CCTest · Blog
Qwen-Drive-1.0: Extending Vision-Language Models to Autonomous Driving
Robotics & Physical AI
cctest.ai

Qwen-Drive-1.0: Extending Vision-Language Models to Autonomous Driving

Qwen-Drive-1.0 explores a unified framework that combines 3D perception, visual question answering, and motion planning while retaining the backbone of a pretrained vision-language model. A BEV perception head and a planning expert connect shared representations to inspectable scene structure and future vehicle trajectories.

Read more
CCTest · Blog
Does On-Policy Distillation Really Distill? The Case for Teacher-Free Adaptation
Reinforcement Learning
cctest.ai

Does On-Policy Distillation Really Distill? The Case for Teacher-Free Adaptation

A new analysis suggests that much of on-policy distillation’s benefit may come from suppressing low-probability tokens rather than transferring meaningful teacher knowledge. The authors use this finding to motivate a teacher-free method called On-Policy Self-Adaptation.

Read more
CCTest · Blog
SpanCalib-VLM Brings Calibrated Span Detection to Vision-Language Hallucinations
Evaluation & Benchmarks
cctest.ai

SpanCalib-VLM Brings Calibrated Span Detection to Vision-Language Hallucinations

SpanCalib-VLM combines a generative vision-language model with a multimodal sequence tagger to locate hallucinated text and recalibrate its confidence. On the English SHROOM-Visions evaluation split, the hybrid system balances span coverage with more reliable scoring.

Read more
CCTest · Blog
Gemini’s Agentic Video Understanding Lets the Model Decide What to Watch
Vision & Video
cctest.ai
Vision & Video

Gemini’s Agentic Video Understanding Lets the Model Decide What to Watch

Google DeepMind has introduced Agentic Video Understanding for Gemini, allowing the model to dynamically search and revisit relevant parts of a video across frames, audio and transcripts. Google reports up to 88% lower token usage, 66% lower cost and 7% higher accuracy on selected benchmarks.

Read more