AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation
Cross-Scale Transfer Learning for Depression Severity Prediction: From PHQ-8 to HAMD-17 Across Languages and Clinical Paradigms
Viggle/Qwen-Image-2.1-viggle-turbo — new model trending #30 on Hugging Face
9 sources 15 min
LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models
LoRA-generating hypernetworks for efficient on-device LLM generative personalization
ACLArena: Agent Continue Learning in Multi-stage Post-training
Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models
Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM
LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys
Mothersuperior/yue2-mothersuperior-realaudio-tokenizer-v4 — new model trending #30 on Hugging Face
9 min
Show HN: MultiMatte, a Promptable Image Background Removal Model
5 min1
Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
1
Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation
1
Edge0/Edge0-35B-A3B-preview — new model trending #30 on Hugging Face
4 min
Continual Learning Mechanisms Compose for Long-Horizon Memorization
1
Alissonerdx/Minimax-H3-ComfyUI — new model trending #30 on Hugging Face
5 min2
OpenVDN/vdn-minimax-h3 — new model trending #12 on Hugging Face
5 min1