arXiv Machine Learning
Jun 5
OPRD: On-Policy Representation Distillation
arXiv:2606. 06021v1 Announce Type: new Abstract: On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities.
Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation
arXiv:2606. 02237v1 Announce Type: new Abstract: Distribution Matching Distillation (DMD) compresses pretrained diffusion models into efficient few-step generators by aligning their noised distributions across all scales.
Related stories
arXiv Machine Learning
Jun 30
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
arXiv:2606. 29287v1 Announce Type: new Abstract: Diffusion and continuous-flow generative models achieve high-quality generation, and their deterministic sampling can be formulated as solving learned ODE dynamics.
arXiv Machine Learning
Jun 11
Beyond Dark Knowledge: Mixup-Based Distillation for Reliable Predictions
arXiv:2606. 12171v1 Announce Type: cross Abstract: Knowledge Distillation (KD) and mixup have proven effective at inducing smoothness in class boundaries; KD captures inherent class relationships in probability distributions, and mixup enforces them through convex combinations of inputs.
arXiv Machine Learning
Jul 8
SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines
arXiv:2601. 01484v2 Announce Type: replace Abstract: Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs.
Hugging Face Trending Papers
Aug 4
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this holds, as when the strongest teacher available and the student one wishes to deploy come from different model families, and find that the standard recipes have no answer: teacher latents cannot serve as targets in a foreign coordinate system, per-pixel losses against a teacher that stochastically re-draws local detail degenerate into blur or divergence, and timestep indices lose their meaning across mismatched schedules.
arXiv Machine Learning
Aug 5
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
arXiv:2608. 03316v1 Announce Type: new Abstract: On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid.
arXiv Machine Learning
Jul 20
SODA: Semi On-Policy Black-Box Distillation for Large Language Models
arXiv:2604. 03873v4 Announce Type: replace Abstract: Black-box knowledge distillation for large language models presents a strict trade-off.
arXiv AI
Jun 2
What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression
arXiv:2606. 01292v1 Announce Type: cross Abstract: Teacher-Student Knowledge Transfer (KT) is ubiquitous in modern machine learning, ranging from classical model compression via Knowledge Distillation (KD) to the emergent phenomenon of Weak-to-Strong (W2S) generalization.
arXiv AI
Jun 30
DOPD: Dual On-policy Distillation
arXiv:2606. 30626v1 Announce Type: new Abstract: On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals.
arXiv AI
Jul 3
DemoPSD: Disagreement-Modulated Policy Self-Distillation
arXiv:2607. 02502v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access.
arXiv AI
Jun 24
ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation
arXiv:2606. 23898v1 Announce Type: cross Abstract: Distilling conditional diffusion models aims to transfer the behavior of a large teacher to a smaller student while preserving alignment across conditioning inputs.
arXiv AI
Jun 24
On the Position Bias of On-Policy Distillation
arXiv:2606. 22600v2 Announce Type: replace-cross Abstract: On-Policy Distillation (OPD) improves the learning efficiency of standard reinforcement learning through dense, token-level supervision from teachers.