Canada

Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames.
However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. 
Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities.
Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video.
On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2\% and +8.7\% J&amp;F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at https://github.com/OpenGVLab/MUTR.

AAAI 2024

Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation

language and vision，multi-modal vision，motion & tracking，segmentation

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

AAAI 2026

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.

Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames.
However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. 
Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities.
Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video.
On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2\% and +8.7\% J&F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at https://github.com/OpenGVLab/MUTR.

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

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-24 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.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/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. 

Cutting planes (cuts) play an important role in solving mixed-integer linear programs (MILPs), as they significantly tighten the dual bounds and improve the solving performance. A key problem for cuts is when to stop cuts generation, which is important for the efficiency of solving MILPs. However, many modern MILP solvers employ hard-coded heuristics to tackle this problem, which tends to neglect underlying patterns among MILPs from certain applications. To address this challenge, we formulate the cuts generation stop problem as a reinforcement learning problem and propose a novel hybrid graph representation model (HYGRO) to learn effective stopping strategies. An appealing feature of HYGRO is that it can effectively capture both the dynamic and static features of MILPs, enabling dynamic decision-making for the stopping strategies. To the best of our knowledge, HYGRO is the first data-driven method to tackle the cuts generation stop problem. By integrating our approach with modern solvers, experiments demonstrate that HYGRO significantly improves the efficiency of solving MILPs compared to competitive baselines, achieving up to 31% improvement.

Learning to Stop Cut Generation for Efficient Mixed-Integer Linear Programming

Nowadays, closed-set perception methods for autonomous driving perform well on datasets containing normal scenes. However, they still struggle to handle anomalies in the real world, such as unknown objects that have never been seen while training. The lack of public datasets to evaluate the model performance on anomaly and corner cases has hindered the development of reliable autonomous driving systems. Therefore, we propose a multimodal Synthetic Dataset for Anomaly and Corner case detection, called SDAC, which encompasses anomalies captured from multi-view cameras and the LiDAR sensor, providing a rich set of annotations for multiple mainstream perception tasks. SDAC is the first public dataset for autonomous driving that categorizes anomalies into object, scene, and scenario levels, allowing the evaluation under different anomalous conditions. Experiments show that closed-set models suffer significant performance drops on anomaly subsets in SDAC. Existing anomaly detection methods fail to achieve satisfactory performance, suggesting that anomaly detection remains a challenging problem. We anticipate that our SDAC dataset could foster the development of safe and reliable systems for autonomous driving.

SDAC: A Multimodal Synthetic Dataset for Anomaly and Corner Case Detection in Autonomous Driving

Identifying novel drug-drug interactions (DDIs) is a crucial task in pharmacology, as the interference between pharmacological substances can pose serious medical risks. In recent years, several network-based techniques have emerged for predicting DDIs. However, they primarily focus on local structures within DDI-related networks, often overlooking the significance of indirect connections between pairwise drug nodes from a global perspective. Additionally, effectively handling heterogeneous information present in both biomedical knowledge graphs and drug molecular graphs remains a challenge for improved performance of DDI prediction. To address these limitations, we propose a Transformer-based relatIon-aware Graph rEpresentation leaRning framework (TIGER) for DDI prediction. TIGER leverages the Transformer architecture to effectively exploit the structure of heterogeneous graph, which allows it direct learning of long dependencies and high-order structures. Furthermore, TIGER incorporates a relation-aware self-attention mechanism, capturing a diverse range of semantic relations that exist between pairs of nodes in heterogeneous graph. In addition to these advancements, TIGER enhances predictive accuracy by modeling DDI prediction task using a dual-channel network, where drug molecular graph and biomedical knowledge graph are fed into two respective channels. By incorporating embeddings obtained at graph and node levels, TIGER can benefit from structural properties of drugs as well as rich contextual information provided by biomedical knowledge graph. Extensive experiments conducted on three real-world datasets demonstrate the effectiveness of TIGER in DDI prediction. Furthermore, case studies highlight its ability to provide a deeper understanding of underlying mechanisms of DDIs.

Dual-Channel Learning Framework for Drug-Drug Interaction Prediction via Relation-Aware Heterogeneous Graph Transformer

Retrieving appropriate records from the external knowledge base to generate informative responses is the core capability of end-to-end task-oriented dialogue systems (EToDs). Most of the existing methods additionally train the retrieval model or use the memory network to retrieve the knowledge base, which decouples the knowledge retrieval task from the response generation task, making it difficult to jointly optimize and failing to capture the internal relationship between the two tasks. In this paper, we propose a simple and unified generative model for task-oriented dialogue systems, which recasts the EToDs task as a single sequence generation task and uses maximum likelihood training to train the two tasks in a unified manner. To prevent the generation of non-existent records, we design the prefix trie to constrain the model generation, which ensures consistency between the generated records and the existing records in the knowledge base. Experimental results on three public benchmark datasets demonstrate that our method achieves robust performance on generating system responses and outperforms the baseline systems. To facilitate future research in this area, the code is available at https://github.com/dzy1011/Uni-ToD.

From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue | VIDEO

Audio-visual segmentation (AVS) aims to locate and segment the sounding objects in a given video, which demands audio-driven pixel-level scene understanding. The existing methods cannot fully process the fine-grained correlations between audio and visual cues across various situations dynamically. They also face challenges in adapting to complex scenarios, such as evolving audio, the coexistence of multiple objects, and more. In this paper, we propose AVSegFormer, a novel framework for AVS that leverages the transformer architecture. Specifically, It comprises a dense audio-visual mixer, which can dynamically adjust interested visual features, and a sparse audio-visual decoder, which implicitly separates audio sources and automatically matches optimal visual features. Combining both components provides a more robust bidirectional conditional multi-modal representation, improving the segmentation performance in different scenarios. Extensive experiments demonstrate that AVSegFormer achieves state-of-the-art results on the AVS benchmark. The code is available at https://github.com/vvvb-github/AVSegFormer.

AVSegFormer: Audio-Visual Segmentation with Transformer

Pandora's problem is a fundamental model that studies optimal search under costly inspection. In the classic version, there are $n$ boxes, each associated with a known cost and a known distribution over values. A strategy inspects the boxes sequentially and obtains a utility that equals the difference between the maximum value of an inspected box and the total inspection cost. Weitzman [1979] presented a surprisingly simple strategy that obtains the optimal expected utility.
    
In this work we introduce a new variant of Pandora's problem in which every box is also associated with a publicly known deadline, indicating the final round by which its value may be chosen. This model captures many real-life scenarios where alternatives admit deadlines, such as candidate interviews and college admissions. Our main result is an efficient threshold-based strategy that achieves a constant approximation relative to the performance of the optimal strategy for the deadlines setting.

Pandora’s Problem with Deadlines | VIDEO

Recently, Large Language Models (LLMs) have shown impressive abilities in code generation. However, existing LLMs' decoding strategies are designed for Natural Language (NL) generation, overlooking the differences between NL and programming languages (PL). Due to this oversight, a better decoding strategy for code generation remains an open question. In this paper, we conduct the first systematic study to explore a decoding strategy specialized in code generation. With an analysis of loss distributions of code tokens, we find that code tokens can be divided into two categories: challenging tokens that are difficult to predict and confident tokens that can be easily inferred. Among them, the challenging tokens mainly appear at the beginning of a code block. Inspired by the above findings, we propose a simple yet effective method: Adaptive Temperature (AdapT) sampling, which dynamically adjusts the temperature coefficient when decoding different tokens. We apply a larger temperature when sampling for challenging tokens, allowing LLMs to explore diverse choices. We employ a smaller temperature for confident tokens avoiding the influence of tail randomness noises. We apply AdapT sampling to LLMs with different sizes and conduct evaluations on two popular datasets. Results show that AdapT sampling significantly outperforms state-of-the-art decoding strategy.

Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models

Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by learning from seen compositions. Composing the learned knowledge of seen primitives, \emph{i.e.}, attributes or objects, into novel compositions is critical for CZSL. In this work, we propose to explicitly retrieve knowledge of seen primitives for compositional zero-shot learning. We present a retrieval-augmented method, which augments standard multi-path classification methods with two retrieval modules. Specifically, we construct two databases storing the attribute and object representations of training images, respectively. For an input training/testing image, we use two retrieval modules to retrieve representations of training images with the same attribute and object, respectively. The primitive representations of the input image are augmented by using the retrieved representations, for composition recognition. By referencing semantically similar images, the proposed method is capable of recalling knowledge of seen primitives for compositional generalization. Experiments on three widely-used datasets show the effectiveness of the proposed method.

Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning | VIDEO

In recent years, there has been a growing interest in exploring dialogues with more complex goals, such as negotiation, persuasion, and emotional support, which go beyond traditional service-focused dialogue systems. Apart from the requirement for much more sophisticated strategic reasoning and communication skills, a significant challenge of these tasks lies in the difficulty of objectively measuring the achievement of their goals in a quantifiable way, making it difficult for existing research to directly optimize the dialogue procedure towards them. In our work, we emphasize the multifaceted nature of complex dialogue goals and argue that it is more feasible to accomplish them by comprehensively considering and jointly promoting their different aspects. To this end, we propose a novel dialogue framework, Cooper, which coordinates multiple specialized agents, each dedicated to a specific dialogue goal aspect separately, to approach the complex objective. Through this divide-and-conquer manner, we make complex dialogue goals more approachable and elicit greater intelligence via the collaboration of individual agents. Experiments on persuasion and emotional support dialogues demonstrate the superiority of our method over a set of competitive baselines.

Cooper: Coordinating Specialized Agents towards a Complex Dialogue Goal

Previous 3D hand pose estimation methods primarily rely on a single modality, either RGB or depth, and the comprehensive utilization of the dual modalities has not been extensively explored. RGB and depth data provide complementary information and thus can be fused to enhance the robustness of 3D hand pose estimation. However, there exist two problems for applying existing fusion methods in 3D hand pose estimation: redundancy of dense feature fusion and ambiguity of visual features. First, pixel-wise feature interactions introduce high computational costs and ineffective calculations of invalid pixels. Second, visual features suffer from ambiguity due to color and texture similarities, as well as depth holes and noise caused by frequent hand movements, which interferes with modeling cross-modal correlations. In this paper, we propose Keypoint-Fusion for RGB-D based 3D hand pose estimation, which leverages the unique advantages of dual modalities to mutually eliminate the feature ambiguity, and performs cross-modal feature fusion in a more efficient way. Specifically, we focus cross-modal fusion on sparse yet informative spatial regions (i.e. keypoints). Meanwhile, by explicitly extracting relatively more reliable information as disambiguation evidence, depth modality provides 3D geometric information for RGB feature pixels, and RGB modality complements the precise edge information lost due to the depth noise. Keypoint-Fusion achieves state-of-the-art performance on two challenging hand datasets, significantly decreasing the error compared with previous single-modal methods.

Downloads

Next from AAAI 2024

Learning to Stop Cut Generation for Efficient Mixed-Integer Linear Programming

Similar lecture

Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory