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
66.88/100
前 3.2%
全站排名 #2,062
发表论文13 篇
平均评分
年均产出4.3 篇/年
Zsolt Kira
研究方向
deep learning · clustering · unsupervised learning · object discovery · semi-supervised learning · self-supervised learning · few-shot learning · continual learning · object detection · scene understanding · multi-modal fusion
11
Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning
ICLR 2026Desk Rejected
23
Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification
ICLR 2026Poster
通讯18
FindingDory: A Benchmark to Evaluate Memory in Embodied Agents
ICLR 2026Rejected
通讯5
Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Models
ICLR 2026Withdrawn
通讯17
Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
NeurIPS 2025Spotlight
三作19
Directional Gradient Projection for Robust Fine-Tuning of Foundation Models
ICLR 2025Poster
通讯28
Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding
ICLR 2025Poster
二作14
ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI
ICLR 2025Rejected