Singapore

Fine-tuning large language models on downstream tasks is crucial for realizing their cross-domain potential but often relies on sensitive data, raising privacy concerns. 
Differential privacy (DP) offers rigorous privacy guarantees and has been widely adopted in fine-tuning; however, naively injecting noise across the high-dimensional parameter space creates perturbations with large norms, degrading performance and destabilizing training. 
We propose DP-SFT, a two-stage subspace fine-tuning method that substantially reduces noise magnitude while preserving formal DP guarantees. Our intuition is that, during fine-tuning, significant parameter updates lie within a low-dimensional task-specific subspace, while other directions change minimally. 
Hence, we only inject DP noise into this subspace to protect privacy without perturbing irrelevant parameters. 
In phase one, we identify the subspace by analyzing principal gradient directions to capture task-specific update signals. 
In phase two, we project full gradients onto this subspace, add DP noise, and map the perturbed gradients back to the original parameter space for model updates, markedly lowering noise impact. 
Experiments on multiple datasets demonstrate that DP-SFT enhances accuracy and stability under stringent DP constraints, accelerates convergence, and achieves substantial gains over DP fine-tuning baselines. It provides a practical solution for differentially private fine-tuning of large models at scale.

AAAI 2026

Differentially Private Subspace Fine-Tuning for Large Language Models

nlp: safety and robustness

nlp: (large) language models

ml: privacy

Welcome to the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Continuing its mission of expanding and involving the science community of all European countries, EACL has selected the Malta community for the 18th EACL. Considering the importance of physical interaction among researchers, the conference will be held at the Hotel Radisson Blu, St. Julians, in Malta, from 17 to 22 of March, 2024. The conference will also feature the possibility to participate virtually. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language. 
#### [Conference Handbook](https://drive.google.com/file/d/13Wn38q0yev6U3RTgnf4Tn5T9GuAuZ-xW/view?usp=sharing) *downloadable*

To access the EACL 2024 event page you need to register [**here**](https://acl.swoogo.com/EACL2024). 

Please register!

EACL 2024

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

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.

Starting from the utilization of deep neural networks to approximate the state-action value function that led to winning one of the most challenging games, to algorithmic advancements that allowed solving problems without even explicitly stating the rules of the challenge at hand, reinforcement learning research has been the center of remarkable scientific progress for the past decade. In this paper, we focus on the key ingredients of this research progress and we analyze the canonical evaluation and design paradigms in reinforcement learning. We introduce the theoretical foundations of the underlying causes outlining that the asymptotic performance of reinforcement learning algorithms does not have a monotone relationship between performance rankings and data-regimes. We conduct large-scale experiments and our results demonstrate that a line of reinforcement learning research under the canonical design paradigms resulted in incorrect conclusions.

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

LLM-based solvers have emerged as a promising means of automating problem modeling and solving. However, they remain unreliable and often depend on iterative repair loops that result in significant latency. We introduce OptiHive, an LLM-based framework that produces high-quality solvers for optimization problems from natural-language descriptions without iterative self-correction. OptiHive uses a single batched LLM query to generate diverse components (solvers, problem instances, and validation tests) and filters out erroneous components to ensure fully interpretable outputs. Taking into account the imperfection of the generated components, we employ a statistical model to infer their true performance, enabling principled uncertainty quantification and solver selection. On tasks ranging from traditional optimization problems to challenging variants of the Multi-Depot Vehicle Routing Problem, OptiHive significantly outperforms baselines, increasing the optimality rate from 5\% to 92\% on the most complex problems.

OptiHive: Ensemble Selection for LLM-Based Optimization via Statistical Modeling

Differentiable simulators represent an environment’s dynamics as a differentiable function. Within robotics and autonomous driving, this property is used in Analytic Policy Gradients (APG), which relies on backpropagating through the dynamics to train accurate policies for diverse tasks. Here we show that differentiable simulation also has an important role in world modeling, where it can impart predictive, prescriptive, and counterfactual capabilities to an agent. Specifically, we design three novel task setups in which the differentiable dynamics are combined within an end-to-end computation graph not with a policy, but a state predictor. This allows us to learn relative odometry, optimal planners, and optimal inverse states. We collectively call these predictors Analytic World Models (AWMs) and demonstrate how differentiable simulation enables their efficient, end-to-end learning. In autonomous driving scenarios, they have broad applicability and can augment an agent’s decision-making beyond reactive control.

Unlocking Efficient Vehicle Dynamics Modeling via Analytic World Models

Multimodal learning has shown significant superiority on various tasks by integrating multiple modalities.
However, the interdependencies among modalities increase the susceptibility of multimodal models to adversarial attacks.
Existing methods mainly focus on attacks on specific modalities or indiscriminately attack all modalities. 
In this paper, we find that these approaches ignore the differences between modalities in their contribution to final robustness, resulting in suboptimal robustness performance.
To bridge this gap, we introduce \textbf{V}ulnerability-\textbf{A}ware \textbf{R}obust \textbf{M}ultimodal \textbf{A}dversarial \textbf{T}raining (\texttt{VARMAT}), a probe-in-training adversarial training method that improves multimodal robustness by identifying the vulnerability of each modality.
To be specific, \texttt{VARMAT} first explicitly quantifies the vulnerability of each modality, grounded in a first-order approximation of the attack objective (Probe). Then, we propose a targeted regularization term that penalizes modalities with high vulnerability, guiding robust learning while maintaining task accuracy (Training).
We demonstrate the enhanced robustness of our method across multiple multimodal datasets involving diverse modalities.
Finally, we achieve $\{12.73\%, 22.21\%, 11.19\%\}$ robustness improvement on three multimodal datasets, revealing a significant blind spot in multimodal adversarial training.

Vulnerability-Aware Robust Multimodal Adversarial Training

Label errors can significantly degrade model performance, making effective mechanisms crucial. Active error correction (AEC) addresses this by prioritizing data points for human re-labeling where corrections are expected to have significant impact. We extend AEC to distributed collaborative learning, where clients hold local data and a central server allocates labeling resources. Existing AEC methods assume centralized access and do not generalize to distributed settings. To overcome this, we use neural network weight gradients from client updates as proxies for local data and apply a Gaussian process in gradient space to strategically select clients for correction. Our method identifies gradient inconsistencies and encourages diversity through a computationally efficient rank-one Cholesky update. Experiments on eight benchmark datasets demonstrate the effectiveness of our approach.

Client-level Active Error Correction in Distributed Learning

Text-to-video models have demonstrated impressive capabilities in producing diverse video content, yet often lack fine-grained control over motion. We introduce MotionFlow, a novel, training-free framework for motion transfer in pre-trained video diffusion models. MotionFlow uniquely leverages cross-attention maps by guiding a test-time optimization of latent representations to align the generated video's attention patterns with those extracted from a source motion. This approach enables the capture and manipulation of complex spatial and temporal dynamics for seamless motion transfer across diverse contexts. Unlike methods relying on direct attention map replacement, which can introduce artifacts, or those requiring model-specific training, MotionFlow operates solely at test-time, robustly handling significant scene and appearance alterations. Our qualitative and quantitative experiments demonstrate that MotionFlow significantly outperforms existing methods in motion fidelity, temporal consistency, and versatility, even during drastic scene transformations.

MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models

Aspect-Based Sentiment Intensity Analysis (ABSIA) has garnered increasing attention, though research largely focuses on domain-specific, sentence-level settings. In contrast, document-level ABSIA--particularly in addressing complex tasks like extracting Aspect-Category-Opinion-Sentiment-Intensity (ACOSI) tuples--remains underexplored.In this work, we introduce DanceHA, a multi-agent framework designed for open-ended, document-level ABSIA with informal writing styles. DanceHA has two main components: Dance, which employs a divide-and-conquer strategy to decompose the long-context ABSIA task into smaller, manageable sub-tasks for collaboration among specialized agents; and HA, Human-AI collaboration for annotation. We release Inf-ABSIA, a multi-domain document-level ABSIA dataset featuring fine-grained and high-accuracy labels from DanceHA. Extensive experiments demonstrate the effectiveness of our agentic framework and show that the multi-agent knowledge in DanceHA can be effectively transferred into student models. Our results highlight the importance of the overlooked informal styles in ABSIA, as they often intensify opinions tied to specific aspects. Code and sample data are available at \url{https://anonymous.4open.science/r/DanceHA}.

DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis

With the advancement of face recognition (FR) systems, privacy-preserving face recognition (PPFR) systems have gained popularity for its accurate recognition, enhanced facial privacy protection and robustness to various attacks. However, there are limited studies to further verify the privacy risks by extracting realistic high-resolution face images from embeddings of these systems, especially for PPFR. In this work, we propose the face embedding mapping (FEM), a general framework that explores Kolmogorov-Arnold Network (KAN) for conducting the embedding-to-face attack by leveraging pre-trained Identity-Preserving diffusion model against state-of-the-art (SOTA) FR and PPFR systems. Based on extensive experiments, we verify that the reconstructed faces can be used for accessing other real-word FR systems.
Besides, the proposed method shows the robustness in reconstructing faces from partial and protected face embeddings. Moreover, FEM can be utilized as a tool for evaluating safety of FR and PPFR systems in terms of privacy leakage.

Realistic Face Reconstruction from Facial Embeddings via Diffusion Models

Recent advances in dance generation have enabled the automatic synthesis of 3D dance motions. However, existing methods still face significant challenges in simultaneously achieving high realism, precise dance–music synchronization, diverse motion expression, and physical plausibility. To address these limitations, we propose a novel approach that leverages a generative masked text-to-motion model as a distribution prior to learn a probabilistic mapping from diverse guidance signals, including music, genre, and pose, into high-quality dance motion sequences. Our framework also supports semantic motion editing, such as motion inpainting and body part modification. Specifically, we introduce a multi-tower masked motion model that integrates a text-conditioned masked motion backbone with two parallel, modality-specific branches: a music-guidance tower and a pose-guidance tower. The model is trained using synchronized and progressive masked training, which allows effective infusion of the pretrained text-to-motion prior into the dance synthesis process while enabling each guidance branch to optimize independently through its own loss function, mitigating gradient interference. During inference, we introduce classifier-free logits guidance and pose-guided token optimization to strengthen the influence of music, genre, and pose signals. Extensive experiments demonstrate that our method sets a new state of the art in dance generation, significantly advancing both the quality and editability over existing approaches.

Walk Before You Dance: High-fidelity and Editable Dance Synthesis via Generative Masked Motion Prior

We introduce LOREN, a curvature-aware zeroth-order (ZO) optimization method for fine-tuning large language models (LLMs). Existing ZO methods, which estimate gradients via finite differences using random perturbations, often suffer from high variance and suboptimal search directions. Our approach addresses these challenges by: (i) reformulating the problem of gradient preconditioning as that of adaptively estimating an anisotropic perturbation distribution for gradient estimation, (ii) capturing curvature through a low-rank block diagonal preconditioner using the framework of natural evolution strategies, and (iii) applying a REINFORCE leave-one-out (RLOO) gradient estimator to reduce variance. Experiments on standard LLM benchmarks show that our method outperforms state-of-the-art ZO methods by achieving higher accuracy and faster convergence, while cutting peak memory usage by up to 27.3% compared with MeZO-Adam.

Content not yet available

Next from AAAI 2026

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Similar lecture

Differentially Private Natural Language Models: Recent Advances and Future Directions

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES