RESEARCH

→ View original post on X — @danshipper

GRIMES_V1 Voice Model Training and Fine-tuning Techniques

By

@danshipper

–

06 August 2023 21h52

Does anyone know anything about how @GRIMES_V1 was trained? It's much better at replicating her voice than you typically see with fine-tuned models imo

→ View original post on X — @localghost

Floating Rocks and Reality Particle Alignment Possibilities

By

@localghost

–

06 August 2023 21h48

you're telling me rocks can float if you align the particles that govern reality in just the right way? imagine the depths we have yet to traverse

AutoRobotics-Zero Discovers Adaptive Robot Control Policies

By

–

06 August 2023 18h02

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.

LLM Self-Check: Zero-Shot Verification for Complex Reasoning

By

–

06 August 2023 18h02

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.

Agent Learns Multimodal World Model with Language Predictions

By

–

06 August 2023 18h02

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.

OpenFlamingo: Open-Source Vision-Language Models Family Released

By

–

06 August 2023 18h02

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.