United States

Recent evaluations of Large Multimodal Models (LMMs) have explored their capabilities in various domains, with only few benchmarks specifically focusing on urban environments. Moreover, existing urban benchmarks have been limited to evaluating LMMs with basic region-level urban tasks under singular views, leading to incomplete evaluations of LMMs&#39; abilities in urban environments.
To address these issues, we present UrBench, a comprehensive benchmark designed for evaluating LMMs in complex multi-view urban scenarios. UrBench contains 11.6K meticulously curated questions at both region-level and role-level that cover 4 task dimensions: Geo-Localization, Scene Reasoning, Scene Understanding, and Object Understanding, totaling 14 task types. In constructing UrBench, we utilize data from existing datasets and additionally collect data from 11 cities, creating new annotations using a cross-view detection-matching method. With these images and annotations, we then integrate LMM-based, rule-based, and human-based methods to construct large-scale high-quality questions. Our evaluations on 21 LMMs show that current LMMs struggle in the urban environments in several aspects. Even the best performing GPT-4o lags behind humans in most tasks, ranging from simple tasks such as counting to complex tasks such as orientation, localization and object attribute recognition, with an average performance gap of 17.4\%. Our benchmark also reveals that LMMs exhibit inconsistent behaviors with different urban views, especially with respect to understanding cross-view relations. 
UrBench datasets and benchmark results will be publicly available.

AAAI 2025

UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios

mult modal vision

## 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.

Recent evaluations of Large Multimodal Models (LMMs) have explored their capabilities in various domains, with only few benchmarks specifically focusing on urban environments. Moreover, existing urban benchmarks have been limited to evaluating LMMs with basic region-level urban tasks under singular views, leading to incomplete evaluations of LMMs' abilities in urban environments.
To address these issues, we present UrBench, a comprehensive benchmark designed for evaluating LMMs in complex multi-view urban scenarios. UrBench contains 11.6K meticulously curated questions at both region-level and role-level that cover 4 task dimensions: Geo-Localization, Scene Reasoning, Scene Understanding, and Object Understanding, totaling 14 task types. In constructing UrBench, we utilize data from existing datasets and additionally collect data from 11 cities, creating new annotations using a cross-view detection-matching method. With these images and annotations, we then integrate LMM-based, rule-based, and human-based methods to construct large-scale high-quality questions. Our evaluations on 21 LMMs show that current LMMs struggle in the urban environments in several aspects. Even the best performing GPT-4o lags behind humans in most tasks, ranging from simple tasks such as counting to complex tasks such as orientation, localization and object attribute recognition, with an average performance gap of 17.4\%. Our benchmark also reveals that LMMs exhibit inconsistent behaviors with different urban views, especially with respect to understanding cross-view relations. 
UrBench datasets and benchmark results will be publicly available.

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

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-25 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.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

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-25 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.



Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy in a federated setting. Existing FedCF methods typically combine distributed Collaborative Filtering (CF) algorithms with privacy-preserving mechanisms, and then preserve personalized information into a user embedding vector. 
However, the user embedding is usually insufficient to preserve the rich information of the fine-grained personalization across heterogeneous clients. This paper proposes a novel personalized FedCF method by preserving users' personalized information into a latent variable and a neural model simultaneously. Specifically, we decompose the modeling of user knowledge into two encoders, each designed to capture shared knowledge and personalized knowledge separately. A personalized gating network is then applied to balance personalization and generalization between the global and local encoders. Moreover, to effectively train the proposed framework, we model the CF problem as a specialized Variational AutoEncoder (VAE) task by integrating user interaction vector reconstruction with missing value prediction.  The decoder is trained to reconstruct the implicit feedback from items the user has interacted with, while also predicting items the user might be interested in but has not yet interacted with. Experimental results on benchmark datasets demonstrate that the proposed method outperforms other baseline methods, showcasing superior performance.

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach

We consider online convex optimization with time-varying constraints and conduct performance analysis using two stringent metrics: dynamic regret with respect to the online solution benchmark, and hard constraint violation that does not allow any compensated violation over time. We propose an efficient algorithm called Constrained Online Learning with Doubly-bounded Queue (COLDQ), which introduces a novel virtual queue that is both lower and upper bounded, allowing tight control of the constraint violation without the need for the Slater condition. We prove via a new Lyapunov drift analysis that COLDQ achieves $\mathcal{O}(T^\frac{1+V_x}{2})$ dynamic regret and $\mathcal{O}(T^{V_g})$ hard constraint violation, where $V_x$ and $V_g$ capture the dynamics of the loss and constraint functions. For the first time, the two bounds smoothly approach to the best-known $\mathcal{O}(T^\frac{1}{2})$ regret and $\mathcal{O}(1)$ violation, as the dynamics of the losses and constraints diminish. For strongly convex loss functions, COLDQ matches the best-known $\mathcal{O}(\log{T})$ static regret while maintaining the $\mathcal{O}(T^{V_g})$ hard constraint violation. We further introduce an expert-tracking variation of COLDQ, which achieves the same performance bounds without any prior knowledge of the system dynamics. Simulation results demonstrate that COLDQ outperforms the state-of-the-art approaches.

Doubly-Bounded Queue for Constrained Online Learning: Keeping Pace with Dynamics of Both Loss and Constraint

As the Ethereum platform continues to mature and gain widespread usage, it is crucial to maintain high standards of smart contract writing practices. While bad practices in smart contracts may not directly lead to security issues, they do elevate the risk of encountering problems. Therefore, to understand and avoid these bad practices, this paper introduces the first systematic study of bad practices in smart contracts, delving into over 35 specific issues. Specifically, we propose a large language models (LLMs)-based framework, SCALM. It combines Step-Back Prompting and Retrieval-Augmented Generation (RAG) to effectively identify and address various bad practices. Our extensive experiments using multiple LLMs and datasets have shown that SCALM outperforms existing tools in detecting bad practices in smart contracts.

SCALM: Detecting Bad Practices in Smart Contracts through LLMs

Materials science text mining (MSTM), involving tasks like property extraction and synthesis action retrieval, is pivotal for advancing research by deriving critical insights from scientific literature. Descriptors, serving as essential task labels, often vary in meaning depending on researchers' usage purposes across different mining tasks. (e.g., Material can refer to both synthesis components and participants in fuel cell experiment). This meaning difference makes it difficult for existing methods, fine-tuned to specific task, to handle the same descriptors in other tasks. To overcome above limitation, we propose MatDuck, a simple and effective approach for Zero-Shot MSTM by evoking material knowledge within large language models (LLMs). Specifically, inspired by the Duck Typing principles in programming languages, we present a ClassDefinition-Style Descriptor generation method that evokes task-specific characteristics to address usage variation. Subsequently, we introduce a code-style in-context learning for zero-shot, which reframes tasks into a code format to better leverage the instantiation capabilities of LLMs. Extensive experiments on eight benchmark datasets demonstrate that MatDuck, as a plug-and-play approach, significantly improves the Zero-Shot MSTM performance of LLMs by an average of 11.3\% across seven tasks, achieving performance comparable to supervised learning.

Zero-Shot Learning for Materials Science Texts: Leveraging Duck Typing Principles

Multi-view clustering (MVC) has achieved remarkable success by leveraging complementary information from different views. Among various approaches, Late Fusion Multi-view Clustering (LFMVC) methods have gained attention for their ability to synthesize base clustering partitions into a unified consensus. However, existing LFMVC methods face challenges in processing noisy and redundant partitions and often overlook high-order correlations across views. In this work, we propose an enhanced LFMVC framework based on a multiple linear kernel K-means approach. Our method introduces a novel generalization error bound that leverages local Rademacher complexity and principal eigenvalue proportion, achieving a convergence rate of $ O(1/\sqrt{nk}) $, a significant improvement over the traditional $ O(k/\sqrt{n}) $ rate. Furthermore, inspired by recent advances in graph filtering, we develop a low-pass filtering strategy to further refine the error bound by improving the principal eigenvalue proportion. Extensive experiments demonstrate the superiority of our method in terms of clustering performance.

Sharper Error Bounds in Late Fusion Multi-view Clustering with Eigenvalue Proportion Optimization

Object pose estimation, crucial in computer vision and robotics applications, faces challenges with the diversity of unseen categories. We propose a zero-shot method to achieve category-level 6-DOF object pose estimation, which exploits both 2D and 3D universal features of input color and point clouds to establish semantic similarity-based correspondences and can be extended to unseen categories without additional model fine-tuning. Our method begins with combining efficient 2D universal features to find sparse correspondences between intra-category objects and gets initial coarse pose. To handle the correspondence degradation of 2D universal features if the pose deviates much from the target pose, we use an iterative strategy to optimize the pose. Subsequently, to resolve pose ambiguities due to shape differences between intra-category objects, the coarse pose is refined by optimizing with dense alignment constraint of 3D universal features. Our method outperforms previous methods on the REAL275 and Wild6D benchmarks for unseen categories. We will release our code upon acceptance.

Universal Features Guided Zero-Shot Category-Level Object Pose Estimation

As Large Language Models (LLMs) continue to evolve, more are being designed to handle long-context inputs. Despite this advancement, most of them still face challenges in accurately handling long-context tasks, often showing the "lost in the middle" issue. We identify that insufficient retrieval capability is one of the important reasons for this issue. To tackle this challenge, we propose a novel approach to design training data for long-context tasks, aiming at augmenting LLMs' proficiency in extracting key information from long context. Specially, we incorporate an additional part named "paraphrasing the original text" when constructing the answer of training samples and then fine-tuning the model. Experimenting on LongBench and NaturalQuestions Multi-document-QA dataset with models of Llama and Qwen series, our method achieves an improvement of up to 8.48% and 4.48% in average scores, respectively, showing effectiveness in improving the model’s performance on long-context tasks.

Training with “Paraphrasing the Original Text” Teaches LLM to Better Retrieve in Long-Context Tasks

Recently, numerous robust image hashing schemes have been developed for content identification. However, many of these schemes face the challenges of maintaining discrimination while simultaneously resisting large-scale attacks. In this paper, we propose a robust image hashing scheme based on Contrastive Masked Autoencoder with weak-strong augmentation Alignment (CMAA). Leveraging contrastive learning, CMAA is designed to learn features that are robust to large-scale and hybrid attacks while maintaining the discrimination of those features.  Specially, it utilizes distribution divergence to align weak attack augmented features with strong attack augmented features, namely weak-strong augmentation alignment, for enhancing the robustness to strong attacks. Additionally, a masked vision transformer is incorporated to further boost content identification performance. CMAA also includes a parameter-free quantization layer to mitigate the loss induced by binarization. Experimental results demonstrate that our method exhibits remarkable robustness against various attacks, including challenging ones such as rotation and hybrid attacks, and delivers excellent identification performance with an $F_1$ score close to 1.0.

Robust Image Hashing Based on Contrastive Masked Autoencoder with Weak-Strong Augmentation Alignment

Sequential recommendation (SR) systems predict user preferences by analyzing time-ordered interaction sequences. A common challenge for SR is data sparsity, as users typically interact with only a limited number of items. 
While contrastive learning has been employed in previous approaches to address the challenges, these methods often adopt binary labels, missing finer patterns and overlooking detailed information in subsequent behaviors of users. Additionally, they rely on random sampling to select negatives in contrastive learning, which may not yield sufficiently hard negatives during later training stages.
In this paper, we propose Future data utilization with Enduring Negatives for contrastive learning in sequential Recommendation (FENRec). Our approach aims to leverage future data with time-dependent soft labels and generate enduring hard negatives from existing data, thereby enhancing the effectiveness in tackling data sparsity. Experiment results demonstrate our state-of-the-art performance across four benchmark datasets, with an average improvement of 6.16% across all metrics.

Future Sight and Tough Fights: Revolutionizing Sequential Recommendation with FENRec

Open-vocabulary Scene Graph Generation (OV-SGG) overcomes the limitations of the closed-set assumption by aligning visual relationship representations with open-vocabulary textual representations. This enables the identification of novel visual relationships, making it applicable to real-world scenarios with diverse relationships.  However, existing OV-SGG methods are constrained by fixed text representations, limiting diversity and accuracy in image-text alignment.  To address these challenges, we propose the Relation-Aware Hierarchical Prompting (RAHP) framework, which enhances text representation by integrating subject-object and region-specific relation information.  Our approach employs entity clustering to manage the complexity of the relation triplet category space, ensuring the practicality of incorporating subject-object information.  Additionally, we utilize a large language model (LLM) to generate detailed region-aware prompts, capturing fine-grained visual interactions and improving alignment between visual and textual modalities.  RAHP also introduces a dynamic selection mechanism within Vision-Language Models (VLMs), which adaptively selects relevant text prompts based on the visual content, reducing noise from irrelevant prompts.  Extensive experiments on the Visual Genome and Open Images v6 datasets demonstrate that our framework consistently achieves state-of-the-art performance, demonstrating its effectiveness in addressing the challenges of open-vocabulary scene graph generation.

Downloads

Next from AAAI 2025

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach

Similar lecture

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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 2025

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach

Similar lecture

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads