影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
64.59/100
前 3.7%
全站排名 #2,355
发表论文23 篇
平均评分
年均产出7.7 篇/年
Jiuxiang Gu
研究方向
Document Understanding · Cross-Modal Retrieval · VQA · Image Captioning · Natural Language Processing · Computer Vision
16
Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
ICLR 2026Poster
二作19
Fastcar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge
ICLR 2026Poster
通讯13
Towards Visual Text Grounding of Multimodal Large Language Model
ICLR 2026Rejected
23
Efficient Reasoning with Hidden Thinking
ICLR 2026Rejected
通讯5
MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing
ICLR 2026Withdrawn
三作19
Image Tokenizer Needs Post-Training
ICLR 2026Rejected
13
Reasoning-Based Personalized Generation for Users with Sparse Data
ICLR 2026Rejected
5
DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance
ICLR 2026Withdrawn
通讯19
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
NeurIPS 2025Poster
16
ImageFolder: Autoregressive Image Generation with Folded Tokens
ICLR 2025Poster
15
SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
ICLR 2025Poster
14
VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use
ICLR 2025Rejected
20
EigenLoRA: Recycle trained Adapters for Resource Efficient Adaptation and Inference
ICLR 2025Rejected
通讯21
CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models
ICLR 2025Rejected
15
ADOPD-Instruct: A Large-Scale Multimodal Dataset for Document Editing
ICLR 2025Rejected
通讯17
OIDA-QA: A Multimodal Benchmark for Analyzing the Opioid Industry Document Archive
ICLR 2025Rejected
通讯4
ControlVAR: Exploring Controllable Visual Autoregressive Modeling
ICLR 2025Withdrawn
5
LLaVA-Read: Enhancing Reading Ability of Multimodal Large Language Models
ICLR 2025Rejected