Studies
Multimodal
Vision, audio, video and multimodal model research
FilterCompanies & models
-
Teaching LVLMs Spatial Skills With 15K Toy Blocks Beats Heavier Real-Scene Pipelines
SpatialBlock-15k: Qwen-based 4B model reaches 51.3% (+25.1 over backbone). 7B gains 17.6% over backbone; 3B beats SpatialLadder by 2.7–3.2% using only synthetic blocks.
By
Editor's picks
- Teaching LVLMs Spatial Skills With 15K Toy Blocks Beats Heavier Real-Scene Pipelines
- TurboVLA Runs Robot Policies at 32 Hz on an RTX 4090 Using Under 1 GB VRAM
- YuE2’s Symbolic Planning Wins 49.3% of Expert Preferences for Music Quality
- VLMs Still Can’t Tell Which Attribute Goes With Which Object — Until Text-Only Finetuning
- Qwen-Image-2.0 Unifies High-Fidelity Generation and Precise Editing in One Model
More stories
-
Crisis Deepfake Detectors Collapse From 90%+ AUC to Chance on Real Generators
RA-Bench: traditional detectors fall from 67.6–98.6% public AUCs to 43.9–57.3% source-level means. Social dissemination cuts fine-tuned FakeR from 46.0% to 1.4%.
-
Latent Visual Reasoning Barely Notices When the Image Changes — ReaLVR Fixes That
Amazon/UAB study: LVR models change predictions only 5.7–13.1% when image edits flip the answer 81–86% of the time. ReaLVR hits 63.7% five-task average on Qwen2.5-VL-7B.
-
Vidu S2 Brings Real-Time 720p Interactive Avatars and Live Video Editing
Tsinghua/Shengshu’s Vidu S2: real-time 720p avatars with dynamic references, plus streaming edits (style, try-on, character/background swap). Human GSB prefers it 85.7–100% on overall quality vs top…