Rahma Chaabouni

25 papers A* 6A 1B 1Journal 12Unranked 4

Year	Rank	Type	Title / Venue / Authors
2024	—	`conf`	Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning. ACL (Findings) Mathieu Rita, Florian Strub, Rahma Chaabouni, Paul Michel, Emmanuel Dupoux, Olivier Pietquin
2024	J	`jnl`	Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning. CoRR Mathieu Rita, Florian Strub, Rahma Chaabouni, Paul Michel, Emmanuel Dupoux, Olivier Pietquin
2024	J	`jnl`	Language Evolution with Deep Learning. CoRR Mathieu Rita, Paul Michel, Rahma Chaabouni, Olivier Pietquin, Emmanuel Dupoux, Florian Strub
2024	A*	`conf`	Memory Consolidation Enables Long-Context Video Understanding. ICML Ivana Balazevic, Yuge Shi, Pinelopi Papalampidi, Rahma Chaabouni, Skanda Koppula, Olivier J. Hénaff
2024	J	`jnl`	Memory Consolidation Enables Long-Context Video Understanding. CoRR Ivana Balazevic, Yuge Shi, Pinelopi Papalampidi, Rahma Chaabouni, Skanda Koppula, Olivier J. Hénaff
2022	A*	`conf`	Emergent Communication at Scale. ICLR Rahma Chaabouni, Florian Strub, Florent Altché, Eugene Tarassov, Corentin Tallec, Elnaz Davoodi, Kory Wallace Mathewson, Olivier Tieleman, Angeliki Lazaridou, Bilal Piot
2021	—	`conf`	Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN. BlackboxNLP@EMNLP Rahma Chaabouni, Roberto Dessì, Eugene Kharitonov
2021	J	`jnl`	Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN. CoRR Rahma Chaabouni, Roberto Dessì, Eugene Kharitonov
2021	—	`—`	Emerging linguistic universals in communicating neural network agents. (Les universaux linguistiques émergeant dans les réseaux de neurones communicants). Rahma Chaabouni
2021	A*	`conf`	What they do when in doubt: a study of inductive biases in seq2seq learners. ICLR Eugene Kharitonov, Rahma Chaabouni
2020	B	`conf`	"LazImpa": Lazy and Impatient neural agents learn to communicate efficiently. CoNLL Mathieu Rita, Rahma Chaabouni, Emmanuel Dupoux
2020	J	`jnl`	"LazImpa": Lazy and Impatient neural agents learn to communicate efficiently. CoRR Mathieu Rita, Rahma Chaabouni, Emmanuel Dupoux
2020	A*	`conf`	Compositionality and Generalization In Emergent Languages. ACL Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux, Marco Baroni
2020	J	`jnl`	Compositionality and Generalization in Emergent Languages. CoRR Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux, Marco Baroni
2020	A*	`conf`	Entropy Minimization In Emergent Languages. ICML Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni
2020	J	`jnl`	What they do when in doubt: a study of inductive biases in seq2seq learners. CoRR Eugene Kharitonov, Rahma Chaabouni
2019	A*	`conf`	Anti-efficient encoding in emergent communication. NeurIPS Rahma Chaabouni, Eugene Kharitonov, Emmanuel Dupoux, Marco Baroni
2019	J	`jnl`	Anti-efficient encoding in emergent communication. CoRR Rahma Chaabouni, Eugene Kharitonov, Emmanuel Dupoux, Marco Baroni
2019	—	`conf`	EGG: a toolkit for research on Emergence of lanGuage in Games. EMNLP/IJCNLP (3) Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni
2019	J	`jnl`	EGG: a toolkit for research on Emergence of lanGuage in Games. CoRR Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni
2019	J	`jnl`	Information Minimization In Emergent Languages. CoRR Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni
2019	—	`conf`	Word-order Biases in Deep-agent Emergent Communication. ACL (1) Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, Marco Baroni
2019	J	`jnl`	Word-order biases in deep-agent emergent communication. CoRR Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, Marco Baroni
2017	A	`conf`	Learning Weakly Supervised Multimodal Phoneme Embeddings. INTERSPEECH Rahma Chaabouni, Ewan Dunbar, Neil Zeghidour, Emmanuel Dupoux
2017	J	`jnl`	Learning weakly supervised multimodal phoneme embeddings. CoRR Rahma Chaabouni, Ewan Dunbar, Neil Zeghidour, Emmanuel Dupoux