Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
Paper • 2511.08577 • Published • 110 •
5
Tianyu Fu
fuvty
AI & ML interests
efficient-llm
large-language-models
sparse-attention
token-routing
latent-iterations
kv-cache
multi-llm
reasoning
inference
systems
Recent Activity
updated a dataset 40 minutes ago
fuvty/mini-opd-deepmath published a dataset about 1 hour ago
fuvty/mini-opd-deepmath upvoted a paper 4 days ago
The Latent Space: Foundation, Evolution, Mechanism, Ability, and OutlookOrganizations
commented a
paper 5 months ago
Apply for community grant: Academic project (gpu)
4
#1 opened 5 months ago
by fuvty
Apply for community grant: Academic project (gpu and storage)
#2 opened 5 months ago
by fuvty
Add `library_name` and sample usage to model card
#1 opened 6 months ago
by 
nielsr
commented a
paper 5 months ago
commented 4
papers 6 months ago
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Paper • 2510.03215 • Published • 99 •
9
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Paper • 2510.03215 • Published • 99 •
9
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Paper • 2510.03215 • Published • 99 •
9
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Paper • 2510.03215 • Published • 99 •
9
Add library name, pipeline tag and project page link
1
#1 opened 10 months ago
by nielsr
Improve dataset card: Clarify task category and add paper link
1
#2 opened 10 months ago
by nielsr
[bot] Conversion to Parquet
#1 opened 10 months ago
by 
parquet-converter
[bot] Conversion to Parquet
#1 opened 10 months ago
by parquet-converter
commented a
paper 10 months ago
Librarian Bot: Add language metadata for dataset
#2 opened almost 2 years ago
by 
librarian-bot
[bot] Conversion to Parquet
#1 opened almost 2 years ago
by parquet-converter