Gleb Molodtsov

Two residual streams in diffusion language models halve the performance gains of adding a second stream by enabling distinct read and write routing patterns.

Prompt adaptation methods don't just change what LLMs say, they fundamentally rewire *how* they compute, with distinct mechanisms for text optimization, prompt tuning, and prefix tuning.

Self-generated QA pairs can introduce significant biases, leading to fragile learning dynamics that may undermine model performance.

Aggressive 2-bit inference can backfire, leading to longer reasoning traces and accuracy drops, but targeted recovery methods can reverse this trend dramatically.