PaperHub

XIAOJUAN QI

~XIAOJUAN_QI2

25
论文总数
12.5
年均投稿
5.8
平均评分
接收情况16/25
会议分布
ICLR
13
NeurIPS
11
ICML
1

发表论文 (25 篇)

202518 篇

5.3
3

Multimodal Context-Aware Transformer with Visual Guidance for Automated 3D Annotation

ICLR 2025Rejected
4.8
4

Rethinking Out-of-Distribution Detection in Vision Foundation Models

ICLR 2025withdrawn
6.0
4

Diff-In: Data Influence Estimation with Differential Approximation

ICLR 2025Rejected
5.3
3

POC: Preventing the Over-Collapse of Classes for Class-Incremental Learning

ICLR 2025Rejected
6.4
4

DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning

NeurIPS 2025Poster
6.0
6

Data Pruning by Information Maximization

ICLR 2025Poster
3.5
4

An Image is Worth $K$ Slots: Data-efficient Scaling of Self-supervised Visual Pre-training

ICLR 2025withdrawn
4.3
4

Granularity Matters in Long-Tail Learning

ICLR 2025withdrawn
6.7
3

SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix

ICLR 2025Poster
7.8
4

UniTok: a Unified Tokenizer for Visual Generation and Understanding

NeurIPS 2025Spotlight
7.3
4

EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes

NeurIPS 2025Spotlight
6.0
4

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

NeurIPS 2025Poster
6.8
4

Understanding Data Influence in Reinforcement Finetuning

NeurIPS 2025Poster
6.8
4

Mixture Compressor for Mixture-of-Experts LLMs Gains More

ICLR 2025Poster
6.8
4

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

NeurIPS 2025Poster
6.1
4

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

ICML 2025Poster
5.4
5

SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models

ICLR 2025Rejected
6.8
4

Scaling RL to Long Videos

NeurIPS 2025Poster
合作者 (20)