Papers by Xiao Fang

14 papers
mPresenter: An Agentic Framework for Generating Multilingual Presentation Videos from Scientific Papers (2026.findings-acl)

Copied to clipboard

Challenge: Existing Paper2Video systems are monolingual and often rely on single-pass pipelines.
Approach: They propose a multilingual agentic Paper2Video system that decomposes the task into planning, audience-oriented critique, layout-aware slide generation, and multilingual figure interpretation.
Outcome: The proposed system improves question-answering accuracy relative to previous systems while maintaining affordable cost and latency.
TrInk: Ink Generation with Transformer Network (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for handwriting generation capture global dependencies and can generate high-quality handwritten samples.
Approach: They propose a Transformer-based model for ink generation, TrInk, which captures global dependencies.
Outcome: The proposed model reduces character error rate and word error rate by 35.56% on the IAM-OnDB dataset compared to previous models.
Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search (2026.findings-acl)

Copied to clipboard

Challenge: LLM-based agents for machine learning engineering rely on tree search to rank candidates.
Approach: They propose an LLM-based agent that operationalizes gradient-based optimization.
Outcome: The proposed agent achieves a state-of-the-art 35.1% any-medal rate on MLE-Bench with a limited budget on a single GPU.
EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary (2025.acl-industry)

Copied to clipboard

Challenge: Existing document question answering methods reduce inference costs and input tokens.
Approach: They propose a retrieval-augmented generation method that automatically extracts useful entities and generates summaries from documents.
Outcome: The proposed method surpasses baseline retrieval-augmented generation (RAG) and long-context question answering (LC) methods achieve higher accuracy by processing entire documents, but at the cost of increased computational Corresponding authors.
i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data (2024.findings-naacl)

Copied to clipboard

Challenge: i-Code V2 is one of the first models capable of generating natural language from any combination of Vision, Language, and Speech data.
Approach: They propose to create a model that can generate natural language from any combination of Vision, Language, and Speech data.
Outcome: i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks.
Watermarking Large Language Models: An Unbiased and Low-risk Method (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have highlighted the risk of misusing them, raising the need for accurate detection of LLM-generated content.
Approach: They propose a method to inject imperceptible identifiers into large language models (LLMs) this method is unbiased and preserves the original token distribution in expectation .
Outcome: The proposed method preserves the original token distribution in expectation and has lower risk of producing unsatisfactory outputs in low-entropy scenarios compared to existing unbiased watermarks.
Human-in-the-loop Robotic Grasping Using BERT Scene Representation (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches for robotic grasping in cluttered scenes are expensive and lack structure information.
Approach: They propose a human-in-the-loop framework for robotic grasping in cluttered scenes . they substitute scene-graph representation with a text representation of the scene using BERT .
Outcome: The proposed framework outperforms object-agnostic and scene-graph based methods on robots and physical robots.
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding (2024.emnlp-main)

Copied to clipboard

Challenge: Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) drafting efficiency has become a bottleneck in the final speedup of speculative drafting, therefore generating longer drafts at less cost can lead to better speedup.
Approach: They propose a method that uses existing model to drafting and target LLM to verify draft in a low-cost parallel manner.
Outcome: The proposed method can achieve speedups of up to 2.4 over speculative decoding and 3.9 over vanilla decoding without fine-tuning draft and target models.
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs (2025.findings-naacl)

Copied to clipboard

Challenge: Existing jailbreak research exhibits limitations in universality, validity, and efficiency . Existing methods for jailbreaking LLMs have limited validity and effectiveness .
Approach: They propose a black-box approach that uses wordplay-guided mapping rule sampling to create universal adversarial prompts.
Outcome: The proposed method efficiently identifies security vulnerabilities across various LLMs, achieving an average success rate of over 80% with fewer than 10 queries.
RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining (2022.acl-long)

Copied to clipboard

Challenge: Large-scale pretrained language models have achieved SOTA results on NLP tasks but are vulnerable to adversarial attacks especially for logographic languages like Chinese.
Approach: They propose a pretrained Chinese Bert that is robust to various forms of adversarial attacks like word perturbation, synonyms, typos, etc.
Outcome: The proposed model outperforms baselines on 5 Chinese NLU tasks without sacrificing performance on clean testsets.
Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training (2022.findings-acl)

Copied to clipboard

Challenge: Existing studies treat named entity recognition as a sequential labeling problem.
Approach: They propose a span selection framework for nested named entity recognition . they propose nesting entities with different input categories would be separately extracted .
Outcome: The proposed framework outperforms competing models on four benchmark datasets.
MATH-IDN: A Multilingual Mathematical Problem Solving Dataset Featuring Local Languages in Indonesia (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models excel at mathematical reasoning in English, but their performance in low-resource languages remains underexplored.
Approach: They propose a multilingual benchmark for mathematical problem solving in Indonesian, Javanese, Sundanese, and Buginese with English as a reference.
Outcome: The proposed model reveals significant performance gaps in low-resource languages, particularly Buginese, and highlights key limitations in current multilingual reasoning capabilities.
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for dataset poisoning require full-dataset poison, which breaks code compilability.
Approach: They propose a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths.
Outcome: The proposed method contaminates 10% of the dataset while maintaining 100% compilability and functional correctness.
TinyBERT: Distilling BERT for Natural Language Understanding (2020.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models are computationally expensive and difficult to efficiently execute on resource-restricted devices.
Approach: They propose a Transformer distillation method that performs Transformer distillations at pre-training and task-specific learning stages.
Outcome: The proposed method accelerates inference and reduces model size while maintaining accuracy.

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