Online Label-Free Gradient Matching for Continual Language Model Training. It centres on Benchmarks, and also names Phi. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability.
Written by Bharat Hunt from the headline and the coverage below. The original reporting is the source of truth.
HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation. It centres on Phi, and also names Benchmarks and GitHub. Reported by arXiv. Bharat Hunt files it under AI Agents — the section covering autonomous and tool-using systems, agent frameworks, MCP and orchestration.
Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation. It centres on Benchmarks, and also names Ollama and Phi. Reported by arXiv. Bharat Hunt files it under AI Tools and AI Models — the section covering applications people use — assistants, editors, search, productivity.
VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations. It centres on AI Safety, and also names Mistral AI and Phi. Reported by arXiv. Bharat Hunt files it under AI Regulation and AI Research — the section covering law, policy, courts, standards and government positions on AI.
AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs. It centres on Inference, and also names Phi and Multimodal. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability.