HN Explorer

zagwdt

↗ HN profile [ 45.6 ms ] full profile

No user record in our sample, but zagwdt has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.

  1. Inference Optimization for MiniMax Sparse Attention (together.ai)
    1 points 0
  2. DeepSeek V4 in vLLM: Efficient Long-Context Attention (vllm-website-pdzeaspbm-inferact-inc.vercel.app)
    3 points 0
  3. Introspective Diffusion Language Models (introspective-diffusion.github.io)
    281 points 15
  4. EinsteinArena: Harnessing the collective intelligence of agents in the wild (einsteinarena.com)
    5 points 0
  5. RL Meets Adaptive Speculative Training (together.ai)
    2 points 0
  6. Weak models excel at long context tasks (together.ai)
    2 points 1
  7. TorchSpec: Speculative Decoding Training at Scale (pytorch.org)
    2 points 0
  8. 1 points 0
  9. Flash Attention 4 (together.ai)
    1 points 0
  10. CoderForge-Preview: SOTA open dataset for training efficient coding agents (together.ai)
    1 points 0
  11. Two years of vector search at Notion: 10x scale, 1/10th cost (notion.com)
    2 points 0
  12. Consistency diffusion language models: Up to 14x faster, no quality loss (together.ai)
    219 points 19