# Sep 21, 2024

## Training Language Models to Self-Correct via Reinforcement Learning
- **SCoRe** is a novel **multi-turn online reinforcement learning** approach that enhances the self-correction capabilities of large language models (LLMs) using only self-generated data, overcoming limitations of previous methods that relied on multiple models or external supervision.

## Forget ChatGPT: why researchers now run small AIs on their laptops
- **Researchers are increasingly opting to run small AI models locally on their laptops** due to the availability of open-weight models and scaled-down versions that maintain competitive performance, allowing for greater control and customization in their work.

## Contextual Retrieval
- **Contextual Retrieval** enhances **Retrieval-Augmented Generation (RAG)** by integrating **Contextual Embeddings** and **Contextual BM25**, achieving a **49% reduction** in retrieval failures and a **67% improvement** when combined with reranking techniques.

## Show HN: Put this touch sensor on a robot and learn super precise tasks
- **AnySkin** revolutionizes tactile sensing by offering a **plug-and-play** solution that enhances versatility and data reusability, addressing limitations seen in existing technologies like **DIGIT** and **ReSkin**.

## CuPy: NumPy and SciPy for GPU
- **CuPy** is a **NumPy/SciPy-compatible** library that enables **GPU-accelerated computing** in Python, allowing users to run existing code on **NVIDIA CUDA** or **AMD ROCm** platforms seamlessly.

## MemoRAG – Enhance RAG with memory-based knowledge discovery for long contexts
- **MemoRAG** enhances retrieval-augmented generation (RAG) by utilizing a **memory-based data interface**, allowing it to manage **up to 1 million tokens** in a single context, thus improving evidence retrieval and response accuracy.

## Scaling up linear programming with PDLP
- **PDLP** is a new **first-order method** solver for large-scale linear programming that enhances efficiency by utilizing **matrix-vector multiplication**, making it more compatible with modern computational technologies like **GPUs** and distributed systems.

## 3D Reconstruction with Spatial Memory
- **Spann3R** introduces a **transformer-based architecture** for dense 3D reconstruction, enabling direct regression of pointmaps from images without prior scene knowledge, enhancing efficiency over its predecessor, DUSt3R.

## Robust Text Classification: Analyzing Prototype-Based Networks
- **Prototype-Based Networks (PBNs)** enhance text classification by improving **robustness** against noise, outperforming traditional Language Models (LMs) in both targeted and static adversarial settings, as shown in recent studies.

## GRIN: GRadient-INformed MoE
- **GRIN** introduces a novel approach to **estimate gradients** for **Mixture-of-Expert (MoE)** training, enhancing the routing of outputs through discrete variables.

## Medical Centers Tap AI, Federated Learning for Better Cancer Detection
- **NVIDIA-powered federated learning** is being utilized by a coalition of U.S. medical centers to enhance **AI-assisted tumor segmentation**, allowing for improved cancer detection without compromising data privacy.

## ‘We’ve Fused Signal Processing and AI’: NVIDIA CEO Outlines Future of Telecom at T-Mobile’s Capital Markets Day
- **NVIDIA's AI Aerial platform** integrates **AI and radio access networks** (AI-RAN) to enhance telecommunications, promising improved network performance and new revenue streams through AI-computing-as-a-service.