Singapore

Offline reinforcement learning (RL) is vulnerable to real-world data corruption, with even robust algorithms failing under challenging observation and mixture corruptions. We posit this failure stems from data corruption creating sharp minima in the loss landscape, leading to poor generalization. To address this, we are the first to apply Sharpness-Aware Minimization (SAM) as a
general-purpose, plug-and-play optimizer for offline RL. SAM seeks flatter minima, guiding models to more robust parameter regions. We integrate SAM into strong baselines for data corruption: IQL, a top-performing offline RL algorithm in this setting, and RIQL, an algorithm designed specifically for data-corruption robustness. We evaluate them on D4RL benchmarks with both random and adversarial corruption. Our SAM-enhanced methods consistently and significantly outperform the original baselines. Visualizations of the reward surface confirm that SAM finds smoother solutions, providing strong evidence for its effectiveness in improving the robustness of offline RL agents.

AAAI 2026

Enhancing Robustness of Offline Reinforcement Learning Under Data Corruption via Sharpness-Aware Minimization (Student Abstract)

machine learning

optimization

reinforcement learning

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022! I believe this conference has been complicated beyond any precedent. Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm. We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community. Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well: we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)

To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

EMNLP 2022

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

technical paper

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.

Bandit algorithms and Large Language Models (LLMs) have
traditionally been studied in separate
domains---decision-making under uncertainty and natural
language processing, respectively. This talk explores their
emerging synergy and the transformative potential that
arises when these paradigms intersect. On one hand, bandit
algorithms can enhance LLM efficiency through fine-tuning,
prompt optimization, adaptive response generation, and
evaluation strategies. On the other, LLMs can enrich bandit
methods by providing contextual understanding, adaptive
policies, predictive insights, and natural language--driven
feedback. I will present a survey of state-of-the-art
research, highlight promising applications in
personalization, dialogue systems, autonomous agents, and
healthcare, and discuss open challenges around scalability,
interpretability, and multi-agent coordination. The goal is
to provide a roadmap for interdisciplinary research at the
intersection of bandits and LLMs, pointing toward more
adaptive, human-centered, and trustworthy AI systems.

Multi-Armed Bandits Meet Large Language Models

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions.
Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a diffusion transformer aims to reconstruct the gaze region of the image, which corresponds to the target manipulated objects. This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention, thus effectively leveraging task-specific visual information and conducting precise manipulation. Moreover, we curate a large-scale pretraining dataset comprising over 100k trajectories and 2 million data samples from open-source robotic datasets, further boosting the model’s generalization in visual reconstruction. Extensive experiments in simulation and the real world demonstrate the superiority of our implicit grounding method, showcasing its capabilities of precise manipulation and generalization.

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

The Segment Anything Model 2 (SAM2) has demonstrated remarkable promptable visual segmentation capabilities in video data, showing potential for extension to medical image segmentation (MIS) tasks involving 3D volumes and temporally correlated 2D image sequences. However, adapting SAM2 to MIS presents several challenges, including the need for extensive annotated medical data for fine-tuning and high-quality manual prompts, which are both labor-intensive and require intervention from medical experts. To address these challenges, we introduce OFL-SAM2, a prompt-free SAM2 framework for label-efficient MIS. Our core idea is to leverage limited annotated samples to train a lightweight mapping network that captures medical knowledge and transforms generic image features into target features, thereby providing additional discriminative target representations for each frame and eliminating the need for manual prompts. Crucially, the mapping network supports online parameter update during inference, enhancing the model’s generalization across test sequences. Technically, we introduce two key components: (1) an online few-shot learner that trains the mapping network to generate target features using limited data, and (2) an adaptive fusion module that dynamically integrates the target features with the memory-attention features generated by frozen SAM2, leading to accurate and robust target representation. Extensive experiments on three diverse MIS datasets demonstrate that OFL-SAM2 achieves state-of-the-art performance with limited training data. The code will be released.

OFL-SAM2: Prompt SAM2 with Online Few-shot Learner for Efficient Medical Image Segmentation

Video recommendation systems heavily rely on user watch time feedback, making accurate watch time prediction a crucial task. However, this task inherently suffers from bias, as recommendation models tend to favor long-duration videos to maximize watch time. This issue, known as duration bias in the watch-time prediction context, can be explained from a causal perspective, where video duration acts as a confounder. Recent works address this bias using backdoor adjustment, isolating the direct effect of content on watch time from observational data. These methods typically discretize video duration into groups, estimate group-wise effects, and then aggregate them via a unified prediction model. However, this aggregation strategy is prone to model misspecification due to feature distribution shift across groups. In this paper, we reinterpret the problem through the lens of invariant learning and propose a novel framework: **D**uration-**I**nvariant **F**eature **L**earning (**DIFL**). DIFL employs a kernel-based regularization that enforces representation invariance across duration groups, reducing sensitivity to group design and improving generalization. This enables more accurate modeling of the direct causal effect and making counterfactual inference. Extensive experiments on both public and real large-scale production datasets demonstrate the effectiveness of our approach, which achieves SOTA performance.

Invariant Feature Learning for Counterfactual Watch-time Prediction in Video Recommendation

Monocular 3D Semantic Scene Completion (SSC) is a challenging yet promising task that aims to infer dense geometric and semantic descriptions of a scene from a single image. While recent object-centric paradigms significantly improve efficiency by leveraging flexible 3D Gaussian primitives, they still rely heavily on a large number of randomly initialized primitives, which inevitably leads to 1) inefficient primitive initialization and 2) outlier primitives that introduce erroneous artifacts. In this paper, we propose SplatSSC, a novel framework that resolves these limitations with a depth-guided initialization strategy and a principled Gaussian aggregator. Instead of random initialization, SplatSSC utilizes a dedicated depth branch composed of a Group-wise Multi-scale Fusion (GMF) module, which integrates multi-scale image and depth features to generate a sparse yet representative set of initial Gaussian primitives. To mitigate noise from outlier primitives, we develop the Decoupled Gaussian Aggregator (DGA), which enhances robustness by decomposing geometric and semantic predictions during the Gaussian-to-voxel splatting process. Complemented with a specialized Probability Scale Loss, our method achieves state-of-the-art performance on the Occ-ScanNet dataset, outperforming prior approaches by over 6.3\% in IoU and 4.1\% in mIoU, while reducing both latency and memory consumption by more than 9.3\%. The code will be released upon acceptance.

SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion

Linear Temporal Logic over finite traces (LTLf) is a widely used formalism with applications in AI, process mining, model checking, and more. 
The primary reasoning task for LTLf is satisfiability checking; yet, the recent focus on explainable AI has increased interest in analyzing inconsistent formulae, making the enumeration of minimal explanations for unsatisfiability a relevant task also for LTLf. 
We introduce a novel technique for enumerating minimal unsatisfiable cores (MUCs) of an LTLf specification. 
The main idea is to encode an LTLf formula into an Answer Set Programming (ASP) specification, such that the minimal unsatisfiable subsets (MUSes) of the ASP program directly correspond to the MUCs of the original LTLf specification.
Leveraging recent advancements in ASP solving yields an MUC enumerator achieving good performance in experiments conducted on established benchmarks from the literature.

Enumerating Minimal Unsatisfiable Cores of LTLf Formulae

Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity raises growing concerns about privacy leakage, toxicity mitigation, and intellectual property violations. Machine Unlearning (MU) offers a practical solution by selectively forgetting targeted knowledge while preserving overall model utility.
When applied to MLLMs, existing neuron-editing-based MU approaches face two fundamental challenges: (i) forgetting becomes inconsistent across modalities because existing point-wise attribution methods fail to capture the structured, layer-by-layer information flow that connects different modalities; and (ii) general knowledge performance declines when sensitive neurons that also support important reasoning paths are pruned, as this disrupts the model’s ability to generalize.
To alleviate these limitations, we propose a multimodal influential neuron path editor (MIP-Editor) for MU. Our approach introduces modality-specific attribution scores to identify influential neuron paths responsible for encoding forget-set knowledge and applies influential-path-aware neuron-editing via representation misdirection. This strategy also enables effective and coordinated forgetting across modalities while preserving the model's general capabilities. Experimental results demonstrate that MIP-Editor achieves a superior unlearning performance on multimodal tasks, with a maximum forgetting rate of 87.75% and up to 54.26% improvement in general knowledge retention. On textual tasks, MIP-Editor achieves up to 80.65% forgetting and preserves 77.90% of general performance.

Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models

Garment simulation is fundamental to various applications in computer vision and graphics, from virtual try-on to digital human modelling. However, conventional physics-based methods remain computationally expensive, hindering their application in time-sensitive scenarios. While graph neural networks (GNNs) offer promising acceleration, existing approaches exhibit poor cross-resolution generalisation, demonstrating significant performance degradation on higher-resolution meshes beyond the training distribution. This stems from two key factors: (1) existing GNNs employ fixed message-passing depth that fails to adapt information aggregation to mesh density variation, and (2) vertex-wise displacement magnitudes are inherently resolution-dependent in garment simulation.
To address these issues, we introduce Propagation-before-Update Graph Network (Pb4U-GNet), a resolution-adaptive framework that decouples message propagation from feature updates. Pb4U-GNet incorporates two key mechanisms: (1) dynamic propagation depth control, adjusting message-passing iterations based on mesh resolution, and (2) geometry-aware update scaling, which scales predictions according to local mesh characteristics. Extensive experiments show that even trained solely on low-resolution meshes, Pb4U-GNet exhibits strong generalisability across diverse mesh resolutions, addressing a fundamental challenge in neural garment simulation.

Pb4U-GNet: Resolution-Adaptive Garment Simulation via Propagation-before-Update Graph Network

Large models have achieved remarkable performance across a range of reasoning and understanding tasks. Prior work often utilizes model ensembles or multi-agent systems to collaboratively generate responses, effectively operating in a server-to-server paradigm. However, such approaches do not align well with practical deployment settings, where a limited number of server-side models are shared by many clients under modern internet architectures. In this paper, we introduce CoLM (Collaboration in Large-Models), a novel framework for collaborative reasoning that redefines cooperation among large models from a client-server perspective. Unlike traditional ensemble methods that rely on simultaneous inference from multiple models to produce a single output, CoLM allows the outputs of multiple models to be aggregated or shared, enabling each client model to independently refine and update its own generation based on these high-quality outputs. This design enables collaborative benefits by fully leveraging both client-side and shared server-side models. We further extend CoLM to vision-language models (VLMs), demonstrating its applicability beyond language tasks. Experimental results across multiple benchmarks show that CoLM consistently improves model performance on previously failed queries, highlighting the effectiveness of collaborative guidance in enhancing single-model capabilities.

CoLM: Collaborative Large Models via a Client-Server Paradigm

Depression represents a global mental health challenge requiring efficient and reliable automated detection methods. Current Transformer- or Graph Neural Networks (GNNs)-based multimodal depression detection methods face significant challenges in modeling individual differences and cross-modal temporal dependencies across diverse behavioral contexts. Therefore, we propose P$^3$HF (Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network) with three key innovations: (1) personality-guided representation learning using LLMs to transform discrete individual features into contextual descriptions for personalized encoding; (2) Hypergraph-Former architecture modeling high-order cross-modal temporal relationships; (3) event-level domain disentanglement with contrastive learning for improved generalization across behavioral contexts. Experiments on MPDD-Young dataset show P$^3$HF achieves around 10\% improvement on accuracy and weighted F1 for binary and ternary depression classification task over existing methods. Extensive ablation studies validate the independent contribution of each architectural component, confirming that personality-guided representation learning and high-order hypergraph reasoning are both essential for generating robust, individual-aware depression-related representations. The code is released at https://github.com/hacilab/P3HF.

Downloads

Next from AAAI 2026

Multi-Armed Bandits Meet Large Language Models

Similar lecture

GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES