HN Explorer

veryluckyxyz

↗ HN profile [ 150 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Scaling Laws for Agent Harnesses via Effective Feedback Compute (arxiv.org)
    1 points 0
  2. Generalizing Test-Time Compute-Optimal Scaling as an Optimizable Graph (huggingface.co)
    2 points 0
  3. Hidden drivers of HRM's performance on ARC-AGI (arcprize.org)
    31 points 2
  4. Set Block Decoding Is a Language Model Inference Accelerator (arxiv.org)
    4 points 0
  5. Deep Think with Confidence (jiaweizzhao.github.io)
    1 points 0
  6. A Batch Size and Token NUM- BER Agnostic Learning Rate Scheduler (arxiv.org)
    2 points 0
  7. Easily Understand Rdma Technology (naddod.com)
    1 points 1
  8. Model Merging in Pre-Training of Large Language Models (arxiv.org)
    2 points 0
  9. Understanding Perception and Reasoning Through Model Merging (arxiv.org)
    2 points 0
  10. Building and better understanding vision-language models (2024) (huggingface.co)
    2 points 0
  11. HF smolagents computer-agent demo (huggingface.co)
    1 points 0
  12. Do Reasoning Models Show Better Verbalized Calibration? (arxiv.org)
    2 points 0
  13. Robustly identifying concepts introduced during chat fine-tuning with crosscoder (arxiv.org)
    6 points 0
  14. Retrieval with Learned Similarities (arxiv.org)
    3 points 0
  15. The Curse of Depth in Large Language Models (arxiv.org)
    1 points 0
  16. Looking Back at Speculative Decoding (research.google)
    36 points 5
  17. Long-Context GRPO (unsloth.ai)
    60 points 22
  18. HippoRAG: Neurobiologically Inspired Long-Term Memory for LLMs (2024) (arxiv.org)
    65 points 4
  19. Learning to Plan and Reason for Evaluation with Thinking-LLM-as-a-Judge (arxiv.org)
    1 points 0
  20. Process Reinforcement Through Implicit Rewards (curvy-check-498.notion.site)
    1 points 0
  21. Explaining Large Language Models Decisions Using Shapley Values (arxiv.org)
    89 points 20
  22. Phi-4 Technical Report (arxiv.org)
    2 points 0
  23. Alignment Faking in LLMs [pdf] (assets.anthropic.com)
    2 points 1
  24. What Makes Rotary Positional Encodings Useful? (arxiv.org)
    1 points 0
  25. Rethinking Softmax: Self-Attention with Polynomial Activations (arxiv.org)
    2 points 0