CCTest · Blog
SpatialBlock Uses Synthetic Block Stacking to Teach LVLMs Spatial Intelligence
Multimodal
cctest.ai
Multimodal

SpatialBlock Uses Synthetic Block Stacking to Teach LVLMs Spatial Intelligence

SpatialBlock proposes a controlled alternative to expensive real-scene geometry annotation: train large vision-language models on synthetic block-manipulation problems first. Its SpatialBlock-15k dataset covers projection, viewpoint changes, structural composition, and color-based spatial anchors.

Read more
CCTest · Blog
Instead of Imitating Answers, LLMs Could Learn by Avoiding Bad Reasoning
Large Language Models
cctest.ai

Instead of Imitating Answers, LLMs Could Learn by Avoiding Bad Reasoning

Negative Self-Distillation introduces a reverse form of self-distillation: rather than copying a privileged solution trace, a model is trained to move away from its own flawed reasoning. The approach aims to preserve exploration and self-correction without requiring external labels.

Read more
CCTest · Blog
Xiaomi Open-Sources CocktailASR-1 to Focus Speech Recognition on a Target Speaker
Speech & Audio
cctest.ai
Speech & Audio

Xiaomi Open-Sources CocktailASR-1 to Focus Speech Recognition on a Target Speaker

Xiaomi has open-sourced CocktailASR-1, an industrial-grade target-speaker automatic speech recognition model designed for overlapping conversations. Instead of relying only on stronger noise reduction, it conditions recognition on the identity of the speaker users want to hear.

Read more