A four-coefficient parameterization lambda_t = sigma(a * h_t + b * u(x) + c + d * gap_t) in which direction-aligned proxies of EOPD and ToDi appear as one-dimensional (1D) restrictions, and which adds multi-channel composition and an explicit bias as further degrees of freedom.
Abstract
Per-token gating of forward/reverse KL losses has become a standard technique for on-policy knowledge distillation (OPD), but existing methods such as EOPD (Jin et al., 2026) and ToDi (Jung et al., 2025) each fix a single gating signal and a single gating direction, and the two have never been compared directly. We introduce a four-coefficient parameterization lambda_t = sigma(a * h_t + b * u(x) + c + d * gap_t) in which direction-aligned proxies of EOPD and ToDi appear as one-dimensional (1D) restrictions, and which adds multi-channel composition and an explicit bias as further degrees of freedom. On TweetEval (Barbieri et al., 2020) emotion and hate, with a Qwen3-32B teacher and a Qwen3-4B student, configurations in the full family reach higher accuracy than the matched-magnitude single-channel (entropy-only / gap-only) 1D restrictions in 33 of 36 comparable cells, and a 26-cell mean-match isolation experiment places dynamic gating ahead of effective-KL-matched static baselines in 19 of 26 cells. Because cells share training data, models, and parameter substructure, we report both counts as exploratory aggregate directional evidence rather than as independent hypothesis tests. Targeted three-seed paired replications of the nine headline comparisons singled out by that sweep -- including a third task, offensive -- are directionally consistent, but individually smaller than the single-seed estimates and not significant at n=3. We therefore present the parameterization primarily as a shared coordinate system for comparing per-token gating designs in short-output classification OPD.
PMOPD ( project-based Multi-Teacher On-Policy Distillation), which constructs subspace memories from the cumulative parameter displacements of different tasks and projects both gradients and optimizer updates to remove components that interfere with protected task directions, establishes geometry-aware optimization as...
You-Zhi Liu, Ruo-Bing Zheng, Bo-Yuan Tong et al.· 0 citations
The Multi-Level Optimal Transport (MultiLevelOT) is introduced, a novel approach that advances the optimal transport for universal cross-tokenizer knowledge distillation and is robust to different student and teacher models across model families, architectures, and parameter sizes.
Xiao Cui, Mo Zhu, Yu-Lei Qin et al.· IEEE Transactions on Pattern...· 2 citations
Across six 300-step runs on an 8-H20 node, every CLOOPD policy improves the one-pass TOP-D anchor at comparable teacher-token scale: macro accuracy rises from 15.41 to 17.78 with CLOOPD-Fixed2 and 19.36 with CLOOPD-Fixed3.
Self-OPD is introduced, a teacher-free OPD framework for flow matching models that turns the student's own self-exploration into step-wise supervision and outperforms prior RL and OPD methods without task-specific teachers.
Shi-Yi Zhang, Mu-Shui Liu, Yunze Tong et al.· 1 citation
The results support a compact, Fisher-conditioned privileged subspace for short-budget OPSD, with strict gains in 11 of the 12 model-checkpoint combinations and an exact tie at 4B step 25.
Yun-Meng Chen, Kun Wang, Pei-Han Li et al.· 1 citation
Direct On-Policy Distillation (Direct-OPD) transfers reinforcement-learning-induced policy improvements from a small model to a larger student by using the token-level log-ratio between post-RL and pre-RL checkpoints as dense supervision on the student's own rollouts. This transfer rewards the policy shift at every sta...
Yibo Zhao, Zi-Xuan Yang, Yun-Shi Lan et al.· 0 citations
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.