wovepaper — the arXiv observatory

papers

Publications (141)

cs.CL2024

Modeling Unified Semantic Discourse Structure for High-quality Headline Generation

Minghui Xu, Hao Fei, Fei Li +4

cs.CV2025

Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image

Yu Zhao, Hao Fei, Xiangtai Li +6

cs.CL2022

Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph

Hao Fei, Shengqiong Wu, Meishan Zhang +2

cs.CL2026

Mental World Modeling

Hao Fei, Yiran Zhao

The paper introduces Mental World Modeling (MWM), a framework that integrates agents' mental states (beliefs, desires, intentions) into world models, and presents a training‑free b…

Publications (141)

Modeling Unified Semantic Discourse Structure for High-quality Headline Generation

Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image

Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph

Mental World Modeling

When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements

Reasoning Implicit Sentiment with Chain-of-Thought Prompting

Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining

End-to-end Semantic Role Labeling with Neural Transition-based Model

Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework

TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognition

Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting

Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction

Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology

Audio-Visual Intelligence in Large Foundation Models

Unified Named Entity Recognition as Word-Word Relation Classification

ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models

DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis

SpeechEE: A Novel Benchmark for Speech Event Extraction

Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene

Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling

DragNeXt: Rethinking Drag-Based Image Editing

LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision

High-order Refining for End-to-end Chinese Semantic Role Labeling

Where, What, Why: Towards Explainable Driver Attention Prediction

I3: Intent-Introspective Retrieval Conditioned on Instructions

OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction

SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models

Recognizing Everything from All Modalities at Once: Grounded Multimodal Universal Information Extraction

Orthogonal Spatial-temporal Distributional Transfer for 4D Generation

Unified Generative and Discriminative Training for Multi-modal Large Language Models

Cross-lingual Semantic Role Labeling with Model Transfer

Grammar Induction from Visual, Speech and Text

Nominal Compound Chain Extraction: A New Task for Semantic-enriched Lexical Chain

ProtT3: Protein-to-Text Generation for Text-based Protein Understanding

Retrofitting Structure-aware Transformer Language Model for End Tasks

Code-MIE: A Code-style Model for Multimodal Information Extraction with Scene Graph and Entity Attribute Knowledge Enhancement

Multi-Granular Multimodal Clue Fusion for Meme Understanding

On the Adaptive Psychological Persuasion of Large Language Models

Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

Grounding is All You Need? Dual Temporal Grounding for Video Dialog

SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding

Entity-centered Cross-document Relation Extraction

Revisiting Conversation Discourse for Dialogue Disentanglement

UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark

Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling

When Words Smile: Generating Diverse Emotional Facial Expressions from Text

A Survey of Ontology Expansion for Conversational Understanding

On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversations

A Systematic Survey of Semantic Role Labeling in the Era of Pretrained Language Models

Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning

LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation

Subband-based Generative Adversarial Network for Non-parallel Many-to-many Voice Conversion

Aggressive Language Detection with Joint Text Normalization via Adversarial Multi-task Learning

Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition

XNLP: An Interactive Demonstration System for Universal Structured NLP

ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models

Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction

Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models

FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents

Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning

Faithful Logical Reasoning via Symbolic Chain-of-Thought

RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation

On Path to Multimodal Generalist: General-Level and General-Bench

De-fine: Decomposing and Refining Visual Programs with Auto-Feedback

Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis

Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinking

In-Context Learning for Few-Shot Nested Named Entity Recognition

CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought

Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought

LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model

Generating Visual Spatial Description via Holistic 3D Scene Understanding

Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing

M3D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction

NExT-GPT: Any-to-Any Multimodal LLM

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

VEGAS: Towards Visually Explainable and Grounded Artificial Social Intelligence

M $^{3}$ D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-level Information Extraction