Fine-tuning and adaptation

LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.

3,511 stories · RSS feed

Hugging Face Trending Papers
Jul 14

Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs

Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when their internal belief is unchanged. We cast this as a failure of internal incentive-compatibility (IC) and present a method for learning and certifying counterfactual report mediators that hold a model's reports to a causal contract: invariant to forbidden influences (pressure, prestige, restyling) and responsive to licensed ones (genuine evidence).

arXiv Machine Learning
Jul 14

Memory Savings at What Cost? A Study of Alternatives to Backpropagation

arXiv:2506. 21833v2 Announce Type: replace Abstract: Forward-mode automatic differentiation (FmAD) and zero-order (ZO) optimization are increasingly proposed as memory-efficient, backpropagation-free alternatives for large language model (LLM) fine-tuning, yet their benefits are typically evaluated only against standard backpropagation (BP), omitting memory-efficient variants such as activation checkpointing.

By Kunjal Panchal, Sunav Choudhary, Yuriy Brun, Hui Guan
arXiv AI
Jul 14

Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial Confinement Fusion

arXiv:2607. 10366v1 Announce Type: new Abstract: Offline-trained surrogates for Inertial Confinement Fusion (ICF) suffer a well-known failure mode that iterative optimizers drive inputs into out-of-distribution (OOD) regions where predictions become unreliable.

By Jiatong Zhao, Tengyue Zhang, Yuhan Wang, Fuyuan Wu, Junchi Yan
arXiv AI
Jul 14

Stable On-Policy Distillation through Adaptive Target Reformulation

arXiv:2601. 07155v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often suffers from a distribution mismatch between training and inference.

By Ijun Jang, Jewon Yeom, Juan Yeo, Hyunggyu Lim, Taesup Kim
arXiv AI
Jul 14

PhysMRV: Physical Memory Retrieval and Verification for Physics Plausibility Reasoning

arXiv:2607. 10190v1 Announce Type: cross Abstract: Video-language models (VLMs) have achieved remarkable performance on video understanding and visual question answering, yet they remain unreliable in reasoning about physical plausibility, where understanding object interactions, causal dynamics, and fundamental physical principles is essential.

By Wenyuan Wang, Lianyu Hu, Hao Wang, Yang Liu