Imagen de Portada

Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Siam, M. K. Khalidi, Tausif-Ul-Islam, Md., Khan, Md. Reshad Romim, Hossain, Mohammed Ali, Amin, Mushfiqul, Khan, Labib Hasan, Farhan, Niloy, Sadeque, Farig
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Gazetteer-Enhanced Bangla Named Entity Recognition with BanglaBERT Semantic Embeddings K-Means-Infused CRF Model
por: Farhan, Niloy, et al.
Publicado: (2024)

Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures
por: Mahi, Ishrak Hamim, et al.
Publicado: (2026)

Transforming Mentorship: An AI Powered Chatbot Approach to University Guidance
por: Rahman, Mashrur, et al.
Publicado: (2025)

How Effectively Can BERT Models Interpret Context and Detect Bengali Communal Violent Text?
por: Khondoker, Abdullah, et al.
Publicado: (2025)

Black-Box Optimization of Mixed Binary-Continuous Variables: Challenges and Opportunities in Evolutionary Model Merging
por: Niloy, Md. Robiul Islam
Publicado: (2026)

AI as Teammate or Tool? A Review of Human-AI Interaction in Decision Support
por: Samu, Most. Sharmin Sultana, et al.
Publicado: (2026)

Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacy
por: Opi, Md Mehrab Hossain, et al.
Publicado: (2025)

A Survey on Agentic Security: Applications, Threats and Defenses
por: Shahriar, Asif, et al.
Publicado: (2025)

From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge
por: Chowdhury, Nafis, et al.
Publicado: (2025)

Frequency-Specific Neural Response and Cross-Correlation Analysis of Envelope Following Responses to Native Speech and Music Using Multichannel EEG Signals: A Case Study
por: Hasan, Md. Mahbub, et al.
Publicado: (2025)

TSDS: Data Selection for Task-Specific Model Finetuning
por: Liu, Zifan, et al.
Publicado: (2024)

BNLI: A Linguistically-Refined Bengali Dataset for Natural Language Inference
por: Haque, Farah Binta, et al.
Publicado: (2025)

Design and Modeling of CdGa2Te4 and ZnGa2Te4 Chalcogenide Compound-Based Photovoltaic Devices: A DFT Study along with SCAPS-1D Simulation
por: Rifat, Md Hasan Shahriar, et al.
Publicado: (2025)

LLM-Based Evaluation of Low-Resource Machine Translation: A Reference-less Dialect Guided Approach with a Refined Sylheti-English Benchmark
por: Rahman, Md. Atiqur, et al.
Publicado: (2025)

Assessing Generalisation Capability of Machine Learning Models for Intrusion Detection
por: Hossain, Md Zakir, et al.
Publicado: (2026)

SWE-Shepherd: Advancing PRMs for Reinforcing Code Agents
por: Dihan, Mahir Labib, et al.
Publicado: (2026)

Involution Fused ConvNet for Classifying Eye-Tracking Patterns of Children with Autism Spectrum Disorder
por: Islam, Md. Farhadul, et al.
Publicado: (2024)

BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment
por: Sajid, Md. Ashiq Ul Islam, et al.
Publicado: (2026)

A Two-Stage Multitask Vision-Language Framework for Explainable Crop Disease Visual Question Answering
por: Hossain, Md. Zahid, et al.
Publicado: (2026)

Benchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIF
por: Sami, K. M. Jubair, et al.
Publicado: (2026)

A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs
por: Sami, K. M. Jubair, et al.
Publicado: (2025)

APP: Accelerated Path Patching with Task-Specific Pruning
por: Andersen, Frauke, et al.
Publicado: (2025)

Leveraging Pre-trained CNNs for Efficient Feature Extraction in Rice Leaf Disease Classification
por: Sobuj, Md. Shohanur Islam, et al.
Publicado: (2024)

Reliability Gated Multi-Teacher Distillation for Low Resource Abstractive Summarization
por: Sumit, Dipto, et al.
Publicado: (2026)

Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models
por: Siddique, Md. Abu Bakor, et al.
Publicado: (2026)

Fusion-Augmented Large Language Models: Boosting Diagnostic Trustworthiness via Model Consensus
por: Siam, Md Kamrul, et al.
Publicado: (2025)

Med-IC: Fusing a Single Layer Involution with Convolutions for Enhanced Medical Image Classification and Segmentation
por: Islam, Md. Farhadul, et al.
Publicado: (2024)

Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?
por: Dipto, Tawsif Tashwar, et al.
Publicado: (2025)

A Linear Time Quantum Algorithm for Pairwise Sequence Alignment
por: Khan, Md. Rabiul Islam, et al.
Publicado: (2023)

Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning
por: Sarkar, Soumajyoti, et al.
Publicado: (2024)

Deconvolving Complex Neuronal Networks into Interpretable Task-Specific Connectomes
por: Wang, Yifan, et al.
Publicado: (2024)

destroR: Attacking Transfer Models with Obfuscous Examples to Discard Perplexity
por: Ahmed, Saadat Rafid, et al.
Publicado: (2025)

Towards AI Evaluation in Domain-Specific RAG Systems: The AgriHubi Case Study
por: Hasan, Md. Toufique, et al.
Publicado: (2026)

Bridging Human and Model Perspectives: A Comparative Analysis of Political Bias Detection in News Media Using Large Language Models
por: Banik, Shreya Adrita, et al.
Publicado: (2025)

Variational Gaussian Mixture Manifold Models for Client-Specific Federated Personalization
por: Puppala, Sai, et al.
Publicado: (2025)

DSTAN-Med: Dual-Channel Spatiotemporal Attention with Physiological Plausibility Filtering for False Data Injection Attack Detection in IoT-Based Medical Devices
por: Hasan, Md Mehedi, et al.
Publicado: (2026)

Development and Characterization of Mikania, Kapok, Wool, Sugarcane, and Pineapple Fiber Reinforced Polyester Composite
por: Rafid Anan, et al.
Publicado: (2024)

Enhanced Stability and Performance of Islanded DC Microgrid Systems Using Optimized Fractional Order Controller and Advanced Energy Management
por: Md. Wahidujjaman, et al.
Publicado: (2025)

NCO4CVRP: Neural Combinatorial Optimization for the Capacitated Vehicle Routing Problem
por: Dihan, Mahir Labib, et al.
Publicado: (2026)

Transient performance improvement of DFIG‐based wind farm by H‐bridge fault current limiter
por: Md. Arafat Hossain, et al.
Publicado: (2024)