Podcast Episodes
Back to Search
Llama 4: Natively Multimodal AI Innovation
Meta AI has introduced its Llama 4 family of large language models, highlighting two new open-weight models: Llama 4 Scout and Llama 4 Maverick, alon…
1Â year, 3Â months ago
Self-Steering Language Models via Probabilistic Programs
This research introduces DISCIPL, a novel framework where language models dictate their own reasoning process for complex tasks. By having a Planner …
1Â year, 3Â months ago
Amazon Q Developer: AI for Data Science in SageMaker Canvas
The provided text introduces Amazon Q Developer in SageMaker Canvas, a new AI tool that allows users to build and deploy machine learning models usin…
1Â year, 3Â months ago
Adaptive SVD for Continual Learning in Large Language Models
This research addresses the challenge of catastrophic forgetting in large language models during continual learning, where adapting to new tasks degr…
1Â year, 3Â months ago
Llama 4: Natively Multimodal AI Innovation
Meta AI has introduced its Llama 4 family of large language models, highlighting two new open-weight models: Llama 4 Scout and Llama 4 Maverick, alon…
1Â year, 3Â months ago
UniOcc: Unified Occupancy Prediction and Forecasting Benchmark
This paper introduces UniOcc, a new benchmark for 3D occupancy forecasting and prediction in autonomous driving. It unifies data from real-world data…
1Â year, 3Â months ago
Graph Counterfactual XAI via Latent Space Traversal
This research introduces a novel method for generating counterfactual explanations for graph-based predictions.The approach utilizes a permutation eq…
1Â year, 3Â months ago
Continual Forgetting for Pre-trained Vision Models
The provided research paper explores the novel problem of continual forgetting in pre-trained vision models, where the goal is to sequentially remove…
1Â year, 3Â months ago
Age of Updates for Adaptive OFDM in Autonomous Vehicles
The provided research explores optimizing communication and sensing for autonomous vehicles using millimeter wave technology and orthogonal frequency…
1Â year, 3Â months ago
Video Generation Improvement via Human Preference Alignment
Recent progress in video generation still struggles with issues like motion instability and prompt alignment. To address this, the study explores inc…
1Â year, 3Â months ago