21 11 45

Lukas Helff

LukasHug

https://www.ml.informatik.tu-darmstadt.de/people/lhelff/index.html

lukashelff

AI & ML interests

I am a PhD student in the AI and ML Lab at TU Darmstadt, specializing in deep learning and computer vision. My research primarily revolves around visual and logical reasoning using deep neural networks, symbolic AI, and Neural-Symbolic AI.

Recent Activity

upvoted a collection about 11 hours ago

Reward Hacking in Reasoning Models

updated a collection about 11 hours ago

Reward Hacking in Reasoning Models

upvoted a paper about 11 hours ago

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking

View all activity

Organizations

liked a Space 4 days ago

SLR-Bench Leaderboard - Reward Hacking in Reasoning Models

🎯

Reward shortcut behavior in LLMs via IPT

liked a dataset 7 days ago

AIML-TUDA/SLR-Homes

Viewer • Updated 6 days ago • 500 • 84 • 1

liked a Space 12 days ago

Isomorphic Perturbation Testing

🔍

Evaluate rule hypotheses for genuine reasoning vs shortcuts

liked a dataset 6 months ago

AIML-TUDA/Rail2Country

Viewer • Updated Dec 4, 2025 • 4.8k • 82 • 3

liked a model 7 months ago

AIML-TUDA/Llama-3.1-8B-SLR

8B • Updated Oct 9, 2025 • 1 • 1

liked 3 datasets 7 months ago

liked a Space 11 months ago

VerifiableRewardsForScalableLogicalReasoning

🚀

Evaluate logical rules with a validation program

liked a dataset 11 months ago

AIML-TUDA/SLR-Bench

Viewer • Updated about 12 hours ago • 38.5k • 1.12k • 4

liked 4 models about 1 year ago

AIML-TUDA/QwenGuard-v1.2-7B

Image-Text-to-Text • 8B • Updated May 12, 2025 • 78 • 5

AIML-TUDA/QwenGuard-v1.2-3B

Image-Text-to-Text • 4B • Updated May 12, 2025 • 23 • 3

EleutherAI/sae-llama-3.1-8b-64x

Updated Jul 22, 2025 • 25 • 17

LukasHug/LlavaGuard-v1.2-0.5B-OV-Default-Policy

Image-Text-to-Text • 0.9B • Updated Mar 20, 2025 • 3 • 1

liked a Space about 1 year ago

Zebra Logic Bench

🦓

Show leaderboard and explore model puzzle results

liked a dataset over 1 year ago

kzhou35/mssbench

Viewer • Updated Nov 27, 2024 • 724 • 471 • 5

liked 2 models over 1 year ago

AIML-TUDA/LlavaGuard-v1.2-0.5B-OV-hf

Image-Text-to-Text • 0.9B • Updated Jan 17, 2025 • 492 • 4

AIML-TUDA/LlavaGuard-v1.2-0.5B-OV

Image-Text-to-Text • 0.9B • Updated Jan 17, 2025 • 116 • 2

liked a dataset over 1 year ago

Spawning/PD12M

Viewer • Updated Jan 9, 2025 • 12.4M • 6.1k • 173

liked a model over 1 year ago

AIML-TUDA/LlavaGuard-v1.2-7B-OV-hf

Image-Text-to-Text • 8B • Updated Jan 17, 2025 • 1.52k • 5