Scholar
Hunar Batra
Google Scholar ID: K3_HjboAAAAJ
University of Oxford
Machine Learning
Language Models
Multimodal AI
Reinforcement Learning
AI Safety
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
533
H-index
6
i10-index
5
Publications
10
Co-authors
4
list available
Contact
No contact links provided.
Publications
8 items
Constitutional Midtraining: Content Presence Drives Alignment Gains
2026
Cited
0
Reasoning Fine-Tuning Induces Persistent Latent Policy States
2026
Cited
0
MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following
2026
Cited
0
Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks
2026
Cited
0
Towards Understanding Multimodal Fine-Tuning: Spatial Features
2026
Cited
0
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
2025
Cited
0
Measuring what Matters: Construct Validity in Large Language Model Benchmarks
2025
Cited
0
Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
arXiv.org · 2024
Cited
13
Resume (English only)
Co-authors
4 total
Ethan Perez
Anthropic
Miles Turpin
Research Scientist, Scale AI
Ronald Clark
University of Oxford
Co-author 4
