Difference between revisions of "AI research trends"
KevinYager (talk | contribs) (Created page with "=Neural (non-token) Latent Representation= * 2024-11: Microsoft: [https://arxiv.org/abs/2411.02820 DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Servi...") |
KevinYager (talk | contribs) (→Neural (non-token) Latent Representation) |
||
| Line 5: | Line 5: | ||
* 2024-12: Meta: [https://ai.meta.com/research/publications/byte-latent-transformer-patches-scale-better-than-tokens/ Byte Latent Transformer: Patches Scale Better Than Tokens]: Instead of tokenization, dynamically convert input byte-stream into patches, yielding gains in compute efficiency, with minimal loss in performance | * 2024-12: Meta: [https://ai.meta.com/research/publications/byte-latent-transformer-patches-scale-better-than-tokens/ Byte Latent Transformer: Patches Scale Better Than Tokens]: Instead of tokenization, dynamically convert input byte-stream into patches, yielding gains in compute efficiency, with minimal loss in performance | ||
* 2024-12: Google DeepMind: [https://arxiv.org/abs/2412.17747 Deliberation in Latent Space via Differentiable Cache Augmentation] | * 2024-12: Google DeepMind: [https://arxiv.org/abs/2412.17747 Deliberation in Latent Space via Differentiable Cache Augmentation] | ||
| + | * 2024-12: [https://github.com/jerber/lang-jepa LANG-JEPA: Learning to Think in Latent Space] | ||
Revision as of 08:59, 24 December 2024
Neural (non-token) Latent Representation
- 2024-11: Microsoft: DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving: LLMs invent their own inter-communication language
- 2024-12: Meta: Training Large Language Models to Reason in a Continuous Latent Space: feeding the latent representation directly back into the model, instead of tokenizing intermediate thoughts (Chain of Continuous Thought, a.k.a. Coconut)
- 2024-12: Meta: Large Concept Models: Language Modeling in a Sentence Representation Space: train a model that operates at a higher level of abstraction than typical word/token LLMs; model operates in a space of concept embeddings (more akin to full sentences than individual words)
- 2024-12: Meta: Byte Latent Transformer: Patches Scale Better Than Tokens: Instead of tokenization, dynamically convert input byte-stream into patches, yielding gains in compute efficiency, with minimal loss in performance
- 2024-12: Google DeepMind: Deliberation in Latent Space via Differentiable Cache Augmentation
- 2024-12: LANG-JEPA: Learning to Think in Latent Space
