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
40.04/100
前 14.4%
全站排名 #9,270
发表论文14 篇
平均评分
年均产出4.7 篇/年
Haoqin Tu
研究方向
AI Safety · Dialogue Systems · Multimodal Interaction · Generative Model · Natural Language Processing
5
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
ICLR 2026Withdrawn
二作5
When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought
ICLR 2026Withdrawn
二作5
LightBagel: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation
ICLR 2026Withdrawn
20
Where in the World? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
ICLR 2026Rejected
4
AHELM: A Holistic Evaluation of Audio-Language Models
ICLR 2026Withdrawn
二作50
MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
ICLR 2025Rejected
23
Autoregressive Pretraining with Mamba in Vision
ICLR 2025Poster
三作11
What If We Recaption Billions of Web Images with LLaMA-3?
ICML 2025Poster
二作24
What If We Recaption Billions of Web Images with LLaMA-3?
ICLR 2025Rejected
二作5
AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
ICLR 2025Withdrawn
二作4
A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?
ICLR 2025Withdrawn
三作