Singapore

The Mixture-of-Experts (MoE) architecture has emerged as a key enabler for scaling large language models (LLMs), empowering increased model capacity with minimal computational overhead through gating-based dynamic expert activation. However, due to the memory demands introduced by expert modules, MoE inference on resource-constrained devices is still challenging. Existing methods such as model compression and parameter offloading provide partial alleviation but often lead to reduced accuracy or increased latency. In this paper, we propose CasMoE, a general and efficient cascaded framework for accelerating MoE inference on resource-constrained devices. CasMoE employs a two-stage offline-online approach to facilitate efficient expert prefetching. In the offline stage, a parameterized Expert Activation Predictor (EAP) is introduced to accurately predict the corresponding expert activation from the incoming prompt. In the online stage, a non-parametric Expert Activation Matcher (EAM) supporting fast expert retrieval is then integrated with the EAP to form a cascade planner that operates independently of the MoE architecture, predicting activated experts for all MoE layers in a single pass prior to decoding. A gating mechanism is also incorporated to dynamically adjust the sensitivity of the EAM and EAP, enabling a flexible trade-off between inference efficiency and quality. Extensive experiments on diverse downstream tasks demonstrate CasMoE’s effectiveness in accelerating inference while preserving high accuracy.

AAAI 2026

CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained Devices

ml: mixture of experts (moe)

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

Long-Tailed Multi-Label Recognition (LTML) is a critical yet challenging task due to two core issues: the severe scarcity of training samples for rare "tail" classes, and the complex co-occurrence patterns among labels that often lead to biased models. To address this, we propose DP-VLPA, a novel Dual-Phase Visual-Language Pretraining and Adaptation framework. In the first phase, our Structured Tail-Aware Generation (STAG) module employs a Large Language Model (LLM) to create detailed descriptions that explicitly emphasize tail classes and their contextual relationships, providing a strong and less-biased feature foundation. In the second adaptation phase, we ensure this knowledge is applied effectively. A Dynamic Query Reweighting (DQR) mechanism forces the model to attend to crucial tail-class evidence. Simultaneously, a Co-occurrence-Aware (COA) loss explicitly teaches the model the statistical dependencies between labels, correcting for co-occurrence biases. Extensive experiments on VOC-LT and COCO-LT datasets demonstrate state-of-the-art performance, achieving mAP scores of 90.72% and 74.42% respectively - surpassing previous best methods by 2.84% and 8.23%. Our code is coming soon.

Dual-Phase Visual-Language Pretraining and Adaptation for Long-Tailed Multi-Label Recognition

Variational autoencoder (VAE)-based frameworks possess a natural advantage in modeling the shared and private information inherent in multimodal data. However, current models focus on improving the quality of shared representations from the reconstruction perspective, lacking explicit mechanisms to model their underlying semantic structure. In this paper, we propose the multimodal Gaussian mixture variational autoencoder with consistency regularizations, which introduces a Gaussian mixture prior over the shared latent space to enhance its semantic structure and encourage the formation of cluster-aware latent representations. To address the cross-modal inconsistency problem under missing modality conditions, we propose a cluster-guided regularization strategy that enforces the cross-modal consistency using the pseudo-category labels from unsupervised clustering. Additionally, we design a self-supervised contrastive regularization strategy to align semantically similar representations across modalities. Extensive experiments on MNIST-SVHN and MNIST-CDCB datasets demonstrate that our method significantly outperforms prior state-of-the-art models in generation, classification, and retrieval tasks.

Multimodal Gaussian Mixture Variational Autoencoder with Consistency Regularizations

Understanding the generalization behavior of in-context learning (ICL) in Transformers remains a fundamental challenge, as most existing theoretical analyses are based on the assumption that data are independently and identically distributed (i.i.d.), an assumption that often does not hold in practice. Motivated by the theoretical insight that ICL operates similarly to gradient-based optimization, we leverage the concept of gradient stability to establish generalization error bounds for ICL without making any distributional assumptions. Our analysis shows that two factors play a central role in ICL generalization: the number of demonstrations in the prompt and their distributional alignment with the query. In particular, increasing the number of demonstrations and improving their alignment with the query distribution lead to better generalization, even without any parameter tuning. Under mild conditions, we further prove that the generalization error can achieve the optimal convergence rate of $O(N^{-\frac{1}{2}})$, where $N$ is the number of demonstrations. Our empirical evaluations validate the effectiveness of our theoretical findings.

Towards Understanding In-Context Learning of Transformers Under Non-I.I.D. Scenarios

Irregularly sampled time series (ISTS), characterized by non-uniform time intervals with natural missingness, are prevalent in real-world applications. Existing approaches for ISTS modeling primarily rely on observed values to impute unobserved ones or infer latent dynamics. However, these methods overlook a critical source of learning signal: the reconstruction error inherently produced during model training. Such error implicitly reflects how well a model captures the underlying data structure and can serve as an informative proxy for unobserved values. To exploit this insight, we propose **iTimER**, a simple yet effective self-supervised pre-training framework for ISTS representation learning. iTimER models the distribution of reconstruction errors over observed values and generates pseudo-observations for unobserved timestamps through a mixup strategy between sampled errors and the last available observations. This transforms unobserved timestamps into noise-aware training targets, enabling meaningful reconstruction signals. A Wasserstein metric aligns reconstruction error distributions between observed and pseudo-observed regions, while a contrastive learning objective enhances the discriminability of learned representations. Extensive experiments on classification, interpolation, and forecasting tasks demonstrate that iTimER consistently outperforms state-of-the-art methods under the ISTS setting.

Beyond Observations: Reconstruction Error-Guided Irregularly Sampled Time Series Representation Learning

Remote sensing change detection (CD) has achieved remarkable progress in recent years. However, little attention has been paid to generalizable change detection (GCD) methods that can effectively generalize to unseen scenarios or domains beyond the training distribution. The major challenges in GCD arise from domain diversity and bitemporal domain shifts in remote sensing images, caused by variations in imaging platforms, acquisition times, geographic regions, and observed events. To tackle these challenges, we propose GenCD, a GCD framework built upon vision foundation models (VFMs). Specifically, GenCD introduces two key components: (1) a Low-Rank Exchange Adaptation (LREA) strategy of VFMs that aligns bitemporal representations while preserving the generalization capacity of VFMs on single-temporal inputs; and (2) a Token-Guided Feature Refinement (TGFR) mechanism that leverages an input-independent token as a guide to refine difference features, improving the discrimination between changed and unchanged regions. We conduct extensive cross-dataset evaluations on eight diverse datasets across three binary CD tasks: land cover, land use, and building-only CD. The results consistently demonstrate the superior generalization of GenCD over SoTA methods, highlighting its effectiveness in GCD.

Exploring Generalizable Remote Sensing Change Detection via Low-Rank Exchange Adaptation of Vision Foundation Model

With the rapid development of multimodal large language models (MLLMs), deploying them on low-resource devices remains challenging. Beyond the model size, long multimodal inputs cause substantial memory overhead in the KV cache, making efficient cache management critical. In this paper, we propose DAVID, a KV cache eviction strategy that adapts to the degree of modality fusion across layers. By analyzing the feature distributions of vision and text tokens, we observe low fusion in early layers and high fusion in deeper layers. Based on this observation, DAVID adopts a decoupled eviction strategy in shallow layers and a super-modal eviction strategy in deeper layers. To support this dynamic switching, we design a lightweight metric that quantifies cross-modal fusion and uses a threshold to determine which layers require decoupling. Experimental results show that DAVID achieves state-of-the-art performance on multiple benchmarks and offers a new perspective on KV cache eviction for MLLMs.

DAVID: Dual-stage Adaptive Vision-text Integrated Decoupling for Multimodal KV Cache Eviction

We propose Anomagic, a zero-shot anomaly generation method that produces semantically coherent anomalies without requiring any exemplar anomalies. By unifying both visual and textual cues through a crossmodal prompt encoding scheme, Anomagic leverages rich contextual information to steer an inpainting‐based generation pipeline. A subsequent contrastive refinement strategy enforces precise alignment between synthesized anomalies and their masks, thereby bolstering downstream anomaly detection accuracy. To facilitate training, we introduce AnomVerse, a collection of 12,987 anomaly–mask–caption triplets assembled from 13 publicly available datasets, where captions are automatically generated by multimodal large language models using structured visual prompts and template‐based textual hints. Extensive experiments demonstrate that Anomagic trained on AnomVerse can synthesize more realistic and varied anomalies than prior methods, yielding superior improvements in downstream anomaly detection. Furthermore, Anomagic can generate anomalies for any normal‐category image using user‐defined prompts, establishing a versatile foundation model for anomaly generation.

Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation

Reasoning-intensive ranking models built on large language models (LLMs) have made notable progress, but existing approaches often rely on very large-scale LLMs and explicit chain-of-thought reasoning, resulting in high computational cost and latency that limit real-world use. To address this, we propose TFRank, an efficient pointwise reasoning ranker based on small-scale LLMs. TFRank combines chain-of-thought data, multi-task training, and fine-grained score supervision to improve ranking performance. Furthermore, with a think-mode switch and pointwise format constraints, TFRank leverages explicit reasoning during training while delivering precise relevance scores for complex queries without generating reasoning chains at inference. Experiments show that TFRank achieves performance comparable to models with four times more parameters on the BRIGHT benchmark, and demonstrates strong competitiveness on the BEIR benchmark. Further analysis shows that TFRank achieves an effective balance between efficiency and performance, providing a practical solution for integrating advanced reasoning into real-world systems.

TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking

Garment-centric fashion image generation aims to synthesize realistic and controllable human models dressing a given garment, which has attracted growing interest due to its practical applications in e-commerce. The key challenges of the task lie in two aspects: (1) faithfully preserving the garment details, and (2) gaining fine-grained controllability over the model's appearance. 
Existing methods typically require performing garment deformation in the generation process, which often leads to garment texture distortions. Also, they fail to control the fine-grained attributes of the generated models, due to the lack of specifically designed mechanisms.
To address these issues, we propose FashionMAC, a novel diffusion-based deformation-free framework that achieves high-quality and controllable fashion showcase image generation. The core idea of our framework is to eliminate the need for performing garment deformation and directly outpaint the garment segmented from a dressed person, which enables faithful preservation of the intricate garment details.
Moreover, we propose a novel region-adaptive decoupled attention (RADA) mechanism along with a chained mask injection strategy to achieve fine-grained appearance controllability over the synthesized human models.
Specifically, RADA adaptively predicts the generated regions for each fine-grained text attribute and enforces the text attribute to focus on the predicted regions by a chained mask injection strategy, significantly enhancing the visual fidelity and the controllability. Extensive experiments validate the superior performance of our framework compared to existing state-of-the-art methods.

FashionMAC: Deformation-Free Fashion Image Generation with Fine-Grained Model Appearance Customization

Label distribution learning (LDL) is a novel paradigm that describe the samples by label distribution of a sample. However, acquiring LDL dataset is costly and time-consuming, which leads to the birth of incomplete label distribution learning (IncomLDL). All the previous IncomLDL methods set the description degrees of "missing" labels in an instance to 0, but remains those of other labels unchanged. This setting is unrealistic because when certain labels are missing, the degrees of the remaining labels will increase accordingly. We fix this unrealistic setting in IncomLDL and raise a new problem: LDL with hidden labels (HidLDL), which aims to recover a complete label distribution from a real-world incomplete label distribution where certain labels in an instance are omitted during annotation. To solve this challenging problem, we discover the significance of proportional information of the observed labels and capture it by an innovative constraint to utilize it during the optimization process. We simultaneously use local feature similarity and the global low-rank structure to reveal the mysterious veil of hidden labels. Moreover, we **theoretically** give the recovery bound of our method, proving the feasibility of our method in learning from hidden labels. Extensive recovery and predictive experiments on various datasets prove the superiority of our method to state-of-the-art LDL and IncomLDL methods. The code is available in the supplementary file.

Downloads

Next from AAAI 2026

Dual-Phase Visual-Language Pretraining and Adaptation for Long-Tailed Multi-Label Recognition

Similar lecture

FIRM-MoE:Fine-GrainedExpert Decomposition for Resource-Adaptive MoE Inference

.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

Dual-Phase Visual-Language Pretraining and Adaptation for Long-Tailed Multi-Label Recognition

Similar lecture

FIRM-MoE:Fine-GrainedExpert Decomposition for Resource-Adaptive MoE Inference

Downloads