Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/7ICML 2026Poster· Deep Learning / Large Language Models

Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding

Amirmohammad Izadi · Hosein Hasani · Fatemeh Askari · Mobin Bagherian · Sadegh Mohammadian · Mohammad Izadi · Mahdieh Baghshah

多模态OpenReview

作者位次 #2/6ICML 2026Poster· Deep Learning / Foundation Models

HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models

Reihaneh Zohrabi · Hosein Hasani · Akshita Gupta · Mahdieh Baghshah · Anna Rohrbach · Marcus Rohrbach

安全多模态OpenReview

一作ACL 2026Findings· Findings of ACL

Mechanistic Interpretability of Large-Scale Counting in LLM s through a S ystem-2 Strategy

Hosein Hasani · Mohammadali Banayeeanzade · Ali Nafisi · Sadegh Mohammadian · Fatemeh Askari · Mobin Bagherian · Amirmohammad Izadi · Mahdieh Soleymani Baghshah

摘要

Large language models (LLMs), despite strong performance on complex mathematical problems, exhibit systematic limitations in counting tasks. This issue arises from the architectural limits of transformers, where counting is performed across layers, leading to degraded precision for larger countin...

可解释性推理评测与基准OpenReview 项目页

Hosein Hasani

获取完整研究档案

联系方式

2026 顶会论文

Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding

HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models

Mechanistic Interpretability of Large-Scale Counting in LLM s through a S ystem-2 Strategy

常见合作者