Mert Yüksekgönül

41 papers A* 10A 1Journal 28Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory. EACL (Volume 1: Long Papers) Mirac Suzgun, Mert Yüksekgönül, Federico Bianchi, Dan Jurafsky, James Zou
2026	J	`jnl`	Learning to Discover at Test Time. CoRR Mert Yüksekgönül, Daniel Koceja, Xinhao Li, Federico Bianchi, Jed McCaleb, Xiaolong Wang, Jan Kautz, Yejin Choi, James Zou, Carlos Guestrin, Yu Sun
2026	J	`jnl`	Sparse Reward Subsystem in Large Language Models. CoRR Guowei Xu, Mert Yüksekgönül, James Zou
2025	J	`jnl`	A ghost mechanism: An analytical model of abrupt learning. CoRR Fatih Dinc, Ege Çirakman, Yiqi Jiang, Mert Yüksekgönül, Mark J. Schnitzer, Hidenori Tanaka
2025	J	`jnl`	Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025. CoRR Nitya Thakkar, Mert Yüksekgönül, Jake Silberg, Animesh Garg, Nanyun Peng, Fei Sha, Rose Yu, Carl Vondrick, James Zou
2025	J	`jnl`	Cost-of-Pass: An Economic Framework for Evaluating Language Models. CoRR Mehmet Hamza Erol, Batu El, Mirac Suzgun, Mert Yüksekgönül, James Zou
2025	J	`jnl`	Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory. CoRR Mirac Suzgun, Mert Yüksekgönül, Federico Bianchi, Dan Jurafsky, James Zou
2025	A*	`conf`	Dynamical phases of short-term memory mechanisms in RNNs. ICML Bariscan Kurtkaya, Fatih Dinc, Mert Yüksekgönül, Marta Blanco-Pozo, Ege Çirakman, Mark J. Schnitzer, Yucel Yemez, Hidenori Tanaka, Peng Yuan, Nina Miolane
2025	—	`conf`	Inefficiencies of Meta Agents for Agent Design. EMNLP (Findings) Batu El, Mert Yüksekgönül, James Zou
2025	J	`jnl`	Inefficiencies of Meta Agents for Agent Design. CoRR Batu El, Mert Yüksekgönül, James Zou
2025	J	`jnl`	Optimizing generative AI by backpropagating language model feedback. Nat. Mert Yüksekgönül, Federico Bianchi, Joseph Boen, Sheng Liu, Pan Lu, Zhi Huang, Carlos Guestrin, James Zou
2025	J	`jnl`	SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning. CoRR Wanjia Zhao, Mert Yüksekgönül, Shirley Wu, James Zou
2025	J	`jnl`	metaTextGrad: Automatically optimizing language model optimizers. CoRR Guowei Xu, Mert Yüksekgönül, Carlos Guestrin, James Y. Zou
2024	A*	`conf`	Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models. ICLR Mert Yüksekgönül, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, Besmira Nushi
2024	A*	`conf`	How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis. ICML Federico Bianchi, Patrick John Chia, Mert Yüksekgönül, Jacopo Tagliabue, Dan Jurafsky, James Zou
2024	J	`jnl`	How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis. CoRR Federico Bianchi, Patrick John Chia, Mert Yüksekgönül, Jacopo Tagliabue, Dan Jurafsky, James Zou
2024	A*	`conf`	KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval. ICLR Marah I Abdin, Suriya Gunasekar, Varun Chandrasekaran, Jerry Li, Mert Yüksekgönül, Rahee Ghosh Peshawaria, Ranjita Naik, Besmira Nushi
2024	J	`jnl`	TextGrad: Automatic "Differentiation" via Text. CoRR Mert Yüksekgönül, Federico Bianchi, Joseph Boen, Sheng Liu, Zhi Huang, Carlos Guestrin, James Zou
2023	J	`jnl`	Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models. CoRR Mert Yüksekgönül, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, Besmira Nushi
2023	A*	`conf`	Beyond Confidence: Reliable Models Should Also Consider Atypicality. NeurIPS Mert Yüksekgönül, Linjun Zhang, James Y. Zou, Carlos Guestrin
2023	J	`jnl`	Beyond Confidence: Reliable Models Should Also Consider Atypicality. CoRR Mert Yüksekgönül, Linjun Zhang, James Zou, Carlos Guestrin
2023	J	`jnl`	ChatGPT Exhibits Gender and Racial Biases in Acute Coronary Syndrome Management. CoRR Angela Zhang, Mert Yüksekgönül, Joshua Guild, James Zou, Joseph C. Wu
2023	A*	`conf`	Discover and Cure: Concept-aware Mitigation of Spurious Correlation. ICML Shirley Wu, Mert Yüksekgönül, Linjun Zhang, James Zou
2023	J	`jnl`	Discover and Cure: Concept-aware Mitigation of Spurious Correlation. CoRR Shirley Wu, Mert Yüksekgönül, Linjun Zhang, James Zou
2023	J	`jnl`	Diversity of Thought Improves Reasoning Abilities of Large Language Models. CoRR Ranjita Naik, Varun Chandrasekaran, Mert Yüksekgönül, Hamid Palangi, Besmira Nushi
2023	J	`jnl`	GPT detectors are biased against non-native English writers. CoRR Weixin Liang, Mert Yüksekgönül, Yining Mao, Eric Wu, James Zou
2023	J	`jnl`	GPT detectors are biased against non-native English writers. Patterns Weixin Liang, Mert Yüksekgönül, Yining Mao, Eric Wu, James Zou
2023	J	`jnl`	Holistic Evaluation of Language Models. Trans. Mach. Learn. Res. Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D. Manning, Christopher Ré, Diana Acosta-Navas, Drew A. Hudson, Eric Zelikman, Esin Durmus, Faisal Ladhak, Frieda Rong, Hongyu Ren, Huaxiu Yao, Jue Wang, Keshav Santhanam, Laurel J. Orr, Lucia Zheng, Mert Yüksekgönül, Mirac Suzgun, Nathan Kim, Neel Guha, Niladri S. Chatterji, Omar Khattab, Peter Henderson, Qian Huang, Ryan Chi, Sang Michael Xie, Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, Yuta Koreeda
2023	J	`jnl`	KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval. CoRR Marah I Abdin, Suriya Gunasekar, Varun Chandrasekaran, Jerry Li, Mert Yüksekgönül, Rahee Ghosh Peshawaria, Ranjita Naik, Besmira Nushi
2023	A*	`conf`	Post-hoc Concept Bottleneck Models. ICLR Mert Yüksekgönül, Maggie Wang, James Zou
2023	J	`jnl`	SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained model debugging and analysis. CoRR Roxana Daneshjou, Mert Yüksekgönül, Zhuo Ran Cai, Roberto A. Novoa, James Zou
2023	A*	`conf`	When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It? ICLR Mert Yüksekgönül, Federico Bianchi, Pratyusha Kalluri, Dan Jurafsky, James Zou
2022	J	`jnl`	Holistic Evaluation of Language Models. CoRR Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D. Manning, Christopher Ré, Diana Acosta-Navas, Drew A. Hudson, Eric Zelikman, Esin Durmus, Faisal Ladhak, Frieda Rong, Hongyu Ren, Huaxiu Yao, Jue Wang, Keshav Santhanam, Laurel J. Orr, Lucia Zheng, Mert Yüksekgönül, Mirac Suzgun, Nathan Kim, Neel Guha, Niladri S. Chatterji, Omar Khattab, Peter Henderson, Qian Huang, Ryan Chi, Sang Michael Xie, Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, Yuta Koreeda
2022	A*	`conf`	Meaningfully debugging model mistakes using conceptual counterfactual explanations. ICML Abubakar Abid, Mert Yüksekgönül, James Zou
2022	J	`jnl`	Post-hoc Concept Bottleneck Models. CoRR Mert Yüksekgönül, Maggie Wang, James Zou
2022	A*	`conf`	SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained debugging and analysis. NeurIPS Roxana Daneshjou, Mert Yüksekgönül, Zhuo Ran Cai, Roberto A. Novoa, James Y. Zou
2022	J	`jnl`	When and why vision-language models behave like bags-of-words, and what to do about it? CoRR Mert Yüksekgönül, Federico Bianchi, Pratyusha Kalluri, Dan Jurafsky, James Zou
2021	J	`jnl`	Learning prototypes for multiple instance learning. Turkish J. Electr. Eng. Comput. Sci. Özgür Emre Sivrikaya, Mert Yüksekgönül, Mustafa Gökçe Baydogan
2021	A	`conf`	Pretraining boosts out-of-domain robustness for pose estimation. WACV Alexander Mathis, Thomas Biasi, Steffen Schneider, Mert Yüksekgönül, Byron Rogers, Matthias Bethge, Mackenzie W. Mathis
2019	J	`jnl`	Learning Maximally Predictive Prototypes in Multiple Instance Learning. CoRR Mert Yüksekgönül, Özgür Emre Sivrikaya, Mustafa Gökçe Baydogan
2019	J	`jnl`	Pretraining boosts out-of-domain robustness for pose estimation. CoRR Alexander Mathis, Mert Yüksekgönül, Byron Rogers, Matthias Bethge, Mackenzie W. Mathis