Search AI Products and News

In the field of artificial intelligence, reward models are a critical component for aligning large language models (LLMs) with human feedback, but existing models face the issue of "reward hacking." These models often focus on superficial features, such as the length or format of responses, rather than identifying genuine quality metrics, such as factual accuracy and relevance. The root cause lies in standard training objectives failing to distinguish between spurious associations and true causal drivers present in the training data. This failure leads to fragile reward models (RMs), which generate misaligned policies.

The domestic open source video generation model CogVideoX-5B has been officially released in the Mota ModelScope community, significantly improving the quality and visual effects of video generation. Based on the large-scale DiT model, this model utilizes a 3D causal variational autoencoder and expert Transformer technology, achieving spatio-temporal joint modeling through 3D-RoPE positional encoding and a 3D full attention mechanism. The use of progressive training techniques allows the model to generate long videos with distinct motion features, coherence, and high quality.

Ant Group has open-sourced the full-chain causal learning system OpenASCE at NeurIPS. OpenASCE supports distributed causal discovery and causal effect estimation. OpenASCE is widely used in credit risk control, marketing optimization, and recommendation scenarios. OpenASCE includes over 20 industrial-grade causal learning algorithms and lowers the application threshold for causal technologies.