Scholar

Assaf Hallak

Google Scholar ID: DdtAyEIAAAAJ

NVIDIA Research

Reinforcement Learning

Google Scholar↗

Citations & Impact

All-time

Citations

656

H-index

10

i10-index

10

Publications

20

Co-authors

0

Contact

No contact links provided.

Publications

6 items

More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search

2026

Cited

0

Who Said Neural Networks Aren't Linear?

2025

Cited

0

Towards Large Language Models with Self-Consistent Natural Language Explanations

2025

Cited

0

"You just can't go around killing people"Explaining Agent Behavior to a Human Terminator

2025

Cited

0

RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression

2025

Cited

0

SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search

arXiv.org · 2023

Cited

3

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)