guhao

marcusguhao's activity

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

updated a collection 8 days ago

indexmem

Collection

4 items • Updated 8 days ago

updated a model 8 days ago

marcusguhao/Qwen3-4B-gate-IndexMem-rvkl16k-local128-b256-decay

Updated 8 days ago

published a model 8 days ago

marcusguhao/Qwen3-4B-gate-IndexMem-rvkl16k-local128-b256-decay

Updated 8 days ago

updated a collection 8 days ago

indexmem

Collection

4 items • Updated 8 days ago

updated a model 8 days ago

marcusguhao/Qwen-3-8B-gqa_indexer_scalar-rvkl_16k_local128_b256_decay

Updated 8 days ago

published a model 8 days ago

marcusguhao/Qwen-3-8B-gqa_indexer_scalar-rvkl_16k_local128_b256_decay

Updated 8 days ago

updated a collection 8 days ago

indexmem

Collection

4 items • Updated 8 days ago

updated a model 8 days ago

marcusguhao/Qwen3-8B-gate-IndexMem

Updated 8 days ago

published a model 8 days ago

marcusguhao/Qwen3-8B-gate-IndexMem

Updated 8 days ago

upvoted a paper 11 days ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published 14 days ago • 65

upvoted 2 papers 14 days ago

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

Paper • 2609.06702 • Published 19 days ago • 26

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

Paper • 2609.11042 • Published 15 days ago • 63

updated a collection about 1 month ago

indexmem

Collection

4 items • Updated 8 days ago

updated a model about 1 month ago

marcusguhao/Qwen-3-8B-gqa_indexer_scalar-stage1

Updated Aug 17

published a model about 1 month ago

marcusguhao/Qwen-3-8B-gqa_indexer_scalar-stage1

Updated Aug 17

upvoted a paper 2 months ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published Mar 12 • 69

authored 3 papers 2 months ago

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published Jul 3 • 85

IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference

Paper • 2605.25475 • Published May 25

Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging

Paper • 2506.23266 • Published Jun 29, 2025 • 1

upvoted a paper 3 months ago

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published Jul 3 • 85