LycheeMemory V2 targets the cost of maintaining long-term memory in long-horizon LLM agents, replacing conventional turn-by-turn memory consolidation with semantic…
This paper studies why large language models keep generating long, expensive reasoning chains on problems beyond their real capability, producing…
This case study reports on using an AI coding agent to carry out a large-scale architectural refactor of a 717,000-line…
This study investigates whether purely rhetorical changes to a scientific manuscript — with the underlying content held constant — can…
Intern-S2-Preview is a family of foundation models built for multimodal scientific reasoning and long-horizon agentic tasks. Its training pipeline combines…
This write-up documents a training experiment pushing a 0.9-million-parameter language model to a token-per-parameter ratio of roughly 222,000:1 — far…
Cloudflare introduced Kitesurf, a browser engine built from scratch in Rust and compiled to WebAssembly to run entirely inside Cloudflare…
Cloudflare detailed the internal AI engineering infrastructure it built for its own workforce of 3,683 employees, using its own products…
Engineer Subhadip Mitra lays out a hierarchical framework for understanding AI model internals, moving from behavioral output analysis through attention…
Meta introduced Muse Glimmer, a 30-billion-parameter open agentic model trained through a three-phase pipeline: pre-training via logit distillation from the…
PyTorch engineers and AMD collaborators upstreamed FP8 training optimizations for AMD Instinct GPUs into TorchAO and TorchTitan, building on techniques…
Researchers introduced Mechanist, an agentic system designed to autonomously discover the mechanisms underlying AI intelligence by combining an interpretability-focused knowledge…
