Singapore

Explainable AI (XAI) is increasingly adopted in manufacturing to support human-in-the-loop decision-making, enabling practitioners to understand, validate, or override AI-driven recommendations. While, in practice, AI engineers and data scientists often select an XAI method (aka., explainer) based on what they are familiar with and past experience, this is not optimal because it is known -- already proved in the literature -- that the interplay among {dataset, model, explainer} can substantially impact the overall level of trustworthiness of the generated explanation. This work presents a functionally grounded evaluation framework for MTS explanations, organized around three trustworthiness pillars: faithfulness, robustness, and complexity. We adapt state-of-the-art metrics from the image and tabular domains to timechannel attributions and integrate them into an interactive decision support system (DSS) named TRUE-X (TRUstworthy EXplanations). TRUE-X enables practitioners to visualize and balance the trade-off between the trustworthiness of the explanation and the accuracy of the model, fostering a more reliable and transparent XAI in human-centric manufacturing.

AAAI 2026

Towards Trustworthy Human-Centered Manufacturing: A Decision Support Tool for {Model x Explainer} Selection

multivariate time series (mts)

human-centered manufacturing

explanation quality

trustworthy ai

explainable ai (xai)

decision support system

[![](https://assets.underline.io/markdown_image/1/image/f25361a85b7c83a7476c0b3c1c0bb1b2.png)](https://drive.google.com/file/d/18jcAcciCBQHj6R07Dbpm2HCOBEIwAOCU/view?usp=sharing)


Dear Colleagues and Friends,

The 33rd IEEE International Conference on Robot and Human Interactive Communication, IEEE RO-MAN 2024, was held at Pasadena Convention Center in Pasadena, USA.

The theme of the IEEE RO-MAN 2024 was **“Embracing Human-Centered HRI”**.

With the continuous technological effort of understanding human needs, creating human-desired robotic systems, and developing real human user experiences, we are marching together towards building a promising and excellent human quality of life, all for our wellness and our next generation.

The conference provided a forum for researchers and practitioners to discuss a variety of topics related to the broad theme of Robot and Human Interactive Communication involving theories, methodologies, technologies, empirical and experimental studies, and generated more insights for the future of Robot and Human Interactive Communication!

We hope you continue to enjoy the post-conference content on Underline!

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

It looks like you are not registered for this event. 

A registration is required to access this event page. 



Registration Is Required

IEEE RO-MAN 2024

The 33rd IEEE International Conference on Robot and Human Interactive Communication was held in Pasadena, California, USA. The theme of the IEEE RO-MAN 2024 was “Embracing Human-Centered HRI”.

workshop 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.

The global surge in end-of-life (EOL) photovoltaic (PV) modules presents a critical sustainability challenge, necessitating recycling processes that minimize environmental impact. Traditional Life Cycle Assessment (LCA) methods, while valuable for retrospective analysis, are too slow and static to guide real-time operational decisions in recycling facilities. This creates a significant gap where operators lack immediate feedback on the greenhouse gas (GHG) consequences of their process choices. To bridge this gap, we propose a human-centric AI framework that transforms recycling operators from passive executors into active agents of sustainability. Rather than pursuing full automation, we develop a situation-aware assistance system that augments human capabilities through predictive intelligence. Our approach centers on an ensemble machine learning model (combining Random Forest and XGBoost) that provides real-time GHG emission predictions based on operational parameters, including energy consumption, ambient temperature, humidity, and process type. Trained on a synthesized dataset spanning 12 distinct EOL PV and e-waste recycling processes, our ensemble achieves an RMSE of 23.38, outperforming individual models and providing stable predictions. By integrating this model into an interactive system, we enable operators to forecast the environmental impact of their actions before execution, effectively addressing the limitations of traditional LCA and fostering more sustainable, informed decision-making at the operational level.

Human-Centric AI for Sustainable Manufacturing: Real-Time Emission-Aware Decision Support in PV Recycling

A central challenge for creating coherent teamwork in human-robot teams is maintaining mutual awareness of team member activities and ongoing task alignment. Hereby, human intention recognition is fundamental to enabling effective adaptation of robotic team members. Existing approaches either focus on short-term motion prediction or lack principled links between intention recognition and adaptive planning. We propose a unified framework as a robot agent architecture that based on hierarchical task decomposition links observable behaviors to high-level tasks planning. The framework contributes three key advances: (i) unified representation of both assigned tasks and models of foreseeable human behavior, (ii) integration of intention recognition with adaptive planning, and (iii) cost-based multi-level planning for task reallocation and motion adaptation. We illustrate its functioning in a manufacturing scenario in which humans and robots collaborate.

Intention-Aware Adaptive Planning in Human-Robot Teams

In this paper, we propose ChatRearrange, a novel framework for the text-guided 3D scene rearrangement task. Instructing an algorithm with a text description to rearrange 3D furniture objects remains an unsolved problem in the 3D field. Unfortunately, developing algorithms to address this problem presents two critical challenges. First, we lack appropriate text-labeled scene data for the training procedure. Second, evaluating performance is challenging due to the absence of appropriate benchmarks. To address the first issue, we propose the ChatRearrange framework, which includes an LLM-based Inverse Distillation algorithm, enabling ChatRearrange to train without description-labeled scene data. Additionally, we incorporate a novel gradient-field-based student network to learn the text-3D knowledge from the LLM. For the second challenge, we benchmark the text-guided 3D scene rearrangement task by proposing a new dataset called TextRoom. We also include various metrics for the evaluation. The results show that our algorithm outperforms other baselines by a large margin. We are committed to releasing all the code and dataset if the paper is accepted.

ChatRearrange: Learning Text-guided 3D Scene Rearrangement

3D assembly tasks require automatic agents’ precise interpretations of visual scenes and structural reasoning. While large Vision-Language Models (VLMs) have shown promising capabilities in general Visual Question Answering (VQA), existing benchmarks inadequately reflect the complexities inherent in assembly reasoning. In this paper, we introduce FurniBench, an assembly-specific VQA benchmark, together with FurniQA, a large-scale dataset covering tasks such as part recognition, connection reasoning, and step ordering. Using Qwen2-VL-2B-Instruct as a base model (39.1% accuracy on FurniBench), we first establish a supervised fine-tuning (SFT) baseline, which highlights both the benefits and the limitations of SFT in this domain. Building on this, we propose Assembly-R1, trained with Group Relative Policy Optimization (GRPO), which substantially enhances reasoning ability and achieves 71.7% accuracy, outperforming the base model, the SFT baseline, and other open-source and closed-source commercial VLM candidates. Our results demonstrate that reinforcement learning offers a more robust path toward generalizable 3D assembly reasoning. We will release the dataset and code upon acceptance of this paper.

Assembly-R1: 3D Assembly Reasoning via RL-based Vision Language Models

Large Language Models (LLMs) have shown remarkable capabilities in document processing, but their inability to provide visual grounding without OCR dependencies poses significant challenges in business-critical applications. Current solutions either require model fine-tuning or rely on external OCR services, introducing additional costs, latency, and limitations in handling derived information. This paper presents ViG-LLM, a novel framework that enables closed-box LLMs to generate localization information through a multi-agent system combining U-Net-based layout deconstruction with viewport identification tasks. Evaluated on the FATURA and CORD dataset, our framework achieves perfect accuracy over spatial reasoning tuned LLM like Amazon Nova Pro, while demonstrating superior template-specific consistency. The framework maintains robust performance across LLM architectures while reducing operational costs by 60% compared to Textract-based solutions. In real-world document processing applications, the framework helps retain the high reasoning capabilities of the system in document information extraction tasks while improving explainability, reliability and human interaction for information verification. Through human-in-the-loop learning and closed-box prompt alignment techniques, ViG-LLM provides a robust, adaptable solution for visual grounding tasks in document processing workflows.


ViG-LLM: Enhancing Visual Grounding Capabilities in Closed-Box LLMs for Document Information Extraction without OCR Dependencies

Causal discovery is central to enable causal models for tasks such as effect es- timation, counterfactual reasoning, and root cause attribution. Yet existing ap- proaches face trade-offs: purely statistical methods (e.g., PC, LiNGAM) often re- turn structures that overlook domain knowledge, while expert-designed DAGs are difficult to scale and time-consuming to construct. We propose CausalFusion, a hybrid framework that combines graph falsification tests with large language mod- els (LLMs) acting as domain-specialized data scientists. LLMs incorporate do- main expertise into candidate structures, while graph falsification tests iteratively refine DAGs to balance statistical validity with expert plausibility. We evaluate CausalFusion through two experiments: (i) a synthetic e-commerce dataset with a precisely defined ground truth DAG, and (ii) real-world supply chain data from Amazon, where the ground truth was constructed with domain experts. To bench- mark performance, we compare against classical causal discovery algorithms (PC, LiNGAM) as well as LLM-only baselines that generate DAGs without iterative falsification. Structural Hamming Distance (SHD) is used as the primary evalu- ation metric to quantify similarity between generated and “true” DAGs. We also analyze different foundational models chain-of-thought traces to examine whether deeper reasoning correlates with improved structural accuracy or reproducibility. Results show that CausalFusion produces DAGs more closely aligned with ground truth than both classical algorithms and LLM-only baselines, while offering in- terpretable reasoning at each iteration, though challenges in reproducibility and generalizability remain.

CausalFusion: Integrating LLMs and Graph Falsification for Causal Discovery

As organizations scale adoption of generative AI, model cost optimization and operational efficiency have emerged as critical factors determining sustainability and accessibility. While Large Language Models (LLMs) demonstrate impressive capabilities across diverse tasks, their extensive computational requirements make them cost prohibitive for routine enterprise use. This limitation motivates the exploration of Small Language Models (SLMs), which can deliver comparable performance in targeted applications while drastically reducing infrastructure overhead (Irugalbandara et al.,2023). In this work, we investigate the feasibility of replacing LLM-driven workflows with optimized SLMs. We trained a domain-adapted SLM to execute representative tasks traditionally handled by LLMs, such as document summarization, query answering, and structured data interpretation. As part of the experiment, we investigated the fine-tuning of facebook opt-350m model (single epoch only) using the Hugging Face TRL (Transformer Reinforcement Learning), specifically the Supervised Fine Tuning (SFT) trainer. The OPT-350M model was released by Meta AI in 2022 as part of the OPT (Open Pretrained Transformer) family of models. Similar studies demonstrate that even models at the 350M parameter scale can meaningfully contribute to instruction tuning pipelines (Mekala et al., 2024). Experimental results demonstrated that our fine-tuned SLM achieves exceptional performance with a 77.55% pass rate on ToolBench evaluation, significantly outperforming all baseline models including ChatGPT-CoT (26.00%), ToolLLaMA-DFS (30.18%), and ToolLLaMA-CoT (16.27%). These benchmarks, first introduced in ToolLLM (Qin et al., 2023) and later stabilized by follow-up efforts (Zhang et al., 2024), have become the standard for evaluating tool-augmented reasoning. Recent work has also extended ToolBench traces to preference-based optimization (Zeng et al., 2024) and designed alternative multi API corpora for tool-use robustness (Liu et al., 2024). These findings emphasize that thoughtful design and targeted training of SLMs can significantly lower barriers to adoption, enabling cost-effective, large-scale integration of generative AI into production systems.

Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning

Computer-Aided Design (CAD) documentation is fundamental to ensuring engineering integrity. However, its verification currently depends on the manual inspection of specifications, drawings, and 3D models. This practice is inherently prone to inefficiency, inconsistency, and undetected errors. To address this gap, we present the CAD Inspection Assistant, a tool-augmented agentic system designed to automate CAD-related document specification verification. At its core, the assistant leverages an agentic Large Language Model (LLM) as a dynamic planner, decomposing complex inspection tasks into executable steps. It then invokes specialized Python tools to extract and analyze data from CAD artifacts. The LLM synthesizes tool outputs to evaluate compliance with project requirements, generating actionable reports that highlight discrepancies. To demonstrate the effect of our work, we collect real-world data and conduct experiments, setting a foundation for intelligent agentic systems in manufacturing workflows.

CAD Inspection Assistant: Tool-Augmented Agentic CAD Inspection Solution

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in cross-modal understanding, yet they remain prone to hallucinations—particularly those driven by overreliance on language and knowledge priors while neglecting visual evidence. We identify and formalize a critical subclass of such hallucinations, termed EvidenCe-prior Hallucination Observation (ECHO), which arises when models generate answers consistent with prior knowledge but inconsistent with manipulated visual inputs. To address the lack of fine-grained, scalable benchmarks for this phenomenon, we introduce the first dedicated ECHO evaluation framework, featuring a triplet-structured dataset of 414 samples (1,242 QA records) across seven domains, constructed via systematic filtering, adversarial image editing, and rigorous annotation. Our benchmark enables precise diagnosis of language-prior dependency through three controlled conditions: Text-QA, Raw-VQA, and Edit-VQA. Evaluations on both titan-class (e.g., GPT-4o, Command A Vision) and workhorse-class (e.g., Qwen2.5-VL) models reveal that stronger language priors correlate with higher ECHO susceptibility. Furthermore, we propose and validate two model-agnostic mitigation strategies—attention-guided evidence region enhancement and reinforcement learning–activated test-time reasoning—which significantly reduce ECHO rates (e.g., ECHO-$\phi$ drops from 6.3\% to 4.8\% in Qwen2.5-VL-3B). Our work provides a reproducible benchmark, interpretable metrics (ECHO--$\Delta$, ECHO--$\phi$, ECHO-$F$), and practical pathways toward more faithful multimodal reasoning.

ECHO: EvidenCe-prior Hallucination Observation

Enterprise meeting environments demand AI assistants that can handle diverse operational tasks—from rapid fact-checking during live discussions to deep cross-meeting analysis for strategic planning—under strict latency, cost, and privacy constraints. Existing meeting benchmarks focus on simplified QA tasks and lack alignment with real-world enterprise workflows where questions arise organically from multi-stakeholder collaboration, span temporal contexts, and require tool-augmented reasoning. 

We address this gap through a grounded dataset construction and learned agent framework. First, we present MeetAll: a bilingual, multimodal corpus derived from 231 meetings (140 hours) with enterprise-informed question injection validated through domain expert review (kappa=0.82) and human discriminability studies (56% detection rate, near-random). Unlike purely synthetic benchmarks, our injection protocol anchors on four enterprise-critical dimensions—cognitive load, temporal context span, domain expertise, and actionable task execution—calibrated via interviews with 15 enterprise meeting stakeholders across finance, healthcare, and tech sectors. 

Second, we introduce MeetBench-XL: a multi-dimensional evaluation protocol calibrated against human judgment (Pearson r=0.78, p<0.01) that measures factual fidelity, user intent alignment, response efficiency, structural clarity, and completeness—criteria prioritized by enterprise users in our needs assessment. 

Third, we propose MeetMaster-XL: a learned dual-policy agent that jointly optimizes routing (fast Talker vs. slow Planner) and tool invocation (retrieval, cross-meeting aggregation, web search) through offline policy learning on quality–latency–cost objectives. Unlike prior rule-based fast/slow systems, our lightweight classifier (1ms overhead) achieves 81.2% routing accuracy and unlocks a superior Pareto frontier: 30% latency reduction on simple queries and 12.4% quality gain on complex tasks over single-model baselines, while remaining deployable on consumer GPUs (RTX 4090, 22GB VRAM). 

We benchmark against commercial APIs (GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro) and provide ablations, robustness tests (noise, overlap, multilingual splits), and a field deployment case study. Resources: https://github.com/huyuelin/MeetBench.

Downloads

Next from AAAI 2026

Human-Centric AI for Sustainable Manufacturing: Real-Time Emission-Aware Decision Support in PV Recycling

Similar lecture

User Decision Guidance with Selective Explanation Presentation from Explainable-AI

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

Human-Centric AI for Sustainable Manufacturing: Real-Time Emission-Aware Decision Support in PV Recycling

Similar lecture

User Decision Guidance with Selective Explanation Presentation from Explainable-AI

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads