Thandar Aye

ohmatasesps's activity

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

upvoted a paper 2 days ago

RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems

Paper • 2609.09657 • Published 5 days ago • 5

upvoted a paper 5 days ago

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 6 days ago • 412

upvoted a paper 12 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 13 days ago • 488

upvoted a paper 19 days ago

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 28 days ago • 340

upvoted 3 papers about 1 month ago

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

Paper • 2608.11924 • Published Aug 12 • 291

The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows

Paper • 2608.06714 • Published Aug 7 • 10

CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents

Paper • 2607.25431 • Published Jul 28 • 113

upvoted 2 papers about 2 months ago

DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation

Paper • 2607.26811 • Published Jul 29 • 93

Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations

Paper • 2607.13399 • Published Jul 15 • 22

upvoted a paper 2 months ago

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

Paper • 2607.01642 • Published Jul 2 • 41

upvoted 4 papers 3 months ago

Looped World Models

Paper • 2606.18208 • Published Jun 16 • 488

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published Jun 8 • 489

Kwai Keye-VL-2.0 Technical Report

Paper • 2606.10651 • Published Jun 9 • 196

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published May 28 • 254

upvoted 6 papers 4 months ago

Xetrieval: Mechanistically Explaining Dense Retrieval

Paper • 2605.29507 • Published May 28 • 21

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Paper • 2605.11609 • Published May 12 • 196

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics

Paper • 2605.12178 • Published May 12 • 66

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published May 7 • 239

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

Paper • 2605.06130 • Published May 7 • 117

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

Paper • 2604.28196 • Published Apr 30 • 76