Papers by Xiaodong Fan

9 papers
Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing reinforcement learning methods for large reasoning models suffer from excessive verbosity, known as "overthinking." Existing models penalize generated tokens to promote conciseness, but these methods encounter two challenges: they may develop hacking behavior in later stages of training by discarding reasoning steps.
Approach: They propose a framework that steers large reasoning models toward more efficient reasoning . they prioritize correctness while imposing penalties for redundant steps .
Outcome: The proposed framework reduces token usage by 69.7% on AIME24.
wav2vec-S: Adapting Pre-trained Speech Models for Streaming (2024.findings-acl)

Copied to clipboard

Challenge: Pre-trained speech models have advanced speech-related tasks, including speech recognition and translation.
Approach: They propose a pre-trained speech model that incorporates modifications to ensure consistent speech representations during training and inference phases for streaming speech inputs.
Outcome: The proposed model outperforms baseline models on speech recognition and translation tasks and achieves a superior balance between quality and latency.
LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline (2025.findings-acl)

Copied to clipboard

Challenge: Large language models perform well in offline machine translation when the complete source sentence is provided . however, in many real scenarios, the source tokens arrive in a streaming manner and simultaneous machine translation is required .
Approach: They propose a new paradigm that includes constructing supervised fine-tuning data for simultaneous machine translation (SiMT) to achieve SiMT, source and target tokens are rearranged into interleaved sequences, separated by special tokens according to varying latency requirements.
Outcome: The proposed approach achieves state-of-the-art performance across various SiMT benchmarks and evaluation metrics while maintaining efficient auto-regressive decoding.
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for explaining "black-box" models such as Influence Functions are becoming more popular.
Approach: They propose a semantic-based evaluation metric that can better align with humans’ judgment of explanations than the widely adopted diagnostic or re-training measures.
Outcome: The proposed method can better align with humans’ judgment of explanations than diagnostic or re-training measures.
Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing document benchmarks focus on English printed texts or simplified Chinese . current vision-language models struggle with visual complexity and poor adaptability .
Approach: They propose a benchmark to evaluate Chinese ancient documents' visual/linguistic complexity . ancient documents are valuable cultural heritage, but they face challenges in digitization and understanding .
Outcome: the first benchmark for Chinese ancient documents evaluates VLMs from OCR to knowledge reasoning . ancient documents carry thousands of years of Chinese history and culture . traditional methods only scan images, while current models struggle with visual complexity .
Datamart-Agent: LLM-Driven Game-Theoretic Agent for Data Marketplace Modeling (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies on data marketplaces model static equilibria and complete information, which limits their realism.
Approach: They propose an LLM-driven game-theoretic agent that makes equilibrium-consistent decisions in analytically tractable data marketplaces with evolving and incomplete-information.
Outcome: The proposed framework matches equilibrium-consistent decision execution in a static data marketplace with a dynamic game tree memory and mechanism-guided reflection without updating parameters.
Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to streaming speech translation use an offline model with a wait-k policy . however, there is a mismatch problem with an offline inference model trained with complete utterances .
Approach: They propose an offline streaming speech translation model with wait-k policy to support different latency requirements.
Outcome: The proposed model achieves better trade-offs between translation quality and latency than baselines.
XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)

Copied to clipboard

Challenge: XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios .
Approach: They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora.
Outcome: The proposed dataset is labeled in English and includes only natural language understanding tasks.
NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing work generates long videos segment by segment sequentially, which is inefficient.
Approach: They propose a Diffusion over Difference architecture for eXtremely Long video generation.
Outcome: The proposed architecture reduces the average inference time from 7.55min to 26s (94.26%) and generates high-quality long videos with both global and local coherence.

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