Papers Read on AI

Education Podcasts

Keeping you up to date with the latest trends and best performing architectures in this fast evolving field in computer science. Selecting papers by comparative results, citations and influence we educate you on the latest research. Consider...

Episodes

ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases

Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities

Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

LightRAG: Simple and Fast Retrieval-Augmented Generation

Aria: An Open Multimodal Native Mixture-of-Experts Model

AgentKit: Structured LLM Reasoning with Dynamic Graphs

PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling

Diffusion Models are Evolutionary Algorithms

Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Internal Consistency and Self-Feedback in Large Language Models: A Survey

On the Diagram of Thought

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation

On the limits of agency in agent-based models

Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery

PuLID: Pure and Lightning ID Customization via Contrastive Alignment