Ziyang
@keyon_zzy
Followers
18
Following
1K
Media
3
Statuses
97
RT @Google: Here’s what’s new for Gemini 2.5 🧵. 2.5 Flash and 2.5 Pro are now stable and generally available in AI Studio, Vertex AI and th….
0
290
0
RT @ddvd233: Thanks @iScienceLuvr for posting about our recent work! . We're excited to introduce QoQ-Med, a multimodal medical foundation….
0
15
0
RT @ddvd233: Excited to share our latest benchmark: CLIMB, where we built a solid data foundation for multimodal clinical models. With 4.51….
0
8
0
RT @HennyJieCC: Introducing TIMER⌛️: a temporal instruction modeling and evaluation framework for longitudinal clinical records! 🏥📈. TIMER….
0
8
0
RT @InceptionAILabs: We are excited to introduce Mercury, the first commercial-grade diffusion large language model (dLLM)! dLLMs push the….
0
991
0
RT @HennyJieCC: We build 𝗠𝗲𝗱𝗛𝗘𝗟𝗠✨: a comprehensive benchmark evaluating AI on realistic clinical tasks that healthcare professionals perfor….
0
5
0
RT @ddvd233: There's nothing that shouts 'pre-training is hitting a wall' more than OpenAI releasing a huge GPT-4.5 model and it not lookin….
0
1
0
RT @omarsar0: Say goodbye to Chain-of-Thought. Say hello to Chain-of-Draft. To address the issue of latency in reasoning LLMs, this work….
0
381
0
RT @xwang_lk: DeepSeek R1 is a great breakthrough for large reasoning models. But how safe is R1 compared to well-prepared o3-mini? Does it….
0
1
0
RT @zhou_xian_: Everything you love about generative models — now powered by real physics!. Announcing the Genesis project — after a 24-mon….
0
3K
0
RT @steph_milani: 🇨🇦 Hi! I’m attending my last @NeurIPSConf as a PhD student, presenting Patient-Ψ at a few workshops. I'm on the job mark….
0
31
0
RT @HennyJieCC: Excited to present two papers at #NeurIPS 2024 this week! Stop by our posters if you're interested in LLMs, graphs, or heal….
0
8
0
RT @SwatiRajwal: Excited to share I'll be attending @NeurIPSConf 2024! I also have one poster presentation accepted:. 📝 What can 1.5 Millio….
0
2
0
interesting!.
🚨 So, why do we need weight decay in modern deep learning? 🚨. The camera-ready version of our NeurIPS 2024 paper is now on arXiv (a major update compared to the first version). Weight decay is traditionally viewed as a regularization method, but its effect in the overtraining
0
0
0