9 papers · 1 filter
Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
Huanran Chen, Huaqing Zhang, Xiao Li +3
The foundational capabilities of large language models are acquired during pretraining on internet-scale, highly heterogeneous data mixtures. In this work, we investigate an intere…
Alignment Dynamics in LLM Fine-Tuning
Yuhan Huang, Huanran Chen, Yinpeng Dong
Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under s…
Diffusion Models as Dataset Distillation Priors
Duo Su, Huyu Wu, Huanran Chen +4
Dataset distillation aims to synthesize compact yet informative datasets from large ones. A significant challenge in this field is achieving a trifecta of diversity, generalization…
Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
Chengcan Wu, Zeming Wei, Huanran Chen +2
While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particula…
Mitigating Overthinking in Large Reasoning Models via Manifold Steering
Yao Huang, Huanran Chen, Shouwei Ruan +3
Recent advances in Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex tasks such as mathematics and coding. However, these models frequently…
Unveiling the Basin-Like Loss Landscape in Large Language Models
Huanran Chen, Yinpeng Dong, Zeming Wei +4
We discover the emergence of \textit{basins} in the loss landscape of large language models. As model scale increases, LLMs become progressively more resilient to random perturbati…