RESEARCH

LLM-Based Multi-Agent Systems: Applications, Benchmarks, and Challenges

By

–

11 February 2024 16h33

10/ LLM-based Multi-Agents – discusses the essential aspects of LLM-based multi-agent systems; it includes a summary of recent applications for problem-solving and word simulation; summarizes datasets, benchmarks, challenges, and future opportunities.

Self-Discover: LLMs Select Reasoning Techniques for Tasks

By

–

11 February 2024 16h33

7/ Self-Discovered Reasoning Structures – proposes a new framework, Self-Discover, that enables LLMs to select from multiple reasoning techniques (e.g., critical thinking and thinking step-by-step) to compose task-specific reasoning strategies.

DeepSeekMath Enhances Mathematical Reasoning with GRPO Optimization

By

–

11 February 2024 16h33

8/ DeepSeekMath – continues pretraining a code base model with 120B math-related tokens; introduces GRPO (a variant to PPO) to enhance mathematical reasoning and reduce training resources via a memory usage optimization scheme.

LLMs for Table Processing: Methods, Benchmarks and Techniques

By

–

11 February 2024 16h33

9/ LLMs for Table Processing – provides an overview of LLMs for table processing, including methods, benchmarks, prompting techniques, and much more.

ALOHA 2: Advanced Bimanual Teleoperation System Improvements

By

–

11 February 2024 16h33

5/ ALOHA 2 – a low-cost system for bimanual teleoperation that improves the performance, user-friendliness, and durability of ALOHA; efforts include hardware improvements such as grippers and gravity compensation with a higher quality simulation model.https://t.co/Xr7TxmqLxX
— DAIR.AI (@dair_ai) 11 février 2024

5/ ALOHA 2 – a low-cost system for bimanual teleoperation that improves the performance, user-friendliness, and durability of ALOHA; efforts include hardware improvements such as grippers and gravity compensation with a higher quality simulation model.

Scaling LLM Agents Through Sampling and Voting Methods

By

–

11 February 2024 16h33

6/ More Agents is All You Need – presents a study on the scaling property of raw agents instantiated by LLMs; finds that performance scales when increasing agents by simply using a sampling-and-voting method.

Phase Transition in Dot-Product Attention: Positional vs Semantic Learning

By

–

11 February 2024 16h33

3/ A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention – studies the theoretical understanding of learning with attention layers by exploring the interplay between positional and semantic attention.

Indirect Reasoning Strengthens LLM Logical Reasoning Power

By

–

11 February 2024 16h33

4/ Indirect Reasoning with LLMs – proposes an indirect reasoning method to strengthen the reasoning power of LLMs; it employs the logic of contrapositives and contradictions to tackle IR tasks such as factual reasoning and mathematic proof.

→ View original post on X — @catherineadenle

OpenAI Microsoft Google Battle for Generative AI Patents

By

@catherineadenle

–

11 February 2024 8h30

OpenAI, Microsoft or Google: Who's Winning the Gen AI Patent Battle? https://
aibusiness.com/nlp/openai-mic
rosoft-or-google-who-s-winning-the-gen-ai-patent-battle-
… #OpenAI #GenAI #TechNews #AIPatent #GoogleAI #Microsoft #AI #IoT