10/ AutoRobotics-Zero – discovers zero-shot adaptable policies from scratch that enable adaptive behaviors necessary for sudden environmental changes; as an example, the authors demonstrate the automatic discovery of Python code for controlling a robot.
@dair_ai
-
Agent Learns Multimodal World Model with Language Predictions
By
–
9/ Agents Model the World with Language – presents an agent that learns a multimodal world model that predicts future text and image representations; it learns to predict future language, video, and rewards.
-
LLM Self-Check: Zero-Shot Verification for Complex Reasoning
By
–
8/ Self-Check – explores whether LLMs can perform self-checks which is required for complex tasks that depend on non-linear thinking and multi-step reasoning; it proposes a zero-shot verification scheme to recognize errors without external resources.
-
OpenFlamingo: Open-Source Vision-Language Models Family Released
By
–
6/ OpenFlamingo – introduces a family of autoregressive vision-language models ranging from 3B to 9B parameters; the technical report describes the models, training data, and evaluation suite.
-
The Hydra Effect: Self-Repairing Properties in Language Models
By
–
7/ The Hydra Effect – shows that language models exhibit self-repairing properties — when one layer of attention heads is ablated it causes another later layer to take over its function.
-
ToolLLM Enables LLMs to Access 16000 Real-World APIs
By
–
3/ ToolLLM – enables LLMs to interact with 16000 real-world APIs; allows data preparation, training, and evaluation; the authors claim that one of their models, ToolLLaMA, has reached the performance of ChatGPT (turbo-16k) in tool use.
-
Skeleton-of-Thought: Parallel API Calls Strategy
By
–
4/ Skeleton-of-Thought – proposes a prompting strategy that firsts generate an answer skeleton and then performs parallel API calls to generate the content of each skeleton point; reports quality improvements in addition to speed-up of up to 2.39x.
-
MetaGPT: LLM-Based Multi-Agent Framework Encoding Human SOPs
By
–
5/ MetaGPT – a framework involving LLM-based multi-agents that encodes human standardized operating procedures (SOPs) to extend complex problem-solving capabilities that mimic efficient human workflows.
-
FLASK: Fine-Grained LLM Evaluation Framework for Alignment Skills
By
–
10/ FLASK – proposes fine-grained evaluation for LLMs based on a range of alignment skill sets; involves 12 skills and can help to provide a holistic view of a model’s performance depending on skill, domain, and level of difficulty.
-
Training Dense Retrievers for LLM In-Context Examples
By
–
9/ Retrieve In-Context Example for LLMs – presents a framework to iteratively train dense retrievers to identify high-quality in-context examples for LLMs.