arXiv:2608. 03796v1 Announce Type: cross Abstract: Small language models are often the only option for deployment under tight latency, cost, and on-premises constraints, but they are rarely trained from scratch: a compressed model is usually recovered through knowledge distillation (KD).
arXiv:2603. 01875v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones.
arXiv:2608.20953v1 Announce Type: cross Abstract: Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and...
arXiv:2606. 20005v1 Announce Type: cross Abstract: Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, model compression, continual learning, and sparse-attention LLM training.
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:2609.37899v1 Announce Type: new Abstract: Zero-order optimization (ZO) trains without backpropagation, making it relevant to forward-only hardware and non-differentiable loss, but its gradient...
arXiv:2606. 05988v1 Announce Type: new Abstract: Reasoning models produce long chain-of-thought traces that are costly to distill and encourage verbose student outputs.
KuaFu is a unified behavior‑compression layer that reduces each user behavior item to 2–4 tokens, dramatically shrinking per‑item cache size while preserving fidelity through a four‑stage training process. In production across four profiling tasks, it matches or outperforms uncompressed single‑task models, boosts GPU throughput by 37–350%, and saves 190 GPUs. On public benchmarks it consistently beats prior compressors at the same compression ratio, and on RecBench a 4B KuaFu model outperforms its 8B counterpart by 1.90 points, contributing to a 1.37% lift in overall GMV on Tencent’s advertising and recommendation platform.
arXiv:2607. 13124v1 Announce Type: cross Abstract: Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse on the free-form generation that deployment actually requires.
arXiv:2605. 07482v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous knowledge, without costly full retraining.
arXiv:2512. 21002v3 Announce Type: replace-cross Abstract: Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data.
The paper investigates whether small models distilled from larger ones behave similarly when using byte versus token tokenization. It introduces two methods—Marginalize‑It (approximate) and End‑Of‑Token (exact)—to convert token logits to byte logits, and conducts a large‑scale study on decoder‑only dense transformers ranging from 1 billion to 1 trillion bytes of data. Results show that while token‑based models excel early, byte‑based models eventually surpass them with more compute, achieving higher performance ceilings, greater data efficiency, and lower logit storage costs.
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.