Context-to-LoRA methods encode documents as low-rank parameter updates, allowing language models to answer without retaining the source text in their decoding context. How reliably do these updates preserve facts and support their use under different instructions? Controlled diagnosis of existing context-to-LoRA method...
Yi Fang, Gaurav Srivastava, Zhenyu Bi et al.· 0 citations
Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for post-training vision-language models (VLMs), but it typically assumes a static training environment. As the actor improves, fixed tasks drift out of its learning frontier: many become trivial, others remain unsolvable; and the learni...
Meng Lu, Li-Geng Zhu, Olivia C. Xiao et al.· 1 citation
The Elastic Selective Spectral Hybrid is introduced, which realizes each Hankel spectral channel as an independent recurrent unit using fitted damped rotation modes and achieves language-modeling quality comparable to similarly sized independently trained models, while smaller exports exhibit a smooth quality-cost trad...
Da-Chuan Song, Chu-Chu Chen, Xuan Wang· 0 citations
Elastic Spectral State Space Models is proposed, a train-once, export-many sequence modeling framework that gains elasticity through spectral approximation of the SSM sequence operator that can be truncated to competitive compact models compared with modern Transformer and SSM baselines at similar parameter scales.
Da-Chuan Song, Ju Yin, Ze-Chen Hu et al.· 1 citation
A model-side aggregation interface is introduced that maintains compact Hash-based HyperLogLog sketch states alongside a frozen language model that improves over direct full-context reasoning over chain-of-thought reasoning.
Da-Chuan Song, Ju Yin, Ze-Chen Hu et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
