#representation-learning 2 items 19 авг S²VOPD: self-supervised visual on-policy distillation lifts Qwen3.5-4B from 70.7% to 77.4% on six fine-grained perception benchmarks UC San Diego research 28 июн ViQ: Text-Aligned Visual Quantized Representations at Any Resolution (ECCV 2026) Tencent Hunyuan research