Assistants on assembly tasks show great potential to benefit humans ranging from helping with everyday tasks to interacting in industrial settings. However, evaluation resources in assembly activities are underexplored. To foster system development, we propose a new multimodal QA evaluation dataset on assembly activities. Our dataset, ProMQA-Assembly, consists of 646 QA pairs that require multimodal understanding of human activity videos and their instruction manuals in an online-style manner. For cost effectiveness in the data creation, we adopt a semi-automated QA annotation approach, where LLMs generate candidate QA pairs and humans verify them. We further improve QA generation by integrating fine-grained action labels to diversify question types. Additionally, we create 81 instruction task graphs for our target assembly tasks. These newly created task graphs are used in our benchmarking experiment, as well as in facilitating the human verification process. With our dataset, we benchmark models, including competitive proprietary multimodal models. We find that ProMQA-Assembly contains challenging multimodal questions, where reasoning models showcase promising results. We believe our new evaluation dataset contributes to the further development of procedural-activity assistants.

Large Language Models (LLMs) provide flexible natural language processing capabilities, while knowledge graphs (KGs) offer explicit and structured knowledge. Integrating these two in a complementary manner enables the development of reliable and verifiable AI systems. In particular, knowledge graph question answering (KGQA) has attracted attention as a means to reduce LLM hallucinations and to leverage knowledge beyond the training data. However, existing KGQA benchmark datasets are biased toward encyclopedic knowledge, limited to a single modality, and lack fine-grained spatiotemporal data, which limits their applicability to real-world scenarios targeted by Embodied AI. We introduce HOME-KGQA, a novel KGQA benchmark dataset built on a multimodal KG of daily household activities. HOME-KGQA consists of complex, multi-hop natural language questions paired with graph database query languages. Compared to existing benchmarks, it includes more challenging questions that involve multi-level spatiotemporal reasoning, multimodal grounding, and aggregate functions. Experimental results show that the LLM-based KGQA methods fail to achieve performance comparable to that on existing datasets when evaluated on HOME-KGQA. This highlights significant challenges that should be addressed for the real-world deployment of KGQA systems. Our dataset is available at https://github.com/aistairc/home-kgqa.

Inspired by their success in image synthesis, diffusion models offer a flexible, iterative alternative to rigid left-to-right text generation. However, a fundamental training-inference discrepancy hinders their performance: models are trained on corrupted ground-truth tokens, but at inference time they must denoise inputs corrupted from their own predictions. To bridge this gap, we propose a unified framework. First, Deeper Self-Prediction (DSP) is a multi-step training objective that teaches robust self-correction by forcing the model to denoise its own intermediate outputs. Second, UCB-guided Decoding is a principled inference algorithm that frames token re-masking as a multi-armed bandit problem, using the Upper Confidence Bound (UCB) to balance exploration and exploitation. Experiments on text generation tasks demonstrate consistent improvements over existing diffusion baselines. The framework achieves higher faithfulness and coherence according to both automatic metrics and LLM-as-a-Judge evaluations.

We present VDAct 2.0, an enhanced benchmark for video-grounded dialogue that builds upon the original VDAct by expanding dialogue coverage and introducing a scalable LLM-assisted filtering pipeline to ensure high-quality, grounded QA pairs. VDAct 2.0 comprises 6,356 human-annotated dialogues with a total of 63,958 turns, grounded in 2,975 household activity videos, with undesirable dialogue turns systematically identified and removed. To achieve this, we design a trigger-based quality framework and calibrate a panel of high-agreement LLMs through human-in-the-loop calibration, allowing scalable QA-turn-level filtering. We benchmark a wide range of pretrained and fine-tuned models, both open-source and proprietary, across standard text generation metrics and LLM-based evaluations. The results highlight both recent advances and remaining challenges in video-grounded dialogue modeling, positioning VDAct 2.0 as a high-fidelity testbed for evaluating and advancing multimodal reasoning in interactive settings.

We propose ELAINE (EngLish-jApanese-chINesE)-medLLM, a trilingual (English, Japanese, Chinese) large language model adapted for the bio-medical domain based on Llama-3-8B. The training dataset was carefully curated in terms of volume and diversity to adapt to the biomedical domain and endow trilingual capability while preserving the knowledge and abilities of the base model. The training follows 2-stage paths: continued pre-training and supervised fine-tuning (SFT). Our results demonstrate that ELAINE-medLLM exhibits superior trilingual capabilities compared to existing bilingual or multilingual medical LLMs without severely sacrificing the base model’s capability.

Multimodal systems have great potential to assist humans in procedural activities, where people follow instructions to achieve their goals. Despite diverse application scenarios, systems are typically evaluated on traditional classification tasks, e.g., action recognition or temporal action localization. In this paper, we present a novel evaluation dataset, ProMQA, to measure the advancement of systems in application-oriented scenarios. ProMQA consists of 401 multimodal procedural QA pairs on user recording of procedural activities, i.e., cooking, coupled with their corresponding instruction. For QA annotation, we take a cost-effective human-LLM collaborative approach, where the existing annotation is augmented with LLM-generated QA pairs that are later verified by humans. We then provide the benchmark results to set the baseline performance on ProMQA. Our experiment reveals a significant gap between human performance and that of current systems, including competitive proprietary multimodal models. We hope our dataset sheds light on new aspects of models’ multimodal understanding capabilities.

This study addresses the discrepancy between training and inference in discrete diffusion models for text generation. We propose two novel strategies: (1) a training schema that considers two-step diffusion processes, allowing the model to use its own predicted output as input for subsequent steps during training and (2) a scheduling technique that gradually increases the probability of using self-generated text as training progresses. Experiments conducted on four widely used text generation benchmark datasets demonstrate that both proposed strategies improve the performance of discrete diffusion models in text generation.

Relation extraction is a crucial natural language processing task that extracts relational triplets from raw text. Syntactic dependencies information has shown its effectiveness for relation extraction tasks. However, in most existing studies, dependency information is used only for traditional encoder-only-based relation extraction, not for generative sequence-to-sequence (seq2seq)-based relation extraction. In this study, we propose a syntax-aware seq2seq pre-trained model for seq2seq-based relation extraction. The model incorporates dependency information into a seq2seq pre-trained language model by continual pre-training with a seq2seq-based dependency parsing task. Experimental results on two widely used relation extraction benchmark datasets show that dependency parsing pre-training can improve the relation extraction performance.

We propose a novel Biomedical domain-specific Non-AutoRegressive Transformer model for natural language generation: BioNART. Our BioNART is based on an encoder-decoder model, and both encoder and decoder are compatible with widely used BERT architecture, which allows benefiting from publicly available pre-trained biomedical language model checkpoints. We performed additional pre-training and fine-tuned BioNART on biomedical summarization and doctor-patient dialogue tasks. Experimental results show that our BioNART achieves about 94% of the ROUGE score to the pre-trained autoregressive model while realizing an 18 times faster inference speed on the iCliniq dataset.

We propose a novel neural method to extract drug-drug interactions (DDIs) from texts using external drug molecular structure information. We encode textual drug pairs with convolutional neural networks and their molecular pairs with graph convolutional networks (GCNs), and then we concatenate the outputs of these two networks. In the experiments, we show that GCNs can predict DDIs from the molecular structures of drugs in high accuracy and the molecular information can enhance text-based DDI extraction by 2.39 percent points in the F-score on the DDIExtraction 2013 shared task data set.

We propose a novel attention mechanism for a Convolutional Neural Network (CNN)-based Drug-Drug Interaction (DDI) extraction model. CNNs have been shown to have a great potential on DDI extraction tasks; however, attention mechanisms, which emphasize important words in the sentence of a target-entity pair, have not been investigated with the CNNs despite the fact that attention mechanisms are shown to be effective for a general domain relation classification task. We evaluated our model on the Task 9.2 of the DDIExtraction-2013 shared task. As a result, our attention mechanism improved the performance of our base CNN-based DDI model, and the model achieved an F-score of 69.12%, which is competitive with the state-of-the-art models.