- Personal website: alexzhang13.github.io 
- Latest Research: Recursive Language Models 
- My newest benchmark on LMs playing video games: https://www.vgbench.com/ 
- My most recent papers: VideoGameBench, KernelBench, SWE-Bench Multimodal 
PhD student at MIT, prev. Princeton CS
- NYC
- 
        
  10:31
  (UTC -04:00) 
- alexzhang13.github.io
Pinned Loading
- 
  videogamebenchvideogamebench PublicBenchmark environment for evaluating vision-language models (VLMs) on popular video games! 
- 
  Ligo-Biosciences/AlphaFold3Ligo-Biosciences/AlphaFold3 PublicOpen source implementation of AlphaFold3 
- 
  gpu-mode/reference-kernelsgpu-mode/reference-kernels PublicOfficial Problem Sets / Reference Kernels for the GPU MODE Leaderboard! 
- 
  ScalingIntelligence/KernelBenchScalingIntelligence/KernelBench PublicKernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA (+ more DSLs) 
- 
  flashattention2-custom-maskflashattention2-custom-mask PublicTriton implementation of FlashAttention2 that adds Custom Masks. 
          Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
  If the problem persists, check the GitHub status page or contact support.





