2 papers
cs.CV2026
Diminishing Returns in Self-Supervised Learning
Oli Bridge, Huey Sun, Botond Branyicskai-Nagy +2
Transformer-based architectures have become a dominant paradigm in vision and language, but their success is often attributed to large model capacity and massive training data. In…
cs.CL2025
Enhancing Instruction-Following Capabilities in Seq2Seq Models: DoLA Adaptations for T5
Huey Sun, Anabel Yong, Lorenzo Gilly +1
Encoder-decoder models such as FLAN-T5 are finetuned to follow instructions, but often fail when the instructions conflict with memorized continuations ingrained during training. T…