Papers with Directed Acyclic Graph

5 papers
Diffusion Directed Acyclic Transformer for Non-Autoregressive Machine Translation (2025.acl-short)

Copied to clipboard

Challenge: Non-autoregressive transformers (NATs) often encounter performance challenges due to the multi-modality problem.
Approach: They propose a direct-acyclic transformer (DAT) that captures multiple translation modalities to paths in a Directed Acyclic Graph (DAG) this allows the model to integrate latent variables into the model, which is crucial for DAT to achieve state-of-the-art performance.
Outcome: The proposed model captures multiple translation modalities to paths in a Directed Acyclic Graph (DAG) but the collaboration with the latent variable introduced through the Glancing training is crucial for the model to attain state-of-the-art performance.
MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains (2025.findings-naacl)

Copied to clipboard

Challenge: Existing benchmarks focus on specific application scenarios, emphasizing task completion but failing to dissect the underlying skills that drive these outcomes.
Approach: They propose a Massive Multitask Agent Understanding benchmark that evaluates LLMs across five domains and offline tasks.
Outcome: The Massive Multitask Agent Understanding (MMAU) benchmark evaluates models across five domains including Tool-use, Directed Acyclic Graph (DAG) QA, Data Science and Machine Learning coding, Contest-level programming and Mathematics.
Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition (2024.lrec-main)

Copied to clipboard

Challenge: Existing models for multimodal Emotion Recognition in conversation (ERC) use text as the main modality for emotion recognition.
Approach: They propose a Directed Acyclic Graph (DAG) approach that integrates textual, acoustic, and visual features within a unified framework.
Outcome: The proposed model outperforms baseline models on the IEMOCAP and MELD datasets.
Legal Judgment Prediction via Topological Learning (D18-1)

Copied to clipboard

Challenge: Existing studies focus on a specific subtask of judgment prediction and ignore the dependencies among subtasks.
Approach: They propose a topological multi-task learning framework that incorporates multiple subtasks and DAG dependencies into judgment prediction.
Outcome: The proposed model improves on baselines on all judgment prediction tasks.
Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) demonstrate remarkable capabilities but their ability to autonomously execute complex real-world tasks remains limited.
Approach: They propose a parallel tool invocation framework that decomposes tasks into parallel tool-using subtasks while aggregating results for subsequent decisions.
Outcome: The proposed method significantly improves task performance while reducing token consumption and inference time.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations