Singapore

The development of multimodal large language models (MLLMs) has advanced general video understanding. However, existing video evaluation benchmarks primarily focus on non-interactive videos, such as movies and recordings. To fill this gap, this paper proposes the first omnimodal benchmark for interactive livestream videos, LiViBench. It features a diverse set of 24 tasks, highlighting the perceptual, reasoning, and livestream-specific challenges. To efficiently construct the dataset, we design a standardized semi-automatic annotation workflow that incorporates the human-in-the-loop at multiple stages. The workflow leverages multiple MLLMs to form a multi-agent system for comprehensive video description and uses a seed-question-driven method to construct high-quality annotations. All interactive videos in the benchmark include audio, speech, and real-time comments modalities. To enhance models&#39; understanding of interactive videos, we design tailored two-stage instruction-tuning and propose a Video-to-Comment Retrieval (VCR) module to improve the model&#39;s ability to utilize real-time comments. Based on these advancements, we develop LiVi-LLM-7B, an MLLM with enhanced knowledge of interactive livestreams. Experiments show that our model outperforms larger open-source models with up to 72B parameters, narrows the gap with leading proprietary models on LiViBench, and achieves enhanced performance on general video benchmarks, including VideoMME, LongVideoBench, MLVU, and VideoEval-Pro.

AAAI 2026

LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding

large multimodal models (lmms)

video understanding & activity analysis

language and vision

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

The development of multimodal large language models (MLLMs) has advanced general video understanding. However, existing video evaluation benchmarks primarily focus on non-interactive videos, such as movies and recordings. To fill this gap, this paper proposes the first omnimodal benchmark for interactive livestream videos, LiViBench. It features a diverse set of 24 tasks, highlighting the perceptual, reasoning, and livestream-specific challenges. To efficiently construct the dataset, we design a standardized semi-automatic annotation workflow that incorporates the human-in-the-loop at multiple stages. The workflow leverages multiple MLLMs to form a multi-agent system for comprehensive video description and uses a seed-question-driven method to construct high-quality annotations. All interactive videos in the benchmark include audio, speech, and real-time comments modalities. To enhance models' understanding of interactive videos, we design tailored two-stage instruction-tuning and propose a Video-to-Comment Retrieval (VCR) module to improve the model's ability to utilize real-time comments. Based on these advancements, we develop LiVi-LLM-7B, an MLLM with enhanced knowledge of interactive livestreams. Experiments show that our model outperforms larger open-source models with up to 72B parameters, narrows the gap with leading proprietary models on LiViBench, and achieves enhanced performance on general video benchmarks, including VideoMME, LongVideoBench, MLVU, and VideoEval-Pro.

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.

AI systems can perpetuate and amplify existing biases and discrimination, prompting academic efforts to develop mitigation techniques. Despite progress, real-world deployments often expose limitations in current methods and tools--- overlooking preprocessing, adopting poor evaluation protocols, and failing to integrate domain knowledge. These gaps hinder the effectiveness and reproducibility of fairness solutions.
AutoML has emerged as a promising approach to optimize AI pipelines and provide an evaluation framework.
However, challenges persist, especially around: intersectionality support, explainability, and stakeholder engagement, which are crucial for fairness and human-centric AI development.
We introduce HAMLET4Fairness, integrating AutoML with human-centered approaches grounded in logic and argumentation. This enhances interactivity and transparency in AI pipeline optimization while supporting intersectional fairness. HAMLET4Fairness leverages multi-objective optimization and bounds the search space by user-defined constraints, adapting the CRISP-DM methodology for co-design and collaborative problem-solving.
We validate HAMLET4Fairness through real-world case studies, showing improved fairness outcomes and scalability. The evaluation also offers insights into how preprocessing choices affect fairness performance.

HAMLET4Fairness: Enhancing Fairness in AI Pipelines Through Human-Centered AutoML and Argumentation

Online continual learning (OCL) aims at learning a non-stationary data stream in a way of reading each data sample only once, and hence suffers from the trade-off of catastrophic forgetting and insufficient learning. In this work, we firstly analytically establish relationship between loss functions and model parameters from the Bayesian perspective. Based on our analysis, we subsequently propose a parameter merging method with gradient-guided supermasks. Our method leverages 1-order and 2-order gradient information to construct supermasks that determine the merging weights between the old and new models. Our method performs direct arithmetic operations on parameters to update models, beyond traditional gradient descent. We further discover that a widely-used premise that 1-order gradients can be negligible is invalid in OCL, due to slow convergence incurred by insufficient learning. Additionally, we utilize a dual-model dual-view distillation strategy that can align output distributions of the new and merged models for each sample, further enhancing model performance. Extensive experiments are conducted on four benchmarks in OCL settings, including CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet-100. Experimental results demonstrate that our method is effective, and achieves a substantial boost over previous methods.

Parameter Merging with Gradient-Guided Supermasks in Online Continual Learning

Human-AI cooperative classification (HAI-CC) aims to develop hybrid intelligent systems that enhance decision-making in various high-stakes real-world scenarios by leveraging both human expertise and AI capabilities. Current HAI-CC methods primarily focus on learning-to-defer (L2D), where decisions are deferred to human experts when AI is not confident, and learning-to-complement (L2C), where AI and human experts make predictions cooperatively. However, existing research in both L2D and L2C has not effectively been explored under diverse expert knowledge to improve decision-making, particularly when constrained by the operation cost of human involvement. In this paper, we address this research gap by proposing the Coverage-constrained Learning to Defer and Complement with Specific Experts (CL2DC) method. In particular, CL2DC assesses input data before making final decisions through either AI prediction alone or by deferring to or complementing a specific human expert. Furthermore, we propose a coverage-constrained optimisation to control the cooperation cost, ensuring it approximates a target probability for AI-only selection. This approach enables an effective assessment of system performance within a specified budget. Comprehensive evaluations on both synthetic and real-world datasets demonstrate that CL2DC achieves superior performance compared to state-of-the-art HAI-CC methods.

Coverage-Constrained Human-AI Cooperation with Multiple Experts

LLM-based multi-agent systems exhibit strong collaborative capabilities but often suffer from redundant communication and excessive token overhead. Existing methods typically enhance efficiency through pretrained GNNs or greedy algorithms, but often isolate pre- and post-task optimization, lacking a unified strategy. To this end, we present SafeSieve, a progressive and adaptive multi-agent pruning algorithm that dynamically refines the inter-agent communication through a novel dual-mechanism. SafeSieve integrates initial LLM-based semantic evaluation with accumulated performance feedback, enabling a smooth transition from heuristic initialization to experience-driven refinement. Unlike existing greedy Top-k pruning methods, SafeSieve employs 0-extension clustering to preserve structurally coherent agent groups while eliminating ineffective links. Experiments across benchmarks (SVAMP, HumanEval, etc.) showcase that SafeSieve achieves 94.01\% average accuracy while reducing token usage by 12.4\%-27.8\%. Results further demonstrate robustness under prompt injection attacks (1.23\% average accuracy drop). In heterogeneous settings, SafeSieve reduces deployment costs by 13.3\% while maintaining performance. These results establish SafeSieve as a robust, efficient, and scalable framework for practical multi-agent systems. Our code can be found in the Supplementary Material.

SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication

Conventional fairness in multi-tenant Large Language Model (LLM) inference services is typically defined by system-centric metrics, such as equitable resource allocation. This paper argues that this paradigm is fundamentally flawed, as it creates a gap between measured system performance and actual user-perceived quality. We challenge this notion by introducing and formalizing Experiential Fairness, a user-centric paradigm that shifts the objective from equality of opportunity (resource access) to equity of outcome (user experience). To operationalize this, we propose ExFairS, a lightweight scheduling framework that evaluates each user's state via a composite metric integrating SLO compliance with resource consumption, and then acts on this evaluation through a credit-based priority mechanism. Extensive experiments on an 8-GPU NVIDIA V100 node show that ExFairS reduces the SLO violation rate by up to 100% and improves system throughput by 14-21.9%, outperforming state-of-the-art schedulers and delivering a demonstrably higher degree of Experiential Fairness.

Experiential Fairness: Bridging the Gap Between User Experience and Resource-Centric Fairness in Online LLM Services

The rapid advancements in artificial intelligence have significantly accelerated the adoption of speech recognition technology, leading to its widespread integration across various applications. However, this surge in usage also highlights a critical issue: audio data is highly vulnerable to unauthorized exposure and analysis, posing significant privacy risks for businesses and individuals. This paper introduces an Information-Obfuscation Reversible Adversarial Example (IO-RAE) framework, the pioneering method designed to safeguard audio privacy using reversible adversarial examples. IO-RAE leverages large language models to generate misleading yet contextually coherent content, effectively preventing unauthorized eavesdropping by humans and Automatic Speech Recognition (ASR) systems. Additionally, we propose the Cumulative Signal Attack technique, which mitigates high-frequency noise and enhances attack efficacy by targeting low-frequency signals. Our approach ensures the protection of audio data without degrading its quality or usability. Experimental evaluations demonstrate the superiority of our method, achieving a targeted misguidance rate of 96.5% and a remarkable 100% untargeted misguidance rate in obfuscating target keywords across multiple ASR models, including a commercial black-box system from Google. Furthermore, the quality of the recovered audio, measured by the Perceptual Evaluation of Speech Quality score, reached 4.45, comparable to high-quality original recordings. Notably, the recovered audio processed by ASR systems exhibited an error rate of 0%, indicating nearly lossless recovery. These results highlight the practical applicability and effectiveness of our IO-RAE framework in protecting sensitive audio privacy.

IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection

Sparse Urban CrowdSensing (Sparse UCS) is a practical paradigm for completing full sensing maps from limited observations. However, existing methods typically rely on a time-discrete assumption, where data is considered static within fixed intervals. This simplification introduces significant errors as real-world data changes continuously. To address this, we propose a framework for time-continuous data completion. Our approach, Time-Aware Mamba-based Deep Matrix Factorization (TIME-DMF), leverages the Mamba architecture as a powerful temporal encoder. Crucially, we enhance Mamba with a novel time-aware mechanism that explicitly incorporates the actual, often irregular, physical time intervals between observations into its state transitions. This allows our model to accurately capture true temporal dynamics and generate high-fidelity data for any queried moment in time through a query-generate mechanism. Extensive experiments on five diverse sensing tasks demonstrate that TIME-DMF significantly outperforms state-of-the-art methods, validating the superiority of the time-continuous paradigm for Sparse UCS. Our code is available at https://anonymous.4open.science/r/Time-DMF-B373/.

Toward Time-Continuous Data Inference in Sparse Urban CrowdSensing

Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language models (LLMs) in recent years. A promising direction to further improve post-pruning performance is weight permutation, which reorders model weights into patterns more amenable to pruning. However, the exponential growth of the permutation search space with the scale of Transformer architectures forces most methods to rely on greedy or heuristic algorithms, limiting the effectiveness of reordering.


In this work, we propose a novel end-to-end learnable permutation framework. Our method introduces a learnable permutation cost matrix to quantify the cost of swapping any two input channels
of a given weight matrix, a differentiable bipartite matching solver to obtain the optimal binary permutation matrix given a cost matrix, and a sparsity optimization loss function to directly optimize the permutation operator.
We extensively validate our approach on vision and language Transformers, demonstrating that our method achieves state-of-the-art permutation results for structured sparsity.

Learnable Permutation for Structured Sparsity on Transformer Models

Recent advances in model compression have highlighted the potential of low-bit precision techniques, with Binary Neural Networks (BNNs) attracting attention for their extreme efficiency. However, extreme quantization in BNNs limits representational capacity and destabilizes training, posing significant challenges for lightweight architectures with depth-wise convolutions.
To address this, we propose a 1.58-bit convolution to enhance expressiveness and a pre-BN residual connection to stabilize optimization by improving the Hessian condition number. These innovations enable the first successful binarization of depth-wise convolutions in BNNs.
Our method achieves 32M OPs on ImageNet with MobileNet V1, establishing a new state-of-the-art in BNNs by outperforming prior methods with comparable OPs. Moreover, it consistently outperforms existing methods on various datasets, including CIFAR-10, CIFAR-100, STL-10, Tiny ImageNet, and Oxford Flowers 102, with accuracy improvements of up to 9.3 percentage points.

BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?

Economic decision‑making depends not only on structured signals—such as prices and taxes—but also on unstructured language, including peer dialogue and media narratives. While multi‑agent reinforcement learning (MARL) has shown promise in optimizing economic decisions, it struggles with the semantic ambiguity and contextual richness of language. We propose LAMP (Language‑Augmented Multi‑Agent Policy), the first framework to integrate language into economic decision‑making, narrowing the gap to real‑world settings.
LAMP follows a Think–Speak–Decide pipeline:
(1) Think interprets numerical observations to extract short‑term shocks and long‑term trends, caching high‑value reasoning trajectories.
(2) Speak crafts and exchanges strategic messages based on the reasoning, updating beliefs by parsing peer communications.
(3) Decide fuses numerical data, reasoning, and reflections into a MARL policy to optimize language‑augmented decision‑making.
Experiments in economic simulation show that LAMP outperforms both MARL and LLM‑only baselines in cumulative return (+63.5%, +34.0%), robustness (+18.8%, +59.4%), and interpretability. These results demonstrates the potential of language‑augmented policies to deliver more effective and robust economic strategies.

Content not yet available

Next from AAAI 2026

HAMLET4Fairness: Enhancing Fairness in AI Pipelines Through Human-Centered AutoML and Argumentation

Similar lecture

ProLongVid: A Simple but Strong Baseline for Long-context Video Instruction Tuning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES