Paper accepted to ICML 2026 as a Spotlight
“Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in Modern Transformers” was accepted to ICML 2026 as a Spotlight.
Posts
Paper accepted to IJCV 2026
“Structural Pruning of Large Vision-Language Models: Pruning Dynamics, Recovery, and Data Efficiency” was accepted to IJCV 2026.
GCPR 2025 Oral: Structural Pruning and Recovery for MLLMs
“Investigating Structural Pruning and Recovery Techniques for Compressing MLLMs” was accepted to GCPR 2025 as an Oral.
ICLR 2025: Revealing and Reducing Gender Biases in Vision and Language Assistants
“Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)” was accepted to ICLR 2025.