“Interesting new research from @AIatMeta on exploring better reasoning using latent space instead of output tokens. “Coconut” (Chain of Continuous Thought) enables more efficient and effective reasoning, particularly for complex planning tasks. In Coconut, the LLM has two modes.
https://x.com/_philschmid/status/1871117240176894247
“New research from Meta FAIR: Large Concept Models (LCM) is a fundamentally different paradigm for language modeling that decouples reasoning from language representation, inspired by how humans can plan high-level thoughts to communicate.
https://x.com/AIatMeta/status/1871263650935365759
Byte Latent Transformer: Patches Scale Better Than Tokens | Research – AI at Meta
https://ai.meta.com/research/publications/byte-latent-transformer-patches-scale-better-than-tokens/
“The license allows commercial usage *without* an revenue caps, only asks one to respect the Use Policy! This makes DeepSeek V3 even more liberal than Llama 3x series 🔥
https://x.com/reach_vb/status/1872256236789584247
“Introducing Meta Video Seal: a state-of-the art comprehensive framework for neural video watermarking. Try the demo ➡️
https://x.com/AIatMeta/status/1870176421248938010
