Singapore

Machine learning has tremendously benefited from graphics processing units (GPUs) to accelerate training and inference by several orders of magnitude. However, this success has not been replicated in general and exact combinatorial optimization. Our key contribution is to propose the first general-purpose discrete constraint programming solver fully implemented on GPU. It is based on integer interval bound propagation and backtracking search. The two main ingredients are (1) ternary constraint network optimized for GPU architectures, and (2) an on-demand subproblems generation strategy. Our constraint solving algorithm is significantly simpler than those found in optimized CPU constraint solvers, yet is competitive with sequential solvers in the MiniZinc 2024 challenge.

AAAI 2026

A GPU-based Constraint Programming Solver

parallel propagation

parallel search

constraint programming

combinatorial optimization

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

technical paper

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.

Environmental modeling faces critical challenges in predicting ecosystem dynamics across unmonitored regions due to limited and geographically imbalanced observation data. This challenge is compounded by spatial heterogeneity, causing models to learn spurious patterns that fit only local data. Unlike conventional domain generalization, environmental modeling must preserve invariant physical relationships and temporal coherence during augmentation. In this paper, we introduce Generalizable Representation Enhancement via Auxiliary Transformations (GREAT), a framework that effectively augments available datasets to improve predictions in completely unseen regions. GREAT guides the augmentation process to ensure that the original governing processes can be recovered from the augmented data, and the inclusion of the augmented data leads to improved model generalization. Specifically, GREAT learns transformation functions at multiple layers of neural networks to augment both raw environmental features and temporal influence. They are refined through a novel bi-level training process that constrains augmented data to preserve key patterns of the original source data. We demonstrate GREAT's effectiveness on stream temperature prediction across six ecologically diverse watersheds in the eastern U.S., each containing multiple stream segments. Experimental results show that GREAT significantly outperforms existing methods in zero-shot scenarios. This work provides a practical solution for environmental applications where comprehensive monitoring is infeasible.

GREAT: Generalizable Representation Enhancement via Auxiliary Transformations for Zero-Shot Environmental Prediction

We introduce Daytime-Memory Guided Nighttime Image Enhancement (DMGNIE) framework, the first framework that turns long-running daytime surveillance videos of a single intersection into persistent “daytime memory” to guide nighttime image enhancement in traffic scenes. Our key insight is simple yet powerful: for a static scene, perfectly exposed daytime frames are, pixel-for-pixel, high-quality illumination prior for the same location under extreme low-light. Due to the complex lighting conditions in real-world traffic scenes, existing low-light image enhancement (LLIE) methods suffer from issues such as overexposure in highlight regions and noise amplification in low-light condition regions, which degrades the performance of downstream computer vision tasks. DMGNIE tackles these issues in two steps: (1) SegBMN, a semantic prior-based background modeling network, distills a clean, static daytime background from hours of video as scene prior guiding the enhancement of nighttime image; (2) a Foreground Localization-Guided Contrastive Learning module avoid the interference from the background prior with foreground objects during the guidance by maximizing the differences between foreground and background features. Finally, We conduct comprehensive experiments on real traffic surveillance datasets of two cities to evaluate the effectiveness. And the experimental results demonstrate that DMGNIE outperforms state-of-the-art baselines and achieves superior performance in challenging low-light conditions.

DMGINE: Day-Memory Guided Nighttime Image Enhancement for Dynamic Traffic Scenes

Deep learning has shown strong performance in time series forecasting tasks. However, issues such as missing values and anomalies in sequential data hinder its further development in prediction tasks. Previous research has primarily focused on extracting feature information from sequence data or addressing these suboptimal data as positive samples for knowledge transfer. A more effective approach would be to leverage these non-ideal negative samples to enhance event prediction. In response, this study highlights the advantages of non-ideal negative samples and proposes the IdealTSF framework, which integrates both ideal positive and negative samples for time series forecasting. IdealTSF consists of three progressive steps: pretraining, training, and optimization. It first pretrains the model by extracting knowledge from negative sample data, then transforms the sequence data into ideal positive samples during training. Additionally, a negative optimization mechanism with adversarial disturbances is applied. Extensive experiments demonstrate that negative sample data unlocks significant potential within the basic attention architecture for time series forecasting. Therefore, IdealTSF is particularly well-suited for applications with noisy samples or low-quality data.

IdealTSF: Can Non-Ideal Data Contribute to Enhancing the Performance of Time Series Forecasting Models?

Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning utilizing rule-based rewards. However, the explicit reasoning process has not yet yielded substantial benefits for audio question answering, and effectively leveraging deep reasoning remains an open challenge, with LALMs still falling short of achieving human-level auditory-language reasoning.
To address these limitations, we propose Audio-Thinker, a reinforcement learning framework designed to enhance the reasoning capabilities of LALMs through improved adaptability, consistency, and effectiveness. Our approach introduces an adaptive think accuracy reward, enabling the model to adjust its reasoning strategies based on task complexity. Furthermore, we incorporate an external reward model to evaluate the overall consistency and quality of the reasoning process, complemented by think-based rewards that assist the model in distinguishing between valid and flawed reasoning paths during training. Experimental results demonstrate that Audio-Thinker models outperform existing reasoning-oriented LALMs across various benchmark tasks, exhibiting superior reasoning and generalization capabilities.

Audio-Thinker: Guiding Large Audio Language Model When and How to Think via Reinforcement Learning

We precisely characterize the expressivity of computable Recurrent Graph Neural Networks (recurrent GNNs). We prove that recurrent GNNs with finite-precision parameters, sum aggregation, and ReLU activation, can compute any graph algorithm that respects the natural message-passing invariance induced by the Color Refinement (or Weisfeiler-Leman) algorithm. While it is well known that the expressive power of GNNs is limited by this invariance [Morris et al., AAAI 2019; Xu et al., ICLR 2019], we establish that recurrent GNNs can actually match this limit. This is in contrast to non-recurrent GNNs, which have the power of Weisfeiler-Leman only in a very weak, "non-uniform", sense where each graph size requires a different GNN to compute with. Our construction introduces only a polynomial overhead in both time and space.
Furthermore, we show that by incorporating random initialization, for connected graphs recurrent GNNs can express all graph algorithms. In particular, any polynomial-time graph algorithm can be emulated on connected graphs in polynomial time by a recurrent GNN with random initialization.

Repetition Makes Perfect: Recurrent Graph Neural Networks Match Message Passing Limit

Vertical Federated Learning (VFL) enables multiple clients with feature-partitioned data to collaboratively train models while preserving privacy by transmitting embeddings instead of raw data. However, such embeddings can still expose sensitive attributes (e.g., gender or race) unrelated to the target task, making them vulnerable to attribute inference attacks. Most existing privacy strategies may provide extra protection, but at the cost of reduced accuracy and excessive privacy budget. In this paper, we propose a novel equilibrium-driven VFL framework with selective privacy protection for sensitive attributes that are difficult to isolate from embeddings, thereby enhancing local privacy with minor accuracy compromise. We introduce two key innovations: (1) a NashCoder, which incorporates a surrogate head to jointly optimize accuracy and privacy; (2) an adaptive decomposition strategy based on Shapley values, which dynamically decomposes the global objective for distributed optimization from an equilibrium perspective. We theoretically analyze our framework and empirically evaluate it on three public datasets against five baselines, demonstrating significant improvements in the accuracy-privacy trade-off under various privacy settings. Extensive experimental results support our theoretical analysis.

Equilibrium-Driven Vertical Federated Learning with Selective Privacy Protection

The "Internet of Agents" (IoA) paradigm, where complex goals are met via large-scale, dynamic Agent-to-Agent (A2A) interactions, creates a vast attack surface for covert channels hidden within seemingly normal activities. Existing security models ignore this hidden communication, and traditional steganography, which generates static carriers, is ill-suited for the interactive, event-driven nature of A2A dialogues. To address this critical gap, we make three contributions. First, we establish a formal threat model for interactive agent ecosystems, defining two hierarchical security properties: statistical imperceptibility (IND-STAT) for entire communication traces and the stronger intention imperceptibility (IND-INT) for individual agent events. Second, we propose the Covert Communication Agent Protocol $\Pi_{\text{CCAP}}$ as a practical instantiation of our model. Third, we comprehensively evaluate $\Pi_{\text{CCAP}}$ across the critical dimensions of capacity, robustness, and imperceptibility, demonstrating its ability to facilitate reliable communication while satisfying our rigorous security requirements. Our work provides a foundational framework to analyze and defend against this new class of threats in the IoA.

Whispering Agents: A Event-Driven Covert Communication Protocol for the Internet of Agents

Flow matching and diffusion bridge models have emerged as leading paradigms in generative speech enhancement, modeling stochastic processes between paired noisy and clean speech signals based on principles such as flow matching, score matching, and Schrödinger bridge. In this paper, we present a framework that unifies existing flow and diffusion bridge models by interpreting them as constructions of Gaussian probability paths with varying means and variances between paired data. Furthermore, we investigate the underlying consistency between the training/inference procedures of these generative models and conventional predictive models. Our analysis reveals that each sampling step of a well-trained flow or diffusion bridge model optimized with a data prediction loss is theoretically analogous to executing predictive speech enhancement. Motivated by this insight, we introduce an enhanced bridge model that integrates an effective probability path design with key elements from predictive paradigms, including improved network architecture, tailored loss functions, and optimized training strategies. Experiments on denoising and dereverberation tasks demonstrate that the proposed method outperforms existing flow and diffusion baselines with fewer parameters and reduced computational complexity. The results also highlight that the inherently predictive nature of this generative framework imposes limitations on its achievable upper-bound performance.

Rethinking Flow and Diffusion Bridge Models for Speech Enhancement

Artificial intelligence holds great promise for clinical decision-making, yet developing models capable of complex diagnostic reasoning across diverse, real-world settings remains a major challenge. Existing benchmarks typically focus on single-image, single-turn tasks and fail to capture the longitudinal, multimodal nature of clinical workflows. We introduce MedAtlas, a new benchmark for evaluating large language models (LLMs) on realistic medical reasoning tasks that are multi-round, multi-modal, and multi-task. MedAtlas supports four key tasks: open-ended QA, closed QA, multi-image reasoning, and multi-turn multimodal multiple-choice QA. Each case features sequential diagnostic stages with diverse imaging modalities (e.g., CT, MRI, PET, ultrasound, X-ray) interleaved with textual histories and dialogue turns, requiring integrated reasoning across images and clinical text. Beyond answer-level supervision, MedAtlas provides structured gold-standard labels for clinical findings and five core medical knowledge aspects: pathophysiology, epidemiology, manifestations, imaging, and treatment. To capture diagnostic fidelity, we propose two new evaluation metrics: Stage Chain Accuracy and Error Propagation Suppression. Benchmarking a range of general and domain-specific models reveals substantial performance gaps in multi-stage clinical reasoning. MedAtlas offers a challenging testbed to advance the development of robust and trustworthy medical AI.

MedAtlas: Evaluating LLMs for Multi-Round, Multi-Task Medical Reasoning Across Diverse Imaging Modalities and Clinical Text

We present HI-SLAM2, a geometry-aware Gaussian SLAM system
that achieves fast and accurate monocular scene
reconstruction using only RGB input. Existing Neural SLAM
or 3DGS-based SLAM methods often trade off between
rendering quality and geometry accuracy, our research
demonstrates that both can be achieved simultaneously with
RGB input alone. The key idea of our approach is to enhance
the ability for geometry estimation by combining
easy-to-obtain monocular priors with learning-based dense
SLAM, and then using 3D Gaussian splatting as our core map
representation to efficiently model the scene. Upon loop
closure, our method ensures on-the-fly global consistency
through efficient pose graph bundle adjustment and instant
map updates by explicitly deforming the 3D Gaussian units
based on anchored keyframe updates. Furthermore, we
introduce a grid-based scale alignment strategy to maintain
improved scale consistency in prior depths for finer depth
details. Through extensive experiments on Replica, ScanNet,
Waymo Open, ETH3D SLAM and ScanNet++ datasets, we
demonstrate significant improvements over existing Neural
SLAM methods and even surpass RGB-D-based methods in both
reconstruction and rendering quality. The project page and
source code are available at https://hi-slam2.github.io/.

Downloads

Next from AAAI 2026

GREAT: Generalizable Representation Enhancement via Auxiliary Transformations for Zero-Shot Environmental Prediction

Similar lecture

A Variant of Concurrent Constraint Programming on GPU

.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

GREAT: Generalizable Representation Enhancement via Auxiliary Transformations for Zero-Shot Environmental Prediction

Similar lecture

A Variant of Concurrent Constraint Programming on GPU

Downloads