Related reading
CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation
CARD is a hierarchical framework for personalized text generation that clusters users for group-specific LoRA adapters and learns individual preferences implicitly. It injects personalization at decoding via lightweight vectors and low-rank logit corrections, achieving superior quality and efficiency compared to baselines.
Hugging Face Daily Papersarxiv.org1 minpaperDecompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering
The paper presents IDSpect, a reward that uses Ideographic Description Sequences to give fine‑grained feedback on Chinese character radicals for text‑to‑image models. Experiments show it improves structural quality and semantic alignment on standard benchmarks without extra inference cost.
Hugging Face Daily Papersarxiv.org1 minpaperMiMo V2.6 models now available on AI Gateway
Vercel AI Gateway now offers three Xiaomi MiMo V2.6 models (Pro, Flash, Pro UltraSpeed) with up to 1 M token context, 1 T total parameters (42 B active per token) for Pro, 309 B total (15 B active) for Flash, and a 20× speed variant. The models support multimodal inputs and can be used via Vercel’s unified API and CLI for coding agents.
Vercelvercel.com1 minreleaseAlibaba open-sources AI model that can detect cancer and nearly 150 conditions
Alibaba's Damo Academy open-sourced Damo Radar, an AI model that detects nearly 150 abdominal conditions, including cancers, from CT scans. It achieved an average AUC of 0.913 across 146 clinical findings and outperformed most human radiologists in a comparative study.
Hacker News front pagescmp.com1 minHN15127
