Kwame Mensah

kwamemen's activity

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

upvoted 3 papers 1 day ago

Velox: Spatial Memory Makes World Models Efficient

Paper • 2610.22311 • Published 11 days ago • 38

Virtual Head Attention

Paper • 2610.17959 • Published 13 days ago • 25

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

Paper • 2610.28763 • Published 6 days ago • 29

upvoted 2 papers 2 days ago

Cache Engineering for Agents

Paper • 2610.28577 • Published 6 days ago • 158

Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation

Paper • 2610.29989 • Published 5 days ago • 172

upvoted 2 papers 3 days ago

MemT-1.0: Towards Memory-Native Evolution

Paper • 2610.26825 • Published 7 days ago • 179

OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners

Paper • 2610.24087 • Published 10 days ago • 53

upvoted 2 papers 4 days ago

DLite: History-free Speculative Decoding for Agentic AI

Paper • 2610.23787 • Published 10 days ago • 35

BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business

Paper • 2610.20424 • Published 12 days ago • 497

upvoted 2 papers 6 days ago

History Replays Itself: Unleashing Long-Context Capability in Linear Attention

Paper • 2610.15715 • Published 15 days ago • 26

More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning

Paper • 2610.19789 • Published 12 days ago • 61

upvoted 2 papers 7 days ago

One Model to Loop Them All: Elastic Latent Recurrence for Language Models

Paper • 2610.12582 • Published 18 days ago • 19

Agent-Reflex: Teaching Language Agents to Act Reflectively

Paper • 2610.17953 • Published 13 days ago • 217

upvoted a paper 12 days ago

From Prompting to Composing: A Spatial Canvas Interface for Poster Generation

Paper • 2610.12230 • Published 18 days ago • 21

upvoted a paper 13 days ago

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

Paper • 2609.38169 • Published 27 days ago • 156

upvoted 2 papers 14 days ago

Towards Looped Models Done Right, Part II: Rethinking at Fixed Points

Paper • 2610.06833 • Published 21 days ago • 35

Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning

Paper • 2609.29123 • Published Sep 24 • 8

upvoted 3 papers 15 days ago

QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models

Paper • 2609.26425 • Published 28 days ago • 23

RealtimeWAM: One-Step Asynchronous World Action Models

Paper • 2610.06617 • Published 21 days ago • 24

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

Paper • 2609.32259 • Published 27 days ago • 104