Image de couverture de livre

FineScope : SAE-guided Data Selection Enables Domain Specific LLM Pruning and Finetuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bhattacharyya, Chaitali, Lee, Hyunsei, Lee, Junyoung, Jang, Shinhyoung, Suh, Il hong, Kim, Yeseong
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs
par: An, Selim, et autres
Publié: (2026)

A Diffusion-Based Framework for Configurable and Realistic Multi-Storage Trace Generation
par: Kim, Seohyun, et autres
Publié: (2025)

RDMM: Fine-Tuned LLM Models for On-Device Robotic Decision Making with Enhanced Contextual Awareness in Specific Domains
par: Nasrat, Shady, et autres
Publié: (2025)

7‐2: Distinguished Paper: Effective 10‐bit OLED Driver IC with 11‐bit DAC, Double Capacitor‐Coupled Adder, and Offset Calibration for Enhanced Panel Driving
par: Changwhan Kim, et autres
Publié: (2025)

TSDS: Data Selection for Task-Specific Model Finetuning
par: Liu, Zifan, et autres
Publié: (2024)

Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics
par: Kim, Jungwoo, et autres
Publié: (2025)

Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning
par: Zhang, Ling, et autres
Publié: (2025)

Improving Domain-Specific ASR with LLM-Generated Contextual Descriptions
par: Suh, Jiwon, et autres
Publié: (2024)

Non-convex relaxation and 1/2-approximation algorithm for the chance-constrained binary knapsack problem
par: Kim, Junyoung, et autres
Publié: (2024)

Multi-Domain Recommendation to Attract Users via Domain Preference Modeling
par: Ju, Hyunjun, et autres
Publié: (2024)

Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning
par: Krishna, Shambhavi, et autres
Publié: (2025)

LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
par: Lee, Suhyeon, et autres
Publié: (2023)

Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gaps
par: Jang, Jiyun, et autres
Publié: (2024)

Dual-Use Commercial and Military Communications on a Single Platform using RAN Domain Specific Language
par: Gatherer, Alan, et autres
Publié: (2024)

Dynamic Anchor Selection and Real-Time Pose Prediction for Ultra-wideband Tagless Gate
par: Choi, Junyoung, et autres
Publié: (2024)

QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill
par: Jones, Dalton, et autres
Publié: (2026)

Hypotaxy‐Enabled Selective Growth of MoS 2 for Laterally‐Connected Edge and van der Waals Bottom Contacts (Adv. Funct. Mater. 41/2026)
par: Donghoon Moon, et autres
Publié: (2026)

Diffusion Deepfake
par: Bhattacharyya, Chaitali, et autres
Publié: (2024)

On Evaluation of Unsupervised Feature Selection for Pattern Classification
par: Kim, Gyu-Il, et autres
Publié: (2026)

Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
par: Jang, Chaeyun, et autres
Publié: (2024)

SLM Finetuning for Natural Language to Domain Specific Code Generation in Production
par: Nair, Renjini R., et autres
Publié: (2026)

LCSB: Layer-Cyclic Selective Backpropagation for Memory-Efficient On-Device LLM Fine-Tuning
par: Park, Juneyoung, et autres
Publié: (2026)

Polymorphic Metaprogramming with Memory Management -- An Adjoint Analysis of Metaprogramming
par: Jang, Junyoung, et autres
Publié: (2024)

Decoding-Free Sampling Strategies for LLM Marginalization
par: Pohl, David, et autres
Publié: (2025)

ASAP: Attention Sink Anchored Pruning
par: Lee, Jaehyuk, et autres
Publié: (2026)

Customized Interior-Point Methods Solver for Embedded Real-Time Convex Optimization
par: Jang, Jae-Il, et autres
Publié: (2025)

A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention
par: Lee, Heejun, et autres
Publié: (2024)

Jack Unit: An Area- and Energy-Efficient Multiply-Accumulate (MAC) Unit Supporting Diverse Data Formats
par: Noh, Seock-Hwan, et autres
Publié: (2025)

More Human, More Efficient: Aligning Annotations with Quantized SLMs
par: Wang, Jiayu, et autres
Publié: (2026)

Optimizing Resource Distribution in a One-Dimensional Logistic Diffusion Model
par: Heo, Junyoung, et autres
Publié: (2025)

Expanding the Attack Scenarios of SAE J1939: A Comprehensive Analysis of Established and Novel Vulnerabilities in Transport Protocol
par: Lee, Hwejae, et autres
Publié: (2024)

MARS: Matching Attribute-aware Representations for Text-based Sequential Recommendation
par: Kim, Hyunsoo, et autres
Publié: (2024)

Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
par: Yoon, Ilhoon, et autres
Publié: (2024)

Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation
par: Lee, Zhan Peng, et autres
Publié: (2025)

Locality-Aware Redundancy Pruning for LLM Depth Compression
par: Yun, Vincent-Daniel, et autres
Publié: (2026)

When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method
par: Zhang, Biao, et autres
Publié: (2024)

FlexNeRFer: A Multi-Dataflow, Adaptive Sparsity-Aware Accelerator for On-Device NeRF Rendering
par: Noh, Seock-Hwan, et autres
Publié: (2025)

Dexterous World Models
par: Kim, Byungjun, et autres
Publié: (2025)

Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures
par: Park, Junyoung, et autres
Publié: (2026)

DSG-KD: Knowledge Distillation from Domain-Specific to General Language Models
par: Cho, Sangyeon, et autres
Publié: (2024)