Paria Rashidinejad

16 papers A* 6Journal 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing. CoRR Zarif Ikram, Arad Firouzkouhi, Stephen Tu, Mahdi Soltanolkotabi, Paria Rashidinejad
2026	J	`jnl`	Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes. CoRR Amrith Setlur, Zijian Wang, Andrew Cohen, Paria Rashidinejad, Sang Michael Xie
2025	J	`jnl`	SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models. CoRR Chenyu Wang, Paria Rashidinejad, DiJia Su, Song Jiang, Sid Wang, Siyan Zhao, Cai Zhou, Shannon Zejiang Shen, Feiyu Chen, Tommi S. Jaakkola, Yuandong Tian, Bo Liu
2025	A*	`conf`	Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking. ICLR Paria Rashidinejad, Yuandong Tian
2024	J	`jnl`	Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking. CoRR Paria Rashidinejad, Yuandong Tian
2023	A*	`conf`	Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning. NeurIPS Hanlin Zhu, Paria Rashidinejad, Jiantao Jiao
2023	J	`jnl`	Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning. CoRR Hanlin Zhu, Paria Rashidinejad, Jiantao Jiao
2023	A*	`conf`	Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian. ICLR Paria Rashidinejad, Hanlin Zhu, Kunhe Yang, Stuart Russell, Jiantao Jiao
2022	J	`jnl`	Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism. IEEE Trans. Inf. Theory Paria Rashidinejad, Banghua Zhu, Cong Ma, Jiantao Jiao, Stuart Russell
2022	J	`jnl`	Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian. CoRR Paria Rashidinejad, Hanlin Zhu, Kunhe Yang, Stuart Russell, Jiantao Jiao
2021	A*	`conf`	Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism. NeurIPS Paria Rashidinejad, Banghua Zhu, Cong Ma, Jiantao Jiao, Stuart Russell
2021	J	`jnl`	Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism. CoRR Paria Rashidinejad, Banghua Zhu, Cong Ma, Jiantao Jiao, Stuart Russell
2021	A*	`conf`	MADE: Exploration via Maximizing Deviation from Explored Regions. NeurIPS Tianjun Zhang, Paria Rashidinejad, Jiantao Jiao, Yuandong Tian, Joseph E. Gonzalez, Stuart Russell
2021	J	`jnl`	MADE: Exploration via Maximizing Deviation from Explored Regions. CoRR Tianjun Zhang, Paria Rashidinejad, Jiantao Jiao, Yuandong Tian, Joseph Gonzalez, Stuart Russell
2020	J	`jnl`	SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory. CoRR Paria Rashidinejad, Jiantao Jiao, Stuart Russell
2020	A*	`conf`	SLIP: Learning to predict in unknown dynamical systems with long-term memory. NeurIPS Paria Rashidinejad, Jiantao Jiao, Stuart Russell