arXiv:2603. 26556v2 Announce Type: replace-cross Abstract: Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs.
arXiv:2607. 19956v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined.
The paper introduces PACT, a tuning method for single-token typed-decision models that leverages contrastive pair data to add four training terms—difference-in-differences margin, permutation-consistency, evidence-necessity, and ordinal transport cost—without requiring new annotations. PACT achieves comparable accuracy to existing recipes while reducing position bias and ordinal error, and it improves robustness and stability across seeds. The authors provide code, data splits, and trained adapters for reproducibility.
Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined. On the BanSum Bangla summarization benchmark, we find that standard KD improves ROUGE-L by only +0.
arXiv:2609.36734v1 Announce Type: new Abstract: Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implic...
arXiv:2609.38342v1 Announce Type: new Abstract: On-policy self-distillation uses a model as its own teacher to provide dense supervision for reasoning, often through reference-solution conditioning....
arXiv:2607. 08268v1 Announce Type: new Abstract: High-volume structured extraction pays a large model's latency on every item, so distilling the task into a small on-device model is attractive: comparable output at a fraction of the time and cost.
The paper introduces Adaptive Local Relational Alignment (ALRA), a logit‑based knowledge distillation method for autoregressive language models that combines student‑generated token proposals with teacher guidance at each prediction position. ALRA dynamically selects the number of candidate tokens based on the teacher’s probability spread, uses Adaptive Local Divergence to match both mass and relative token distributions, and applies Student‑Weighted Pairwise Relational Alignment to focus on high‑probability token pairs. Experiments on The Pile show that 200M‑ and 500M‑parameter students trained with ALRA outperform the best baseline by roughly 1 percentage point and surpass pre‑training without distillation by over 2 percentage points on nine zero‑shot benchmarks.
arXiv:2605. 31191v2 Announce Type: replace Abstract: We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effectiveness in ResNet-based image classification on CIFAR-10.
arXiv:2609.36246v1 Announce Type: new Abstract: We present OLIVE (OnLine InterVEntion). At each iteration, the evolving student policy generates a new prefix, the teacher continues it autoregressivel...
arXiv:2606. 00798v1 Announce Type: cross Abstract: Parameter compression of class-conditional diffusion models reveals an underexplored limitation in output-level distillation: the unconditional score branch remains unsupervised, leaving the classifier-free guidance gap underdetermined in the student.
arXiv:2609.23697v1 Announce Type: cross Abstract: Multi-teacher on-policy distillation allows a student to learn from complementary specialists on its own trajectories. Domain-routed approaches, howe...