Podcast Episodes
Back to Search
Parameter-Efficient Continual Learning: A Survey
This survey explores Parameter-Efficient Continual Fine-Tuning (PECFT), a method that combines the adaptability of Continual Learning (CL) with the e…
1Â year, 3Â months ago
Building an Agent: LLM, Loop, and Tokens
Thorsten Ball's article argues that creating a functional code-editing agent is surprisingly straightforward. It posits that the core components are …
1Â year, 3Â months ago
Uncertainty-Guided Lung Tumor Segmentation via Coarse-to-Fine Refinement
This research paper introduces a novel two-stage framework for more accurately identifying lung tumors in CT scans. The approach first performs a coa…
1Â year, 3Â months ago
Complex Instruction-Based Image Editing Benchmark
This research introduces Complex-Edit, a new benchmark for evaluating how well image editing models follow instructions with varying levels of comple…
1Â year, 3Â months ago
Sleep-Time Compute: Pre-computation for Efficient LLM Inference
This research introduces "sleep-time compute," a novel method for enhancing large language model efficiency by allowing them to process contextual in…
1Â year, 3Â months ago
Miras: A Framework for Designing Deep Learning Architectures
This paper introduces Miras, a novel framework for designing sequence models by drawing parallels between neural architectures and associative memory…
1Â year, 3Â months ago
RUKA: A Compact and Affordable Humanoid Robotic Hand
This paper introduces RUKA, a newly designed open-source, low-cost, and anthropomorphic robotic hand intended for research in dexterous manipulation.…
1Â year, 3Â months ago
GenEAva: Expressive Cartoon Avatar Generation via Diffusion
The provided paper introduces GenEAva, a novel framework for generating high-quality cartoon avatars with detailed facial expressions by fine-tuning …
1Â year, 3Â months ago
VCR-Bench: Video Chain-of-Thought Reasoning Evaluation
The provided text introduces VCR-Bench, a novel benchmark designed to evaluate the Chain-of-Thought (CoT) reasoning capabilities of large vision-lang…
1Â year, 3Â months ago
Automating LLM Hallucination Detection with Reasoning
This Amazon Science blog post introduces HalluMeasure, a novel approach for automatically detecting hallucinationsin large language model outputs. Th…
1Â year, 3Â months ago