Mohammadhossein Bateni

Research scientist@Google·美国·OpenReview

研究方向

active learning · data efficiency · model efficiency · sampling · distributed computation · streaming algorithms · coresets · sketches · clustering · planar graphs · network design · approximation algorithms

5.0

Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories

ICLR 2026Rejected

4.0

Less is More: Adaptive Coverage Sampling for Synthetic Training Data

ICLR 2026Rejected

三作

4.0

Shared Embedding Optimization: A Two-Stage Approach for Efficient and Effective Feature Embedding

ICLR 2026Withdrawn

3.6

Synthetic Text Generation for Training Large Language Models via Gradient Matching

ICML 2025Poster

三作

4.3

Less is More: Adaptive Coverage for Synthetic Training Data

ICLR 2025Rejected

三作

3.0

NanoMoE: Scaling Mixture of Experts to Individual Layers for Parameter-Efficient Deep Learning

合作者 (20)

MohammadTaghi Hajiaghayi

Mohammadhossein Bateni

Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories

Less is More: Adaptive Coverage Sampling for Synthetic Training Data

Shared Embedding Optimization: A Two-Stage Approach for Efficient and Effective Feature Embedding

Universal Ordering for Efficient PAC Learning

Replicable Online pricing

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation

DeepCrossAttention: Supercharging Transformer Residual Connections

Synthetic Text Generation for Training Large Language Models via Gradient Matching

Less is More: Adaptive Coverage for Synthetic Training Data

NanoMoE: Scaling Mixture of Experts to Individual Layers for Parameter-Efficient Deep Learning