Salvatore Raieli

Too Many Thoughts for Nothing: Can Large Reasoning Models Really Reason?

Only the Beginning Matters: How the LLM Decides Where to Focus Attention

Knowing Isn’t Doing: Teach Reasoning, Not Facts, to Your LLM give a subtitle

Apes Strong Together, AI Agents Not: Why Multi-Agent Systems Fail

To Know or To Do? Your LLM Can’t Have It All (Yet)

The Socratic AI: Knows Others, But Not Itself

This Is the End of Normalization, and the Transformer Feels Fine

Adapat to Survive: LLMs Meet Evolution

On the Other Side of the Mirror: How Language Models Align with the Human Brain

Is Wikipedia an Endangered Species? Is ChatGPT Its Predator?

A Malicious Seed: Fine-Tuning LLMs to Grow Bad Behaviors

How Much Data Does ChatGPT Need to Reason? Less Than You Think

The LLMs’ Dilemma: Thinking Too Much OR Too Little?

Follow the Ants, They Know the Path: Enhancing LLM Reasoning with ACO-ToT

Do You Know Yourself, ChatGPT? Can You Explain Your Behavior?

What if Hallucination Is a Spark of Creativity? Harnessing LLM Flaws for Drug Discovery

Can I Really Trust You, ChatGPT? Bridging AI Confidence and Human Understanding

Beyond Text: Navigating Toward a Multimodal RAG Horizon

The Dream Machine: Decoding Why LLMs Hallucinate Reality

You Cache Only Once: Cache-Augmented Generation (CAG) Instead Of RAG

Do Not Flip a Coin: When to Use RAG or Long Context LLMs

Learning is a simple task, complex plans are doomed to fail

How Far Is AI from Human Intelligence?

What Is The Best Therapy For a Hallucinating AI Patient?

LLMs and the Student Dilemma: Learning to Solve or Learning to Remember?

You Know Nothing, John LLM: Why Do You Answer Anyway?

The Cultural Lens of AI: Which Party Would Your LLM Vote?

Be Yourself: Does Assigning Roles Hurt AI Performance?

Charting the Linguistic Seas: Navigating the Uncharted Waters of Human Language with an LLM

Taming the Attention Hydra: Is Too Much Attention Slowing Down Transformers

Believe In Yourself: Do LLMs Internally Know What Is True?

Neighbors Count: Boosting Document Embeddings with Contextual Encoding

Kolmogorov-Arnold Transformer (KAT): Is the MLP Headed for Retirement?

To CoT or Not to CoT: Do LLMs Really Need Chain-of-Thought?

OpenAI’s New ‘Reasoning’ AI Models Arrived: Will They Survive the Hype?

A Brave New World for Scientific Discovery: Are AI Research Ideas Better?

DeepMind’s AlphaProteo: Revolutionizing Protein Design with Machine Learning

Sometimes Noise is Music: How Beneficial Noise Can Improve Your RAG

AI Emergent Properties: What Makes AI Suddenly Learn New Tricks

The Convergence of Graph and Vector RAGs: A New Era in Information Retrieval

From Syntax to Semantics: How Code Turns LLMs into Better Models

Can AI Replace Human Researchers

Safekeep Science’s Future: Can LLMs Transform Peer Review?

DeepMind’s AlphaProof: Achieving Podium Glory at the Math OlympiadModel

Beyond Human Feedback: How to Teach a Genial AI Student

Expanding Language, Expanding Thought: Vocabulary Size in LLM Scaling

Past Imperfect: Jailbreaking LLMs with Past Tense Requests

Navigating the Seas of Reason: A Geometric Odyssey to Enhance LLM Reasoning Capabilities

Chat Quijote and the Windmills: Navigating AI Hallucinations on the Path to Accuracy

GraphRAG: Combining Retrieval and Summarization

How Achieving Performance and Efficiency in RAG

PlanRAG: Plan Your Way to Better Decisions

The Goldfish LLM: Swimming Through Data Without Memorizing It

An LLM Student’s Handbook: Mastering the Art of Learning and Retaining Knowledge

Maybe GPT Isn’t the Best: BERTs Can Master Generative In-Context Learning

The imitation game: Taming the gap between open source and proprietary models

META’S ImageBind: The Embedding Glue for Your Modalities

scGPT: When Transformers Meet Biology and Fall in Love

AudioGPT: bridging text to music

META DINO: how self-supervised learning is changing computer vision