Soham Nandi

Computer Science Engineering, specializing in Artificial Intelligence and Machine learning

Soham Nandi is a technical writer based in Memari, India. His academic background is in Computer Science Engineering, specializing in Artificial Intelligence and Machine learning. He has extensive experience in Data Analytics, Machine Learning, and Python. He has worked on group projects that required the implementation of Computer Vision, Image Classification, and App Development.

Soham's passion for AI and Machine Learning propels him toward his goal of becoming a distinguished Machine Learning Engineer and leveraging his knowledge to help the less fortunate. His projects include the Rice grain classifier and Handwriting-based Personality Detector, and he is certified in Data Analytics and Data Science.

Drawing inspiration from writers ranging from Satyajit Ray to Mark Manson, he has his own science fiction stories and blog. He also creates content on personal development and mental health through his Instagram handle. Beyond the screen and code, Soham's world is filled with music. With the ability to play the guitar, ukulele, and drums, he rocks to the tunes of the metal and rock genres, using music as a creative outlet, planning to start a band of his own.

Articles from Soham

CoTracker3 Revolutionizes Point Tracking by Simplifying Architectures and Leveraging Real Video Data

Researchers at Meta AI and Oxford University introduced CoTracker3, a simplified point-tracking model that bridges synthetic and real video data using semi-supervised learning. The model outperforms state-of-the-art trackers with far less data.

21 Oct 2024

Hybrid Autoregressive Transformer Revolutionizes Visual Generation, Outperforming Diffusion Models

MIT, NVIDIA, and Tsinghua researchers introduced HART, a hybrid autoregressive model, improving image generation quality and efficiency by combining discrete and continuous tokens. HART rivals diffusion models while being significantly faster and more efficient.

20 Oct 2024

G7 Toolkit Empowers Governments to Deploy Ethical and Transparent AI

The G7 Toolkit for Artificial Intelligence in the Public Sector outlines strategies for ethical, secure, and effective AI deployment in governments, emphasizing human rights and transparency. It includes case studies and best practices to guide responsible AI adoption globally.

17 Oct 2024

EvolveDirector Revolutionizes AI Image Generation with Less Data and Superior Results

Researchers introduced EvolveDirector, a framework that trains high-quality text-to-image models using fewer data by leveraging vision-language models, outperforming top models like Stable Diffusion and DeepFloyd IF.

16 Oct 2024

Pixtral 12B Outperforms Larger Models in Multimodal Tasks and Text Processing

Researchers introduced Pixtral 12B, a multimodal language model that excels at understanding images and text. It surpasses larger models on multimodal benchmarks while retaining strong language performance.

15 Oct 2024

LLMs Encode Truth Better Than They Show, Revealing New Strategies for Error Detection

Researchers from Apple, Google, and Technion reveal that large language models (LLMs) encode more truthfulness in specific "exact answer tokens" than previously known, enabling better error detection and insights into mitigating hallucinations.

14 Oct 2024

Combining Large Models Unlocks New Levels Of Performance In AI Research

Researchers explored large-scale model merging, showing that combining large instruction-tuned models improves performance and generalization across various tasks, even surpassing multitask-trained models.

14 Oct 2024

ImageFolder: Autoregressive Image Generation with Folded Tokens

Paper introduces ImageFolder, a cutting-edge semantic image tokenizer that enhances generation efficiency and quality by using folded tokens, parallel token prediction, and quantizer dropout techniques, significantly reducing token length without compromising image detail.

10 Oct 2024

OpenAI's o1 Model Excels in Reasoning But Struggles with Rare and Complex Tasks

Researchers analyzed OpenAI’s o1 model and found it improves reasoning performance, but still retains probabilistic biases from autoregressive training, especially in rare or complex tasks.

9 Oct 2024

ComfyGen Transforms Text-to-Image Generation With Prompt-Based Workflow Adaptation

Researchers introduce ComfyGen, a novel approach to text-to-image generation using prompt-adaptive workflows, significantly improving image quality by tailoring workflows based on specific prompts.

8 Oct 2024