Locating the precise files or functions that need modification when addressing a bug report or feature request is one of…
Strawberry Fields: Build, Simulate, and Optimize Photonic Quantum Circuits in Python 831
If you’re exploring quantum computing but want to move beyond abstract theory and into hands-on experimentation—especially with light-based (photonic) systems—Strawberry…
XVerse: Precise Multi-Subject Image Generation with Independent Identity and Attribute Control 603
Generating realistic images with multiple distinct subjects—each retaining their unique identity and visual attributes like pose, lighting, or clothing style—has…
ICPC-Eval: Stress-Test LLM Reasoning with Real-World Competitive Programming Challenges 739
Evaluating the true reasoning capabilities of large language models (LLMs) in coding has long been hampered by benchmarks that are…
EmbodiedScan: A First-Person 3D Perception Suite for Building Language-Grounded Embodied AI Agents 635
In the rapidly evolving field of embodied artificial intelligence (AI), agents—whether physical robots or virtual avatars—must understand complex indoor environments…
Cosmos-Transfer1: Generate Realistic, Controllable World Simulations from Multimodal Inputs for Robotics and Autonomous Driving 695
Cosmos-Transfer1 is a powerful conditional world generation model developed by NVIDIA as part of its Cosmos World Foundation Models (WFMs)…
NextStep-1: High-Fidelity Autoregressive Image Generation Without Diffusion or Discrete Token Loss 553
Autoregressive (AR) models have long dominated natural language generation, but applying the same step-by-step prediction approach to images has been…
RLinf: Accelerate Large-Scale Reinforcement Learning for Agentic AI and Embodied Intelligence 503
Reinforcement learning (RL) is rapidly becoming the engine behind next-generation agentic AI—powering everything from math-reasoning language models to vision-guided robotic…
LongLive: Real-Time Interactive Long Video Generation with Seamless Prompt Control 656
Creating long, coherent, and high-quality videos from text has long been a formidable challenge in generative AI. Existing approaches—especially diffusion-based…
Cube: Generate 3D Assets from Text Prompts—No Modeling Skills Required 844
Imagine describing a “mechanical lobster with tank treads” in plain English and instantly getting a usable 3D model—no Blender expertise,…