Papers by Zichen Wen

8 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.
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.
Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning (2025.acl-long)

Copied to clipboard

Challenge: Using fine-tuning on task-specific data is essential for large language models to be effective in specialized tasks.
Approach: They propose a method that leverages few-shot in-context learning with the model to be fine-tuned.
Outcome: The proposed method outperforms existing methods with a 3.1-point improvement and a 7.4 speedup on the Llama-3-8B-Instruct model using just 10% of the dataset.
Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods (2026.acl-long)

Copied to clipboard

Challenge: Recent efforts to accelerate inference in Multimodal Large Language Models have focused on visual token compression.
Approach: They propose a framework that leverages downsampling as a discriminator to denoise existing benchmarks.
Outcome: The proposed evaluation framework leverages downsampling as a discriminator to denoise existing benchmarks.
StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding (2026.findings-acl)

Copied to clipboard

Challenge: StreamMeCo is an efficient Stream Agent Memory Compression framework for video understanding.
Approach: They propose an efficient Stream Agent Memory Compression framework that evicts redundant memory nodes and introduces a time-decay memory retrieval mechanism to mitigate performance degradation.
Outcome: The proposed framework achieves 1.87 speedup in memory retrieval while delivering an average accuracy improvement of 1.0% on three challenging benchmark datasets.
TEMP: Taxonomy Expansion with Dynamic Margin Loss through Taxonomy-Paths (2021.emnlp-main)

Copied to clipboard

Challenge: Existing taxonomies are unable to maintain coverage due to the rising of new concepts . TEMP uses pre-trained contextual encoders to predict the position of new ideas .
Approach: They propose a self-supervised taxonomy expansion method that ranks taxonomies by ranking them . they use pre-trained contextual encoders to train the model with dynamic margin loss .
Outcome: The proposed method outperforms state-of-the-art taxonomy expansion methods by 14.3% and 15.8% on public benchmarks.
AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems (2026.acl-long)

Copied to clipboard

Challenge: Automated expansion methods often result in bloated structures with redundant agents, leading to excessive token consumption.
Approach: They propose a plug-and-play compression framework for graph-structured multi-agent workflows . they estimate the importance score of each agent and remove redundant agents .
Outcome: Experiments show that AgentSlimming reduces average token cost by 78.9% with negligible performance degradation.
TreeMAN: Tree-enhanced Multimodal Attention Network for ICD Coding (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to automatically assign ICD codes ignore crucial information contained in structured medical data, which is hard to be captured from the noisy clinical notes.
Approach: They propose to use a Tree-enhanced multimodal attention network to fuse tabular features and textual features into multimodal representations by enhancing the text representations with tree-based features.
Outcome: The proposed method outperforms state-of-the-art methods on two MIMIC datasets.

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