Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
zunhai  submitted a paper about 11 hours ago
ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
zunhai  authored a paper 1 day ago
ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
Bohansss  authored a paper 1 day ago
ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
View all activity

Papers

StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions

Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

View all Papers

startlux-models 's collections 4

StartLux-Decision-v1.1 AutoThink
v1.1, October 2026. Read-or-Think: one-pass answer, a short thought only when unsure. 4B, 9B, 27B.
StartLux-Decision-v1.1 Instant
v1.1, October 2026. Typed decisions in one forward pass: a probability for every option. 0.8B to 27B.
Massive Activations in Hybrid Linear Attention Models
Official PAS, ISP, gating-ablation, and scale-study checkpoints for Massive Activations in Hybrid Linear Attention Models.
StartLux-Decision-v1.1 AutoThink
v1.1, October 2026. Read-or-Think: one-pass answer, a short thought only when unsure. 4B, 9B, 27B.
StartLux-Decision-v1.1 Instant
v1.1, October 2026. Typed decisions in one forward pass: a probability for every option. 0.8B to 27B.
Massive Activations in Hybrid Linear Attention Models
Official PAS, ISP, gating-ablation, and scale-study checkpoints for Massive Activations in Hybrid Linear Attention Models.