric specifically for evaluating recognition of phonetically ambiguous text, and verify the effectiveness of the proposed method on multiple public datasets, achieving a significant breakthrough especially in distinguishing visually similar phonemes.

LinProVSR: Linguistics-Knowledge Guided Progressive Disambiguation Network for Visual Speech Recognition

Clustering is a fundamental tool that has garnered significant interest across a wide range of applications including text analysis. To improve clustering accuracy, many researchers have proposed incorporating background knowledge, typically in the form of must‑link and cannot‑link constraints, to guide the clustering process.
With the recent advent of large language models (LLMs), there is growing interest in improving clustering quality through LLM-based automatic constraint generation. In this paper, we propose a novel constraint‑generation approach that reduces resource consumption by generating constraint sets rather than using traditional pairwise constraints. This improves both query efficiency and constraint accuracy compared to state‑of‑the‑art methods. We further introduce a constrained clustering algorithm tailored to the characteristics of LLM-generated constraints. Our method incorporates a confidence threshold and a penalty mechanism to address potentially inaccurate constraints. We evaluate our approach on five text datasets, considering both the cost of constraint generation and overall clustering performance. The results show that our method achieves clustering accuracy comparable to the state-of-the-art algorithms while reducing the number of LLM queries by more than 20 times.

Optimized Algorithms for Text Clustering with LLM-Generated Constraints

The success of large language models (LLMs) in cognitive tasks prompts the question of whether their next-token prediction (NTP) paradigm can be adapted to model physiological signals from wearable devices. A key target for this adaptation is photoplethysmography (PPG), the most prevalent sensing modality in consumer wearables for non-invasive monitoring of diverse physiological conditions. Unlike in NLP, where NTP aligns with generative objectives, physiological signal analysis involves fundamentally different tasks, such as continuous parameter estimation (regression) and discrete state recognition (classification). This disparity creates a semantic mismatch between the pre-training paradigm and the downstream tasks. To bridge this gap, we propose PPGPT, the first foundation model that reformulates NTP into next-feature token prediction (NFTP), learning hierarchical feature transition probabilities to unify pre-training and downstream objectives. PPGPT features a novel dual-stream encoder that generates feature tokens by jointly modeling temporal dynamics and local-global morphological patterns. The model is developed using a two-stage training framework: it is first pre-trained on a large-scale mixed dataset of 1.6 billion data points and then validated on our newly released BioMTL benchmark, which includes data from 172 subjects over 285 days across seven different tasks. Extensive experiments show that PPGPT significantly outperforms competing methods, achieving a 16.5\% improvement in F1-score and a 25.9\% reduction in Mean Absolute Error (MAE). Furthermore, the model demonstrates robust few-shot learning capabilities.

Downloads

Next from AAAI 2026

GT-SNT: A Linear-Time Transformer for Large-Scale Graphs via Spiking Node Tokenization

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

GT-SNT: A Linear-Time Transformer for Large-Scale Graphs via Spiking Node Tokenization

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads