A New Approach to 3D Scene Understanding: Replacing Heavy Segmentation Models for a 16x Speedup Post date August 26, 2025 Post author By Instancing Post categories In 3d-instance-segmentation, 3d-perception, computer-vision, open-vocabulary-ai, rgbd, scene-understanding, yolo-world, zero-shot-learning
Why LLMs Struggle with Arithmetic Puzzles Post date August 23, 2025 Post author By Extrapolate Post categories In data-synthesis-pipeline, fine-tuning-on-synthetic-data, mathematical-reasoning-ai, out-of-domain-benchmarking, reasoning-verification, symbolic-reasoning-ai, synthetic-data-generation, zero-shot-learning
Testing Large Language Models on Math Puzzles Post date August 23, 2025 Post author By Extrapolate Post categories In data-synthesis-pipeline, fine-tuning-on-synthetic-data, mathematical-reasoning-ai, out-of-domain-benchmarking, reasoning-verification, symbolic-reasoning-ai, synthetic-data-generation, zero-shot-learning
Evaluating Fine-Tuned LLMs on Reasoning Puzzles Post date August 23, 2025 Post author By Extrapolate Post categories In data-synthesis-pipeline, fine-tuning-on-synthetic-data, mathematical-reasoning-ai, out-of-domain-benchmarking, reasoning-verification, symbolic-reasoning-ai, synthetic-data-generation, zero-shot-learning
A Framework for Synthesizing Arithmetical Puzzle Datasets for Large Language Models Post date August 23, 2025 Post author By Extrapolate Post categories In data-synthesis-pipeline, fine-tuning-on-synthetic-data, mathematical-reasoning-ai, out-of-domain-benchmarking, reasoning-verification, symbolic-reasoning-ai, synthetic-data-generation, zero-shot-learning
How LLMs Learn to Solve Complex Math Post date August 23, 2025 Post author By Extrapolate Post categories In data-synthesis-pipeline, fine-tuning-on-synthetic-data, hackernoon-top-story, mathematical-reasoning-ai, out-of-domain-benchmarking, reasoning-verification, synthetic-data-generation, zero-shot-learning
What Happens When Your Prompt Is Too Obscure? Post date July 10, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
A Close Look at Misalignment in Pretraining Datasets Post date July 10, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
The Link Between Concept Frequency and AI Performance, Seen Through Images and Words Post date July 10, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
The HackerNoon Newsletter: Pixels, Paperbacks, and Power (7/9/2025) Post date July 9, 2025 Post author By Noonification Post categories In ai, censorship, hackernoon-newsletter, latest-tect-stories, noonification, python, zero-shot-learning
How Concept Frequency Affects AI Image Accuracy Post date July 9, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
Across Metrics and Prompts, Frequent Concepts Outperform in Zero-Shot Learning Post date July 9, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
What 34 Vision-Language Models Reveal About Multimodal Generalization Post date July 9, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
How Dataset Diversity Impacts AI Model Performance Post date July 9, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
‘Let It Wag!’ and the Limits of Machine Learning on Rare Concepts Post date July 8, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
AI Training Data Has a Long-Tail Problem Post date July 8, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
AI Models Trained on Synthetic Data Still Follow Concept Frequency Trends Post date July 8, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
Analyzing the Impact of Pretraining Frequency on Zero-Shot Performance in Multimodal Models Post date July 8, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
How AI Models Count and Match Concepts in Images and Text Post date July 8, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, multimodal-models, object-detection-ai, text-to-image-generation, zero-shot-learning
What 300GB of AI Research Reveals About the True Limits of “Zero-Shot” Intelligence Post date July 8, 2025 Post author By The FewShot Prompting Publication Post categories In ai-dataset-curation, ai-generalization, clip, concept-frequency-ai, hackernoon-top-story, multimodal-models, object-detection-ai, zero-shot-learning
What It Takes to Train a Versatile Speech AI System Post date June 20, 2025 Post author By Phonology Technology Post categories In audio-language-model, automatic-speech-recognition, generalization-capability, instruction-finetuning, multimodal-learning, multitask-learning, speech-processing, zero-shot-learning
How We Pre-Trained a 300M Parameter Audio Encoder With Random Quantization Post date June 19, 2025 Post author By Phonology Technology Post categories In audio-language-model, automatic-speech-recognition, generalization-capability, instruction-finetuning, multimodal-learning, multitask-learning, speech-processing, zero-shot-learning
A Unified Multimodal Approach to Speech Processing with LLMs Post date June 19, 2025 Post author By Phonology Technology Post categories In audio-language-model, automatic-speech-recognition, generalization-capability, instruction-finetuning, multimodal-learning, multitask-learning, speech-processing, zero-shot-learning
Advancing Multimodal Video Generation with Responsible AI and Stylization Post date January 13, 2025 Post author By Teleplay Technology Post categories In llms, multimodal-ai, self-supervised-learning, super-resolution-ai, text-to-video-evaluation, video-generation-ai, videopoet, zero-shot-learning
Sciencx
Sciencx