SCALE (Selective Control of Adaptation via Local Entropy), an entropy-guided adaptation-strength-control method that freezes the pretrained model and the SFT delta and learns bounded token- and module-specific gates by minimizing predictive entropy alone is proposed.
Cun-Chun Li, Hao-Nan He, Yi-Fan Gao et al.· 0 citations
SciWalker, a framework for synthesizing scientific coding problems through operator-chain sampling and execution feedback, enables scalable task generation while promoting scientific grounding, computational diversity, and executability.
Chen-Xi Li, Wen-Xuan Zeng, Yun Luo et al.· 0 citations
This paper makes the first attempt to fine-tune MoE models with MoE-style low-rank adaptation via a dual-channel Routing-Conditioned Projection module, which reuses base router activations to inform LoRA routing and introduces a single global LoRA expert pool shared across all layers.
Qingyu Yang, Haonan He, Minglei Li et al.· arXiv.org· 0 citations
This work introduces a student reference KL loss and mask the advantages of special termination tokens to mitigate the problem of excessive generation length and frequent truncation, and improves on science benchmarks such as HLE and HiPhO, suggesting that OPD transfers reasoning capabilities that generalize beyond the...
Hao-Nan He, Hao Lei, Yun Luo et al.· 5 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.