Papers by Shiyu Zhu

7 papers
Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query (2025.emnlp-main)

Copied to clipboard

Challenge: Existing KV cache eviction methods prune tokens using prefilling-stage attention scores, causing inconsistency with actual inference queries.
Approach: They propose a lookahead q-cache framework that generates low-cost pseudo lookaheaded queries to better approximate the true decoding-stage queries.
Outcome: The proposed framework outperforms existing methods on LongBench and Needle-in-a-Haystack benchmarks and can be flexibly combined to yield further improvements.
ActionStudio: A Lightweight Framework for Data and Training of Large Action Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing infrastructure for efficient agentic data processing and model training remains underdeveloped.
Approach: They propose a lightweight and extensible data and training framework for large action models . they propose to unify diverse agent trajectories using Unified Format 2.0 .
Outcome: The proposed framework shows 9 higher throughput than existing frameworks and performs well across public and realistic agent benchmarks.
PersLEARN: Research Training through the Lens of Perspective Cultivation (2023.acl-demo)

Copied to clipboard

Challenge: PersLEARN is a tool designed to facilitate the cultivation of scientific perspectives . junior researchers struggle to identify the perspectives reflected in the literature and struggle to develop their own viewpoints.
Approach: They propose a tool to facilitate the cultivation of scientific perspectives by interacting with a prompt-based model and allowing students to develop their own perspectives explicitly.
Outcome: The proposed tool outperforms baseline approaches across multiple domains of literature from different perspectives.
Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated exceptional performance in reasoning tasks, particularly in mathematics.
Approach: They propose a dynamic self-consistency framework that integrates System 1 and System 2 reasoning to improve token efficiency and latency.
Outcome: The proposed method outperforms existing methods, achieving up to 47% reduction in token consumption and 43% reduction in inference latency without significant performance loss.
Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets (P19-1)

Copied to clipboard

Challenge: Natural Language Sentence Matching (NLSM) is a popular NLP task.
Approach: They propose to use QuoraQP to train and evaluate NLSM models using a selection bias framework.
Outcome: The proposed framework can improve generalization ability of trained models and give more trustworthy evaluation results for real-world adoptions.
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding (2025.findings-acl)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) are limited by context length when processing long videos.
Approach: They propose a training-free method that flexibly reduces redundancy by allocating compression ratios among time and model layers with theoretical guarantees.
Outcome: Experiments on videoMME, MLVU, LongVideoBench, and LVBench show that AdaRETAKE outperforms existing methods by 2.3% and 2.8% for 7B and 72B models.
Web Sitemap Knowledge Can Enhance Autonomous Browsing (2026.findings-acl)

Copied to clipboard

Challenge: Existing web agents suffer from limited robustness, efficiency and task success due to lack of structural understanding of websites and lack of browsing priors in pre-trained models.
Approach: They propose an agent-oriented sitemap protocol that integrates structured website knowledge into web agents.
Outcome: The proposed agent-oriented sitemap improves robustness, efficiency and effectiveness without extra training.

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