minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
Paper • 2605.30263 • Published • 57
Alan
hiyata
AI & ML interests
ML applications in virus-host network prediction, synthetic genome generation, and genomic dataset design.
Recent Activity
updated a dataset 6 days ago
hiyata/Virus-Host-Genomes-updates-v2Organizations
None yet
upvoted 2
papers 9 days ago
upvoted 2
papers 12 days ago
upvoted 6
papers 16 days ago
Forecasting Scientific Progress with Artificial Intelligence
Paper • 2605.22681 • Published • 43
Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning
Paper • 2605.22642 • Published • 35
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Paper • 2605.16928 • Published • 93
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Paper • 2605.14678 • Published • 104
Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
Paper • 2605.22109 • Published • 169
TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
Paper • 2605.22355 • Published • 177
upvoted 5
papers 23 days ago
Topology-Preserving Neural Operator Learning via Hodge Decomposition
Paper • 2605.13834 • Published • 5
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Paper • 2605.06527 • Published • 44
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
Paper • 2605.14386 • Published • 60
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 111
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
Paper • 2605.13301 • Published • 159
upvoted 5
papers 26 days ago
Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon
Paper • 2605.09708 • Published • 5
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
Paper • 2605.10813 • Published • 16
Pixal3D: Pixel-Aligned 3D Generation from Images
Paper • 2605.10922 • Published • 33
Qwen-Image-2.0 Technical Report
Paper • 2605.10730 • Published • 110
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
Paper • 2605.09063 • Published • 80