7). Challenges in Human-Agent Communication – present a comprehensive analysis of key challenges in human-agent communication, focusing on how humans and AI agents can effectively establish common ground and mutual understanding. https://
microsoft.com/en-us/research
/uploads/prod/2024/12/HCAI_Agents.pdf
…
@dair_ai
-
Challenges in Human-Agent Communication: Establishing Common Ground
By
–
-
GenCast ML Weather Model Outperforms Leading Forecasting Systems
By
–
6). GenCast – an ML weather prediction model that outperforms the world's leading operational weather forecasting system (ECMWF's ENS) in both accuracy and speed.
-
ALAMA: Framework for Language Agents Learning Mechanisms
By
–
4). ALAMA – a new framework that helps language agents automatically learn when to use different mechanisms (ReAct, CoT, Reflection, etc.) for automatically completing tasks, improving on current approaches that use fixed or predefined mechanisms.
-
Auto-RAG: Autonomous Iterative Retrieval Model with Superior Performance
By
–
5). Auto-RAG – an autonomous iterative retrieval model with superior performance across many datasets; Auto-RAG is a fine-tuned LLM that leverages the decision-making capabilities of an LLM.
-
Reverse Thinking Improves LLM Reasoning Performance Efficiency
By
–
3). Reverse Thinking – shows that training LLMs to learn "reverse thinking" helps to improve performance in commonsense, math, and logical reasoning tasks. It claims to outperform a standard fine-tuning method trained on 10x more forward reasoning.
-
Genie 2: Foundation Model Generates Playable 3D AI Training Environments
By
–
2). Genie 2 – a foundation world model that generates playable 3D environments from single prompt images, enabling endless training scenarios for AI agents with features like physics simulation, character animation, and object interactions…https://t.co/OvKvtfJLVz
— DAIR.AI (@dair_ai) 8 décembre 20242). Genie 2 – a foundation world model that generates playable 3D environments from single prompt images, enabling endless training scenarios for AI agents with features like physics simulation, character animation, and object interactions…
-
OpenAI o1 Model Series Demonstrates 50% Faster Reasoning Capabilities
By
–
1). OpenAI o1 – a model series trained with large-scale reinforcement learning to reason using chain of thought; o1 shows significant improvements across benchmarks related to math, code, and science; o1 is claimed to be 50% faster in generating thinking steps than o1-preview.
-
Top ML Papers Week: Genie 2, GenCast, OpenAI o1
By
–
It was a huge week of AI and LLM papers. Here are the top ML Papers of the Week (Dec 2-8): – Genie 2
– GenCast
– OpenAI o1
– Auto-RAG
– Reverse Thinking
– Retrieval-Augmented Reasoning for LLMs Read on for more: -
ChatGPT Language Games: Measuring Bullshit in LLM Outputs
By
–
10). Measuring Bullshit in Language Games Played by ChatGPT – proposes that LLM-based chatbots play the ‘language game of bullshit’; by asking ChatGPT to generate scientific articles on topics where it has no knowledge or competence, the authors were able to provide a reference
-
LLM-Based Generative Agents Simulate 1000 Real Individuals
By
–
9). Generative Agent Simulations of 1,000 People – introduces a new agent architecture that uses LLMs to create behavioral simulations of real individuals, achieving 85% accuracy in replicating human responses on the General Social Survey and reducing demographic biases compared