0

Xiaoyu Shen

Papers
21

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
21papers

Authored papers

21

HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit

arXiv 2026

2026

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention

arXiv 2026

2026

Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models

arXiv 2026

2026

UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking

arXiv 2026

2026

Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning

arXiv 2025

2025

Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices

CVPR 2025 1

2025

LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding

arXiv 2025

2025

LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model

arXiv 2025

2025

MultiConIR: Towards multi-condition Information Retrieval

arXiv 2025

2025

Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant

arXiv 2025

2025

Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning

arXiv 2025

2025

InternLM-Law: An Open Source Chinese Legal Large Language Model

arXiv 2024

2024

Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation

arXiv 2024

2024

The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models

arXiv 2024

2024

MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration

arXiv 2024

2024

xPQA: Cross-Lingual Product Question Answering across 12 Languages

arXiv 2023

2023

A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks

arXiv 2023

2023

SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects

arXiv 2023

2023

Logical Fallacy Detection

arXiv 2022

2022

MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages

arXiv 2022

2022

A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation

NAACL 2022 7

2022

Affiliations

No known affiliations.

Frequent co-authors

10

from 21 papers