New York Site views —Page views —
← All series

AI paper roundups

Dated selections of recent papers with reading notes on their methods and evidence.

Reading order

  1. Five research directions, from multimodal memory to small-model agents
  2. Five papers on agent world models, scaling laws, multi-image reasoning, 3D reconstruction and watermarking
  3. Five papers on pixel-level multimodality, 3D video constraints, clinical evaluation, RoPE and classification theory
  4. Five AI papers for a closer reading on May 9, 2026
  5. Five papers on test-time scaling, driving data, 3D representations, image generation and KGQA
  6. Five AI papers to read on May 12, 2026
  7. Five papers on embodied-agent verifiers, benchmark integrity, VLM failures, GUI grounding and implicit preferences