Papers by Zeyuan Li

8 papers
Leveraging Social Context for Humor Recognition and Sense of Humor Evaluation in Social Media with a New Chinese Humor Corpus - HumorWB (2024.lrec-main)

Copied to clipboard

Challenge: Existing humor computing research focuses on content while neglecting interaction relationships in social media.
Approach: They propose a dataset which introduces social context information from social media . they propose 'humor recognition' task and 'horror evaluation task'
Outcome: The proposed model incorporates social context information from social media . it shows that it is efficient and can be used to evaluate humor in real life .
Rethinking Long Context Generation from the Continual Learning Perspective (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) struggle with processing long contexts due to the limited context window.
Approach: They propose to combine a limited context window with a continual learning perspective to improve LLMs' efficiency in processing long contexts.
Outcome: The proposed models improve the performance of Large Language Models (LLMs) by integrating learning strategies with existing approaches.
VisualEDU: A Benchmark for Assessing Coding and Visual Comprehension through Educational Problem-Solving Video Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . advanced proprietary models show promise, but struggle with increasing task complexity .
Approach: VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . it integrates meta-prompt learning, visual and code feedback, and a drawing toolkit to enhance output quality.
Outcome: VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . it integrates meta-prompt learning, visual and code feedback, and a drawing toolkit to improve output quality.
Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding (2026.acl-long)

Copied to clipboard

Challenge: Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability.
Approach: They propose a shortcut decoding framework that integrates probes over internal hidden states with step-level entropy to detect convergence of reasoning during generation and adaptively selects between a fast-exit path and a stability-verified path to remove redundant steps while preserving answer correctness.
Outcome: The proposed framework reduces token usage by approximately 35% and maintains accuracy comparable to full CoT decoding.
Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization (2025.acl-long)

Copied to clipboard

Challenge: Protein language models pose significant risks of generating harmful sequences, e.g., viral transmissibility, drug resistance, environmental imbalances, public health crises, etc.
Approach: They propose a protein-based model that integrates prior knowledge via a Protein Safety Knowledge Graph to minimize the risk of generating harmful sequences.
Outcome: The proposed framework reduces the likelihood of producing hazardous sequences while maintaining high functionality.
World Models with Hints of Large Language Models for Goal Achieving (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods address this by adding intrinsic rewards, but they fail to provide meaningful guidance in long-horizon decision-making tasks with large state and action spaces lacking purposeful exploration.
Approach: They propose a multi-modal model-based RL approach that integrates the proposed hinting subgoals into the model rollouts to encourage goal discovery and reaching in challenging tasks.
Outcome: The proposed model outperforms existing methods in challenging, sparse-reward environments such as HomeGrid, Crafter, and Minecraft by 41.8%, 21.1%, and 9.9%.
Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated impressive performance, but they keep repeating similar mistakes due to their inability to capture relationships among samples.
Approach: They propose a tuning-free rule accumulation framework that guides LLMs in improving their performance by learning from previous mistakes.
Outcome: The proposed framework improves over baselines by a large margin over previous frameworks.
InstructProtein: Aligning Human and Protein Language via Knowledge Instruction (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are a promising new approach to understanding biological sequences such as proteins.
Approach: They propose an LLM that can generate protein sequences in human and protein languages by pre-training an Lm on protein and natural language corpora and supervised instruction tuning to facilitate alignment.
Outcome: The proposed model outperforms state-of-the-art LLMs on protein-text generation tasks by a large margin.

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