Kimi k1.5
Kimi k1.5 is an advanced multi-modal model trained with reinforcement learning (RL) that achieves state-of-the-art reasoning performance across multiple benchmarks and modalities. It outperforms existing models such as GPT-4o and Claude Sonnet 3.5 in short-CoT tasks by a large margin and matches OpenAI's o1 in long-CoT performance.
Detailed Introduction
Kimi k1.5 is an o1-level multi-modal model trained with reinforcement learning (RL) that achieves state-of-the-art reasoning performance across multiple benchmarks and modalities. It outperforms existing models such as GPT-4o and Claude Sonnet 3.5 in short-CoT tasks by a large margin and matches OpenAI's o1 in long-CoT performance. Key ingredients of Kimi k1.5 include long context scaling, improved policy optimization, a simplistic RL framework, and multi-modal training.
MoreAI
Emotion: Anxiety,Stress,Relief | Quick mood, mind & mental quiz
In 1 minute, find the cause of mood swings, intense emotional changes, low energy, and more.
Psych-101: Human Psychological Experiment Transcripts Dataset
Psych-101 is a dataset of natural language transcripts from human psychological experiments, comprising trial-by-trial data from 160 experiments and 60,092 participants, making 10,681,650 choices. It provides valuable insights into human decision-making processes and is available under the Apache License 2.0.
ICASSP2022-Depression: Automatic Depression Detection
This repository provides code and data for automatic depression detection using a GRU/BiLSTM-based model. It includes an emotional audio-textual corpus designed to support the diagnosis of psychological distress conditions such as anxiety, depression, and post-traumatic stress disorder.