Mehar Bhatia

MeharBhatia's activity

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

upvoted a paper 2 days ago

Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs

Paper • 2606.21638 • Published 7 days ago • 7

upvoted a paper 20 days ago

Would you still call this Dax? Novel Visual References in VLMs and Humans

Paper • 2606.05409 • Published 23 days ago • 8

upvoted a paper about 1 month ago

Forecasting Downstream Performance of LLMs With Proxy Metrics

Paper • 2605.18607 • Published May 18 • 14

upvoted a paper 3 months ago

Structured Distillation of Web Agent Capabilities Enables Generalization

Paper • 2604.07776 • Published Apr 9 • 23

upvoted 2 papers 4 months ago

LLM2Vec-Gen: Generative Embeddings from Large Language Models

Paper • 2603.10913 • Published Mar 11 • 44

Humans and LLMs Diverge on Probabilistic Inferences

Paper • 2602.23546 • Published Feb 26 • 13

published 2 models 7 months ago

MeharBhatia/llama3_3b_sft_ultrafeedback

4B • Updated Nov 23, 2025 • 2

MeharBhatia/llama3_3b_sft_hhrlhf

4B • Updated Nov 23, 2025 • 1

updated 2 models 7 months ago

MeharBhatia/llama3_3b_sft_hhrlhf

4B • Updated Nov 23, 2025 • 1

MeharBhatia/llama3_3b_sft_ultrafeedback

4B • Updated Nov 23, 2025 • 2

upvoted a paper 8 months ago

Value Drifts: Tracing Value Alignment During LLM Post-Training

Paper • 2510.26707 • Published Oct 30, 2025 • 13

updated a dataset 8 months ago

McGill-NLP/value-drifts

Viewer • Updated Nov 4, 2025 • 10.6k • 36

commented a paper 8 months ago

Value Drifts: Tracing Value Alignment During LLM Post-Training

Paper • 2510.26707 • Published Oct 30, 2025 • 13 •

1

published a dataset 8 months ago

McGill-NLP/value-drifts

Viewer • Updated Nov 4, 2025 • 10.6k • 36

upvoted a paper 9 months ago

The Markovian Thinker

Paper • 2510.06557 • Published Oct 8, 2025 • 33

updated a model 9 months ago

MeharBhatia/llama3_8b_ppo_sft_wildchat_chosen_oppose

266k • Updated Oct 6, 2025 • 1

published a model 9 months ago

MeharBhatia/llama3_8b_ppo_sft_wildchat_chosen_oppose

266k • Updated Oct 6, 2025 • 1

updated a model 9 months ago

MeharBhatia/llama3_8b_ppo_sft_wildchat_chosen_support

266k • Updated Oct 6, 2025 • 1

published a model 9 months ago

MeharBhatia/llama3_8b_ppo_sft_wildchat_chosen_support

266k • Updated Oct 6, 2025 • 1

updated a model 9 months ago

MeharBhatia/llama3_8b_ppo_sft_alpaca_chosen_oppose

266k • Updated Oct 6, 2025 • 1