The paper investigates how synthetic tasks influence language‑model pretraining by distinguishing diagnostic, teachable, and transferable signals. In a controlled setting where 70% of the data is general Python and 30% is a mixture of curated synthetic tasks, literature‑derived probes, and OpenCodeInstruct, 14 of 27 tasks show teachability, with curated tasks outperforming literature probes. Curated synthetic data provides conditional value: it boosts downstream performance when mixed with OpenCodeInstruct but is less effective when used alone, and a loss‑based scheduler can misalign short‑term loss reduction with long‑term transfer.
By Ohad Rubin
arXiv:2610.00873v1 Announce Type: cross
Abstract: In many industrial applications, 1) tabular data is scarce and imbalanced and thus requires synthetic expansion; 2) input distributions drift between...
By Hongyu Cao, Xinyuan Wang, Arun Vignesh Malarkkan, Kunpeng Liu, Haifeng Chen, Yanjie Fu
arXiv:2608.21386v1 Announce Type: cross
Abstract: Given a task described by a few examples, how should a model be specialized to it? Four mechanisms are available -- zero-shot, in-context attention,...
By John C. Howell
arXiv:2609. 22041v1 Announce Type: new Abstract: Reinforcement learning is increasingly used to align image generators with reward signals, and Flow-GRPO recently extended this paradigm to flow-matching models by treating the denoising sampler as a stochastic policy that can be optimized from reward feedback.
By Yufeng Wang, Parivesh Priye, Meeshawn Marathe, Ramit Pahwa
arXiv:2607. 03103v1 Announce Type: cross Abstract: Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding knowledge sharing across anatomically related tasks.
By Jiahao Liu, Hang Wei, Shuai Wu
The paper introduces a transformer-based framework that learns an in‑context score operator for diffusion models, allowing the model to perform reverse‑diffusion sampling on unseen target distributions specified by a small empirical context set. By representing the task‑dependent score as a Gaussian‑kernel conditional mean and approximating it with a transformer‑based query‑dependent attention architecture, the method can adapt to new tasks without retraining or parameter updates. The authors provide theoretical generalization‑error bounds and evaluate the approach on scientific and visual datasets, noting strong performance on simple task families and limitations as task complexity grows.
By Wuzhe Xu, Zhaiming Shen, Yulong Lu, Wenjing Liao, Rongjie Lai
arXiv:2606. 06712v1 Announce Type: cross Abstract: We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs).
By Xingyu Su, Jacob Helwig, Shubham Parashar, Atharv Chagi, Lakshmi Jotsna, Degui Zhi, James Caverlee, Dileep Kalathil, Shuiwang Ji
arXiv:2610.15339v1 Announce Type: new
Abstract: Current fMRI encoding models frame prediction as deterministic regression, yet identical stimuli evoke a distribution of neural responses (arising from...
By Bui Van Hung, Hoang-Son Vo, Mai Duc Minh Huy, Dang Thanh Vu, Soo-Hyung Kim
The paper introduces VDOT++, a unified distillation framework for few-step video generation across text-to-video, image-to-video, and condition-based tasks. It extends the previous VDOT method by incorporating an asymmetric unbalanced optimal transport distillation that allows student tokens to carry less mass, and an α1 ground cost that uses a weighted median to preserve modes. The approach combines distribution matching with adversarial refinement and cross-scale distillation, achieving competitive performance on multiple video benchmarks with only four sampling steps.
By Yutong Wang, Xingtong Ge, Enhuai Liu, Yunke Wang, Tianfan Xue, Yu Qiao, Yaohui Wang, Xinyuan Chen, Chang Xu
The paper argues that diffusion-based action policies can use a frozen, observation‑free backbone as a reusable trajectory prior, with task adaptation handled entirely by the conditioning pathway. By pretraining a general action head on forward‑kinematics data and then freezing it, the authors show that a single backbone can match or outperform normally trained models on MimicGen and LIBERO. Their experiments reveal that a small 5 M‑parameter MLP backbone can rival large U‑Net and transformer backbones, indicating that action backbones are often over‑parameterized and that image‑style architectures may not be the best fit for low‑dimensional action generation.
By Jian Zhou, Sihao Lin, Shuai Fu, Zerui Li, Gengze Zhou, Qi WU
arXiv:2610.15407v1 Announce Type: new
Abstract: An end-to-end success rate alone cannot distinguish failure to learn an action from failure to apply it as task state changes. We study this distinctio...
By Dong Nie, Rui Lan, Yixin Nie, Lingzi Hong
The paper compares two low‑budget methods for converting a 30B Mixture‑of‑Experts autoregressive language model into a diffusion language model. One method updates a subset of the model’s weights in‑place, while the other freezes the context tower and conditions on a frozen causal copy via cross‑attention. With only 1B training tokens, the frozen‑tower approach achieves a HumanEval pass@10 score of 71.60 versus 6.19 for the in‑place method, and retains 95% of the parent’s GSM8K and 99% of its MMLU‑Pro performance.
By Wentao Lu, Jesse Clark, Tianyu Zhu