Sining H

husining's activity

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

liked a dataset about 18 hours ago

Visionarys/kvcache

Updated Jan 26 • 129 • 10

upvoted 2 papers about 18 hours ago

DLoop: Looped Speculative Decoding

Paper • 2610.07659 • Published 8 days ago • 15

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Paper • 2609.38169 • Published 15 days ago • 131

liked 3 models 1 day ago

position-specialist-speculative-decoding/llama2-13b-chat-poss2

Updated Aug 29, 2025 • 81 • 8

KVCache-ai/DeepSeek-R1-GGML-FP8-Hybrid

Updated Mar 4, 2025 • 22

KVCache-ai/Qwen3-30BA3B-GGUF

31B • Updated Apr 29, 2025 • 105 • 12

upvoted a paper 1 day ago

Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute

Paper • 2610.10845 • Published 7 days ago • 11

liked a dataset 3 days ago

ihbkaiser/korean-speculative-decoding-table1-bundle

Updated 5 days ago • 80 • 4

liked a model 3 days ago

CedricHwang/qwen2.5-0.5b-modelopt-pruning-gradnas

0.3B • Updated Dec 28, 2025 • 14 • 7

upvoted 2 papers 3 days ago

Learning Functional Subspaces for Neural Network Compression

Paper • 2609.40127 • Published 14 days ago • 25

HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing

Paper • 2610.05842 • Published 9 days ago • 13

liked 3 models 4 days ago

position-specialist-speculative-decoding/Speed-E3-Llama3.1-8B-Instruct-vllm

0.9B • Updated Jan 28 • 86 • 6

position-specialist-speculative-decoding/llama2-13b-chat-poss3

Updated Aug 29, 2025 • 78 • 6

KVCache-ai/DeepSeek-V3-GGML-FP8-Hybrid

Updated Feb 24, 2025 • 10

upvoted a paper 4 days ago

Multilinguality in Hybrid Attention LLMs

Paper • 2609.35378 • Published 16 days ago • 11

liked 3 models 5 days ago

position-specialist-speculative-decoding/llama3-8b-instruct-poss3

Updated Aug 29, 2025 • 23 • 7

xformAI/opt-6.7b-ub-16-qcqa-best-for-KV-cache

Updated Jan 24, 2024 • 9

Lapisbird/cob-pruning-models

Updated Nov 19, 2025 • 9

upvoted a paper 5 days ago

ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context

Paper • 2609.36684 • Published 15 days ago • 20

liked a dataset 7 days ago

open-llm-leaderboard-old/details_saarvajanik__facebook-opt-6.7b-gqa-ub-16-best-for-KV-cache

Updated Jan 28, 2024 • 553 • 9