PowerInfer-2 Achieves 29x Speedup, Running 47-Billion Parameter LLMs on Smartphones Post date August 26, 2025 Post author By Writings, Papers and Blogs on Text Models Post categories In Edge AI, efficient-ai, heterogeneous-computing, mobile-ai, on-device-language-models, power-infer-2, system-for-ml
Drop the Heavyweights: YOLO‑Based 3D Segmentation Outpaces SAM/CLIP Post date August 26, 2025 Post author By Instancing Post categories In 3d-segmentation, computer-vision, efficient-ai, instance-segmentation, open-vocabulary-ai, open-yolo-3d, point-clouds, yolo
No SAM, No CLIP, No Problem: How Open‑YOLO 3D Segments Faster Post date August 26, 2025 Post author By Instancing Post categories In 3d-segmentation, computer-vision, efficient-ai, instance-segmentation, open-vocabulary-ai, point-clouds, robotics-ai, yolo-3d
How Idefics2 Answers the Unasked Questions in Vision-Language Modeling Post date July 15, 2025 Post author By Pierluigi Vinciguerra Post categories In ai-model-designs, efficient-ai, idefics-2, ml-benchmarks, multimodal-ai, open-source-ai, transformer-models, vision-language-models
RNNs vs. Transformers: Innovations in Scalability and Efficiency Post date January 14, 2025 Post author By Gating Post categories In ai-research, deep-learning, efficient-ai, linear-attention, rnn-models, scalable-ai, ssm-models, transformers
Hawk and Griffin: Mastering Long-Context Extrapolation in AI Post date January 14, 2025 Post author By Gating Post categories In ai-extrapolation, deep-learning, efficient-ai, griffin-model, hawk-model, language-models, long-context-ai, token-prediction
Griffin Model: Advancing Copying and Retrieval in AI Tasks Post date January 14, 2025 Post author By Gating Post categories In ai-extrapolation, copying-tasks, deep-learning, efficient-ai, griffin-model, language-models, retrieval-tasks, transformers
Hawk and Griffin Models: Superior Latency and Throughput in AI Inference Post date January 14, 2025 Post author By Gating Post categories In ai-inference, deep-learning, efficient-ai, griffin-model, hawk-model, high-throughput, low-latency, transformers
Hawk and Griffin Models: Superior NLP Performance with Minimal Training Data Post date January 13, 2025 Post author By Gating Post categories In ai-research, deep-learning, efficient-ai, griffin-model, hawk-model, llama-v2, nlp-performace, rnn-models
Griffin Models: Outperforming Transformers with Scalable AI Innovation Post date January 13, 2025 Post author By Gating Post categories In ai-research, chinchilla-scaling, deep-learning, efficient-ai, griffin-model, rnn-models, scalable-ai, transformers
Recurrent Models Scale as Efficiently as Transformers Post date January 13, 2025 Post author By Gating Post categories In deep-learning, efficient-ai, griffin-model, hybrid-ai, nlp-scaling, rnn-models, sequence-processing, transformers
RG-LRU: A Breakthrough Recurrent Layer Redefining NLP Model Efficiency Post date January 13, 2025 Post author By Gating Post categories In ai-models, deep-learning, efficient-ai, gating, nlp-innovations, rg-lru, rnn-models, temporal-mixing
RNN Models Hawk and Griffin: Transforming NLP Efficiency and Scaling Post date January 13, 2025 Post author By Gating Post categories In ai-models, deep-learning, efficient-ai, language-models, multi-query-attention, nlp-research, rnn-model, scalable-ai
Sciencx
Sciencx