The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 168
नेहा गुप्ता
Rnair1999
·
AI & ML interests
Working on AI projects: transformers, datasets and fine-tuning.
Recent Activity
upvoted a paper 24 days ago
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems updated a model about 1 month ago
Rnair1999/efficient-attention-analysisOrganizations
None yet
upvoted 2
papers 24 days ago
upvoted 4
papers about 1 month ago
Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations
Paper • 2609.32522 • Published • 22
PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation
Paper • 2609.34759 • Published • 34
Raven: The Harness of Harnesses for Composable Agentic Intelligence
Paper • 2609.33439 • Published • 101
In-Context Learning for Robots: Methods and Applications
Paper • 2609.36012 • Published • 91