Hrayr Harutyunyan

32 papers A* 9B 1Journal 21Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	In-context Learning in Presence of Spurious Correlations. Trans. Mach. Learn. Res. Hrayr Harutyunyan, Rafayel Darbinyan, Samvel Karapetyan, Hrant Khachatrian
2025	J	`jnl`	Continuous Chain of Thought Enables Parallel Exploration and Reasoning. CoRR Halil Alperen Gozeten, Muhammed Emrullah Ildiz, Xuechen Zhang, Hrayr Harutyunyan, Ankit Singh Rawat, Samet Oymak
2025	J	`jnl`	Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation. CoRR Sangmin Bae, Yujin Kim, Reza Bayat, Sungnyun Kim, Jiyoun Ha, Tal Schuster, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Aaron C. Courville, Se-Young Yun
2025	A*	`conf`	Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA. ICLR Sangmin Bae, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Seungyeon Kim, Tal Schuster
2024	J	`jnl`	A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs. CoRR Ankit Singh Rawat, Veeranjaneyulu Sadhanala, Afshin Rostamizadeh, Ayan Chakrabarti, Wittawat Jitkrittum, Vladimir Feinberg, Seungyeon Kim, Hrayr Harutyunyan, Nikunj Saunshi, Zachary Nado, Rakesh Shivanna, Sashank J. Reddi, Aditya Krishna Menon, Rohan Anil, Sanjiv Kumar
2024	J	`jnl`	In-context Learning in Presence of Spurious Correlations. CoRR Hrayr Harutyunyan, Rafayel Darbinyan, Samvel Karapetyan, Hrant Khachatrian
2024	J	`jnl`	Mimetic Initialization Helps State Space Models Learn to Recall. CoRR Asher Trockman, Hrayr Harutyunyan, J. Zico Kolter, Sanjiv Kumar, Srinadh Bhojanapalli
2024	J	`jnl`	Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA. CoRR Sangmin Bae, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Seungyeon Kim, Tal Schuster
2023	A*	`conf`	A Meta-Learning Approach to Predicting Performance and Data Requirements. CVPR Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt Schiele, Ashwin Swaminathan, Stefano Soatto
2023	J	`jnl`	A Meta-Learning Approach to Predicting Performance and Data Requirements. CoRR Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt Schiele, Ashwin Swaminathan, Stefano Soatto
2023	J	`jnl`	Identifying and Disentangling Spurious Features in Pretrained Image Representations. CoRR Rafayel Darbinyan, Hrayr Harutyunyan, Aram H. Markosyan, Hrant Khachatrian
2023	J	`jnl`	On information captured by neural networks: connections with memorization and generalization. CoRR Hrayr Harutyunyan
2023	A*	`conf`	Supervision Complexity and its Role in Knowledge Distillation. ICLR Hrayr Harutyunyan, Ankit Singh Rawat, Aditya Krishna Menon, Seungyeon Kim, Sanjiv Kumar
2023	J	`jnl`	Supervision Complexity and its Role in Knowledge Distillation. CoRR Hrayr Harutyunyan, Ankit Singh Rawat, Aditya Krishna Menon, Seungyeon Kim, Sanjiv Kumar
2022	A*	`conf`	Failure Modes of Domain Generalization Algorithms. CVPR Tigran Galstyan, Hrayr Harutyunyan, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan
2022	B	`conf`	Formal limitations of sample-wise information-theoretic generalization bounds. ITW Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan
2022	J	`jnl`	Formal limitations of sample-wise information-theoretic generalization bounds. CoRR Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan
2022	J	`jnl`	Identifying geopolitical event precursors using attention-based LSTMs. Frontiers Artif. Intell. K. S. M. Tozammel Hossain, Hrayr Harutyunyan, Yue Ning, Brendan Kennedy, Naren Ramakrishnan, Aram Galstyan
2021	A*	`conf`	Estimating informativeness of samples with Smooth Unique Information. ICLR Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
2021	J	`jnl`	Estimating informativeness of samples with Smooth Unique Information. CoRR Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
2021	J	`jnl`	Failure Modes of Domain Generalization Algorithms. CoRR Tigran Galstyan, Hrayr Harutyunyan, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan
2021	A*	`conf`	Information-theoretic generalization bounds for black-box learning algorithms. NeurIPS Hrayr Harutyunyan, Maxim Raginsky, Greg Ver Steeg, Aram Galstyan
2021	J	`jnl`	Information-theoretic generalization bounds for black-box learning algorithms. CoRR Hrayr Harutyunyan, Maxim Raginsky, Greg Ver Steeg, Aram Galstyan
2020	J	`jnl`	Improving Generalization by Controlling Label-Noise Information in Neural Network Weights. CoRR Hrayr Harutyunyan, Kyle Reing, Greg Ver Steeg, Aram Galstyan
2020	A*	`conf`	Improving generalization by controlling label-noise information in neural network weights. ICML Hrayr Harutyunyan, Kyle Reing, Greg Ver Steeg, Aram Galstyan
2019	J	`jnl`	Efficient Covariance Estimation from Temporal Data. CoRR Hrayr Harutyunyan, Daniel Moyer, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan
2019	A*	`conf`	Fast structure learning with modular regularization. NeurIPS Greg Ver Steeg, Hrayr Harutyunyan, Daniel Moyer, Aram Galstyan
2019	A*	`conf`	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing. ICML Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan
2019	J	`jnl`	MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing. CoRR Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Hrayr Harutyunyan, Nazanin Alipourfard, Kristina Lerman, Greg Ver Steeg, Aram Galstyan
2017	J	`jnl`	Disentangled Representations via Synergy Minimization. CoRR Greg Ver Steeg, Rob Brekelmans, Hrayr Harutyunyan, Aram Galstyan
2017	—	`conf`	Disentangled representations via synergy minimization. Allerton Greg Ver Steeg, Rob Brekelmans, Hrayr Harutyunyan, Aram Galstyan
2017	J	`jnl`	Multitask Learning and Benchmarking with Clinical Time Series Data. CoRR Hrayr Harutyunyan, Hrant Khachatrian, David C. Kale, Aram Galstyan