Aditi Rao

araochihiro's activity

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

upvoted 2 papers 1 day ago

Smaller Models, Better Rejects: Preference Distillation Scaling

Paper • 2609.38987 • Published 8 days ago • 28

CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning

Paper • 2609.36820 • Published 9 days ago • 39

upvoted 2 papers 2 days ago

DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation

Paper • 2609.33711 • Published 11 days ago • 19

The Low-Rank Structure of VLA Reinforcement Learning

Paper • 2609.34599 • Published 10 days ago • 21

upvoted 2 papers 3 days ago

ROSS: Relearning from Self-Generated Rollouts through Selective Supervision

Paper • 2609.35954 • Published 10 days ago • 50

Scaling Properties of Same-Family On-Policy Distillation

Paper • 2609.32722 • Published 12 days ago • 324

upvoted 2 papers 6 days ago

Learning to Learn from Context: Synthetic Training from Perturbed Public Documents

Paper • 2609.33642 • Published 11 days ago • 32

Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers

Paper • 2609.32814 • Published 12 days ago • 22

upvoted a paper 8 days ago

Training Object Permanence in World Models

Paper • 2609.28654 • Published 15 days ago • 243

upvoted 4 papers 9 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 496

Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models

Paper • 2609.26637 • Published 16 days ago • 26

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

Paper • 2609.27334 • Published 15 days ago • 56

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

Paper • 2609.23038 • Published 19 days ago • 63

upvoted a paper 13 days ago

The Functionalizer: Lossless Functional Decomposition for Subword Tokenization

Paper • 2609.15991 • Published 20 days ago • 17

upvoted a paper 14 days ago

MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads

Paper • 2609.09206 • Published Sep 5 • 11

upvoted a paper 15 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 21 days ago • 139

upvoted a paper 16 days ago

A Zeroth-Order Paradigm for LLM Preference Alignment

Paper • 2609.19144 • Published 22 days ago • 32