Singapore

Egocentric point tracking aims to localize points on object surfaces from a first-person perspective and serves as a critical step toward embodied intelligence. Recent methods rely on video input, tracking query points through feature matching across consecutive frames. 
However, these methods struggle in highly dynamic settings—a common challenge in first-person perspectives, where the head-mounted camera undergoes frequent and abrupt rotations, resulting in high angular velocities, motion blur, and large inter-frame displacements.
In contrast, event cameras capture motion at microsecond temporal resolution, naturally avoiding blur and delivering low-latency, high-fidelity cues crucial for egocentric point tracking.
Moreover, rapid egocentric motion disrupts local smoothness, breaking the assumption that spatially adjacent regions share similar motion. Event dynamics expose global motion trends, guiding coherent modeling and consistent feature flow.
Therefore, this paper proposes a mamba-based tracking framework that constructs feature modeling paths aligned with the dominant motion trend extracted from events, and modulates feature propagation along these paths based on local motion intensity, enhancing stability by suppressing unreliable signals and emphasizing consistent cues.
Additionally, a motion-adaptive suppression module enhances temporal robustness by adaptively suppressing correlation features based on motion intensity variations, mitigating the effects of intensity fluctuations and partial observability.
To facilitate research in this domain, a multimodal dataset named DVS-EgoPoints with both events and videos for egocentric point tracking is collected. Experiments on the DVS-EgoPoints dataset and a simulation benchmark demonstrate superior performance over state-of-the-art methods, especially under challenging motion and occlusion conditions.

AAAI 2026

E-MaT:Event-oriented Mamba for Egocentric Point Tracking

point tracking

event camera

computer 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

Visual Place Recognition (VPR) has advanced significantly with high-capacity foundation models like DINOv2, achieving remarkable performance. Nonetheless, their substantial computational cost makes deployment on resource-constrained devices impractical. In this paper, we introduce an efficient asymmetric VPR framework that incorporates a high-capacity gallery model for offline feature extraction with a lightweight query network for online processing. A key challenge in this setting is ensuring compatibility between these heterogeneous networks, which conventional approaches address through computationally expensive k-NN-based compatible training. To overcome this, we propose a geographical memory bank that structures gallery features using geolocation metadata inherent in VPR databases, eliminating the need for exhaustive k-NN computations. Additionally, we introduce an implicit embedding augmentation technique that enhances the query network to model feature variations despite its limited capacity. Extensive experiments demonstrate that our method not only significantly reduces computational costs but also outperforms existing asymmetric retrieval techniques, establishing a new aspect for VPR in resource-limited environments.

Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing

How far are deep models from real-world video anomaly understanding (VAU)? Current works typically emphasize on detecting unexpected occurrences deviated from normal patterns or comprehending anomalous events with interpretable descriptions. However, they exhibit only a superficial comprehension of real-world anomalies, with limited breadth in complex principles and subtle context that distinguish the anomalies from normalities, e.g., climbing cliffs with safety gear vs. without it. To this end, we introduce CueBench, the first of its kind Benchmark, devoted to Context-aware video anomalies within a Unified Evaluation framework. We comprehensively establish an event-centric hierarchical taxonomy that anchors two core event types: 14 conditional and 18 absolute anomaly events, defined by their refined semantics from diverse contexts across 174 scenes and 198 attributes. Based on this, we propose to unify and benchmark context-aware VAU with various challenging tasks across recognition, temporal grounding, detection, and anticipation. This also serves as a rigorous and fair probing evaluation suite for generative-discriminative as well as generalized-specialized vision-language models (VLMs). To address the challenges underlying CueBench, we further develop Cue-R1 based on R1-style reinforcement fine-tuning with verifiable, task-aligned, and hierarchy-refined rewards in a unified generative manner. Extensive results on CueBench reveal that, existing VLMs are still far from satisfactory real-world anomaly understanding, while our Cue-R1 surpasses these state-of-the-art approaches by over 24% on average.

CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World

Vision-Language Navigation (VLN) enables agents to navigate in complex environments by following natural language instructions grounded in visual observations. Although most existing work has focused on ground-based robots or outdoor Unmanned Aerial Vehicles (UAVs), indoor UAV-based VLN remains underexplored, despite its relevance to real-world applications such as inspection, delivery, and search-and-rescue in confined spaces. 
To bridge this gap, we introduce \textbf{IndoorUAV}, a novel benchmark and method specifically tailored for VLN with indoor UAVs. We begin by curating over 1,000 diverse and structurally rich 3D indoor scenes from the Habitat simulator. Within these environments, we simulate realistic UAV flight dynamics to collect diverse 3D navigation trajectories manually, further enriched through data augmentation techniques. Furthermore, we design an automated annotation pipeline to generate natural language instructions of varying granularity for each trajectory. This process yields over 16,000 high-quality trajectories, comprising the \textbf{IndoorUAV-VLN} subset, which focuses on long-horizon VLN. 
To support short-horizon planning, we segment long trajectories into sub-trajectories by selecting semantically salient keyframes and regenerating concise instructions, forming the \textbf{IndoorUAV-VLA} subset. 
Finally, we introduce \textbf{IndoorUAV-Agent}, a novel navigation model designed for our benchmark, leveraging task decomposition and multimodal reasoning.
We hope IndoorUAV serves as a valuable resource to advance research on vision-language embodied AI in the indoor aerial navigation domain.

IndoorUAV: Benchmarking Vision-Language UAV Navigation in Continuous Indoor Environments

While recent 3D head avatar creation methods attempt to animate facial dynamics, they often fail to capture personalized details, limiting realism and expressiveness.
To fill this gap, we present DipGuava (Disentangled and Personalized Gaussian UV Avatar), a novel 3D Gaussian head avatar creation method that successfully generates avatars with personalized attributes from monocular video.
DipGuava is the first method to explicitly disentangle facial appearance into two complementary components, trained in a structured two-stage pipeline that significantly reduces learning ambiguity and enhances reconstruction fidelity.
In the first stage, we learn a stable geometry-driven base appearance that captures global facial structure and coarse expression-dependent variations.
In the second stage, the personalized residual details not captured in the first stage are predicted, including high-frequency components and nonlinearly varying features such as wrinkles and subtle skin deformations.
These components are fused via dynamic appearance fusion that integrates residual details after deformation, ensuring spatial and semantic alignment.
This disentangled design enables DipGuava to generate photorealistic, identity-preserving avatars, consistently outperforming prior methods in both visual quality and quantitative performance, as demonstrated in extensive experiments.

DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video

Weakly supervised phrase localization (WSPL) aims to localize visual objects mentioned by given phrases, but learning without human-annotated bounding boxes. Previous works struggle in multi-object scenarios, where objects in the background often simultaneously appear with the target objects. To this end, we propose a Diffusion-Assisted PrOgressive learning framework (i.e., DAPO) for WSPL task in this paper.
Specifically, we score the difficulty of training samples based on the quantity of objects and the level of semantic alignment. These samples are then incorporated progressively during training, in an order by their difficulty scores. To address the sample imbalance problem, we propose a Generation-Assisted Tuning (GAT) method for the grounding network. First, to enrich the samples from few-object scenarios, we leverage Stable Diffusion (SD) to generate images with phrases. Second, we introduce an attention-driven scheme to guide SD's attention on mentioned objects. Finally, we design a diffusion-guided loss, which helps the grounding network learn the objects' layouts. Extensive experiments show that our DAPO framework outperforms the strong baselines on benchmark datasets. The source code will be publicly available on GitHub after the double-blind phase.

Diffusion-Assisted Progressive Learning for Weakly Supervised Phrase Localization

Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models' (LLMs) exceptional long-context understanding and reasoning abilities enable LLM-based ASR (LLM-ASR) to leverage historical context for recognizing conversational speech, which has a high degree of contextual relevance. However, existing conversational LLM-ASR methods use a fixed number of preceding utterances or the entire conversation history as context, resulting in significant ASR confusion and computational costs due to massive irrelevant and redundant information. This paper proposes a multi-modal retrieval-and-selection method named MARS that augments conversational LLM-ASR by enabling it to retrieve and select the most relevant acoustic and textual historical context for the current utterance. Specifically, multi-modal retrieval obtains a set of candidate historical contexts, each exhibiting high acoustic or textual similarity to the current utterance. Multi-modal selection calculates the acoustic and textual similarities for each retrieved candidate historical context and, by employing our proposed near-ideal ranking method to consider both similarities, selects the best historical context. Evaluations on the Interspeech 2025 Multilingual Conversational Speech Language Model Challenge dataset show that the LLM-ASR, when trained on only 1.5K hours of data and equipped with the MARS, outperforms the state-of-the-art top-ranking system trained on 179K hours of data.

Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR

With the rapid advancement of deep learning, drug target interaction (DTI) prediction has seen substantial performance enhancements. However, existing methodologies face a critical, yet unaddressed challenge, i.e., the $\textbf{Modality Reliability Gap}$. Such a gap arises from the unpredictable variance in the informativeness and reliability of 1D sequence versus 3D structural data across different drug-target pairs, critically limiting model robustness and domain generalization capabilities.
To overcome it, we introduce $\textbf{DrugCMF}$, a novel $\textbf{Drug}$-Target interaction prediction method via $\textbf{C}$onfidence-aware $\textbf{M}$ultimodal $\textbf{F}$usion framework designed specifically to bridge the Modality Reliability Gap. Specifically, the DrugCMF employs a four-stage approach: (1) it extracts rich features by utilizing four pre-trained models to obtain token-level embeddings from both 1D sequences and 3D structures. (2) it preserves modality informativeness by independently learning interaction patterns within each modality through a Token-level Interaction module. (3) it explicitly quantifies the reliability gap by employing a novel confidence estimation mechanism to dynamically learn weights for each modality. (4) it bridges the gap by using these confidence scores to guide a learnable cross-modal fusion module, adaptively fusing information from the most trustworthy source.
By methodically addressing the Modality Reliability Gap, DrugCMF significantly outperforms SOTA methods. Extensive experiments demonstrate its superior performance and robustness (Our Code is available in the supplementary materials).

Bridging the Modality Reliability Gap in Drug-Target Interaction Prediction via a Confidence-aware Multimodal Fusion Framework

Recent studies have shown that unsupervised graph contrastive learning (GCL) is vulnerable to adversarial attacks. Automatic adversarial augmentation techniques are proposed to improve both the effectiveness and robustness of GCL. Existing methods typically regard unsupervised contrastive loss as the adversarial goal, essentially aiming to maximize inter-view instance-wise discrepancies between adversarial and original views. However, such attacks overlook intra-view neighborhood inconsistency, which hinders the robustness of GCL models against local neighborhood noises, resulting in performance degradation on low-homophily graphs. To tackle this issue, we propose a novel adversarial contrastive paradigm, named Edge self-aDversarial Augmentation for Graph Contrastive Learning (EDA-GCL). We theoretically establish that the adversarial objective of the intra-view neighborhood is equivalent to maximizing the discrepancy between bidirectional edge features. Hence, we build our adversarial framework based on edge self-adversarial learning. It generates pairwise adversarial augmentations from the original view by learning distinct neighborhood connectivity structures. The learned pairwise adversarial views are utilized for GCL model training in the minimization stage. Notably, this edge-level adversarial approach reduces the computational complexity to the level of the edge number. Experiments on various graph tasks and complex noise scenarios demonstrate the superiority and robustness of our EDA-GCL.

Edge Self-Adversarial Augmentation Enhances Graph Contrastive Learning Against Neighborhood Inconsistency

This paper proposes a two-stage text-to-floorplan generation framework that combines the reasoning capability of Large Language Models (LLMs) with the generative power of diffusion models. In the first stage, we leverage a Chain-of-Thought (CoT) prompting strategy to guide an LLM in generating an initial layout, Layout-Init, from natural language descriptions, which ensures a user-friendly and intuitive design process. However, Layout-Init may lack precise geometric alignment and fine-grained structural details due to the inherent limitations of LLMs. To address this, in the second stage we propose a Dual-Noise Prior-Preserved Diffusion (DNPP-Diffusion) model to refine Layout-Init into a final floorplan that better adheres to physical constraints and user requirements. By combining LLMs and a dedicated refining model, our approach is able to generate high-quality floorplans without requiring large-scale domain-specific training data. Experimental results demonstrate its advantages in comparison with state of the art methods, and validate its effectiveness in home design applications. Our code will be made publicly available.

HouseTune: Two-Stage Floorplan Generation with LLM Assistance

Multimodal sentiment analysis (MSA) aims to infer emotional states by effectively integrating textual, acoustic, and visual modalities. Despite notable progress, existing multimodal fusion methods often neglect modality-specific structural dependencies and semantic misalignment, limiting their quality, interpretability, and robustness. To address these challenges, we propose a novel framework called the Structural-Semantic Unifier (SSU), which systematically integrates modality-specific structural information and cross-modal semantic grounding for enhanced multimodal representations. Specifically, SSU dynamically constructs modality-specific graphs by leveraging linguistic syntax for text and a lightweight, text-guided attention mechanism for acoustic and visual modalities, thus capturing detailed intra-modal relationships and semantic interactions. We further introduce a semantic anchor, derived from global textual semantics, that serves as a cross-modal alignment hub, effectively harmonizing heterogeneous semantic spaces across modalities. Additionally, we develop a multi-view contrastive learning objective that promotes discriminability, semantic consistency, and structural coherence across intra- and inter-modal views. Extensive evaluations on two widely-used benchmark datasets, CMU-MOSI and CMU-MOSEI, demonstrate that SSU consistently achieves state-of-the-art performance while significantly reducing computational overhead compared to prior methods. Comprehensive qualitative analyses further validate SSU’s interpretability and its ability to capture nuanced emotional patterns through semantically-grounded interactions.

Content not yet available

Next from AAAI 2026

Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing

Similar lecture

Motion-Aware Object Tracking via Motion and Geometry-Aware Cues