Singapore

Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and reasoning and allow models to exploit global context, failing to rigorously evaluate true causal and stepwise reasoning. We present CausalStep, a benchmark designed for explicit stepwise causal reasoning in videos. CausalStep segments videos into causally linked units and enforces a strict stepwise question-answer (QA) protocol, requiring sequential answers and preventing shortcut solutions. Each question includes carefully constructed distractors based on error type taxonomy to ensure diagnostic value. The benchmark features 100 videos across six categories and 1,852 multiple-choice QA pairs. We introduce seven diagnostic metrics for comprehensive evaluation, enabling precise diagnosis of causal reasoning capabilities. Experiments with leading proprietary and open-source models, as well as human baselines, reveal a significant gap between current models and human-level stepwise reasoning. CausalStep provides a rigorous benchmark to drive progress in robust and interpretable video reasoning.

AAAI 2026

CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos

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.

Generalized Category Discovery (GCD) aims to classify unlabeled data by leveraging knowledge from labeled categories.
While existing methods have achieved remarkable progress, they often treat images as flat feature sets, neglecting the intrinsic hierarchy: where key objects dominate meaning and backgrounds serve as context. For instance, in images of a dog either standing on grass or lying on a bed, the dog remains the central semantic element, whereas the background varies. Motivated by this, we propose LEArning Intrinsic Hierarchy (LEAH), a lightweight plug-and-play module designed to model hierarchical structure within images. LEAH consists of two components: a pruner that filters task-irrelevant tokens to extract key objects, and a constructor that embeds key objects and full images into hyperbolic space using adaptive entailment cones to capture compositional semantics. LEAH can be easily integrated into existing GCD frameworks with minimal modification. When applied to SimGCD, it achieves up to 13.2\% accuracy improvement on fine-grained benchmarks, demonstrating its effectiveness in discovering subtle inter-class differences through hierarchical modeling.

Learning Intrinsic Hierarchy for Generalized Category Discovery

Standpoint logics offer unified modal logic-based formalisms for representing multiple heterogeneous viewpoints. At the same time, many non-monotonic reasoning frameworks can be naturally captured using modal logics — in particular using the modal logic S4F. In this work, we propose a novel formalism called S4F Standpoint Logic, which generalises both S4F and standpoint propositional logic and is therefore capable of expressing multi-viewpoint, non-monotonic semantic commitments. We define its syntax and semantics and analyze its computational complexity, obtaining the result that S4F Standpoint Logic is not computationally harder than its constituent logics, whether in monotonic or non-monotonic form. We also outline mechanisms for credulous and sceptical acceptance and illustrate the framework with an example.

Non-Monotonic S4F Standpoint Logic

Weakly supervised semantic segmentation (WSSS) suffers from an inherent mismatch between coarse image-level annotations and dense pixel-level predictions. To bridge this gap, existing methods primarily focus on generating refined class activation maps (CAM) as pseudo-labels. However, we argue that this focus is insufficient as it overlooks a critical component: the segmentation decoder. The decoder is typically trained through superficial alignment of predictions with pseudo-labels in the logit space. Given the noisy nature of such labels, this naive supervision leads to error accumulation and limits performance. To address this, we propose an Uncertainty-Guided Reliable Learning (UGRL) framework that exerts dual control to reshape the learning process, achieving robust supervision that escapes the CAM shadow. The cornerstone of UGRL is a prototype-driven uncertainty modeling module that estimates the reliability of class-wise supervision. The modeled uncertainty enables two synergistic control mechanisms. First, it adaptively modulates classification and segmentation losses, encouraging the model to learn from more trustworthy signals. Second, it guides the structuring of the decoder’s feature space. Rather than relying solely on superficial alignment, UGRL enforces deeper representation alignment by applying contrastive learning on reliable pixels. This enables rich semantic transfer to fine-grained segmentation details. Extensive experiments on PASCAL VOC and MS COCO demonstrate that our method surpasses other state-of-the-art WSSS methods. Code is available at https://anonymous.4open.science/r/UGRL-70C3/.

Escaping the CAM Shadow: Uncertainty-Guided Reliable Learning for Weakly Supervised Semantic Segmentation

LiDAR-based 3D object detection models often struggle to generalize to real-world environments due to limited object diversity in existing datasets. To tackle it, we introduce the first generalized cross-domain few-shot (GCFS) task in 3D object detection, aiming to adapt a source-pretrained model to both common and novel classes in a new domain with only few-shot annotations. We propose a unified framework that learns stable target semantics under limited supervision by bridging 2D open-set semantics with 3D spatial reasoning. Specifically, an image-guided multi-modal fusion module injects transferable 2D semantic cues into the 3D detection pipeline via vision-language models, while a physically-aware box search enhances 2D-to-3D alignment via LiDAR priors. To capture class-specific semantics from sparse data, we further introduce contrastive-enhanced prototype learning, which encodes few-shot instances into discriminative semantic anchors and stabilizes representation learning. Extensive experiments on four GCFS benchmarks demonstrate the effectiveness and generality of our approach in realistic deployment settings. The code will be publicly available.

From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning

With the growing adoption of Machine-Learning-As-A-Service (MLaaS), Private Inference (PI) has emerged as a promising solution to address its security concerns through cryptographic techniques. However, nonlinear operations in neural networks contribute the majority of the computational and communication overhead in PI. Existing studies mainly focus on optimizing and reducing the number of ReLU activations in neural networks,but traditional pruning methods may mistakenly remove ReLUs that are critical for maintaining model accuracy. To accurately evaluate the importance of ReLU in the network, we propose ReLUPruner, a method that uses Taylor expansion to accurately quantify the impact on loss before and after ReLU replacement. Furthermore, we establish a hierarchical importance metric to guide layer-wise ReLU budget allocation and adopt a progressive pruning strategy to dynamically adjust the pruning rate of each layer according to the training progress. Extensive experiments on various models and datasets show that ReLUPruner achieves a good balance between ReLU budget and model accuracy, with a 1.89\% improvement over the existing SOTA method 1.89\% (90.12\%, 12.9k ReLU budget, CIFAR10), 3.62\% (77.9\% 50k ReLU budget, CIFAR100) and 2.66\% (56.13\%,30k ReLU budget, Tiny-ImageNet), while achieving superior accuracy even without additional fine-tuning stage.

ReLUPruner: Rethinking ReLU Importance with Taylor Expansion for Efficient Private Inference

Precise detection of driver mental fatigue is critical for reducing traffic accidents and enhancing road safety. Compared with vision-based detection—which is susceptible to illumination and occlusion—multimodal physiological‑signal-based approaches integrate complementary information from diverse biosignals, delivering more faithful and objective fatigue assessments. However, adverse factors such as motion artifacts and environmental noise induce ceaseless deterioration to physiological signals, which markedly degrade the performance of existing multimodal fusion methods. To address this challenge, we propose Multimodal Uncertainty-based Self-driven Evolution, MUSE, reallocating modality contributions in real time via overall uncertainty minimization, thereby enabling efficient collaborative fusion of multi‐source predictions. Theoretically, MUSE guarantees a provably bounded cumulative error, and its generalization error approaches the Bayesian‑optimal fusion as iterations progress. Operating in a closed loop without labels or manual recalibration, MUSE presents superior suitability for real‑world driving scenarios compared to supervised algorithms. On the large‑scale driving fatigue dataset SEED‑VIG, MUSE outperforms existing models in both classification (92.2\% accuracy) and regression tasks, substantiating its robustness and practicality as a promising driving fatigue detection solution.

MUSE: Multimodal Uncertainty-Based Self-Driven Evolution for Robust Physiological-Signal–Based Driver Fatigue Detection

Gaussian Processes (GPs), as a nonparametric learning method, offer flexible modeling capabilities and calibrated uncertainty quantification for function approximations. Additionally, GPs support online learning by efficiently incorporating new data with polynomial-time computation, making them well-suited for safety-critical dynamical systems that require rapid adaptation. However, the inference and online updates of exact GPs, when processing streaming data, incur cubic computation time and quadratic storage memory complexity, limiting their scalability to large datasets in real-time settings. In this paper, we propose a streaming kernel-induced progressively generated expert framework of Gaussian processes (SkyGP) that addresses both computational and memory constraints by maintaining a bounded set of experts, while inheriting the learning performance guarantees from exact Gaussian processes. Furthermore, two SkyGP variants are introduced, each tailored to a specific objective, either maximizing prediction accuracy (SkyGP-Dense) or improving computational efficiency (SkyGP-Fast). The effectiveness of SkyGP is validated through extensive benchmarks and real-time control experiments demonstrating its superior performance compared to state-of-the-art approaches.

Streaming Generated Gaussian Process Experts for Online Learning and Control

The application of message-passing Graph Neural Networks has been a breakthrough for important network science problems. However, the competitive performance often relies on using handcrafted structural features as inputs, which increases computational cost and introduces bias into the otherwise purely data-driven network representations. Here, we eliminate the need for handcrafted features by introducing an attention mechanism and utilizing message-iteration profiles, in addition to an effective algorithmic approach to generate a structurally diverse training set of small synthetic networks. Thereby, we build an expressive message-passing framework and use it to efficiently solve the NP-hard problem of Network Dismantling, virtually equivalent to vital node identification, with significant real-world applications. Trained solely on diversified synthetic networks, our proposed model—MIND: Message Iteration Network Dismantler—generalizes to large, unseen real networks with millions of nodes, outperforming state-of-the-art network dismantling methods. Increased efficiency and generalizability of the proposed model can be leveraged beyond dismantling in a range of complex network problems.

Learning Network Dismantling Without Handcrafted Inputs

Large Reasoning Models (LRMs) achieve promising results on complex reasoning tasks but remain susceptible to hallucinations. Existing hallucination detection methods based on Large Language Models (LLMs) often focus solely on final answers, overlooking inconsistencies between the answer and reasoning process. This limitation reduces their ability to detect hallucinations during inference. Moreover, training-free approaches lack mechanisms for confidence estimation, resulting in an unquantified detection output. In contrast, training-based methods can provide fine-grained assessments but often neglect the self-correction capability of LRMs, where earlier errors may be corrected in subsequent steps, leading to inaccurate hallucination detection. To address these challenges, we propose \textbf{ConfFuse}, a unified framework that fuses global and local confidence scores for hallucination detection. A Global Hallucination Detection Model (GHDM) is trained using Direct Preference Optimization (DPO) to assess hallucinations at the level of entire reasoning chains, yielding global confidence estimates. Simultaneously, a Process Reward Model (PRM) estimates step-wise confidence scores to capture local logical flaws. A weighted fusion strategy combines the global confidence score with the minimum local score to jointly reflect overall reasoning consistency and local soundness. Experimental evaluations demonstrate that ConfFuse surpasses Qwen3-1.7B and Qwen3-8B by up to 11.86\% and 5.46\% in F1 score on in-distribution datasets, and achieves average improvements of 4.65\% and 2.80\% on out-of-distribution datasets. These results verify the effectiveness and generalizability of the proposed framework.

Global-Local Confidence Fusion for Hallucination Detection in Mathematical Reasoning Task

Deep learning has demonstrated expert-level performance in melanoma classification, positioning it as a powerful tool in clinical dermatology. However, model opacity and the lack of interpretability remain critical barriers to clinical adoption, as clinicians often struggle to trust the decision-making processes of black-box models. To address this gap, we present a Cross-Modal Explainable Framework (CMEF) that leverages contrastive learning as the core mechanism for achieving interpretability. Specifically, CMEF maps clinical criteria for melanoma diagnosis—namely Asymmetry, Border, and Color (ABC)—into the Vision Transformer embedding space using dual projection heads, thereby aligning clinical semantics with visual features. The aligned representations are subsequently translated into structured textual explanations via natural language generation, creating a transparent link between raw image data and clinical interpretation. Experiments on public datasets demonstrate 92.79% accuracy and an AUC of 0.961, along with significant improvements across multiple interpretability metrics. Qualitative analyses further show that the spatial arrangement of the learned embeddings aligns with clinicians’ application of the ABC rule, effectively bridging the gap between high-performance classification and clinical trust.

Downloads

Next from AAAI 2026

Learning Intrinsic Hierarchy for Generalized Category Discovery

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

Learning Intrinsic Hierarchy for Generalized Category Discovery

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads