Aashiq Muhamed

24 papers A* 4Journal 12Unranked 8

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language. EACL (Volume 1: Long Papers) Mena Attia, Aashiq Muhamed, Mai Alkhamissi, Thamar Solorio, Mona T. Diab
2026	J	`jnl`	DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment. CoRR James Wedgwood, Aashiq Muhamed, Mona T. Diab, Virginia Smith
2026	—	`conf`	RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models. EACL (Volume 1: Long Papers) Aashiq Muhamed, Leonardo F. R. Ribeiro, Markus Dreyer, Virginia Smith, Mona T. Diab
2025	J	`jnl`	Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language. CoRR Mena Attia, Aashiq Muhamed, Mai Alkhamissi, Thamar Solorio, Mona T. Diab
2025	J	`jnl`	CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation. CoRR Aashiq Muhamed
2025	—	`conf`	CoRAG: Collaborative Retrieval-Augmented Generation. NAACL (Short Papers) Aashiq Muhamed, Mona T. Diab, Virginia Smith
2025	J	`jnl`	CoRAG: Collaborative Retrieval-Augmented Generation. CoRR Aashiq Muhamed, Mona T. Diab, Virginia Smith
2025	—	`conf`	Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models. NAACL (Findings) Aashiq Muhamed, Mona T. Diab, Virginia Smith
2025	J	`jnl`	NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA. Trans. Mach. Learn. Res. Marlon Tobaben, Mohamed Ali Souibgui, Rubèn Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas Jälkö, Lei Kang, Andrey Barsky, Vincent Poulain D'Andecy, Aurélie Joseph, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kenta Niwa, Iifan Tyou, Hiro Ishii, Rio Yokota, Ragul N, Rintu Kutum, Josep Lladós, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
2025	J	`jnl`	Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs. CoRR Xiangchen Song, Aashiq Muhamed, Yujia Zheng, Lingjing Kong, Zeyu Tang, Mona T. Diab, Virginia Smith, Kun Zhang
2025	J	`jnl`	RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models. CoRR Aashiq Muhamed, Leonardo F. R. Ribeiro, Markus Dreyer, Virginia Smith, Mona T. Diab
2025	J	`jnl`	SAEs CoRR Aashiq Muhamed, Jacopo Bonato, Mona T. Diab, Virginia Smith
2024	A*	`conf`	Adversarial Text to Continuous Image Generation. CVPR Kilichbek Haydarov, Aashiq Muhamed, Xiaoqian Shen, Jovana Lazarevic, Ivan Skorokhodov, Chamuditha Jayanga Galappaththige, Mohamed Elhoseiny
2024	J	`jnl`	Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models. CoRR Aashiq Muhamed, Mona T. Diab, Virginia Smith
2024	A*	`conf`	GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients. EMNLP Aashiq Muhamed, Oscar Li, David P. Woodruff, Mona T. Diab, Virginia Smith
2024	J	`jnl`	Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients. CoRR Aashiq Muhamed, Oscar Li, David P. Woodruff, Mona T. Diab, Virginia Smith
2024	J	`jnl`	NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA. CoRR Marlon Tobaben, Mohamed Ali Souibgui, Rubèn Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas Jälkö, Lei Kang, Andrey Barsky, Vincent Poulain D'Andecy, Aurélie Joseph, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kenta Niwa, Iifan Tyou, Hiro Ishii, Rio Yokota, Ragul N, Rintu Kutum, Josep Lladós, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
2023	J	`jnl`	An In-depth Look at Gemini's Language Abilities. CoRR Syeda Nahida Akter, Zichun Yu, Aashiq Muhamed, Tianyue Ou, Alex Bäuerle, Ángel Alexander Cabrera, Krish Dholakia, Chenyan Xiong, Graham Neubig
2023	—	`conf`	ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models. ACL (2) Jianyi Zhang, Aashiq Muhamed, Aditya Anantharaman, Guoyin Wang, Changyou Chen, Kai Zhong, Qingjun Cui, Yi Xu, Belinda Zeng, Trishul Chilimbi, Yiran Chen
2023	A*	`conf`	Training Large-scale Foundation Models on Emerging AI Chips. KDD Aashiq Muhamed, Christian Bock, Rahul Solanki, Youngsuk Park, Yida Wang, Jun Huan
2023	—	`conf`	Web-Scale Semantic Product Search with Large Language Models. PAKDD (3) Aashiq Muhamed, Sriram Srinivasan, Choon Hui Teo, Qingjun Cui, Belinda Zeng, Trishul Chilimbi, S. V. N. Vishwanathan
2022	—	`conf`	DCAF-BERT: A Distilled Cachable Adaptable Factorized Model For Improved Ads CTR Prediction. WWW (Companion Volume) Aashiq Muhamed, Jaspreet Singh, Shuai Zheng, Iman Keivanloo, Sujan Perera, James Mracek, Yi Xu, Qingjun Cui, Santosh Rajagopalan, Belinda Zeng, Trishul Chilimbi
2021	—	`conf`	Gated Transformer for Decoding Human Brain EEG Signals. EMBC Yunzhe Tao, Tao Sun, Aashiq Muhamed, Sahika Genc, Dylan Jackson, Ali Arsanjani, Suri Yaddanapudi, Liang Li, Prachi Kumar
2021	A*	`conf`	Symbolic Music Generation with Transformer-GANs. AAAI Aashiq Muhamed, Liang Li, Xingjian Shi, Suri Yaddanapudi, Wayne Chi, Dylan Jackson, Rahul Suresh, Zachary C. Lipton, Alexander J. Smola