Papers by Yifeng Li

11 papers
Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More (2025.emnlp-main)

Copied to clipboard

Challenge: Vision tokens in multimodal large language models often dominate computational overhead due to excessive length compared to linguistic modality.
Approach: They propose a token pruning method which defines an importance criterion for vision tokens and prunes the unimportant vision token during inference.
Outcome: The proposed method can prune 88.9% of vision tokens while maintaining comparable performance.
Can We Afford The Perfect Prompt? Balancing Cost and Accuracy with the Economical Prompting Index (2025.coling-main)

Copied to clipboard

Challenge: Prompt engineering is a growing subdiscipline of natural language processing . a lack of appropriate consideration for the financial constraints of computationally burdensome methods can limit their adoption and impact.
Approach: They propose a new metric that combines accuracy scores with token consumption to reflect different resource constraints.
Outcome: The economic prompting index (EPI) measures the performance of 6 prompting techniques across 10 widely-used language models and 4 diverse datasets.
Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem? (2025.findings-acl)

Copied to clipboard

Challenge: Multimodal large language models have shown remarkable performance for cross-modal understanding and generation, yet suffer from severe inference costs.
Approach: They propose to prune redundant tokens in MLLMs to reduce computation and storage costs.
Outcome: The proposed method reduces the computational and storage costs of MLLMs by identifying redundant tokens and pruning them.
NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to generate research ideas rely on retrieval or prompt engineering to generate ideas.
Approach: They propose a method that uses iterative planning and search to boost creative potential of LLMs by integrating external knowledge with broader and deeper insights.
Outcome: The proposed method outperforms the current state-of-the-art in generating 2.5 times more top-rated ideas based on 170 seed papers in a Swiss Tournament evaluation.
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)

Copied to clipboard

Challenge: Existing solutions for visual document understanding lack granularity of document textlines.
Approach: They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts.
Outcome: The proposed system performs better on various VDU tasks in English and Chinese.
WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models (2023.emnlp-industry)

Copied to clipboard

Challenge: Existing typography solutions lack adaptability, creativity, and computational efficiency.
Approach: They propose a user-driven framework for artistic typography synthesis based on the Large Language Model (LLM) the LLM Engine interprets user inputs and generates actionable prompts for the other modules, transforming abstract concepts into tangible designs.
Outcome: The proposed framework incorporates four key modules: the LLM Engine, SemTypo, StyTyPo, and TexTyPO.
Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for training large language models rely heavily on high-quality parallel data, which are often scarce or unavailable for low-resource languages.
Approach: They propose a reinforcement training method using only monolingual text to elevate LLMs’ translation capabilities on massive low-resource languages while retaining their performance on high-resourced languages.
Outcome: The proposed model outperforms LLaMAX, one of the strongest open-source multilingual LLMs on 1,414 language directions on Flores-101 dataset.
SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) achieve strong reasoning with Chain-of-Thought prompting, but long and redundant traces substantially increase inference cost.
Approach: They propose a training-free and plug-and-play decoding method that reduces CoT overhead without modifying model weights.
Outcome: Experiments on GSM8K, MMLU, GPQA, and BBH show that SyncThink achieves 62.00% average Top@1 accuracy using 656 generated tokens and 28.68s latency, compared to 61.22%, 2141 tokens, and 92.01s for full CoT decoding.
Intra-Correlation Encoding for Chinese Sentence Intention Matching (2020.coling-main)

Copied to clipboard

Challenge: Existing methods to improve sentence intention matching for Chinese text are limited due to the particularity of the text.
Approach: They propose a method that combines character-granularity and word-granulularity features to perform sentence intention matching.
Outcome: The proposed method can capture sentence feature information from multiple perspectives and correlation information between different levels of sentences.
Picturing Ambiguity: A Visual Twist on the Winograd Schema Challenge (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models have demonstrated remarkable success in tasks like the Winograd Schema Challenge (WSC), showcasing advanced textual common-sense reasoning.
Approach: They propose a framework to isolate models' ability in pronoun disambiguation from other visual processing challenges.
Outcome: The proposed framework isolates the models’ ability in pronoun disambiguation from other visual processing challenges.
Fusion or Defusion? Flexible Vision-and-Language Pre-Training (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to vision-and-language pretraining (VLP) lack effectiveness and efficiency in downstream multimodal tasks.
Approach: They propose a flexible vision-and-language pre-training model by incorporating cross-modal fusions into a dual-encoder architecture and a cross-module knowledge transfer strategy to guide the training process.
Outcome: The proposed model is well-equipped with effectiveness and efficiency compared with other strong VLP models.

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