#post-training-optimization News & Analysis

5 articles tagged with #post-training-optimization. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

5 articles

AIBullisharXiv – CS AI · Jun 87/10

🧠

ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models

ActQuant introduces a novel post-training quantization framework that compresses Vision-Language-Action models to sub-4-bit weights while maintaining 94-95% performance, enabling practical deployment on edge devices. The method combines action-guided bit allocation with curvature-aware optimization, achieving 5.3× compression on major VLA models and validated performance on physical robotic hardware.

AIBullisharXiv – CS AI · May 277/10

🧠

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders

Researchers introduce SAERL, a data engineering framework that uses Sparse Autoencoders to extract intrinsic signals from LLM internals for improved reinforcement learning post-training. The method achieves 3% accuracy gains and 20% faster convergence on math reasoning tasks by modeling data diversity, difficulty, and quality—demonstrating that model internals provide practical signals beyond external training data metrics.

AIBullisharXiv – CS AI · Jun 256/10

🧠

EPTS: Elastic Post-Training Sparsity for Efficient Large Language Model Compression

Researchers introduce EPTS, a new framework for compressing large language models that enables a single optimized model to perform efficiently across multiple sparsity levels, eliminating the need for separate optimization for each deployment scenario. This approach combines Multi-Sparsity Hierarchy LoRA and a Feature Mixer mechanism to maintain performance while reducing computational requirements.

AIBullisharXiv – CS AI · Jun 96/10

🧠

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger

Researchers propose WMSS, a post-training optimization method that leverages weak model checkpoints to improve strong language models beyond conventional saturation points. The approach identifies and addresses learning gaps through entropy dynamics, achieving performance gains in mathematical reasoning and code generation without additional inference costs.

AIBullisharXiv – CS AI · Jun 46/10

🧠

MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models

Researchers introduce MorphoQuant, a post-training quantization framework designed to compress omni-modal large language models to 4-bit precision while preserving cross-modal performance. The method addresses distribution heterogeneity across different data modalities through bias compensation and quantization grid optimization, achieving results that rival higher-precision baselines.