Training Specialist LLMs on Your Phone: Forward-Only Optimization via Block-Spectral Coordinates
cs.LG, cs.SY, eess.SY
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- MobileFineTuner: A Mobile-Native Framework for On-Device LLM Fine-Tuning in Real-World Embedded AI Applications
- Adam: A Method for Stochastic Optimization
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values
- ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
- Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost
- MAI-UI Technical Report: Real-World Centric Foundation GUI Agents
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis