Difference between revisions of "AI research trends"

From GISAXS
Jump to: navigation, search
(Memory)
(Retrieval beyond RAG)
Line 63: Line 63:
 
* 2024-12: [https://arxiv.org/abs/2412.11919 RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation]
 
* 2024-12: [https://arxiv.org/abs/2412.11919 RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation]
 
* 2025-03: Microsoft: [https://www.microsoft.com/en-us/research/blog/introducing-kblam-bringing-plug-and-play-external-knowledge-to-llms/ Introducing KBLaM: Bringing plug-and-play external knowledge to LLMs]
 
* 2025-03: Microsoft: [https://www.microsoft.com/en-us/research/blog/introducing-kblam-bringing-plug-and-play-external-knowledge-to-llms/ Introducing KBLaM: Bringing plug-and-play external knowledge to LLMs]
 +
* 2025-06: [https://arxiv.org/abs/2506.06266 Cartridges: Lightweight and general-purpose long context representations via self-study]
 
* 2025-07: [https://arxiv.org/pdf/2507.07957 MIRIX: Multi-Agent Memory System for LLM-Based Agents] ([https://mirix.io/ mirix])
 
* 2025-07: [https://arxiv.org/pdf/2507.07957 MIRIX: Multi-Agent Memory System for LLM-Based Agents] ([https://mirix.io/ mirix])
 
* 2025-08: [https://arxiv.org/abs/2508.16153 Memento: Fine-tuning LLM Agents without Fine-tuning LLMs]
 
* 2025-08: [https://arxiv.org/abs/2508.16153 Memento: Fine-tuning LLM Agents without Fine-tuning LLMs]

Revision as of 13:32, 15 February 2026

System 2 Reasoning

See: Increasing AI Intelligence

Memory

Reviews

Big Ideas

LLM Weights Memory

Context Length

Extended Context

Context Remaking

Retrieval beyond RAG

See also: AI tools: Retrieval Augmented Generation (RAG)

Working Memory

Long-Term Memory

Storage and Retrieval

Episodic Memory

Continual Learning

Updating Weights at Inference-time

Parameters as Tokens

Internal Thought Representation Space

Visual Thinking

Neural (non-token) Latent Representation

Altered Transformer

Tokenization

Generation Order

Diffusion Language Models

Related: Image Synthesis via Autoregression/Diffusion

Sampling

Daydreaming, brainstorming, pre-generation

Pre-generation

Missing Elements

  • Memory
  • Continuous learning/update
  • Robust contextual model
  • Long-time-horizon coherence
  • Fluid intelligence
  • Agency
  • Modeling of self
  • Daydreaming

Memes

See Also