🎉 @Routerprtocl ($AIR) is bringing double rewards to #KuCoin#! 🔹 Activity 1: AIR GemSlot Carnival – Share 900,000 AIR Prize Pool 🔹 Activity 2: Learn About $AIR – 200,000 AIR Don’t miss your chance to earn more as $AIR goes live on #KuCoinSpotMarket#! 👉 Follow @Routerprtocl and @kucoincom on X or join our Discord to stay updated. #KuCoinGemSlot# #PIPEDOG# #KuCoinAffiliates# #KuListing#

26 LLM routers are secretly injecting malicious tool calls and stealing creds. One drained our client $500k wallet. We also managed to poison routers to forward traffic to us. Within several hours, we can directly take over ~400 hosts. Check our paper:

VulnCheck found a backdoor in Zbtlink routers. Chinese router maker Zbtlink then replied the code in its firmware is "solely intended for after-sales maintenance." Its download page has since pulled the affected firmware over "firmware security vulnerabilities." 👀 VulnCheck's Jacob Baines says 20+ Zbtlink models ship with a root-level implant that phones home to a hardcoded C2 with no authentication, anyone on the network path can hijack it. Stay vigilant. These routers are sold as ZBT, ZBTWiFi and Wiflyer on Amazon and Alibaba.

We desperately need a smart model router. 1. We’re seeing a model explosion: GPT-5.6, Grok 4.5, Muse Spark 1.1, GLM-5.2, and Fable 5 all launched within the past month. 2. Even for a single model family like GPT-5.6, there're 3 (Sol, Terra, Luna) and 5 reasoning-effort levels. That is far too many decisions for users to make manually. The best model should be selected automatically based on the task, latency, quality, and cost.

🧮 Are you just letting your MoE router train on vibes? This paper proposes a mathematically grounded design principle: align router rows with the principal singular direction of their expert matrices. Title: Redesign Mixture-of-Experts Routers with Manifold Power Iteration URL: 📝 Overview MoE efficiently activates only a subset of experts per input, and the router decides which experts to use. This paper argues that aligning each router row with the principal singular direction of its expert matrix better represents token-expert affinity. ❓ Challenges Solved Each router row acts as an "expert proxy" computing similarity, but there was no principled guideline for how to design that proxy vector. There was no clear principle for condensing expert information into a representative vector. 💡 Methodology & Proposed Approach ・The proposed Manifold Power Iteration (MPI) adopts a "Power-then-Retract" paradigm ・It runs power iteration on the router weights to converge toward the principal singular direction ・A retraction operation imposes norm constraints, balancing computational efficiency and training stability ・It also provides a theoretical proof that router rows converge to the principal singular directions 🎯 Use Cases It gives the routing design of large MoE LLMs a principled guideline rather than heuristics, useful when you want to improve expert utilization, such as reducing skew toward particular experts. 📊 Experimental Results ・The authors pretrained MoE models across scales from 1B to 11B parameters and verified that alignment improves effectiveness ・Aligning to the principal singular direction makes expert-activation decisions more effective As MoE becomes a standard component of large LLMs, this is a foundational contribution answering why routing should be designed a certain way. #MoE# #LLM#