ZoomGain-4B
Fine-grained visual perception VLM (ZoomGain-4B)
None defined yet.
Fine-grained visual perception VLM (ZoomGain-4B)
1.75M-param TTS decoder, 30x smaller than Kokoro's
Hindi text-to-speech, 62M params, 6 voices
One image to 3D Gaussian splats at any token budget
Radiology reports with outlined findings (X-ray, CT, MRI)
One-step two-speaker dialogue separation
4.5M-param English TTS, two voices, 24 kHz, runs on CPU
Vietnamese ASR with speaker diarization and timestamps
Streaming Chinese⇄English speech-to-speech translation
Swap a character between two images with MiniMax-H3-Image
Diffusion-based compressed video enhancement
Photo to structured JSON scene record on CPU
Text-prompted multi-view echocardiography segmentation
Neuro-symbolic multi-robot task planning with a VLM planner
Agricultural image question answering with AgroNVILA
Fine-grained multimodal perception VLM
Steer SD v1.4 away from memorization at inference time
Multilingual speech recognition, Qwen3-ASR fine-tune
Spatial reasoning QA over video with the MVRD-distilled VLM
Calibrated medical answers from text and images
Thai & mixed Thai-English streaming speech-to-text
Telugu text-to-speech, 62M params, 6 voices
Multilingual speech-to-text for 25 European languages
Calibrated medical answers from text and images