Sleeping
Agents
GRPO Reward Hacking Demo
🎯
Reward-hacked vs KL-regularised GRPO, side by side
Rohan Jain PRO
rohanjain2312
·
AI & ML interests
None yet
Recent Activity
updated a Space 5 days ago
rohanjain2312/grpo-reward-hacking-demo updated a model 5 days ago
rohanjain2312/grpo-reward-hacking-fixed-cap-qwen05b updated a model 5 days ago
rohanjain2312/grpo-reward-hacking-fixed-kl-qwen05bOrganizations
spaces 11
Paused
Agents
Candlestick Pattern Detector
📈
YOLO candlestick pattern detector + honest signal test
Paused
Agents
forecast_bench — AI vs Classical Forecasting
📉
Classical statistics vs AI foundation models
Sleeping
Agents
Self-Healing Code Agent
🚀
Autonomous agent that self-heals Python code errors.
No application file
Agents
Toolsmith Demo
🌖
Sleeping
Agents
FinCompress
🗜
FinBERT compression via KD, INT8 quant, and pruning
models 10
rohanjain2312/grpo-reward-hacking-fixed-cap-qwen05b
Text Generation • 0.5B • Updated • 186
rohanjain2312/grpo-reward-hacking-fixed-kl-qwen05b
Text Generation • 0.5B • Updated • 523
rohanjain2312/grpo-reward-hacked-sentiment-qwen05b
Text Generation • 0.5B • Updated • 541
rohanjain2312/candlestick-pattern-recognition-system-yolo
Object Detection • Updated • 650
rohanjain2312/forecastbench-chronos
Time Series Forecasting • Updated • 476
rohanjain2312/toolsmith-qwen3-4b
Updated
rohanjain2312/graphbench-gat-checkpoint
Updated
rohanjain2312/FinCompress_student
Updated
rohanjain2312/distilbert-mood-classifier
67M • Updated • 6
rohanjain2312/medical-mistral-7b
Text Generation • 7B • Updated • 4