0

Ke Xu

Papers
20

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
20papers

Authored papers

20

Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models

arXiv 2026

2026

SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation

arXiv 2026

2026

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

arXiv 2025

2025

An Engorgio Prompt Makes Large Language Model Babble on

arXiv 2024

2024

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

arXiv 2024

2024

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

ICCV 2025

2024

MIO: A Foundation Model on Multimodal Tokens

arXiv 2024

2024

ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images

arXiv 2024

2024

Large Language Model for Science: A Study on P vs. NP

arXiv 2023

2023

Multimodal Federated Learning via Contrastive Representation Ensemble

arXiv 2023

2023

OWL: A Large Language Model for IT Operations

arXiv 2023

2023

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models

arXiv 2023

2023

EQ-Net: Elastic Quantization Neural Networks

ICCV 2023 1

2023

SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning

arXiv 2023

2023

Lighting up NeRF via Unsupervised Decomposition and Enhancement

ICCV 2023 1

2023

Referring Image Segmentation Using Text Supervision

ICCV 2023 1

2023

SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device

ICCV 2023 1

2023

CoSQA: 20,000+ Web Queries for Code Search and Question Answering

ACL 2021 5

2021

Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting

EMNLP 2021 11

2021

BERT Loses Patience: Fast and Robust Inference with Early Exit

NeurIPS 2020 12

2020

Affiliations

No known affiliations.

Frequent co-authors

10

from 20 papers