Singapore

Accurate identification of mosquito species is crucial for controlling vector-borne diseases, yet visual or acoustic methods alone are often insufficient. We propose a multimodal deep-learning framework that combines high-resolution images with wingbeat audio using a SwinV2 vision transformer and an Audio Spectrogram Transformer, thereby capturing complementary cues. On a six-species dataset, it achieves 97% accuracy, comparable to the best single-modality baseline, and is designed to improve robustness under noise or environmental variation, demonstrating the value of integrating multiple data sources for reliable mosquito surveillance.

AAAI 2026

WingBeats and Snapshots: Fusing Sound and Vision for Mosquito Monitoring (Student Abstract)

acoustic analysis

mosquito species identification

multimodal fusion

computer vision

deep learning

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

If you see this page it means you are not logged in or registered.

If you feel like you see this message by mistake please make sure you are logged in with the email you registered with.

If you are not registered yet, you can do so [**here**](https://www.sebiology.org/events/seb-conference-prague-2024/registration2024.html). 

Please login or register

SEB Conference 2024

SEB’s Annual Conference is celebrated for creating the perfect composition of research, new discoveries and collaborative connections. Be creative and innovative by exchanging ideas and knowledge with masters of biology from all over the world.

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.

Anime hair design is crucial but challenging, as it conveys personality and emotion through stylized geometry and layered structure. In this work, we propose a sketch-guided approach for intuitive control of multimodal diffusion transformers (MMDiT) to generate semantically consistent anime hairstyles. We adopt a wisp-level flowline input integrated with a fine-tuned MMDiT to transfer hairstyles while preserving character identity. We believe that this fine-grained sketch control within the MMDiT framework may offer a promising path for structured anime hair editing.

Sketch-Guided Anime Hair Editing Using Multimodal Diffusion Transformer (Student Abstract)

Diffusion models conditioned on identity embeddings enable the generation of synthetic face images that consistently preserve identity across multiple samples. Recent work has shown that introducing an additional negative condition through classifier-free guidance during sampling provides a mechanism to suppress undesired attributes, thus improving inter-class separability. Building on this insight, we propose a dynamic weighting scheme for the negative condition that adapts throughout the sampling trajectory. This strategy leverages the complementary strengths of positive and negative conditions at different stages of generation, leading to more diverse yet identity-consistent synthetic data.

AdaptDiff: Adaptive Guidance in Diffusion Models for Diverse and Identity-Consistent Face Synthesis (Student Abstract)

Offline reinforcement learning (RL) is vulnerable to real-world data corruption, with even robust algorithms failing under challenging observation and mixture corruptions. We posit this failure stems from data corruption creating sharp minima in the loss landscape, leading to poor generalization. To address this, we are the first to apply Sharpness-Aware Minimization (SAM) as a
general-purpose, plug-and-play optimizer for offline RL. SAM seeks flatter minima, guiding models to more robust parameter regions. We integrate SAM into strong baselines for data corruption: IQL, a top-performing offline RL algorithm in this setting, and RIQL, an algorithm designed specifically for data-corruption robustness. We evaluate them on D4RL benchmarks with both random and adversarial corruption. Our SAM-enhanced methods consistently and significantly outperform the original baselines. Visualizations of the reward surface confirm that SAM finds smoother solutions, providing strong evidence for its effectiveness in improving the robustness of offline RL agents.

Enhancing Robustness of Offline Reinforcement Learning Under Data Corruption via Sharpness-Aware Minimization (Student Abstract)

Bandit algorithms and Large Language Models (LLMs) have
traditionally been studied in separate
domains---decision-making under uncertainty and natural
language processing, respectively. This talk explores their
emerging synergy and the transformative potential that
arises when these paradigms intersect. On one hand, bandit
algorithms can enhance LLM efficiency through fine-tuning,
prompt optimization, adaptive response generation, and
evaluation strategies. On the other, LLMs can enrich bandit
methods by providing contextual understanding, adaptive
policies, predictive insights, and natural language--driven
feedback. I will present a survey of state-of-the-art
research, highlight promising applications in
personalization, dialogue systems, autonomous agents, and
healthcare, and discuss open challenges around scalability,
interpretability, and multi-agent coordination. The goal is
to provide a roadmap for interdisciplinary research at the
intersection of bandits and LLMs, pointing toward more
adaptive, human-centered, and trustworthy AI systems.

Multi-Armed Bandits Meet Large Language Models

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions.
Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a diffusion transformer aims to reconstruct the gaze region of the image, which corresponds to the target manipulated objects. This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention, thus effectively leveraging task-specific visual information and conducting precise manipulation. Moreover, we curate a large-scale pretraining dataset comprising over 100k trajectories and 2 million data samples from open-source robotic datasets, further boosting the model’s generalization in visual reconstruction. Extensive experiments in simulation and the real world demonstrate the superiority of our implicit grounding method, showcasing its capabilities of precise manipulation and generalization.

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

The Segment Anything Model 2 (SAM2) has demonstrated remarkable promptable visual segmentation capabilities in video data, showing potential for extension to medical image segmentation (MIS) tasks involving 3D volumes and temporally correlated 2D image sequences. However, adapting SAM2 to MIS presents several challenges, including the need for extensive annotated medical data for fine-tuning and high-quality manual prompts, which are both labor-intensive and require intervention from medical experts. To address these challenges, we introduce OFL-SAM2, a prompt-free SAM2 framework for label-efficient MIS. Our core idea is to leverage limited annotated samples to train a lightweight mapping network that captures medical knowledge and transforms generic image features into target features, thereby providing additional discriminative target representations for each frame and eliminating the need for manual prompts. Crucially, the mapping network supports online parameter update during inference, enhancing the model’s generalization across test sequences. Technically, we introduce two key components: (1) an online few-shot learner that trains the mapping network to generate target features using limited data, and (2) an adaptive fusion module that dynamically integrates the target features with the memory-attention features generated by frozen SAM2, leading to accurate and robust target representation. Extensive experiments on three diverse MIS datasets demonstrate that OFL-SAM2 achieves state-of-the-art performance with limited training data. The code will be released.

OFL-SAM2: Prompt SAM2 with Online Few-shot Learner for Efficient Medical Image Segmentation

Video recommendation systems heavily rely on user watch time feedback, making accurate watch time prediction a crucial task. However, this task inherently suffers from bias, as recommendation models tend to favor long-duration videos to maximize watch time. This issue, known as duration bias in the watch-time prediction context, can be explained from a causal perspective, where video duration acts as a confounder. Recent works address this bias using backdoor adjustment, isolating the direct effect of content on watch time from observational data. These methods typically discretize video duration into groups, estimate group-wise effects, and then aggregate them via a unified prediction model. However, this aggregation strategy is prone to model misspecification due to feature distribution shift across groups. In this paper, we reinterpret the problem through the lens of invariant learning and propose a novel framework: **D**uration-**I**nvariant **F**eature **L**earning (**DIFL**). DIFL employs a kernel-based regularization that enforces representation invariance across duration groups, reducing sensitivity to group design and improving generalization. This enables more accurate modeling of the direct causal effect and making counterfactual inference. Extensive experiments on both public and real large-scale production datasets demonstrate the effectiveness of our approach, which achieves SOTA performance.

Invariant Feature Learning for Counterfactual Watch-time Prediction in Video Recommendation

Monocular 3D Semantic Scene Completion (SSC) is a challenging yet promising task that aims to infer dense geometric and semantic descriptions of a scene from a single image. While recent object-centric paradigms significantly improve efficiency by leveraging flexible 3D Gaussian primitives, they still rely heavily on a large number of randomly initialized primitives, which inevitably leads to 1) inefficient primitive initialization and 2) outlier primitives that introduce erroneous artifacts. In this paper, we propose SplatSSC, a novel framework that resolves these limitations with a depth-guided initialization strategy and a principled Gaussian aggregator. Instead of random initialization, SplatSSC utilizes a dedicated depth branch composed of a Group-wise Multi-scale Fusion (GMF) module, which integrates multi-scale image and depth features to generate a sparse yet representative set of initial Gaussian primitives. To mitigate noise from outlier primitives, we develop the Decoupled Gaussian Aggregator (DGA), which enhances robustness by decomposing geometric and semantic predictions during the Gaussian-to-voxel splatting process. Complemented with a specialized Probability Scale Loss, our method achieves state-of-the-art performance on the Occ-ScanNet dataset, outperforming prior approaches by over 6.3\% in IoU and 4.1\% in mIoU, while reducing both latency and memory consumption by more than 9.3\%. The code will be released upon acceptance.

SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion

Linear Temporal Logic over finite traces (LTLf) is a widely used formalism with applications in AI, process mining, model checking, and more. 
The primary reasoning task for LTLf is satisfiability checking; yet, the recent focus on explainable AI has increased interest in analyzing inconsistent formulae, making the enumeration of minimal explanations for unsatisfiability a relevant task also for LTLf. 
We introduce a novel technique for enumerating minimal unsatisfiable cores (MUCs) of an LTLf specification. 
The main idea is to encode an LTLf formula into an Answer Set Programming (ASP) specification, such that the minimal unsatisfiable subsets (MUSes) of the ASP program directly correspond to the MUCs of the original LTLf specification.
Leveraging recent advancements in ASP solving yields an MUC enumerator achieving good performance in experiments conducted on established benchmarks from the literature.

Enumerating Minimal Unsatisfiable Cores of LTLf Formulae

Manual creation of IT monitoring dashboard widgets is slow, error-prone, and a barrier for both novice and expert users. We present NOVAID, an interactive chatbot that leverages Large Language Models (LLMs) to generate IT monitoring widgets directly from natural language queries. Unlike general natural language–to-visualization tools, NOVAID addresses IT operations–specific challenges: specialized widget types like SLO charts, dynamic API-driven data retrieval, and complex contextual filters. The system combines a domain-aware semantic parser, fuzzy entity matching, and schema completion to produce standardized widget JSON specifications. An interactive clarification loop ensures accuracy in underspecified queries. On a curated dataset of 271 realistic queries, NOVAID achieves promising accuracy (up to 94.10% in metric extraction) across multiple LLMs. A user study with IT engineers yielded a System Usability Scale score of 74.2 for NOVAID, indicating good usability. By bridging natural language intent with operational dashboards, NOVAID demonstrates clear potential and a path for deployment in enterprise ITOps monitoring platforms.

Downloads

Next from AAAI 2026

Sketch-Guided Anime Hair Editing Using Multimodal Diffusion Transformer (Student Abstract)

Similar lecture

Using neural networks to track mosquito pose