Hassan Mansoor

15 papers A* 3Journal 8Unranked 4
YearRankTypeTitle / Venue / Authors
2025 A* conf
AuPair: Golden Example Pairs for Code Repair.
ICML
Aditi Mavalankar, Hassan Mansoor, Zita Marinho, Mariia Samsikova, Tom Schaul
2025 J jnl
AuPair: Golden Example Pairs for Code Repair.
CoRR
Aditi Mavalankar, Hassan Mansoor, Zita Marinho, Masha Samsikova, Tom Schaul
2025 — conf
Self-play through Computational Runtimes improves Chart Reasoning.
ACL (Findings)
Tautvydas Misiunas, Hassan Mansoor, Jasper Uijlings, Oriana Riva, Victor Carbune
2024 — conf
Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs.
NAACL-HLT (Findings)
Victor Carbune, Hassan Mansoor, Fangyu Liu, Rahul Aralikatte, Gilles Baechler, Jindong Chen, Abhanshu Sharma
2024 J jnl
Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs.
CoRR
Victor Carbune, Hassan Mansoor, Fangyu Liu, Rahul Aralikatte, Gilles Baechler, Jindong Chen, Abhanshu Sharma
2024 — conf
LLMs cannot find reasoning errors, but can correct them given the error location.
ACL (Findings)
Gladys Tyen, Hassan Mansoor, Victor Carbune, Peter Chen, Tony Mak
2024 J jnl
PERL: Parameter Efficient Reinforcement Learning from Human Feedback.
CoRR
Hakim Sidahmed, Samrat Phatale, Alex Hutcheson, Zhuonan Lin, Zhang Chen, Zac Yu, Jarvis Jin, Roman Komarytsia, Christiane Ahlheim, Yonghao Zhu, Simral Chaudhary, Bowen Li, Saravanan Ganesh, Bill Byrne, Jessica Hoffmann, Hassan Mansoor, Wei Li, Abhinav Rastogi, Lucas Dixon
2024 A* conf
RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback.
ICML
Harrison Lee, Samrat Phatale, Hassan Mansoor, Thomas Mesnard, Johan Ferret, Kellie Lu, Colton Bishop, Ethan Hall, Victor Carbune, Abhinav Rastogi, Sushant Prakash
2024 A* conf
ScreenAI: A Vision-Language Model for UI and Infographics Understanding.
IJCAI
Gilles Baechler, Srinivas Sunkara, Maria Wang, Fedir Zubach, Hassan Mansoor, Vincent Etter, Victor Carbune, Jason Lin, Jindong Chen, Abhanshu Sharma
2024 J jnl
ScreenAI: A Vision-Language Model for UI and Infographics Understanding.
CoRR
Gilles Baechler, Srinivas Sunkara, Maria Wang, Fedir Zubach, Hassan Mansoor, Vincent Etter, Victor Carbune, Jason Lin, Jindong Chen, Abhanshu Sharma
2024 J jnl
VQA Training Sets are Self-play Environments for Generating Few-shot Pools.
CoRR
Tautvydas Misiunas, Hassan Mansoor, Jasper Uijlings, Oriana Riva, Victor Carbune
2023 J jnl
LLMs cannot find reasoning errors, but can correct them!
CoRR
Gladys Tyen, Hassan Mansoor, Peter Chen, Tony Mak, Victor Carbune
2023 J jnl
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback.
CoRR
Harrison Lee, Samrat Phatale, Hassan Mansoor, Kellie Lu, Thomas Mesnard, Colton Bishop, Victor Carbune, Abhinav Rastogi
2023 J jnl
The Impact of Preference Agreement in Reinforcement Learning from Human Feedback: A Case Study in Summarization.
CoRR
Sian Gooding, Hassan Mansoor
2016 — conf
Towards Semi-Automatic Size Measurement of User Interfaces in Web Applications with IFPUG SNAP.
IWSM-Mensura
Hassan Mansoor, Miroslaw Ochodek