Fine-tuning ML interatomic potentials via a new LoRA-based Equitrain framework with minimal additional data improves phonon and thermal predictions over base and scratch-trained models in 53 systems.
hub
Lora vs full fine-tuning: An illusion of equivalence
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 16representative citing papers
Image-LoRA selectively adapts only visual tokens and chosen attention heads in VLMs, matching standard LoRA performance with lower parameter count and FLOPs.
Omni-Attribute is a new open-vocabulary image attribute encoder trained on semantically linked pairs with dual objectives to produce disentangled representations for personalization and compositional generation.
DG-Hard uses Donoho-Gavish hard thresholding on the fine-tuning weight delta to separate task-aligned signal from noise-like residual, recovering damaged capabilities while preserving target-task gains.
PRiSE-EEG is a prior-guided EEG foundation model that allocates shared and specialized experts across depth using CKA-derived sigmoid mappings and reports strong cross-paradigm results on 12 benchmarks.
Full finetuning with the pretraining optimizer reduces forgetting compared to other optimizers or LoRA while achieving comparable new-task performance.
Fine-tuned MLLMs achieve competitive skeletal landmark localization on synthetic and real X-ray datasets compared to deep learning baselines and demonstrate reasoning for sequential C-arm navigation.
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
GAIN's multiplicative modulation preserves pretrained weight column spans during sequential domain adaptation, yielding 7-13% better prior-domain perplexity than LoRA across 774M-70B models while matching replay-augmented baselines without storing data.
ALL-FEM fine-tunes LLMs on a corpus of verified FEniCS scripts and uses multi-agent workflows to automate finite element code generation, achieving 71.79% success on 39 benchmarks across elasticity, flow, and coupled problems.
Fine-tuning text-to-video models on sparse low-quality synthetic data for physical camera controls outperforms fine-tuning on photorealistic data.
SEAT preserves epistemic abstention in LLMs during knowledge adaptation via sparse tuning and entity-perturbed KL regularization, yielding 18-101% better abstention on unknown queries while retaining near-perfect knowledge acquisition.
Supervised fine-tuning with 0.1% labeled data outperforms all 60 tested prompt variants for CLIPSeg cloud segmentation on satellite imagery under domain shift.
Training transformers by optimizing only half the DCT coefficients per linear layer achieves validation loss within 0.024 of a dense baseline on Shakespeare character prediction, outperforming matched-parameter LoRA due to preserved rank flexibility.
Fine-tuned small language models trained on a synthetic Windows event log dataset with remediation steps outperform larger models in issue detection and solution generation with lower computational cost.
A 14B model trained on synthetic data from Brazilian clinical guidelines outperforms larger LLMs on new benchmarks for Brazilian healthcare protocols.
citing papers explorer
-
Parameter-Efficient Fine-Tuning of Machine-Learning Interatomic Potentials for Phonon and Thermal Properties
Fine-tuning ML interatomic potentials via a new LoRA-based Equitrain framework with minimal additional data improves phonon and thermal predictions over base and scratch-trained models in 53 systems.
-
Selective LoRA for Visual Tokens and Attention Heads
Image-LoRA selectively adapts only visual tokens and chosen attention heads in VLMs, matching standard LoRA performance with lower parameter count and FLOPs.
-
Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization
Omni-Attribute is a new open-vocabulary image attribute encoder trained on semantically linked pairs with dual objectives to produce disentangled representations for personalization and compositional generation.
-
Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining
DG-Hard uses Donoho-Gavish hard thresholding on the fine-tuning weight delta to separate task-aligned signal from noise-like residual, recovering damaged capabilities while preserving target-task gains.
-
PRiSE-EEG: A Prior-Guided Foundation Model with Depth-Stratified Experts for Cross-Paradigm EEG Representation Learning
PRiSE-EEG is a prior-guided EEG foundation model that allocates shared and specialized experts across depth using CKA-derived sigmoid mappings and reports strong cross-paradigm results on 12 benchmarks.
-
Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less
Full finetuning with the pretraining optimizer reduces forgetting compared to other optimizers or LoRA while achieving comparable new-task performance.
-
Autonomous Skeletal Landmark Localization towards Agentic C-Arm Control
Fine-tuned MLLMs achieve competitive skeletal landmark localization on synthetic and real X-ray datasets compared to deep learning baselines and demonstrate reasoning for sequential C-arm navigation.
-
TLoRA: Task-aware Low Rank Adaptation of Large Language Models
TLoRA jointly optimizes LoRA initialization via task-data SVD and sensitivity-driven rank allocation, delivering stronger results than standard LoRA across NLU, reasoning, math, code, and chat tasks while using fewer trainable parameters.
-
GAIN: Multiplicative Modulation for Domain Adaptation
GAIN's multiplicative modulation preserves pretrained weight column spans during sequential domain adaptation, yielding 7-13% better prior-domain perplexity than LoRA across 774M-70B models while matching replay-augmented baselines without storing data.
-
ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods
ALL-FEM fine-tunes LLMs on a corpus of verified FEniCS scripts and uses multi-agent workflows to automate finite element code generation, achieving 71.79% success on 39 benchmarks across elasticity, flow, and coupled problems.
-
Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation
Fine-tuning text-to-video models on sparse low-quality synthetic data for physical camera controls outperforms fine-tuning on photorealistic data.
-
SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention
SEAT preserves epistemic abstention in LLMs during knowledge adaptation via sparse tuning and entity-perturbed KL regularization, yielding 18-101% better abstention on unknown queries while retaining near-perfect knowledge acquisition.
-
Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift
Supervised fine-tuning with 0.1% labeled data outperforms all 60 tested prompt variants for CLIPSeg cloud segmentation on satellite imagery under domain shift.
-
Training Transformers in Cosine Coefficient Space
Training transformers by optimizing only half the DCT coefficients per linear layer achieves validation loss within 0.024 of a dense baseline on Shakespeare character prediction, outperforming matched-parameter LoRA due to preserved rank flexibility.
-
Fine-Tuning Small Language Models for Solution-Oriented Windows Event Log Analysis
Fine-tuned small language models trained on a synthetic Windows event log dataset with remediation steps outperform larger models in issue detection and solution generation with lower computational cost.
-
Teaching LLMs Brazilian Healthcare: Injecting Knowledge from Official Clinical Guidelines
A 14B model trained on synthetic data from Brazilian clinical guidelines outperforms larger LLMs on new benchmarks for Brazilian healthcare protocols.