venturebeat
Phi-4 proves that a 'data-first' SFT methodology is the new differentiator

AI engineers often chase performance by scaling up LLM parameters and data, but the trend toward smaller, more efficient, and better-focused models has accelerated. The Phi-4 fine-tuning methodology is the cleanest public example of a training approach that smaller enterprise teams can copy. It shows how a carefully chosen dataset and fine-tuning strategy can make a 14B model compete with much larger ones.The Phi-4 model was trained on just 1.4 million carefully chosen prompt-response pairs. Instead of brute force, the Microsoft Phi-4 research team focused on “teachable” examples at the edge of the model’s abilities and rigorous data curation. The Phi-4 reasoning smart data playbook demonstrates how strategic data curation with replicable SFT and RL can elevate a 14B model beyond m [...]

Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

venturebeat
Microsoft built Phi-4-reasoning-vision-15B to know when to think — and when thinking is a waste of time

Microsoft on Tuesday released Phi-4-reasoning-vision-15B, a compact open-weight multimodal AI model that the company says matches or exceeds the performance of systems many times its size — while co [...]

Match Score: 404.58

Destination
Microsoft expands its SLM lineup with new multimodal and mini Phi-4 models

Microsoft has added two new models to its Phi small language model family: Phi-4-multimodal, which can handle audio, images and text simultaneously, and Phi-4-mini, a streamlined model focused on text [...]

Match Score: 94.29

venturebeat
Artificial Analysis overhauls its AI Intelligence Index, replacing popular benchmarks with 'real-world' tests

The arms race to build smarter AI models has a measurement problem: the tests used to rank them are becoming obsolete almost as quickly as the models improve. On Monday, Artificial Analysis, an indepe [...]

Match Score: 72.94

venturebeat
MIT's new fine-tuning method lets LLMs learn new skills without losing old ones

When enterprises fine-tune LLMs for new tasks, they risk breaking everything the models already know. This forces companies to maintain separate models for every skill.Researchers at MIT, the Improbab [...]

Match Score: 69.76

venturebeat
Researchers trained an open source AI search agent, Harness-1, that outperforms GPT-5.4 on recalling relevant information

A joint research collaboration between researchers at the University of Illinois at Urbana-Champaign (UIUC), UC Berkeley, and the open source AI-native vector database platform Chroma unveiled Harness [...]

Match Score: 66.78

Destination
How Phi-4-Reasoning Redefines AI Reasoning by Challenging “Bigger is Better” Myth

Microsoft's recent release of Phi-4-reasoning challenges a key assumption in building artificial intelligence systems capable of reasoning. Since the introduction of chain-of-thought reasoning in [...]

Match Score: 66.13

Destination
Microsoft introduces Phi-4-mini-flash-reasoning with up to 10x higher token throughput

Microsoft has introduced Phi-4-mini-flash-reasoning, a lightweight AI model built for scenarios with tight computing, memory, or latency limits. Designed for edge devices and mobile apps, the model ai [...]

Match Score: 66.00

venturebeat
AI models that simulate internal debate dramatically improve accuracy on complex tasks

A new study by Google suggests that advanced reasoning models achieve high performance by simulating multi-agent-like debates involving diverse perspectives, personality traits, and domain expertise.T [...]

Match Score: 58.21

Destination
Microsoft releases full Phi-4 model with weights under MIT license

Microsoft Research's new Phi-4 LLM matches the abilities of much larger models while using just 14 billion parameters - about one-fifth the size of similar systems.<br /> The article Micros [...]

Match Score: 56.73