Papers by Yizhou Chen

12 papers
HCSpec: Two-Tier Horizontal Cascade Speculative Decoding for High-Efficiency Large Language Model Inference (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to decode large language models adopt a homogeneous architecture . autoregressive decoding is a bottleneck because tokens must be generated sequentially .
Approach: They propose a framework that organizes heterogeneous position-specialized draft modules into a horizontal cascade.
Outcome: The proposed framework outperforms the current state-of-the-art (EAGLE3) and achieves 3.72x acceleration over vanilla decoding.
RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated strong capabilities across various domains, but their large-scale deployment faces a major obstacle: the high computational cost of long-sequence inference.
Approach: They propose an algorithm that retains key-value vectors until they are no longer needed to solve reasoning tasks.
Outcome: The proposed algorithm achieves high accuracy with O(L) time but O(N) memory complexities.
Communication-Efficient Desire Alignment for Proactive Embodied Human–Agent Interaction (2026.acl-long)

Copied to clipboard

Challenge: Effective real-world human–agent interactions are long-term and repeated.
Approach: They propose a simulation that uses a proxy user with value-driven preferences and natural language behavior to evaluate how agents adapt to users across interactions and satisfy their desires.
Outcome: HA-Desire, a home assistance simulation, shows that agents can adapt to user needs and provide proactive assistance within limited communication.
Open-Set Living Need Prediction with Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to living need prediction treat it as a closed-set classification problem, severely limiting their ability to capture diversity and complexity of living needs.
Approach: They propose a system leveraging large language models for unrestricted need prediction that leverages Maslow's hierarchy of needs to align predictions with human living needs.
Outcome: The proposed system outperforms closed-set approaches on need-based life service recall by an average of 19.37% on real-world datasets.
How Do Large Language Models Perform in Dynamical System Modeling (2025.findings-naacl)

Copied to clipboard

Challenge: Recent data-driven methods often use graph neural networks (GNNs) to learn interactions between objects.
Approach: They propose prompting techniques for dynamical system modeling and evaluate their performance . they find that large language models demonstrate competitive performance without training .
Outcome: The proposed methods show competitive performance without training compared to state-of-the-art methods in dynamical system modeling.
Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs? (2025.findings-acl)

Copied to clipboard

Challenge: Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance.
Approach: They develop a series of billion-scale grammar-based code representations that incorporate grammar rules into the code generation process.
Outcome: Experiments on HumanEval and MBPP show that grammar-based representations reduce syntax errors and improve performance even in billion-scale models.
Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach: They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome: The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.
FUSE: Measure-Theoretic Compact Fuzzy Set Representation for Taxonomy Expansion (2024.findings-acl)

Copied to clipboard

Challenge: Existing work models taxonomy concepts as vectors or geometric objects, but fuzzy sets are efficient for concept modeling.
Approach: They propose a set representation learning task based on fuzzy set approximation . they demonstrate remarkable improvements in taxonomy expansion using FUSE .
Outcome: The proposed framework improves taxonomy expansion performance by 23% over baselines.
Few-Shot Representation Learning for Out-Of-Vocabulary Words (P19-1)

Copied to clipboard

Challenge: Existing methods for learning word embedding assume there are enough occurrences for each word in the corpus to accurately estimate the representation of words.
Approach: They propose to fit a representation function to predict an oracle embedding vector based on limited contexts.
Outcome: The proposed model outperforms existing methods in constructing an accurate embedding for OOV words and improves downstream tasks when the embeddable is utilized.
Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing MLLMs are strong at understanding single plots, but struggle with multi-step reasoning . Existing approaches to manage context in chart reasoning include text-based chain-of-thought prompting .
Approach: They propose a hierarchical visual agent framework that iteratively constructs a working context in an image–text space.
Outcome: The proposed framework improves on strong multimodal baselines.
Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing large language models can perform abstract reasoning tasks but are they actually engaging in rule-based reasoning beyond mere memorization?
Approach: They propose a method to examine whether large language models perform abstract reasoning . they fine-tune the model to learn those contradictory rules and assess its generalization ability .
Outcome: The proposed approach examines whether large language models perform abstract reasoning by altering their original understanding of fundamental rules.
Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for learning missing facts in knowledge graphs are limited by insufficiency of alignment information and inconsistency of described facts.
Approach: They propose a framework for embedding learning and ensemble knowledge transfer across KGs.
Outcome: The proposed framework improves state-of-the-art methods on language-specific KGs.

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