Papers by Haoyu Wu

12 papers
End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for grounding video frames with dense annotations require enormous amount of human effort.
Approach: They propose to ground natural language in video frames with only one frame labeled . they propose an end-to-end model that eliminates interference of irrelevant frames .
Outcome: The proposed model can ground natural language in all video frames with only one frame labeled . the proposed model eliminates interference of irrelevant frames based on branch search and cropping techniques .
Defending against Indirect Prompt Injection by Instruction Detection (2025.findings-emnlp)

Copied to clipboard

Challenge: Indirect Prompt Injection attacks can be exploited by LLMs that are embedded with external data.
Approach: They propose a detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.
Outcome: The proposed approach reduces the success rate of attacks to 0.03% on the BIPIA benchmark.
Cognitive Scaffold: From Fluid Context to Crystallized Memory for Long-Horizon DeepResearch Agents (2026.acl-long)

Copied to clipboard

Challenge: Scaling LLM-based agents to long-horizon deep research is constrained by context-noise trade-off . solving a single query may require hundreds of interactions with noisy environments .
Approach: They propose a factorized memory architecture that decouples the cognitive state into a Fluid Working Context for immediate reasoning and a persistent Knowledge Graph for long-term retention.
Outcome: The Cognitive Scaffold outperforms baselines on Xbench-DeepSearch, BrowseComp-ZH, and GAIA . it achieves 74.7% Avg@3 and 87.0% Pass@3 on xbench, browseComp, and 88.3% Pass@3.
Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment (2023.acl-long)

Copied to clipboard

Challenge: Existing speech-text pre-training methods are limited to one or two specific tasks, despite their success in speech-language processing tasks.
Approach: They propose a temporal position prediction task to capture the speech-text alignment . they use a textual dialog pre-training task to generalize a response selection task .
Outcome: The proposed model is superior in learning speech-text alignment and multi-turn dialog context.
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach: They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome: The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.
SoMeLVLM: A Large Vision Language Model for Social Media Processing (2024.findings-acl)

Copied to clipboard

Challenge: Genereal domain large models lack nuanced multimodal understanding of social media . general domain models focus more on text than other modalities, which is not consistent with real-world user habits.
Approach: They propose a Large Vision Language Model for Social Media Processing that combines five key capabilities to understand and generate real social media behavior.
Outcome: The proposed model achieves state-of-the-art performance in multiple social media tasks.
Detecting Continuously Evolving Scam Calls under Limited Annotation: A LLM-Augmented Expert Rule Framework (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to detect scam calls rely on labeled data and assume static distribution of scam narratives.
Approach: They propose a method leveraging large language models to detect continuously evolving scam calls . scammers continuously evolve their tactics, making these methods less effective .
Outcome: The proposed approach is based on large language models to detect continuously evolving scam calls.
Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach: They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome: The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.
Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have achieved great success in various NLP tasks, but the vast model parameters pose challenges in downstream fine-tuning.
Approach: They propose a task-agnostic prompting strategy that analyzes each dialogue utterance before task execution to enhance LLMs' comprehension in multi-turn dialogues.
Outcome: The proposed strategy outperforms other zero-shot prompts and matches or exceeds efficacy of few-shot ones.
Can Large Language Models Tackle Graph Partitioning? (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have remarkable capabilities in understanding complex tasks, but they can only handle graph partitioning tasks that require global perception abilities.
Approach: They propose a pipeline for coarsening, reasoning, and refining to enable LLMs to perform graph partitioning on small-scale graphs.
Outcome: The proposed pipeline can handle graph partitioning tasks on small graphs with coarsening, reasoning, and refining.
FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining (2022.acl-long)

Copied to clipboard

Challenge: Tables store rich numerical data, but numerical reasoning over tables is still a challenge.
Approach: They propose a spreadsheet formula is a valuable supervision for numerical reasoning in tables.
Outcome: The proposed method outperforms state-of-the-art methods on three representative datasets of formula prediction, question answering, and cell type classification.
NL2Formula: Generating Spreadsheet Formulas from Natural Language Queries (2024.findings-eacl)

Copied to clipboard

Challenge: Creating spreadsheet formulas remains a tedious and error-prone task for many end-users . a novel task is proposed to generate spreadsheet formulae from a user's NL query .
Approach: They propose a task to generate formulas that are grounded on a spreadsheet table given a Natural Language query as input.
Outcome: The proposed task generates formulas that are grounded on a spreadsheet table, given a natural language query as input.

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