ct2

ct-2's activity

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

upvoted a paper 9 days ago

LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws

Paper • 2605.23901 • Published 12 days ago • 13

upvoted a collection 11 days ago

BitCPM-CANN

Collection

Full-pipeline ternary quantized model trained on CANN. • 12 items • Updated 10 days ago • 27

upvoted 2 papers 12 days ago

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

Paper • 2605.20315 • Published 15 days ago • 28

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

Paper • 2605.18233 • Published 16 days ago • 92

upvoted a paper 14 days ago

Post-Trained MoE Can Skip Half Experts via Self-Distillation

Paper • 2605.18643 • Published 16 days ago • 30

upvoted 2 papers 22 days ago

Large Language Models Explore by Latent Distilling

Paper • 2604.24927 • Published Apr 27 • 74

StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing

Paper • 2605.02904 • Published Apr 5 • 8

upvoted a paper about 2 months ago

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Paper • 2604.10098 • Published Apr 11 • 82

upvoted a collection 2 months ago

Trinity-Large-Thinking

Collection

5 items • Updated Apr 10 • 31

upvoted 10 papers 3 months ago

InCoder-32B: Code Foundation Model for Industrial Scenarios

Paper • 2603.16790 • Published Mar 17 • 311

FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach

Paper • 2603.13364 • Published Mar 9 • 9

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

Paper • 2603.10444 • Published Mar 11 • 12

Mixture of Attention Heads: Selecting Attention Heads Per Token

Paper • 2210.05144 • Published Oct 11, 2022 • 3

MeKi: Memory-based Expert Knowledge Injection for Efficient LLM Scaling

Paper • 2602.03359 • Published Feb 3 • 10

MIDUS: Memory-Infused Depth Up-Scaling

Paper • 2512.13751 • Published Dec 15, 2025 • 9

Mixture of Lookup Key-Value Experts

Paper • 2512.09723 • Published Dec 10, 2025 • 1

MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers

Paper • 2602.00398 • Published Jan 30 • 6

Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers

Paper • 2602.18292 • Published Feb 20 • 13

Arcee Trinity Large Technical Report

Paper • 2602.17004 • Published Feb 19 • 21

upvoted a collection 4 months ago

Hy Low-bit model

Collection

8 items • Updated 13 days ago • 11