PyTorch
PulseAugur coverage of PyTorch — every cluster mentioning PyTorch across labs, papers, and developer communities, ranked by signal.
28 day(s) with sentiment data
-
AI model recovers keystrokes with 85% accuracy using laptop microphone audio
Researchers have developed a method to recover typed text by analyzing laptop microphone audio. A convolutional neural network (CNN) was trained on log-mel spectrograms of individual keystrokes, achieving approximately …
-
CuTeDSL emerges as new GPU kernel path for LLM inference, challenging CUTLASS
The landscape of GPU kernel engineering for LLM inference is shifting, with CuTeDSL emerging as a potential successor to C++ CuTe/CUTLASS. This evolution is highlighted by industry trends in technologies like FlashAtten…
-
Free Pascal and BLAS offer faster matrix multiplication for AI development
A user explored the performance of Python for AI tasks, noting its slowness but acknowledging the extensive AI ecosystem as its primary advantage. They conducted a test comparing Free Pascal and BLAS for matrix multipli…
-
AI agents automate data prep, while new Python ML compiler speeds LLM compression
Researchers have developed a new open-source machine learning compiler stack written in just 5,000 lines of Python. This stack offers unprecedented transparency by lowering large language models to CUDA with six interme…
-
New C++ engine HASE achieves 33M steps/sec for multi-agent RL training
Researchers have developed a new C++ engine called Hide-And-Seek-Engine (HASE) designed to significantly improve the efficiency of training reinforcement learning agents in decentralized, partially observable environmen…
-
New algorithm speeds up EigenDecomposition for large matrices in deep learning
Researchers have developed a new batch-efficient algorithm for EigenDecomposition (ED), a critical computation in computer vision and deep learning. This divide-and-conquer approach aims to overcome the computational bo…
-
VkSplat pipeline boosts 3D Gaussian Splatting training with Vulkan compute
Researchers have developed VkSplat, a novel training pipeline for 3D Gaussian Splatting (3DGS) that utilizes Vulkan compute for enhanced performance and broader compatibility. This new approach offers a significant spee…
-
Neural ODEs advance with mixed precision training and causal forecasting methods
Researchers have developed a new mixed-precision training framework for Neural Ordinary Differential Equations (Neural ODEs) to reduce computational costs. This framework uses low-precision computations for evaluating n…
-
DeepSeek V4 First Release Adaptation Behind: Why does Ascend insist on not doing a CUDA compatibility layer?
Huawei's Ascend AI accelerators are forging a unique path by eschewing CUDA compatibility to build an independent ecosystem. This strategy focuses on deep architectural changes in their latest Ascend 950 chips to addres…
-
Studies benchmark AutoML and BiLSTM for NLP tasks, showing mixed results
Researchers have compared traditional machine learning methods with deep learning models for various natural language processing tasks, including fine-grained emotion classification and sentiment analysis. Studies utili…
-
New HDET method explores hyperparameters for large model training
Researchers have introduced Hyperparameter-Divergent Ensemble Training (HDET), a novel method designed to optimize the training of large neural networks. HDET repurposes data-parallel replicas to simultaneously explore …
-
IBM Research integrates vLLM into its RITS Platform for AI development
IBM Research has integrated vLLM, an open-source library for fast LLM inference, into its RITS Platform. This integration aims to enhance the platform's capabilities by leveraging vLLM's efficient processing for large l…
-
PointTransformerX offers portable, efficient 3D point cloud processing without sparse algorithms
Researchers have developed PointTransformerX (PTX), a new vision transformer backbone for processing 3D point clouds that eliminates the need for custom CUDA operators. This PyTorch-native model achieves competitive acc…
-
New Rose optimizer offers low VRAM, fast convergence, and great results
A new PyTorch optimizer named Rose has been released under the Apache 2.0 license. Developed by Matthew K., Rose is designed to be stateless, offering significantly lower VRAM usage compared to optimizers like AdamW, wi…
-
HubRouter offers sub-quadratic routing for sequence models, improving throughput
Researchers have developed HubRouter, a novel module designed to replace computationally expensive O(n^2) attention layers in sequence models with a more efficient O(nM) hub-mediated routing system. This new primitive u…
-
NVIDIA Cosmos Predict 2.5 fine-tuned for robots; new ShadowPEFT method emerges
NVIDIA has released a guide for fine-tuning its Cosmos Predict 2.5 world model for robot video generation using parameter-efficient techniques like LoRA and DoRA. This method allows for adaptation to specific domains, s…
-
Together AI Cloud enhances RL pipelines with TorchForge and tool integrations
Together AI is enhancing its cloud platform to support advanced reinforcement learning (RL) pipelines, integrating TorchForge and Monarch for distributed training. The platform now offers low-latency GPU communication a…
-
Kimi K2 model boasts 1T parameters and SOTA HLE, while Soumith Chintala departs PyTorch
Kimi K2, a new model from Kimi, boasts 1 trillion parameters and achieves state-of-the-art results on the HLE benchmark. It also demonstrates capabilities in BrowseComp and TauBench. Separately, Soumith Chintala has dep…
-
Thinking Machines names Soumith Chintala new CTO, forms vLLM team
Thinking Machines has appointed Soumith Chintala as its new Chief Technology Officer, succeeding Barret Zoph. Chintala, who has a decade of experience in AI research and development, is expected to lead the company's te…
-
OCaml ecosystem Raven offers type-safe ML tools mirroring Python libraries
Raven is a new ecosystem of OCaml libraries designed for numerical computing, machine learning, and data science. It aims to provide type-safe alternatives to popular Python libraries such as NumPy, JAX, and PyTorch. Th…