3 papers
cs.LG2026
Do We Really Need KL Divergence for On-Policy Distillation of Large Language Models?
Wenze Lin, Jiyuan Long, Jiale Zhao +11
Since the advent of knowledge distillation, KL divergence has been the standard loss in distillation. Recently, on-policy distillation (OPD) has emerged as an efficient post-traini…
cs.LG2026
OLEDLM: A Unified Language Model for OLED Molecular Design
Fukang Wen, Yuchong Tang, Jingyuan Li +9
The development of organic light-emitting diode (OLED) materials faces the compounded challenges of an astronomically large chemical space, stringent quantum-chemical constraints,…
cs.LG2026
Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction
Jingyuan Li, Xiaoyi Jiang, Fukang Wen +5
Discrete diffusion models based on continuous-time Markov chains (CTMCs) have shown strong performance on language and discrete data generation, yet existing approaches typically p…