Bilgehan Sel

21 papers A* 6Journal 12Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
Reinforcement Learning with Backtracking Feedback.
CoRR
Bilgehan Sel, Vaishakh Keshava, Phillip Wallis, Lukas Rutishauser, Ming Jin, Dingcheng Li
2026 J jnl
Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning.
CoRR
Bilgehan Sel, Xuanli He, Alwin Peng, Ming Jin, Jerry Wei
2025 J jnl
Backtracking for Safety.
CoRR
Bilgehan Sel, Dingcheng Li, Phillip Wallis, Vaishakh Keshava, Ming Jin, Siddhartha Reddy Jonnalagadda
2025 A* conf
LLMs Can Plan Only If We Tell Them.
ICLR
Bilgehan Sel, Ruoxi Jia, Ming Jin
2025 J jnl
LLMs Can Plan Only If We Tell Them.
CoRR
Bilgehan Sel, Ruoxi Jia, Ming Jin
2025 A* conf
LLMs Can Reason Faster Only If We Let Them.
ICML
Bilgehan Sel, Lifu Huang, Naren Ramakrishnan, Ruoxi Jia, Ming Jin
2025 J jnl
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning.
IEEE Trans. Pattern Anal. Mach. Intell.
Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, Qingwei Lin, Alois Knoll, Ming Jin
2024 J jnl
A CMDP-within-online framework for Meta-Safe Reinforcement Learning.
CoRR
Vanshaj Khattar, Yuhao Ding, Bilgehan Sel, Javad Lavaei, Ming Jin
2024 A* conf
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models.
ICML
Bilgehan Sel, Ahmad Al-Tawaha, Vanshaj Khattar, Ruoxi Jia, Ming Jin
2024 A* conf
Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation.
AAAI
Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, Qingwei Lin, Ming Jin, Alois Knoll
2024 J jnl
Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation.
CoRR
Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, Qingwei Lin, Ming Jin, Alois Knoll
2024 — conf
Democratizing Energy Management with LLM-Assisted Optimization Autoformalism.
SmartGridComm
Ming Jin, Bilgehan Sel, Fnu Hardeep, Wotao Yin
2024 J jnl
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning.
CoRR
Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, Qingwei Lin, Alois Knoll, Ming Jin
2024 — conf
Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs.
ACL (1)
Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin
2024 J jnl
Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs.
CoRR
Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin
2023 A* conf
A CMDP-within-online framework for Meta-Safe Reinforcement Learning.
ICLR
Vanshaj Khattar, Yuhao Ding, Bilgehan Sel, Javad Lavaei, Ming Jin
2023 J jnl
A Human-on-the-Loop Optimization Autoformalism Approach for Sustainability.
CoRR
Ming Jin, Bilgehan Sel, Fnu Hardeep, Wotao Yin
2023 J jnl
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models.
CoRR
Bilgehan Sel, Ahmad Al-Tawaha, Vanshaj Khattar, Lu Wang, Ruoxi Jia, Ming Jin
2023 — conf
Learning-to-Learn to Guide Random Search: Derivative-Free Meta Blackbox Optimization on Manifold.
L4DC
Bilgehan Sel, Ahmad Al-Tawaha, Yuhao Ding, Ruoxi Jia, Bo Ji, Javad Lavaei, Ming Jin
2023 A* conf
On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds.
AAAI
Ming Jin, Vanshaj Khattar, Harshal Kaushik, Bilgehan Sel, Ruoxi Jia
2022 J jnl
On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds.
CoRR
Ming Jin, Vanshaj Khattar, Harshal Kaushik, Bilgehan Sel, Ruoxi Jia