Singapore

Event cameras offer unparalleled advantages such as high temporal resolution, low latency, and high dynamic range. However, their limited spatial resolution poses challenges for fine-grained perception tasks. In this work, we propose an ultra-lightweight, stream-based event-to-event super-resolution method based on Spiking Neural Networks (SNNs), designed for real-time deployment on resource-constrained devices. To further reduce model size, we introduce a novel Dual-Forward Polarity-Split Event Encoding strategy that decouples positive and negative events into separate forward paths through a shared SNN. Furthermore, we propose a Learnable Spatio-temporal Polarity-aware Loss (LearnSTPLoss) that adaptively balances temporal, spatial, and polarity consistency using learnable uncertainty-based weights. Experimental results demonstrate that our method achieves competitive super-resolution performance on multiple datasets while significantly reducing model size and inference time. The lightweight design enables embedding the module into event cameras or using it as an efficient front-end preprocessing for downstream vision tasks.

AAAI 2026

Ultralight Polarity-Split Neuromorphic SNN for Event-Stream Super-Resolution

event camera

super resolution

#### Welcome to the 43rd annual ICALEO!

Attention laser enthusiasts, innovators, and industry leaders! Get ready to immerse yourself in the exciting world of lasers at the 43rd annual ICALEO conference. This year, we gathered in the iconic city of Hollywood, California, for cutting-edge technology, groundbreaking presentations, and unparalleled networking opportunities.
Whether you're a seasoned professional or new to the field of photonics, the 43rd annual ICALEO had something for everyone. 

#### General Chair Welcome Message

It is with immense joy and anticipation that I extend a warm welcome to each and every one of you as the General Chair of this year's ICALEO conference.

This year, we find ourselves in the iconic setting of Hollywood, serving as a fitting backdrop for the extraordinary developments in laser technology and applications unfolding in our community.

Our main sessions cover a diverse range of topics, from the intricacies of micro and nano processing to the transformative power of laser additive manufacturing. We will explore the frontiers of battery technology, delve into the intricate world of artificial intelligence, and witness the seamless integration of lasers into these realms.

For those joining us for the first time, we extend an especially heartfelt welcome. ICALEO is not just a conference; it's a convergence of minds, ideas, and innovations. Beyond the formal sessions, I encourage you to engage in informal exchanges. The spirit of discovery and camaraderie is as much a part of the ICALEO experience as the scheduled sessions.

Thank you for being a part of ICALEO 2024. Whether you are a returning participant or a first-time attendee, your presence adds immeasurable value to our vibrant community. May this conference be, this year again, a catalyst for inspiration, collaboration, and breakthroughs that will resonate in our community and beyond.

Eric Mottay 
Congress General Chair, ICALEO 2024


#### About LIA

The Laser Institute of America (LIA) is the professional society for laser applications and safety. Our mission is to foster lasers, laser applications, and laser safety worldwide. Serving the industrial, medical, research and government communities for over 50 years, LIA offers technical information, training and networking opportunities to laser users
from around the globe.

#### About LIA Conferences

The conferences of the Laser Institute of America are the town square of the laser community. A large and diverse group, laser professionals often find themselves disconnected from each other. LIA conferences, however, bring the university researcher, the business executive and the production floor user together under one roof for a unique and
rewarding networking opportunity.

#### Program Tracks
Below is the list of all tracks that were on ICALEO 2024 Conference.

##### Laser Additive Manufacturing
* The Laser Additive Manufacturing (LAM) track is a forum to explore the latest innovations and research in laser-based additive manufacturing (LAM). The Laser Additive Manufacturing track focuses on diverse topics, including laser-based powder bed fusion (PBF-LB), directed energy deposition (DED), and other emerging techniques revolutionizing modern manufacturing processes. From materials science to process optimization, from design innovation to industrial implementation, this track connects researchers, engineers, and industry leaders to exchange insights and share breakthroughs in laser additive manufacturing.

##### Laser Materials Macroprocessing
* The Macroprocessing track comprises some of the most productive laser processing applications. Although these applications have been broadly adopted, researchers and industry are persistently innovating to provide new techniques and novel technologies to advance macro materials processing. The attendees will share and discuss those exciting achievements of their research with peers in these macroscopic specialized sessions.

##### Laser Materials Microprocessing
* The Microprocessing track will consist of papers and talks featuring a wide spectrum of applications and innovative equipment for materials processing in microscales with a strong focus on processes with Short and Ultrashort Pulsed Lasers. The presentations will introduce the latest and greatest advancements in their respective fields, presented by world-leading companies and research organizations. This year we will have talks around the headlines of “Beam shaping”, “Glass”, “Surface processing” and “Drilling” between other topics.

##### Frontiers in Laser Applications
* The Frontier in Laser Applications (FLA) track explores recent, cutting-edge applications of lasers, highlighting innovation at the transition of research and industry. The track has included presentations from a variety of fields: Novel 3-D Printing, Advanced Manufacturing, Laser Manufactured Devices, and Frontiers in Laser Processing. The sessions under the Frontier in Laser Application track promise to bring diverse and unique perspectives from real-world applications across laser manufacturing.

##### Laser in Battery Manufacturing
* Electrification is crucial to address global environmental challenges. The laser plays a key role in most manufacturing steps in battery production with all possible laser applications from ablation, structuring, welding, cutting, and marking. Further improvements in the batteries’ power densities, fast charging properties, and yield in battery production are related to photonics and, thus, lasers. We will hear and discuss the latest developments in research, development, and industrial applications. Join us for this year’s Battery Track.

##### Artifical Intelligence in Laser Processing
* The track ‘Artificial Intelligence in Laser Processing’ at ICALEO 2024 explores the fusion of AI and laser manufacturing. Discover cutting-edge research on optimizing laser processes and enhancing manufacturing efficiency. Explore AI’s diverse applications in parameter optimization, quality prediction, real-time process monitoring, and control. Join us to unlock the potential of AI-driven solutions revolutionizing laser materials processing, delivering unprecedented precision, productivity, and innovation.

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.

It looks like you are not registered for this event. To access the site please register [**here**](https://icaleo.org/attend). 

Are you an LIA Member? Find a special discount code in your LIA account at https://www.lia.org/user to apply to your registration for additional savings!

Please register!

ICALEO 2024

Attention laser enthusiasts, innovators, and industry leaders! Get ready to immerse yourself in the exciting world of lasers at the 43rd annual ICALEO conference. 

poster

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.

To access this event page, you need to log in with the **email address you registered with**. 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.

Guidance is an emerging concept that improves the empirical performance of real-time, sub-optimal multi-agent pathfinding (MAPF) methods. It offers additional information to MAPF algorithms to mitigate congestion on a global scale by considering the collective behavior of all agents across the entire workspace. This global perspective helps reduce agents' waiting times, thereby improving overall coordination efficiency. In contrast, this study explores an alternative approach: providing local guidance in the vicinity of each agent. While such localized methods involve recomputation as agents move and may appear computationally demanding, we empirically demonstrate that supplying informative spatiotemporal cues to the planner can significantly improve solution quality without exceeding a moderate time budget. When applied to LaCAM, a leading configuration-based solver, this form of guidance establishes a new performance frontier for MAPF.

Local Guidance for Configuration-Based Multi-Agent Pathfinding

Quantization is a pivotal technique for enhancing communication efficiency in Federated Learning (FL). Traditional quantization methods often set uniform intervals, may fail to adequately characterize non-uniform data distributions, thus leading to substantial estimation errors and degrated model performance. Non-uniform quantization can better solve the problem. However, when applied to FL, it would bring additional communication overheads for the alignment of parameter distributions among distributed models. To address this issue, we propose Bisection Interval Quantization (BIQ), a novel non-uniform quantization framework for FL with great communication efficiency. In particular, BIQ works by optimizing the interval selection through recursive bisection among distributed clients without extra parameter communication. For scenarios involving amounts of boundary inputs, we further design Weighted Bisection Interval Quantization (WBIQ), which incorporates maximum likelihood estimation to refine boundary value reconstruction to enhance the estimation quality of boundary inputs. Our theoretical analysis rigorously establishes, for the first time under biased quantization conditions, that both BIQ and WBIQ achieve tighter error bounds and enhanced stability. Extensive experiments validate that both BIQ and WBIQ significantly accelerate the convergence of FL model training when compared to the state-of-the-art quantizers under both convex and non-convex settings.

BIQ: Bisection Interval Quantization for Communication-efficient Federated Learning

Accurate prediction of compound protein interactions (CPIs) is crucial for drug discovery. 
However, existing deep learning-based methods suffer from hidden biases and poor cross-domain generalization, leading to spurious correlations and inadequate representation of unseen compound-protein pairs. 
To address these limitations, we propose FuseMine, a multimodal deep learning framework that jointly leverages molecular structures and biological sequences for reliable CPI prediction.
Specifically, FuseMine adopting a dual-representation strategy for each molecule. It employs a convolutional encoder to capture structural features, combined with pretrained large language models for extracting semantic information from sequences. We propose a novel Multi-modal Feature Orchestration Aggregation (MFOA) module that enables deep and synergistic fusion between the structural features and the sequential semantics of molecules, effectively capturing the complementary patterns across modalities. Additionally, we design a Reduction Differential Feature Mining (RDFM) module to further enhance the representation of discriminative features, thereby improving the model’s generalization capability. Extensive experiments on multiple benchmark datasets demonstrate that our framework consistently outperforms state-of-the-art methods in both intra-domain and cross-domain scenarios. These results highlight the synergistic value of combining structural and sequential data for CPIs. Code is available at https://anonymous.4open.science/r/FuseMine.

FuseMine: Robust Multi-Modal Compound-Protein Interaction Prediction via Differential Attention Feature Mining

Frequency Modulated Continuous Wave (FMCW) radars can measure subtle chest wall oscillations to enable non-contact heartbeat sensing. However, traditional radar-based heartbeat sensing methods face performance degradation due to noise. Learning-based radar methods achieve better noise robustness but require costly labeled signals for supervised training. To overcome these limitations, we propose the first unsupervised framework for radar-based heartbeat sensing via Augmented Pseudo-Label and Noise Contrast (Radar-APLANC). We propose to use both the heartbeat range and noise range within the radar range matrix to construct the positive and negative samples, respectively, for improved noise robustness. Our Noise-Contrastive Triplet (NCT) loss only utilizes positive samples, negative samples, and pseudo-label signals generated by the traditional radar method, thereby avoiding dependence on expensive ground-truth physiological signals. We further design a pseudo-label augmentation approach featuring adaptive noise-aware label selection to improve pseudo-label signal quality. Extensive experiments on the Equipleth dataset and our collected radar dataset demonstrate that our unsupervised method achieves performance comparable to state-of-the-art supervised methods.

Radar-APLANC: Unsupervised Radar-based Heartbeat Sensing via Augmented Pseudo-Label and Noise Contrast

User interface (UI) design is an iterative process in which designers progressively refine their work with design software such as Figma or Sketch. Recent advances in vision–language models (VLMs) with tool invocation suggest these models can operate the design software to edit a UI design through iteration. Understanding and enhancing this capacity is important, as it highlights VLMs’ potential to collaborate with designers within conventional software. However, as no existing benchmark evaluates the tool-based design performance, the capacity remains unknown. To address this, we introduce CANVAS, a benchmark for VLMs on tool-based user interface design. Our benchmark contains 598 tool-based design tasks paired with ground-truth references sampled from 3.3K mobile UI designs across 30 function-based categories (e.g., onboarding, messaging). In each task, a VLM updates the design step-by-step, through context-based tool invocations (e.g., create a rectangle as a button background), linked to design software. Specifically, CANVAS incorporates two task types: (i) design replication evaluates the ability to reproduce a whole UI screen; (ii) design modification evaluates the ability to modify a specific part of an existing screen. Results suggest that leading models exhibit more strategic tool invocations, improving design quality. Furthermore, we identify common error patterns models exhibit, guiding future work in enhancing tool-based design capabilities.

CANVAS: A Benchmark for Vision-Language Models on Tool-Based User Interface Design

Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these graphs often assume that the distributions of training and testing data are consistent. This assumption leads to significant performance degradation when faced with out-of-distribution (OOD) data. In this paper, we address the challenge of node-level OOD detection in text-attributed graphs, with the goal of maintaining accurate node classification while simultaneously identifying OOD nodes. We propose a novel approach, LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs (LECT), which integrates large language models (LLMs) and energy-based contrastive learning. The proposed method involves generating high-quality OOD samples by leveraging the semantic understanding and contextual knowledge of LLMs to create dependency-aware pseudo-OOD nodes, and applying contrastive learning based on energy functions to distinguish between in-distribution (IND) and OOD nodes. The effectiveness of our method is demonstrated through extensive experiments on six benchmark datasets, where our method consistently outperforms state-of-the-art baselines, achieving both high classification accuracy and robust OOD detection capabilities.

LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs

Recent unsupervised domain adaptation (UDA) methods have shown great success in addressing classical domain shifts (e.g., synthetic-to-real), but they still suffer under complex shifts (e.g. geographical shift), where both the background and object appearances differ significantly across domains. Prior works showed that the language modality can help in the adaptation process, exhibiting more robustness to such complex shifts. In this paper, we introduce TRUST, a novel UDA approach that exploits the robustness of the language modality to guide the adaptation of a vision model. TRUST generates pseudo-labels for target samples from their captions and introduces a novel uncertainty estimation strategy that uses normalised CLIP similarity scores to estimate the uncertainty of the generated pseudo-labels. Such estimated uncertainty is then used to reweight the classification loss, mitigating the adverse effects of wrong pseudo-labels obtained from low-quality captions. To further increase the robustness of the vision model, we propose a multimodal soft-contrastive learning loss that aligns the vision and language feature spaces, by leveraging captions to guide the contrastive training of the vision model on target images. In our contrastive loss, each pair of images acts as both a positive and a negative pair and their feature representations are attracted and repulsed with a strength proportional to the similarity of their captions. This solution avoids the need for hardly determining positive and negative pairs, which is critical in the UDA setting. Our approach outperforms previous methods, setting the new state-of-the-art on classical (DomainNet) and complex (GeoNet) domain shifts.

TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation

In multi-view clustering (MVC), complementary and consistent information from multiple views is integrated to improve clustering performance. However, inter-view sample correspondences may be partially missing in practice, making it difficult to learn cross-view consistency, which leads to the partially view-aligned problem (PVP). Most existing partially view-aligned clustering (PVC) methods first learn cross-view consistent representations based on known alignments, and then recover missing correspondences by measuring cross-view similarity between samples. However, such an indirect alignment recovery process depends on high-quality consistent representations and lacks effective utilization of known alignments, often resulting in sub-optimal outcomes. To address this, we propose a novel direct alignment recovery perspective, instantiated as K-Nearest Neighbors Direct Alignment (KNNDA). Specifically, we first construct an alignment domain by mapping the aligned neighbors of each unaligned sample into the aligned view. Then, we compute alignment confidence based on the similarity between known aligned pairs of neighbors. In particular, we use a dynamic threshold to filter out unreliable alignments. Finally, new alignments are generated within the high-confidence alignment domain. Contrastive loss is used to learn consistent representations for clustering. Comprehensive experiments on several real-world datasets show the effectiveness and superiority of our module in partially view-aligned clustering.

KNNDA: A New Perspective of Alignment Recovery for Partially View-Aligned Clustering

Accurate vessel segmentation in X-ray angiograms is crucial for numerous clinical applications. However, the scarcity of annotated data presents a significant challenge, which has driven the adoption of self-supervised learning (SSL) methods such as masked image modeling (MIM) to leverage large-scale unlabeled data for learning transferable representations. Unfortunately, conventional MIM often fails to capture vascular anatomy because of the severe class imbalance between vessel and background pixels, leading to weak vascular representations. To address this, we introduce Vascular anatomy-aware Masked Image Modeling (VasoMIM), a novel MIM framework tailored for X-ray angiograms that explicitly integrates anatomical knowledge into the pre-training process. Specifically, it comprises two complementary components: anatomy-guided masking strategy and anatomical consistency loss. The former preferentially masks vessel-containing patches to focus the model on reconstructing vessel-relevant regions. The latter enforces consistency in vascular semantics between the original and reconstructed images, thereby improving the discriminability of vascular representations. Empirically, VasoMIM achieves state-of-the-art performance across three datasets. These findings highlight its potential to facilitate X-ray angiogram analysis.

VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly training on offline preference data to align with human preferences. During DPO training, the reference model serves as a data weight adjuster. However, the common practice of initializing the policy and reference models identically in DPO can lead to inefficient data utilization and impose a performance ceiling. Meanwhile, the absence of a reference model in Simple Preference Optimization (SimPO) reduces training robustness and requires stricter conditions to prevent catastrophic forgetting. In this work, we propose Pre-DPO, a simple yet effective DPO-based training paradigm that improves preference optimization by introducing a guiding reference model. This reference model provides foresight into the desired policy state achievable through the training preference data, serving as a guiding mechanism that adaptively assigns higher weights to samples more suitable for the model and lower weights to those less suitable. Extensive experiments on the AlpacaEval 2 and Arena-Hard v0.1 benchmarks demonstrate that Pre-DPO consistently improves the performance of both DPO and SimPO, without relying on external models or additional data. Our code, data, and technical appendix can be found in the Supplementary Material.

Downloads

Next from AAAI 2026

Local Guidance for Configuration-Based Multi-Agent Pathfinding

Similar lecture

Event-Based Vision in Laser Welding: An Approach for Process Monitoring

.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

Local Guidance for Configuration-Based Multi-Agent Pathfinding

Similar lecture

Event-Based Vision in Laser Welding: An Approach for Process Monitoring

Downloads