Singapore

This paper focuses on jailbreaking attacks against large language models (LLMs), eliciting them to generate objectionable content in response to harmful user queries. Unlike previous LLM-jailbreaks that directly orient to LLMs, our approach begins by constructing a multimodal large language model (MLLM) through the incorporation of a visual module into the target LLM. Subsequently, we conduct an efficient MLLM-jailbreak to generate jailbreaking embeddings embJS. Finally, we convert the embJS into text space to facilitate the jailbreaking of the target LLM. Compared to direct LLM-jailbreaking, our approach is more efficient, as MLLMs are more vulnerable to jailbreaking than pure LLM. Additionally, to improve the attack success rate (ASR) of jailbreaking, we propose an image-text semantic matching scheme to identify a suitable initial input. Extensive experiments demonstrate that our approach surpasses current state-of-the-art methods in terms of both efficiency and effectiveness. Moreover, our approach exhibits superior cross-class jailbreaking capabilities.

AAAI 2026

Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak

jailbreak

multimodal

## 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.

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.

Graph Contrastive Learning (GCL) has recently emerged as a powerful paradigm for modeling user–item interactions and learning high-quality representations in recommender systems. While existing GCL-based methods benefit from data augmentation and sampling strategies, they often overlook the inherent limitations of the contrastive objectives: 1) Stacking multiple Graph Convolutional Network layers to capture high-order information often causes the over-smoothing phenomenon, where node representations become overly similar. 2) Structurally similar negative sample pairs may exhibit high cosine similarity, causing gradient saturation during representation optimization. To address the above challenges, we revisit matrix factorization in recommendation models and uncover its implicit connection to a parallel graph filter bank. This perspective reveals how overly aggressive low-pass or high-pass filtering distorts feature distributions, contributing to gradient saturation. Building on this insight, we propose Light Cosine Similarity Collaborative Filtering (LightCSCF), a margin-constrained method that improves gradient optimization in contrastive learning by focusing on structurally hard examples, alleviating both gradient saturation and boundary over-smoothing. Extensive experiments on three real-world datasets demonstrate that LightCSCF consistently outperforms state-of-the-art baselines in recommendation accuracy and robustness to data sparsity.

Revisiting Contrastive Learning in Collaborative Filtering via Parallel Graph Filters

The development of machine learning models increasingly relies on high-quality data that resides in private domains. To enable secure and value-driven data exchange under strict privacy regulations, federated learning (FL) has emerged as a key primitive by enabling the trading of model utilities instead of raw data. Among existing solutions, \textit{martFL} (CCS 2023) represents the most state-of-the-art FL-based data marketplace architecture, integrating privacy-preserving model evaluation, anomaly filtering, and verifiable trading protocols to enable robust and fair model utility exchange without revealing raw data. Despite its strengths, \textit{martFL} suffers from critical weaknesses at the evaluation layer, including plaintext score exposure and unverifiable and manipulable participant selection. To address these challenges, we propose \textit{MartDE}, a dedicated evaluation framework that augments FL data marketplaces with robust, privacy-preserving, and auditable mechanisms. \textit{MartDE} introduces encrypted utility scoring with client-side decryption to preserve score confidentiality, formally bounded anomaly filtering via squared similarity quantization, adaptive participant selection based on global model performance, and commitment-based verification to ensure consistency between declared and evaluated scores. We implement \textit{MartDE} and evaluate it across diverse datasets and adversarial conditions. Results show that \textit{MartDE} achieves superior accuracy, robustness, and cost-efficiency, providing a strong foundation for secure and trustworthy utility-driven data markets.

MartDE: A Privacy-Preserving and Cost-Efficient Evaluation Framework for Data Marketplaces

Test-time adaptation (TTA) has proven effective in mitigating performance drops under single-domain distribution shifts by updating model parameters during inference. However, real-world deployments often involve mixed distribution shifts---where test samples are affected by diverse and potentially conflicting domain factors---posing significant challenges even for state-of-the-art TTA methods. A key limitation in existing approaches is their reliance on a unified adaptation path, which fails to account for the fact that optimal gradient directions can vary significantly across different domains. Moreover, current benchmarks focus only on synthetic or homogeneous shifts, failing to capture the complexity of real-world heterogeneous mixed distribution shifts.
To address this, we propose MoETTA, a novel entropy-based TTA framework that integrates the Mixture-of-Experts (MoE) architecture. Rather than enforcing a single parameter update rule for all test samples, MoETTA introduces a set of structurally decoupled experts, enabling specialization along diverse gradient directions. This design allows the model to better accommodate heterogeneous shifts through flexible and disentangled parameter updates.
To simulate realistic deployment conditions, we introduce two new benchmarks: potpourri and potpourri+. While classical settings focus solely on synthetic corruptions (i.e., ImageNet-C), potpourri encompasses a broader range of domain shifts—including natural, artistic, and adversarial distortions—capturing more realistic deployment challenges. On top of that, potpourri+ further includes source-domain samples to evaluate robustness against catastrophic forgetting.
Extensive experiments across three mixed distribution shifts settings show that MoETTA consistently outperforms strong baselines, establishing new state-of-the-art performance and highlighting the benefit of modeling multiple adaptation directions via expert-level diversity.

MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm

We consider differentially private deep learning (DPDL), a standing challenge. Existing solutions on DPDL either require the assumption of a trusted data server (centralized DPDL) or suffer from poor utility (local DPDL); and hence their adoptions are hampered in real-world scenarios. We present CRYPTDP, a crypto-assisted differentially private deep learning approach in the two-server model. CRYPTDP employs two non-colluding servers to collaboratively and efficiently train differentially private deep learning over the secret shares of data owners' private data while protecting the confidentiality of the data from untrusted servers. CRYPTDP is the first approach with the best of both local DPDL and centralized DPDL models, which does not resort to trusted server like local DPDL and has the utility like centralized DPDL. In particular, we also make three innovations for addressing the major challenges like poor performance and security that beset CRYPTDP: We introduce a new secure computation and differential privacy friendly activation function; we propose a novel garbled-circuits-free most significant bit extraction protocol, and using the protocol we propose efficient and secure garbled-circuits-free protocols for activation function and max pooling over secret shares; leveraging noisy weights, we propose lightweight privacy-peserving convolution and fully connected layer computation protocols without costly secure multiplication. Exhaustive experiments show that CRYPTDP delivers significantly better performance than the state-of-the-art local DPDL, yields higher accuracy than the state-of-the-art centralized DPDL, and can achieve two orders of magnitude faster runtime than the state-of-the-art approach.

Efficient, Secure, Differentially Private Deep Learning in the Two-Server Model

As Large Language Models (LLMs) are increasingly popularized in the multilingual world, ensuring hallucination-free factuality becomes markedly crucial. 
However, existing benchmarks for evaluating the reliability of Multimodal Large Language Models (MLLMs) predominantly focus on textual or visual modalities with a primary emphasis on English, which creates a gap in evaluation when processing multilingual input, especially in speech.
To bridge this gap, we propose a novel Cross-lingual and Cross-modal Factuality benchmark (CCFQA). 
Specifically, the CCFQA benchmark contains parallel speech-text factual questions across 8 languages, designed to systematically evaluate MLLMs' cross-lingual and cross-modal factuality capabilities. 
Our experimental results demonstrate that current MLLMs still face substantial challenges on the CCFQA benchmark. 
Furthermore, we propose a few-shot transfer learning strategy that effectively transfers the Question Answering (QA) capabilities of LLMs in English to multilingual Spoken Question Answering (SQA) tasks, achieving competitive performance with GPT-4o-mini-Audio using just 5-shot training.
We release CCFQA as a foundational research resource to promote the development of MLLMs with more robust and reliable speech understanding capabilities. The code and the dataset are publicly available at: https://github.com/yxduir/ccfqa.

CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation

Condensed datasets offer a compact representation of larger datasets, but training models directly on them or using them to enhance model performance through knowledge distillation (KD) can result in suboptimal outcomes due to limited information. To address this, we propose a method that expands condensed datasets using model inversion, a technique for generating synthetic data based on the impressions of a pre-trained model on its training data. This approach is particularly well-suited for KD scenarios, as the teacher model is already pre-trained and retains knowledge of the original training data. By creating synthetic data that complements the condensed samples, we enrich the training set and better approximate the underlying data distribution, leading to improvements in student model accuracy during knowledge distillation. Our method demonstrates significant gains in KD accuracy compared to using condensed datasets alone and outperforms standard model inversion-based KD methods by up to 11.4% across various datasets and model architectures. Importantly, it remains effective even when using as few as one condensed sample per class, and can also enhance performance in few-shot scenarios where only limited real data samples are available.

Condensed Data Expansion Using Model Inversion for Knowledge Distillation

Cross-city urban flow prediction is critical for democratizing smart application benefits in data-scarce developing cities. However, existing methods face an inherent performance ceiling, constrained by both the inevitably finite samples from the source city and the distributional gap between cities. In this paper, we present PLM-CUP, the first theoretically-grounded framework that breaks this bottleneck by leveraging a pre-trained language model (PLM) as an additional source domain. Through an information-theoretic analysis of the generalization error bound, we reveal that the key challenge lies in constructing a semantic bridge encoder and a task-specific adapter to enable cross-domain alignment when incorporating a PLM. Accordingly, PLM-CUP adopts a three-stage architecture, including a semantic bridge encoder that transforms spatiotemporal flow patterns into languagealigned representations via trend-periodicity decomposition, a PLM fine-tuned for knowledge transfer, and a task adapter with spatiotemporal self-attention to conduct multi-step prediction. We further introduce GDAConv, a graph convolution module with dual activation functions that enhances spatial modeling throughout the framework. Experiments on real-world datasets demonstrate that PLM-CUP significantly outperforms state-of-the-art baselines, validating the effectiveness of the proposed PLM enhanced cross-city transfer paradigm for urban flow prediction.

Exploiting Pre-trained Language Model for Cross-city Urban Flow Prediction Guided by Information-theoretic Analysis

Enabling robots to grasp disorganized cloth for efficient storage is valuable in robot-assisted room organization. Diverse deformations of cloth and the stacking of multiple items limit grasping-pose estimation that relies on annotations. This necessitates segmenting each cloth item in an unsupervised manner before estimating the grasping position. However, existing segmentation methods primarily focus on improving metrics such as Intersection-over-Union and Pixel Accuracy, which cannot effectively measure the segmentation errors of the cloth area and thus lead to failure grasping position estimation. To address this challenge, we use False Discovery Rate (FDR) as a novel measure of segmentation errors and analyze its impact on grasping success. Our preliminary study reveals a negative correlation between segmentation FDR and grasping success rate, highlighting the need for more reliable segmentation in cluttered cloth scenarios. Therefore, we propose an unsupervised cloth segmentation network based on feature distance-weighted constraints, designed to reduce the false discovery rate in cloth area perception without requiring expensive pixel-level manual annotations. Additionally, to estimate the grasping position on the perceived cloth area, we introduce a strategy based on cloth surface wrinkle analysis, which operates without the need for annotations or training. By integrating the proposed segmentation network and grasping strategy, we develop a robotic system capable of sequentially grasping cluttered cloth from a table. Extensive real-world robotic experiments demonstrate the effectiveness of our approach, outperforming multiple baseline methods in segmentation FDR and grasping success rate.

Effective Robotic Cloth Grasping Through Suppressing False Discoveries

Video snapshot compressive imaging (SCI) captures dynamic scene sequences through a two-dimensional (2D) snapshot, fundamentally relying on optical modulation for hardware compression and the corresponding software reconstruction. While mainstream video SCI using random binary modulation has demonstrated success, it inevitably results in temporal aliasing during compression. One-hot modulation, activating only one sub-frame per pixel, provides a promising solution for achieving perfect temporal decoupling, thereby alleviating issues associated with aliasing. However, no algorithms currently exist to fully exploit this potential. To bridge this gap, we propose an algorithm specifically designed for one-hot masks. First, leveraging the decoupling properties of one-hot modulation, we transform the reconstruction task into a generative video inpainting problem and introduce a stochastic differential equation (SDE) of the forward process that aligns with the hardware compression process. Next, we identify limitations of the pure diffusion method for video SCI and propose a novel framework that combines one-step regression initialization with one-step diffusion refinement. Furthermore, to mitigate the spatial degradation caused by one-hot modulation, we implement a dual optical path at the hardware level, utilizing complementary information from another path to enhance the inpainted video. To our knowledge, this is the first work integrating diffusion into video SCI reconstruction. Experiments conducted on synthetic datasets and real scenes demonstrate the effectiveness of our method.

3One2: One-Step Regression plus One-Step Diffusion for One-Hot Modulation in Dual-Path Video Snapshot Compressive Imaging

Diffusion models have recently shown promise in time series forecasting, particularly for probabilistic predictions. However, they often fail to achieve state-of-the-art point estimation performance compared to regression-based methods. This limitation stems from difficulties in providing sufficient contextual bias to track distribution shifts and in balancing output diversity with the stability and precision required for point forecasts. Existing diffusion-based approaches mainly focus on full-distribution modeling under probabilistic frameworks, often with likelihood maximization objectives, while paying little attention to dedicated strategies for high-accuracy point estimation. Moreover, other existing point prediction diffusion methods frequently rely on pre-trained or jointly trained mature models for contextual bias, sacrificing the generative flexibility of diffusion models.

To address these challenges, we propose SimDiff, a single-stage, end-to-end framework. SimDiff employs a single unified Transformer network carefully tailored to serve as both denoiser and predictor, eliminating the need for external pre-trained or jointly trained regressors. It achieves state-of-the-art point estimation performance by leveraging intrinsic output diversity and improving mean squared error accuracy through multiple inference ensembling. Key innovations, including normalization independence and the median-of-means estimator, further enhance adaptability and stability. Extensive experiments demonstrate that SimDiff significantly outperforms existing methods in time series point forecasting. The implementation is publicly available at https://anonymous.4open.science/r/SimDiff-A41D.

Downloads

Next from AAAI 2026

Revisiting Contrastive Learning in Collaborative Filtering via Parallel Graph Filters

Similar lecture

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking

.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 2026

Revisiting Contrastive Learning in Collaborative Filtering via Parallel Graph Filters

Similar lecture

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking

Downloads