2 papers
cs.CL2026
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
Yuchen Cai, Ding Cao, Liang Lin +9
On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and…
cs.CL2026
EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs
Liang Lin, Chunxi Luo, Kaiwen Luo +9
Audio Large Language Models (ALLMs) are highly vulnerable to real-world noise, which often induces severe semantic drift and hallucinations. Existing robustness methods primarily r…