soskek/dynamic_routing_between_capsules
Implementation of Dynamic Routing Between Capsules, Sara Sabour, Nicholas Frosst, Geoffrey E Hinton, NIPS 2017 (⭐ 205)
Collaborative Filtering for Predicting User Preferences for Organizing Objects
As service robots become more and more capable of performing useful tasks for us, there is a growing need to teach robots how we expect them to carry out these tasks. However, different users typically have their own preferences, for example with res...
Nichola Goddard - Wikipedia
Captain Nichola Kathleen Sarah Goddard, MSM (May 2, 1980 – May 17, 2006) was the first Canadian woman to be killed in action since World War II, the first
How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
Vision-Language-Action (VLA) models have recently demonstrated impressive capabilities across various embodied AI tasks. While deploying VLA models on real-world robots imposes strict real-time inference constraints, the inference performance landsca...
SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositori…
Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their proficiency...
Del (disambiguation) - Wikipedia
logic DEL or Del, for Delaware, one of the United States DEL or Del, for Delhi, the capital of India Del, for the constellation Delphinus Del., for a
IDEA-Research/Grounding-DINO-1.5-API
Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series (⭐ 1086)
ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities
Although great progress has been made in 3D visual grounding, current models still rely on explicit textual descriptions for grounding and lack the ability to reason human intentions from implicit instructions. We propose a new task called 3D reasoni...
Improved GUI Grounding via Iterative Narrowing
Graphical User Interface (GUI) grounding plays a crucial role in enhancing the capabilities of Vision-Language Model (VLM) agents. While general VLMs, such as GPT-4V, demonstrate strong performance across various tasks, their proficiency in GUI groun...
facebookresearch/grounded-video-description
Video Grounding and Captioning (⭐ 332)
Metaphysical grounding - Wikipedia
Metaphysical grounding is a relation of metaphysical dependence that aims to capture how certain facts or entities obtain “in virtue of” others. It is
mbzuai-oryx/groundingLMM
[CVPR 2024 ?] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks. (⭐ 945)
Estimates of Stellar Weak Interaction Rates for Nuclei in the Mass Range A=65-80
We estimate lepton capture and emission rates, as well as neutrino energy loss rates, for nuclei in the mass range A=65-80. These rates are calculated on a temperature/density grid appropriate for a wide range of astrophysical applications includin...
100% renewable electricity in Japan
Japan has committed to carbon neutrality by 2050. Emissions from the electricity sector amount to 42% of the total. Solar photovoltaics (PV) and wind comprise three quarters of global net capacity additions because of low and falling prices. This pro...
[2511.02864] Mathematical exploration and discovery at scale
Nov 3, 2025 · We present AlphaEvolve as a powerful new tool for mathematical discovery, capable of exploring vast search spaces to solve complex optimization problems at scale, often with significantly …
AlphaEvolve: A coding agent for scientific and algorithmic discovery
In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as tackling open scientific problems or optimizing critical pieces of computa...
AlphaEvolve: A coding agent for scientific and algorithmic discovery
Jun 16, 2025 · In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as …
Reactive NaN Repair for Applying Approximate Memory to Numerical Applications
Applications in the AI and HPC fields require much memory capacity, and the amount of energy consumed by main memory of server machines is ever increasing. Energy consumption of main memory can be greatly reduced by applying approximate computing in...
CoT-Valve: Length-Compressible Chain-of-Thought Tuning
Chain-of-Thought significantly enhances a model's reasoning capability, but it also comes with a considerable increase in inference costs due to long chains. With the observation that the reasoning path can be easily compressed under easy tasks but s...
Photo caption - Wikipedia
Photo captions, also known as cutlines, are a few lines of text used to explain and elaborate on published photographs. In some cases captions and cutlines