Chenfeng_X

@chenfeng_x

Assistant Professor @UTCompSci, PhD @UCBerkeley. Working on something really works

following
followers

ORL claims similar performance at much higher speed than speculative decoding

The ORL team says co-designing algorithms, its training and inference engine, and kernels improves the speed–intelligence trade-off.

2 Sources, 5d ago, first seen 5d ago

Introspective Diffusion Language Models set for a COLM 2026 oral spotlight on October 8

A project researcher says introspective consistency helps diffusion language models match autoregressive quality while keeping fast parallel decoding.

4 Sources, 11d ago, updated 11d ago

Featured in

ORL claims similar performance at much higher speed than speculative decoding

Introspective Diffusion Language Models set for a COLM 2026 oral spotlight on October 8

Featured in

ORL claims similar performance at much higher speed than speculative decoding

Introspective Diffusion Language Models set for a COLM 2026 oral spotlight on October 8