Singapore

General-purpose Vision-Language Models (VLMs) are increasingly integral to modern AI systems for document understanding, yet their ability to perform fine-grained layout analysis remains severely underdeveloped. Overcoming this requires a large-scale, high-fidelity training dataset. However, current annotation methods, which rely on parsing rendered PDFs, are costly, error-prone, and fail to scale effectively. This work introduces a paradigm shift in data acquisition to resolve this bottleneck. We present LaTeX2Layout, a novel and generalizable procedural pipeline that obtains ground-truth layout information not from the final PDF, but directly from the LaTeX compilation process itself. By instrumenting the compiler, our method produces pixel-perfect bounding boxes and reading order, entirely bypassing the ambiguities of post-rendering parsers. This efficient and accurate pipeline enables us to generate a massive dataset of 140K pages, including 120K programmatically-generated variants that more than double the layout diversity of real-world datasets. This unique dataset allows us to fine-tune a highly efficient 3B parameter VLM, employing a curriculum learning strategy that re-ranks training examples from simple to complex layouts to optimize convergence. Our model establishes a new state-of-the-art, achieving a Kendall&#39;s Tau of 0.95 for reading order and a mAP@0.5 of 0.91 for element grounding---a nearly 200\% relative improvement over formidable zero-shot baselines like GPT-4o and Claude-3.7. To foster reproducible research and future innovation, we make our data generation pipeline, dataset, and all models openly available.

AAAI 2026

LaTeX2Layout: High-Fidelity, Scalable Document Layout Annotation Pipeline for Layout Detection

layout detection

cv applications

large vision models

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

General-purpose Vision-Language Models (VLMs) are increasingly integral to modern AI systems for document understanding, yet their ability to perform fine-grained layout analysis remains severely underdeveloped. Overcoming this requires a large-scale, high-fidelity training dataset. However, current annotation methods, which rely on parsing rendered PDFs, are costly, error-prone, and fail to scale effectively. This work introduces a paradigm shift in data acquisition to resolve this bottleneck. We present LaTeX2Layout, a novel and generalizable procedural pipeline that obtains ground-truth layout information not from the final PDF, but directly from the LaTeX compilation process itself. By instrumenting the compiler, our method produces pixel-perfect bounding boxes and reading order, entirely bypassing the ambiguities of post-rendering parsers. This efficient and accurate pipeline enables us to generate a massive dataset of 140K pages, including 120K programmatically-generated variants that more than double the layout diversity of real-world datasets. This unique dataset allows us to fine-tune a highly efficient 3B parameter VLM, employing a curriculum learning strategy that re-ranks training examples from simple to complex layouts to optimize convergence. Our model establishes a new state-of-the-art, achieving a Kendall's Tau of 0.95 for reading order and a mAP@0.5 of 0.91 for element grounding---a nearly 200\% relative improvement over formidable zero-shot baselines like GPT-4o and Claude-3.7. To foster reproducible research and future innovation, we make our data generation pipeline, dataset, and all models openly available.

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.

Achieving pixel-level registration between SAR and optical images remains a challenging task due to their fundamentally different imaging mechanisms and visual characteristics. Although deep learning has achieved great success in many cross-modal tasks, its performance on SAR-Optical registration tasks is still unsatisfactory. Gradient-based information has traditionally played a crucial role in handcrafted descriptors by highlighting structural differences. However, such gradient cues have not been effectively leveraged in deep learning frameworks for SAR-Optical image matching. To address this gap, we propose SOMA, a dense registration framework that integrates structural gradient priors into deep features and refines alignment through a hybrid matching strategy. Specifically, we introduce the Feature Gradient Enhancer (FGE), which embeds multi-scale, multi-directional gradient filters into the feature space using attention and reconstruction mechanisms to boost feature distinctiveness. Furthermore, we propose the Global-Local Affine-Flow Matcher (GLAM), which combines affine transformation and flow-based refinement within a coarse-to-fine architecture to ensure both structural consistency and local accuracy. Experimental results demonstrate that SOMA significantly improves registration precision, increasing the CMR@1px by 12.29% on the SEN1-2 dataset and 18.50% on the GFGE_SO dataset. In addition, SOMA exhibits strong robustness and generalizes well across diverse scenes and resolutions.

SOMA: Feature Gradient Enhanced Affine-Flow Matching for SAR-Optical Registration

Text-attributed graphs (TAGs), which associate rich textual descriptions with each node, are widely employed to represent complex relationships among real-world textual entities.
Currently, representation learning for TAGs leverages large language models (LLMs) to transform node-matched textual descriptions into node features or labels, followed by message passing in graph neural networks (GNNs) that further improves the expressiveness of graph representation learning.
Nevertheless, a simple experiment we conducted demontrates that not all LLMs are readily compatible with GNNs.
A salient finding indicates that architectural heterogeneity among LLMs manifests as substantial performance gap across diverse TAGs representation learning.
Moreover, the node semantics encoded by LLMs are often misaligned with the message passing in GNNs, causing $\textit{performance collapse}$. 
Motivated by this observation, we propose a noval self-supervised graph learning framework called $\underline{S}$tage-$\underline{A}$ware $\underline{G}$raph $\underline{C}$ontrastive $\underline{L}$earning (SAGCL).
In particular, we propose the node-oriented mixture of experts (NodeMoE) to assign suitable candidate experts for each node. 
It flexibly balances the strengths of different language experts by low-rank decomposition and reparameterization strategies. 
Subsequently, to align the inductive biases of graph structures with the semantic perception capabilities of LLMs, the message passing in GNNs is decoupled into the feature transformation and the feature propagation stage. 
Given the two stage views, stage-aware graph contrastive learning is proposed to match the node semantics encoded by the LLM with the locally aware topological patterns within the GNN via self-supervised contrastive learning.
Experiments on eight datasets and three diverse tasks demonstrate the effectiveness of SAGCL.

Stage-Aware Graph Contrastive Learning with Node-oriented Mixture of Experts

Open-set noisy label learning faces a critical challenge in maintaining robust DNN performance when training data contains both in-distribution noisy (IDN) and out-of-distribution (OOD) samples. These noisy samples induce overconfident but erroneous predictions due to their ambiguous positions relative to category boundaries. Current methods address this by filtering noisy samples based on visual features alone, they fail to resolve the semantic ambiguity near decision boundaries, where limited visual cues lead to unreliable sample purification. To this end, we propose Content Diversity-guided Ambiguity Mitigation (CDgAM), a novel framework that leverages diverse contents to mitigate visual ambiguity in open-set noisy label learning. CDgAM leverages textual descriptions of intra-class commonality and inter-class disparity to dynamically refine semantic boundaries, reducing bias in prototype learning. To further suppress early-stage uncertainty in visual representations, we design a region-sensitive distillation regularization that transfers boundary-aware knowledge from a multimodal large language model to the target DNN. Extensive experiments conducted on various datasets with different noise levels demonstrate the effectiveness of our CDgAM, outperforming state-of-the-art methods for open-set noisy label learning.

Content Diversity-guided Ambiguity Mitigation for Open-Set Noisy Label Learning

Vision Transformers (ViTs) have achieved strong performance in video action recognition, but their high computational cost limits their practicality. Lightweight CNNs are more efficient but suffer from accuracy gaps. Cross-Architecture Knowledge Distillation (CAKD) addresses this by transferring knowledge from ViTs to CNNs, yet existing methods often struggle with architectural mismatch and overlook the value of stronger homogeneous CNN teachers. To tackle these challenges, we propose a Dual-Teacher Knowledge Distillation framework that leverages both a heterogeneous ViT teacher and a homogeneous CNN teacher to collaboratively guide a lightweight CNN student. We introduce two key components: (1) Discrepancy-Aware Teacher Weighting, which dynamically fuses the predictions from ViT and CNN teachers by assigning adaptive weights based on teacher confidence and prediction discrepancy with the student, enabling more informative and effective supervision; and (2) a Structure Discrepancy-Aware Distillation strategy, where the student learns the residual features between ViT and CNN teachers via a lightweight auxiliary branch, focusing on transferable architectural differences without mimicking all of ViT’s high-dimensional patterns. Extensive experiments on benchmarks including HMDB51, EPIC-KITCHENS-100, and Kinetics-400, demonstrate that our method consistently outperforms state-of-the-art distillation approaches, achieving notable performance improvements with a maximum accuracy gain of 5.95% on HMDB51.

Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video Models

Deep learning has shown strong potential in modeling complex spatiotemporal dynamics. However, most existing methods depend on densely and uniformly sampled data, which is often unavailable in practice due to sensor and cost limitations. In many real-world settings, such as mobile sensing and physical experiments, data are burst-sampled with short high-frequency segments followed by long gaps, making it difficult to learn accurate dynamics from sparse observations. To address this issue, we propose Physics-Informed Multi-Scale Recurrent Learning (PIMRL), a novel framework specifically designed for burst-sampled spatiotemporal data. PIMRL combines macro-scale latent dynamics inference with micro-scale adaptive refinement guided by incomplete prior information from partial differential equations (PDEs). It further introduces a temporal message-passing mechanism to effectively propagate information across burst intervals. This multi-scale architecture enables PIMRL to model complex systems accurately even under severe data scarcity. We evaluate our approach on five benchmark datasets involving 1D to 3D multi-scale PDEs. The results show that PIMRL consistently outperforms state-of-the-art baselines, achieving substantial improvements and reducing errors by up to 80\% in the most challenging settings, which demonstrates the clear advantage of our model. Our work demonstrates the effectiveness of physics-informed recurrent learning for accurate and efficient modeling of sparse spatiotemporal systems.

PIMRL: Physics-Informed Multi-Scale Recurrent Learning for Burst-Sampled Spatiotemporal Dynamics

Facial Expression Recognition (FER) seeks to classify affective states from facial images, which remains a challenging problem due to variations in real-world conditions. FER task becomes particularly complex when handling unconstrained environments characterized by partial occlusions, different head poses, and so on. To address the above problems, current approaches rely on extensive learnable parameters and complex model architectures, which inevitably lead to overfitting and cause the FER model to focus on non-discriminative facial regions. In this work, we propose an HKAFER model that can adaptively enhance visual expression representations through efficiently fine-tuning the image encoder in large Visual Foundation Models (VFMs) and Vision-Language Models (VLMs). Specifically, we establish Heterogeneous Kronecker Adaptation (HeKA), which consists of multi-scale adapters based on Kronecker product in a parallel manner, offering significantly diverse subspaces to learn the incremental matrices. Besides, we also propose Dual-Branch Interactive Router (DBIR) to dynamically assign the weights of adapters, which promotes collaboration and information flow among them. In this way, our HKAFER can effectively capture robust spatial features and the regional associations. Experimental results demonstrate that our proposed model not only outperforms state-of-the-art methods on several FER benchmarks but also uses significantly fewer trainable parameters.

HKAFER: Achieve Visual Parameter-Efficient Fine-Tuning via Heterogeneous Kronecker Adaptation for Facial Expression Recognition

The proliferation of synthetic facial imagery has intensified the need for robust Open-World DeepFake Attribution (OW-DFA), which aims to attribute both known and unknown forgeries using labeled data for known types and unlabeled data containing a mixture of known and novel types. However, existing OW-DFA methods face two critical limitations: 1) A confidence skew that leads to unreliable pseudo-labels for novel forgeries, resulting in biased training. 2) An unrealistic assumption that the number of unknown forgery types is known a priori. To address these challenges, we propose a Confidence-aware Asymmetric Learning (CAL) framework, which adaptively balances model confidence across known and novel forgery types. CAL mainly consists of two components: Confidence-aware Consistency Regularization (CCR) and Asymmetric Confidence Reinforcement (ACR). CCR mitigates pseudo-label bias by dynamically scaling sample losses based on normalized confidence, gradually shifting the training focus from high- to low-confidence samples. ACR complements this by separately calibrating confidence for known and novel classes through selective learning on high-confidence samples, guided by their confidence gap. Together, CCR and ACR form a mutually reinforcing loop that significantly improves the model's OW-DFA performance. Moreover, we introduce a Dynamic Prototype Pruning (DPP) strategy that automatically estimates the number of novel forgery types in a coarse-to-fine manner, removing the need for unrealistic prior assumptions and enhancing the scalability of our methods to real-world OW-DFA scenarios. Extensive experiments on the standard and OW-DFA benchmark and a newly extended benchmark incorporating advanced manipulations demonstrate that CAL consistently outperforms previous methods, achieving new state-of-the-art performance on both known and novel forgery attribution. Code and datasets will be made publicly available.

Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning

The challenge in WiFi-based cross-domain Behavior Recognition lies in the significant interference of domain-specific signals on gesture variation. However, previous methods alleviate this interference by mapping the phase from multiple domains into a common feature space. If the Doppler Frequency Shift (DFS) signal is used to dynamically supplement the phase features to achieve better generalization, enabling model to not only explore a wider feature space but also avoid potential degradation of gesture semantic information. Specifically, we propose a novel Salient-aware Adaptive WiFi Sensing for Cross-domain Behavior Recognition (Wi-CBR}, which constructs a dual-branch self-attention module that captures temporal features from phase information reflecting dynamic path length variations, while extracting spatial features from DFS correlated with motion velocity. Moreover, we design a Saliency Guidance Module that employs group attention mechanisms to mine critical activity features, and utilizes gating mechanisms to optimize information entropy, facilitating feature fusion and enabling effective interaction between salient and non-salient behavior characteristics. Extensive experiments on two large-scale public datasets (Widar3.0 and XRF55) demonstrate the superior performance of our method in both in-domain and cross-domain scenarios.

Wi-CBR: Salient-aware Adaptive WiFi Sensing for Cross-domain Behavior Recognition

Human motion synthesis in 3D scenes relies heavily on scene comprehension, while current methods focus mainly on scene structure but ignore the semantic understanding. In this paper, we propose a human motion synthesis framework that take an unified Scene Semantic Occupancy (SSO) for scene representation, termed SSOMotion. We design a bi-directional tri-plane decomposition to derive a compact version of the SSO, and scene semantics are mapped to an unified feature space via CLIP encoding and shared linear dimensionality reduction. Such strategy can derive the fine-grained scene semantic structures while significantly reduce redundant computations. We further take these scene hints and movement direction derived from instructions for motion control via frame-wise scene query. Extensive experiments and ablation studies conducted on cluttered scenes using ShapeNet furniture, as well as scanned scenes from PROX and Replica datasets, demonstrate its cutting-edge performance while validating its effectiveness and generalization ability.

Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancy

With the increasing scale and complexity of graph data, node attributes are also becoming richer and more complex, spanning multi-view/modal features and informative text. Classic GNNs equipped with shallow encoders are no longer sufficient to handle such data independently, making model collaboration across different architectures an inevitable trend. 
Recently, the integration of Large Language Models (LLMs) and GNNs has attracted significant attention. However, the inherent disparity between these models remains a key challenge. 
Promising solutions have considered fine-tuning Small Language Models (SLMs) to bridge the gap between GNNs and frozen LLMs. 
Yet, this introduces another problem: large and small models bring complementary views of knowledge, but how to effectively integrate them and allow mutual refinement remains a significant research gap.
To address these challenges, we introduce COLA, a collaborative large–small model framework that enables seamless cooperation among semantic LLMs, task-specific fine-tuned SLMs, and structure-aware GNNs.
COLA features a unique Consensus–Complement Coordination (CoCo) mechanism, wherein the Mixture-of-Coordinators (MoC) architecturally aligns the LLM and SLM. Built upon MoC, a flexible graph-knowledge infusion strategy encourages the joint alignment and graph knowledge learning of textual representations. Extensive evaluations across nine diverse datasets demonstrate that COLA consistently achieves state-of-the-art performance, validating the effectiveness and generality of our collaborative paradigm.

Content not yet available

Next from AAAI 2026

SOMA: Feature Gradient Enhanced Affine-Flow Matching for SAR-Optical Registration

Similar lecture

Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding