IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/fla-org/flash-linear-attention
Project page: https://xpeng-robotics.github.io/iron-fm
Sources
- DeepSeek-V3 Technical Report
- Qwen3 Technical Report
- GLM-5: from Vibe Coding to Agentic Engineering
- Kimi K3: Open Frontier Intelligence
- MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
- Olmo Hybrid: From Theory to Practice and Back
- MiMo-V2-Flash Technical Report
- PACT: Parameterized Clipping Activation for Quantized Neural Networks
- Olmo 3
- MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
- MiniCPM4: Ultra-Efficient LLMs on End Devices
- Attention Is All You Need
- Kimi Linear: An Expressive, Efficient Attention Architecture
- GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
- RoFormer: Enhanced Transformer with Rotary Position Embedding
- Searching for Activation Functions
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
- Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
- Decoupled Weight Decay Regularization
- Fewer Truncations Improve Language Modeling
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
- Agents' Last Exam
- 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