FIELD NOTES TOPIC

computer graphics

5 notes, newest first.

  1. RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

    Source note ·

    A new benchmark called RealisticTritonBench was introduced to test the ability of large language models (LLMs) to generate GPU kernels for real-world AI frameworks. This benchmark addresses limitations in previous…

  2. GS-Agent: Creating 4D Physical Worlds With Generative Simulation

    Source note ·

    Researchers have developed GS-Agent, a system that uses natural language descriptions to automatically generate realistic, dynamic, and controllable 4D physical worlds. This is achieved through an end-to-end…

  3. GS-Agent: Creating 4D Physical Worlds With Generative Simulation

    Source note ·

    Researchers have developed GS-Agent, a system that generates realistic, dynamic, and controllable 4D physical worlds from natural language descriptions using an end-to-end multi-agent framework. The system emulates…

  4. SGA: Plug&Play Geometric Verification for Educational Video Synthesis

    Source note ·

    Researchers propose a new module called Symbolic Geometric Agent (SGA) that works with existing animation pipelines to improve spatial correctness and visual legibility for educational videos. The SGA intercepts code…

  5. CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis

    Source note ·

    The paper proposes CARLA-GS, a modular pipeline for synthesizing corner cases in autonomous driving simulations. The pipeline decouples visual representation, semantic reasoning, and physics-based execution while…