Bohan Sun

Bohansss's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset 5 days ago

startlux-models/DecisionPivot

Preview • Updated 6 days ago • 1.07k • 6

upvoted a paper 5 days ago

DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems

Paper • 2610.28522 • Published 7 days ago • 74

New activity in startlux-models/ReaDy-Qwen3.8-27B 7 days ago

Add pipeline tag and link to paper

#1 opened 7 days ago by

nielsr

authored 4 papers 8 days ago

ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models

Paper • 2610.20503 • Published 13 days ago • 9

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

Paper • 2608.12149 • Published Aug 12 • 30

SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference

Paper • 2604.22575 • Published Apr 24 • 1

SpikingBrain Technical Report: Spiking Brain-inspired Large Models

Paper • 2509.05276 • Published Sep 5, 2025 • 5

upvoted 2 papers 9 days ago

ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models

Paper • 2610.20503 • Published 13 days ago • 9

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

Paper • 2610.17309 • Published 15 days ago • 81

liked a model 12 days ago

startlux-models/ReaDy-Qwen3.8-27B

Text Generation • 2B • Updated 7 days ago • 115 • 4

updated a model 12 days ago

startlux-models/ReaDy-Qwen3.8-27B

Text Generation • 2B • Updated 7 days ago • 115 • 4

published a model 12 days ago

startlux-models/ReaDy-Qwen3.8-27B

Text Generation • 2B • Updated 7 days ago • 115 • 4

upvoted a paper 26 days ago

FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution

Paper • 2609.36651 • Published 28 days ago • 34

upvoted a collection 27 days ago

StartLux-Decision-v1

Collection

Typed decision models from 0.8B to 27B. Every question comes back with a probability for each option. • 21 items • Updated 16 days ago • 12

liked a model about 1 month ago

BAAI/Brainmu-Spike

Updated Sep 16 • 341 • 11

upvoted a paper 2 months ago

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

Paper • 2608.12149 • Published Aug 12 • 30

upvoted a paper 5 months ago

ICA Lens: Interpreting Language Models Without Training Another Dictionary

Paper • 2606.11722 • Published Jun 10 • 18

upvoted a collection 5 months ago

Hybrid Linear Attention Research

Collection

All 1.3B & 340M hybrid linear-attention experiments. • 62 items • Updated Sep 11, 2025 • 15

liked a dataset over 1 year ago

GTSinger/GTSinger

Viewer • Updated Feb 9, 2025 • 69 • 34.4k • 41