United States

Glass surfaces are becoming increasingly ubiquitous as modern buildings tend to use a lot of glass panels. This, however, poses substantial challenges to the operations of autonomous systems such as robots, self-driving cars, and drones, as the glass panels can become transparent obstacles to navigation. Existing works attempt to exploit various cues, including glass boundary context or reflections, as a prior. However, they are all based on input RGB images. We observe that the transmission of 3D depth sensor light through glass surfaces often produces blank regions in the depth maps, which can offer additional insights to complement the RGB image features for glass surface detection. 
In this work, we propose a large-scale RGB-D glass surface detection dataset, \textit{RGB-D GSD}, for rigorous experiments and future research. It contains 3,009 images offering a wide range of real-world RGB-D glass surface categories, paired with precise annotations. Moreover, we propose a novel glass surface detection framework combining RGB and depth information, with two novel modules: a cross-modal context mining (CCM) module to adaptively learn individual and mutual context features from RGB and depth information, and a depth-missing aware attention (DAA) module to explicitly exploit spatial locations where missing depths occur to help detect the presence of glass surfaces.
Experimental results show that our proposed model outperforms state-of-the-art methods.

AAAI 2025

Leveraging RGB-D Data with Cross-Modal Context Mining for Glass Surface Detection

low level physics based vision

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.



Sequential recommendation aims to predict the next item a user is likely to interact with based on their historical interaction sequence. Capturing user intent is crucial in this process, as each interaction is typically driven by specific intentions (e.g., buying skincare products for skin maintenance, buying makeup for cosmetic purposes, etc.). However, users often have multiple, dynamically changing intents, making it challenging for models to accurately learn these intents when relying on the entire historical sequence as input. To address this, we developed a novel framework called Intent Oriented Contrastive Learning for Sequential Recommendation (IOCLRec). This framework begins by segmenting users’ sequential behaviors into multiple subsequences, which represent the coarse-grained intents of users at different points in their interaction history. These subsequences form the basis for the three contrastive learning modules within IOCLRec. The fine-grained intent contrastive learning module uncovers detailed intent representations, while the single-intent and multi-intent contrastive learning modules utilize intent-oriented data augmentation operators to capture the diverse intents of users. These three modules work synergistically, driving comprehensive performance optimization in intricate sequential recommendation scenarios. Our method has been extensively evaluated on four public datasets, demonstrating superior effectiveness.

Intent Oriented Contrastive Learning for Sequential Recommendation

Recent research explores the potential of Diffusion Models (DMs) for consistent object editing, which aims to modify object position, size, and composition, etc., while preserving the consistency of objects and background without changing their texture and attributes. Current inference-time methods often rely on DDIM inversion, which inherently compromises efficiency and the achievable consistency of edited images. Recent methods also utilize energy guidance which iteratively updates the predicted noise and can drive the latents away from the original image, resulting in distortions. In this paper, we propose PixelMan, an inversion-free and training-free method for achieving consistent object editing via Pixel Manipulation and generation, where we directly create a duplicate copy of the source object at target location in the pixel space, and introduce an efficient sampling approach to iteratively harmonize the manipulated object into the target location and inpaint its original location, while ensuring image consistency by anchoring the edited image to be generated to the pixel-manipulated image as well as by introducing various consistency-preserving optimization techniques during inference. Experimental evaluations based on benchmark datasets as well as extensive visual comparisons show that in as few as 16 inference steps, PixelMan outperforms a range of state-of-the-art training-based and training-free methods (usually requiring 50 steps) on multiple consistent object editing tasks.

PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation

Designing expressive generative models that support exact and efficient inference is a core question in probabilistic ML. Probabilistic circuits (PCs) offer a framework where this tractability-vs-expressiveness trade-off can be analyzed theoretically. Recently, squared PCs encoding subtractive mixtures via negative parameters have emerged as tractable models that can be exponentially more expressive than monotonic PCs, i.e., PCs with positive parameters only. In this paper we provide a more precise theoretical characterization of the expressiveness relationships among these models. First, we prove that squared PCs can be less expressive than monotonic ones. Second, we formalize a novel class of PCs – sum of squares PCs – that can be exponentially more expressive than both squared and monotonic PCs. Around sum of squares PCs, we build an expressiveness hierarchy that allows us to precisely unify and separate different tractable model classes such as Born Machines and PSD models, and other recently introduced tractable probabilistic models by using complex parameters. Finally, we empirically show the effectiveness of sum of squares circuits in performing distribution estimation.

Sum of Squares Circuits

Large Language Models (LLMs) have permeated various Natural Language Processing (NLP) tasks. For the summarization tasks, LLMs can generate well-structured rationales, which consist of Essential Aspects (EA), Associated Sentences (AS) and Triple Entity Relations (TER). These rationales guide smaller models ($\leq$1B) to produce better summaries. However, their high deployment costs ($\geq$70B), such as substantial storage space and high computing requirements, limit their utilization in resource-constrained environments. Furthermore, effectively distilling these structured rationales from LLMs into Small Language Models (SLMs) models remains a challenge. To address this, we propose the $\textbf{L}$LM-based $\textbf{S}$tructured $\textbf{R}$ationale-guided $\textbf{M}$ulti-view $\textbf{W}$eak-gate $\textbf{F}$usion framework (LSR-MWF). The framework initially employs LLMs to dig structural rationales from a document, considering multiple viewpoints such as EA, AS, and TER. Then, it develop a multi-step summary generation evaluation strategy to select high-quality structured rationales. Subsequently, it aligns with these rationales using additional modules organized in a hierarchical structure. Finally, the framework integrates the features output by these modules with original abstractive model through a weak-gated mechanism. Experimental results on two publicly available CNN/DailyMail and XSum datasets show that our method improves the performance of the abstractive model, outperforming baselines by 11.2\% and 5.8\%, respectively. In addition, our method improves the interpretability of summary generation from the viewpoints of EA, AS and TER.

Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive Summarization

Enhancing the performance of semantic segmentation models with multi-spectral images (RGB-IR) is crucial, particularly for low-light and adverse environments. While multimodal fusion techniques aim to learn cross-modality features for generating fused images or engage in knowledge distillation, they often treat multi-modal and missing modality scenarios as separate challenges, which is not an optimal
approach. To address this, a novel multi-modal fusion approach called Optically-Guided Pixel-level contrastive learning Network (OGP-Net) is proposed, which uses Distillation with Multi-View Contrastive (DMC) and Distillation for Uni-modal Retention (DUR) to maintain the correlation between modality-shared and modality-specific features. DMC aligns the unimodal features by projecting the semantic information across modalities into a unified latent space, ensuring that the feature maps retain multi-modal representations. Pixel-level multi-view contrastive learning is then introduced, enabling modality-invariant representation learning. DUR is introduced to preserve modality-specific information by distilling detailed textures from RGB images into the optical branch of OGP-Net. Additionally, the Gated Spectral Unit (GSU) is incorporated into the framework to eliminate manual tuning and prevent forced feature alignment. Comprehensive experiments show that OGP-Net outperforms state-of-the-art models in multi-modal and missing modality scenarios across
three public benchmarking datasets. It achieves quicker convergence and learns efficiently from limited training samples.

OGP-Net: Optical Guidance Meets Pixel-Level Contrastive Distillation for Robust Multi-Modal and Missing Modality Segmentation

Graph neural networks for hyperbolic space has emerged as a powerful tool for embedding datasets exhibiting a highly non-Euclidean latent anatomy e.g.,  graphs with hierarchical structures. While several Hyperbolic Graph Neural Networks (Hy-GNNs) have been developed to enhance the representation of hierarchical datasets, they remain susceptible to noise and adversarial attacks, posing serious risks in critical applications. The absence of robust Hy-GNN frameworks underscores a pressing problem. This research addresses this challenge by introducing HyperDefender—a robust and flexible approach designed to fortify Hy-GNNs against adversarial attacks and noises. HyperDefender aims to secure the reliability of applications that depend on the integrity of hierarchical graph-structured data in real-world scenarios. Experimental results demonstrate that HyperDefender significantly improves node classification accuracy across various attacks, effectively mitigating the performance degradation typically observed in Hy-GNNs when the hierarchy in original datasets is compromised.

HyperDefender: A Robust Framework for Hyperbolic GNNs

Handling heterogeneous data in tabular datasets poses a significant challenge for deep learning models. While attention-based architectures and self-supervised learning have achieved notable success, their application to tabular data remains less effective over linear and tree based models.
Although several breakthroughs have been achieved by models which transform tables into uni-modal transformations like image, language and graph, these models often underperform in the presence of feature heterogeneity.
To address this gap, we introduce **TabGLM** (**Tab**ular **G**raph **L**anguage **M**odel), a novel multi-modal architecture designed to model both structural and semantic information from a table. 
TabGLM transforms each row of a table into a fully connected graph and serialized text, which are then encoded using a graph neural network (GNN) and a text encoder, respectively. By aligning these representations, TabGLM leverages complementary information from both modalities through a joint multi-modal self-supervised learning objective, thereby enhancing feature learning.
TabGLM's flexible graph-text pipeline efficiently processes heterogeneous datasets combining structural and semantic information with significantly fewer parameters than state-of-the-art approaches. Evaluations across 26 benchmark datasets demonstrate substantial performance gains, with TabGLM achieving an average AUCROC improvement of upto 6% over existing tabular learning methods.

TabGLM: Tabular Graph Language Model for Learning Transferable Representations Through Multi-Modal Consistency Minimization

This paper presents the Text Encoding Diffusion Model (TEncDM), a novel approach to diffusion modeling that operates in the space of pre-trained language model encodings. In contrast to traditionally used embeddings, encodings integrate contextual information. In our approach, we also employ a transformer-based decoder, specifically designed to incorporate context in the token prediction process. We conduct a comprehensive examination of the influence of the encoder, decoder, noise scheduler, and self-conditioning on zero-shot generation. Furthermore, we compare TEncDM with previous approaches on three conditional text generation tasks: QQP, XSum, and Wiki-Auto. The results show that TEncDM exhibits superior performance compared to existing non-autoregressive diffusion models.

TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings

Gaussian Process Regression (GPR) is a powerful and elegant method for learning complex functions from noisy data with a wide range of applications, including in safety-critical domains. Such applications have two key features: (i) they require rigorous error quantification, and (ii) the noise is often bounded and non-Gaussian due to, e.g., physical constraints. While error bounds for applying GPR in the presence of non-Gaussian noise exist, they tend to be overly restrictive and conservative in practice. In this paper, we provide novel error bounds for GPR under bounded support noise. Specifically, by relying on concentration inequalities and assuming that the latent function has low complexity in the reproducing kernel Hilbert space (RKHS) corresponding to the GP kernel, we derive both probabilistic and deterministic bounds on the error of the GPR. We show that these errors are substantially tighter than existing state-of-the-art bounds and are particularly well-suited for GPR with neural network kernels, i.e., Deep Kernel Learning (DKL). Furthermore, motivated by applications in safety-critical domains, we illustrate how these bounds can be combined with stochastic barrier functions to successfully quantify the safety probability of an unknown dynamical system from finite data. We validate the efficacy of our approach through several benchmarks and comparisons against existing bounds. The results show that our bounds are consistently smaller, and that DKLs can produce error bounds tighter than sample noise, significantly improving the safety probability of control systems.

Error Bounds for Gaussian Process Regression Under Bounded Support Noise with Applications to Safety Certification

In perpetual voting, multiple decisions are made in different moments of time. Taking the history of previous decisions into account allows us to satisfy properties such as proportionality over periods of time. In this paper, we consider the following question: is there a perpetual approval voting method that guarantees that no voter is dissatisfied too many times? We identify a sufficient condition on voter behavior ---which we call 'bounded conflicts' condition---under which a sublinear growth of dissatisfaction is possible. We provide a tight upper bound on the growth of dissatisfaction under bounded conflicts, using techniques from Kolmogorov complexity. We also observe that the approval voting with binary choices mimicks the machine learning setting of prediction with expert advice. This allows us to exemplify a voting method with sublinear guarantees on dissatisfaction under bounded conflicts, based on the standard techniques from prediction with expert advice.

Leveraging RGB-D Data with Cross-Modal Context Mining for Glass Surface Detection

Downloads

Next from AAAI 2025

Intent Oriented Contrastive Learning for Sequential Recommendation