Papers by Yifu Qiu

11 papers
Can VLMs Predict Future States? Bootstrapping World Models from Inverse Dynamics (2026.findings-acl)

Copied to clipboard

Challenge: unified vision–language models (VLMs) struggle to generate physically plausible transitions between frames from instructions.
Approach: They find that VLMs struggle to generate physically plausible transitions between frames from instructions.
Outcome: The proposed model outperforms state-of-the-art image editing models on Aurora-Bench . it achieves the best average human evaluation across all subsets of Aurora-bench compared with other models .
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling (2025.findings-emnlp)

Copied to clipboard

Challenge: Best-of-N (BoN) sampling generates multiple responses and selects the best one, achieving improved performance but with a high computational cost.
Approach: They propose a framework that integrates a speculative tree-search strategy into Best-of-N (BoN) Sampling.
Outcome: The proposed framework outperforms Best-of-N (BoN) sampling but has high computational cost . tree-search strategy reduces computational overhead while maintaining high output quality .
DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine (2022.emnlp-main)

Copied to clipboard

Challenge: Existing datasets for non-English passage retrieval are lacking in quality and accuracy.
Approach: They present a large-scale Chinese dataset for passage retrieval . they reduce false negatives by manually annotating results pooled from multiple retrievers .
Outcome: The proposed dataset reduces false negatives in development and testing sets and removes similar training queries.
Abstractive Summarization Guided by Latent Hierarchical Document Structure (2022.emnlp-main)

Copied to clipboard

Challenge: Sequential abstractive summarizations often do not capture hierarchical and inter-sentential dependencies in the summmarized document.
Approach: They propose a hierarchy-aware graph neural network which captures hierarchical and inter-sentential dependencies in the summmarized document.
Outcome: The proposed model improves strong sequence models such as BART with a 0.55 and 0.75 margin in ROUGE-1/2/L for CNN/DM and XSum.
Detecting and Mitigating Hallucinations in Multilingual Summarisation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing faithfulness metrics for abstractive summarisation models focus on English . metric mFACT is best suited to detect hallucinations in cross-lingual transfer .
Approach: They propose a method to evaluate the faithfulness of non-English summaries by translation-based transfer from multiple English faithfulness metrics.
Outcome: The proposed method reduces hallucinations in cross-lingual transfer by weighing the loss of each training example by its faithfulness score.
EEE-QA: Exploring Effective and Efficient Question-Answer Representations (2024.lrec-main)

Copied to clipboard

Challenge: Current approaches to question answering rely on pre-trained language models like RoBERTa.
Approach: They propose a pooling approach that embeds all answer candidates with the question . they also propose enabling cross-reference between answer choices .
Outcome: The proposed methods improve throughput and memory efficiency with little sacrifice in performance.
Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation (2024.findings-naacl)

Copied to clipboard

Challenge: Knowledge-to-text generators often struggle to faithfully generate descriptions for input facts . we propose a decoding-only method to reduce hallucinations .
Approach: They propose a decoding-only method to generate accurate descriptions for input facts . they use a Natural Language Inference model as the model and replace it with a task-specific HVM .
Outcome: The proposed method improves faithfulness with minimal impact on quality and in/out-of-distribution evaluations.
What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations (2025.acl-long)

Copied to clipboard

Challenge: VISTA dataset contains 18,599 recorded AI conference presentations . large multimodal models exhibit reduced performance in scientific contexts, study shows .
Approach: They propose a dataset specifically designed for video-to-text summarization in scientific domains.
Outcome: This paper compares the performance of large models with human models and shows that they improve on human models.
Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks like LOFT often overestimate LCLM performance by providing overly simplified contexts.
Approach: They propose to use retrieval-attention-probing to filter and de-noise long contexts during decoding and joint retrieval head training alongside the generation head to improve LCLM performance.
Outcome: The proposed approach outperforms RAG and GPT-4-Turbo on most tasks despite being a much smaller model.
Are Large Language Model Temporally Grounded? (2024.naacl-long)

Copied to clipboard

Challenge: Recent large language models lack a consistent temporal model of textual narratives . sentence ordering in unlabelled texts is only weakly correlated with event ordering .
Approach: They evaluate LLMs with textual narratives and evaluate their common-sense knowledge . they find that LLM models struggle the most with self-consistency .
Outcome: The proposed models lack a consistent temporal model of textual narratives.
Iterative Multilingual Spectral Attribute Erasure (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for debiasing are unable to exploit this opportunity because they operate on individual languages.
Approach: They propose to iterate multilingual spectral attribute error (IMSAE) to mitigate joint bias subspaces across multiple languages through iterative SVD-based truncation.
Outcome: The proposed method outperforms monolingual and cross-lingual approaches while maintaining model utility.

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