PaperHub
影响力指数
41.78/100
前 13.2%
全站排名 #8,488
发表论文20 篇
平均评分4.6
年均产出10.0 篇/年

Xiaobin Hu

Researcher@National University of Singapore·新加坡·OpenReview
研究方向

LLM · Diffusion model · Deep learning and computer vision

6.0
14

VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models

ICLR 2026Rejected
6.0
16

Towards One-step Causal Video Generation via Adversarial Self-Distillation

ICLR 2026Poster
6.0
14

Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow

ICLR 2026Poster
5.5
22

MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems

ICLR 2026Poster
5.5
19

IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment

ICLR 2026Poster
5.5
20

Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models

ICLR 2026Poster
5.0
21

Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning

ICLR 2026Rejected
4.7
16

M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding

ICLR 2026Poster
4.5
5

ShortcutBreaker: Low-Rank Noisy Bottleneck with Global Perturbation Attention for Multi-Class Unsupervised Anomaly Detection

ICLR 2026Withdrawn
三作
4.5
5

Align Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuning

ICLR 2026Withdrawn
4.5
5

The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection

ICLR 2026Withdrawn
4.0
5

OracleAgent: A Multimodal Reasoning Agent for Oracle Bone Script Research

ICLR 2026Withdrawn
三作
3.6
6

TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement

ICLR 2026Withdrawn
3.5
5

Data-free VFX Self-Mining

ICLR 2026Withdrawn
2.5
6

HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding

ICLR 2026Rejected
2.0
4

DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation

ICLR 2026Withdrawn
合作者 (20)