arxivJul 31bullish
arXiv:2607.28590v1 Announce Type: cross Abstract: Multimodal on-policy distillation (OPD) transfers fine-grained visual knowledge by supervising student-generated trajectories with a privileged-view teacher. Yet its next-token corrections are source-mixed, combining visual signals with linguistic pr
arxivJul 31
arXiv:2606.13657v3 Announce Type: replace Abstract: On-policy distillation (OPD) has recently become a prominent post-training recipe by combining two desirable ingredients: on-policy student-generated trajectories and dense token-level teacher supervision. Yet how this hybrid training regime shapes
arxivJul 16
arXiv:2607.11948v1 Announce Type: cross Abstract: Regulated financial institutions operating under data-residency rules need tenant-owned language models that can run inside the institution's perimeter. This paper combines two related FAOS studies into one mechanism-and-control article. First, it re
arxivJun 17
arXiv:2605.12227v2 Announce Type: replace Abstract: Existing approaches to post-train models for long-context tasks face complementary limitations: (i) supervised fine-tuning (SFT) provides stable supervision but suffers from exposure bias; (ii) reinforcement learning methods such as Group Relative
arxivJun 11bullish
arXiv:2606.04694v2 Announce Type: replace Abstract: Small language models (SLMs) are efficient and scalable, but their multilingual capabilities degrade severely at sub-billion scales, especially for Southeast Asian (SEA) languages. We introduce DuDi, a dual-signal multilingual distillation framewor
arxivJun 4bullish
arXiv:2606.04694v1 Announce Type: new Abstract: Small language models (SLMs) are efficient and scalable, but their multilingual capabilities degrade severely at sub-billion scales, especially for Southeast Asian (SEA) languages. We introduce DuDi, a dual-signal multilingual distillation framework th
arxivJun 3bullish
arXiv:2606.02684v1 Announce Type: cross Abstract: On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms. Recent OPD methods increasingly focus on selecting which trajectories to learn from, which tokens are most info
arxivMay 13bullish
arXiv:2605.09192v1 Announce Type: new Abstract: Agent skills can remarkably improve task success rates by using human-written procedural documents, but their quality is difficult to assess without environment-grounded verification. Existing skill generation methods heavily rely on preference logs ra