Amrutha Saseendran

16 papers A* 7Journal 7Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding. CoRR Yanzheng Xiang, Lan Wei, Yizhen Yao, Qinglin Zhu, Hanqi Yan, Chen Jin, Philip Alexander Teare, Dandan Zhang, Lin Gui, Amrutha Saseendran, Yulan He
2025	A*	`conf`	Balancing Act: Diversity and Consistency in Large Language Model Ensembles. ICLR Ahmed Abdulaal, Chen Jin, Nina Montaña Brown, Aryo Pradipta Gema, Daniel C. Castro, Daniel C. Alexander, Philip Alexander Teare, Tom Diethe, Dino Oglic, Amrutha Saseendran
2025	—	`conf`	DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations. EMNLP (Findings) Aryo Pradipta Gema, Chen Jin, Ahmed Abdulaal, Tom Diethe, Philip Alexander Teare, Beatrice Alex, Pasquale Minervini, Amrutha Saseendran
2025	A*	`conf`	Diffusion Instruction Tuning. ICML Chen Jin, Ryutaro Tanno, Amrutha Saseendran, Tom Diethe, Philip Alexander Teare
2025	J	`jnl`	Diffusion Instruction Tuning. CoRR Chen Jin, Ryutaro Tanno, Amrutha Saseendran, Tom Diethe, Philip Teare
2025	J	`jnl`	Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States. CoRR Qinglin Zhu, Yizhen Yao, Runcong Zhao, Yanzheng Xiang, Amrutha Saseendran, Chen Jin, Philip Teare, Bin Liang, Yulan He, Lin Gui
2025	A*	`conf`	Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation. ICML Zhihua Liu, Amrutha Saseendran, Lei Tong, Xilin He, Fariba Yousefi, Nikolay Burlutskiy, Dino Oglic, Tom Diethe, Philip Alexander Teare, Huiyu Zhou, Chen Jin
2025	J	`jnl`	Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation. CoRR Zhihua Liu, Amrutha Saseendran, Lei Tong, Xilin He, Fariba Yousefi, Nikolay Burlutskiy, Dino Oglic, Tom Diethe, Philip Teare, Huiyu Zhou, Chen Jin
2024	A*	`conf`	An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning. ICML Chen Jin, Ryutaro Tanno, Amrutha Saseendran, Tom Diethe, Philip Teare
2024	J	`jnl`	DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations. CoRR Aryo Pradipta Gema, Chen Jin, Ahmed Abdulaal, Tom Diethe, Philip Teare, Beatrice Alex, Pasquale Minervini, Amrutha Saseendran
2023	J	`jnl`	An Image is Worth Multiple Words: Learning Object Level Concepts using Multi-Concept Prompt Learning. CoRR Chen Jin, Ryutaro Tanno, Amrutha Saseendran, Tom Diethe, Philip Teare
2023	—	`—`	Optimizing the latent space of deep generative models. Amrutha Saseendran
2022	A*	`conf`	Trading off Image Quality for Robustness is not Necessary with Regularized Deterministic Autoencoders. NeurIPS Amrutha Saseendran, Kathrin Skubch, Stefan Falkner, Margret Keuper
2021	A*	`conf`	Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation. ICCV Amrutha Saseendran, Kathrin Skubch, Margret Keuper
2021	J	`jnl`	Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation. CoRR Amrutha Saseendran, Kathrin Skubch, Margret Keuper
2021	A*	`conf`	Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders. NeurIPS Amrutha Saseendran, Kathrin Skubch, Stefan Falkner, Margret Keuper