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
63.43/100
前 3.9%
全站排名 #2,496
发表论文14 篇
平均评分
年均产出4.7 篇/年
Mehrdad Farajtabar
研究方向
LLM Reasoning · LLM Efficient Inference · Mixture of Expert Models · Large Language Models · Clip Models · Multimodal Models · Continual Learning
11
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
ICML 2025Poster
25
TiC-LM: A Multi-Year Benchmark for Continual Pretraining of Language Models
ICLR 2025Rejected
33
GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
ICLR 2025Poster
通讯24
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
NeurIPS 2025Poster
通讯19
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
ICLR 2025Rejected
32
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
ICLR 2025Rejected