Author: Sajjad Ansari

Sajjad Ansari
51 POSTS0 COMMENTS
Sajjad Ansari is a final year undergraduate from IIT Kharagpur. As a Tech enthusiast, he delves into the practical applications of AI with a focus on understanding the impact of AI technologies and their real-world implications. He aims to articulate complex AI concepts in a clear and accessible manner.

Exploring Offline Reinforcement Learning RL: Offering Practical Advice for Domain-Specific Practitioners and Future Algorithm Development

Data-driven methods that convert offline datasets of prior experiences into policies are a key way to solve control problems in various fields. There are...

OpenVLA: A 7B-Parameter Open-Source VLA Setting New State-of-the-Art for Robot Manipulation Policies

A major weakness of current robotic manipulation policies is their inability to generalize beyond their training data. While these policies, trained for specific skills...

TiTok: An Innovative AI Method for Tokenizing Images into 1D Latent Sequences

In recent years, image generation has made significant progress due to advancements in both transformers and diffusion models. Similar to trends in generative language...

Large Generative Graph Models (LGGMs): A New Class of Graph Generative Model Trained on a Large Corpus of Graphs

Large Generative Models (LGMs) like GPT, Stable Diffusion, Sora, and Suno have recently made remarkable strides in creating creative and meaningful content, greatly boosting...

How Scale Impacts Predicting Downstream Capabilities of Frontier AI Models: Understanding the Elusiveness

Predicting the scaling behavior of frontier AI systems like GPT-4, Claude, and Gemini is essential for understanding their potential and making decisions about their...

DiffUCO: A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization

Sampling from complex, high-dimensional target distributions, such as the Boltzmann distribution, is crucial in many scientific fields. For instance, predicting molecular configurations depends on...

Demonstration ITerated Task Optimization (DITTO): A Novel AI Method that Aligns Language Model Outputs Directly with Userโ€™s Demonstrated Behaviors

Language models (LMs) are designed to reflect a broad range of voices, leading to outputs that don't perfectly match any single perspective. To avoid...

GROKFAST: A Machine Learning Approach that Accelerates Grokking by Amplifying Slow Gradients

Grokking is a newly developed phenomenon where a model starts to generalize well long after it has overfitted to the training data. It was...

This AI Paper Explores the Extent to which LLMs can Self-Improve their Performance as Agents in Long-Horizon Tasks in a Complex Environment Using the...

Large language models (LLMs) have shown their potential in many natural language processing (NLP) tasks, like summarization and question answering using zero-shot and few-shot...

Nearest Neighbor Speculative Decoding (NEST): An Inference-Time Revision Method for Language Models to Enhance Factuality and Attribution Using Nearest-Neighbor Speculative Decoding

Large language models (LLMs) have proven their potential to handle multiple tasks and perform extremely well across various applications. However, it is challenging for...

Structurally Flexible Neural Networks: An AI Approach to Solve a Symmetric Dilemma for Optimizing Units and Shared Parameters

The advent of deep neural networks (DNNs) has led to remarkable improvements in controlling artificial agents using the optimization of reinforcement learning or evolutionary...

Newton Informed Neural Operator: A Novel Machine Learning Approach for Computing Multiple Solutions of Nonlinear Partials Differential Equations

Neural networks have been widely used to solve partial differential equations (PDEs) in different fields, such as biology, physics, and materials science. Although current...

๐Ÿ ๐Ÿ Join the Fastest Growing AI Research Newsletter...

X