LaMoC: Loss-Aware Modular Compression for LLMs

arXiv:2608.30226 · cs.AI, cs.CL, cs.PF · Submitted 2026-08-31 · Read on arXiv

cs.AI, cs.CL, cs.PF

Submitted: 2026-08-31

Updated: 2026-08-31

Code: https://github.com/tatsu-lab/stanford_alpaca

Terminology

• Calibration — 32× in this paper · explained in 7 episodes
• Pruning — 31× in this paper · explained in 4 episodes
• Accuracy — 22× in this paper · explained in 1 episode
• Trace — 14× in this paper · explained in 2 episodes
• Perplexity — 13× in this paper · explained in 3 episodes
• Ablation — 10× in this paper · explained in 1 episode
• Alignment — 8× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Empirical Fisher — 6× in this paper
• Decode — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Reconstruction Error — 3× in this paper · explained in 2 episodes
• Adaptive Strategy — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Modularity — 2× in this paper · explained in 9 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Activation Sparsity — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• EXAONE 4.5 Technical Report
• The Llama 3 Herd of Models
• LatentLLM: Attention-Aware Joint Tensor Compression
• AdaSVD: Adaptive Singular Value Decomposition for Large Language Models
• Pointer Sentinel Mixture Models
• Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs
• A3 : an Analytical Low-Rank Approximation Framework for Attention
• Qwen3 Technical Report
• ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection