जीवितो धर्ममासाद्य रामात्सत्यपराक्रमात्॥ Mahabharata CE 12.149.62
"It has been heard that Rama, truthful in his valour, killed the shudra Shambuka, resorted to dharma, and brought a brahmana child back to life."
The Sambuka episode of Ramayana cannot be a medieval or modern creation as it is cited as a popular story in Mahabharata.
In the Grdhra Gomayu samvada (dialogue between vulture and jackal) in Apaddharma-parva, the jackal mentions the killing of Sambuka by Sri Rama.
The Pandits knew much better Skt then he did. But don't try to fool us that they knew a better, non-casteist reading of the Sastras. It is their kind (think of Swami Karpatri, Puri Sankaracarya) who inserted the Sambhuka story into the Ramayana to justify the starkest casteism. https://t.co/zhuIAtyd00
— Koenraad Elst (@Koenraad_Elst) November 23, 2021
जीवितो धर्ममासाद्य रामात्सत्यपराक्रमात्॥ Mahabharata CE 12.149.62
"It has been heard that Rama, truthful in his valour, killed the shudra Shambuka, resorted to dharma, and brought a brahmana child back to life."
As per Ramayana, Sambuka wanted to reach the heaven in his physical body and become a deva.
तपश्चकार दुर्बुद्धिरिच्छन् माहेश्वरं पदम् ।
अनन्यवध्यं तं तस्माज्जघान पुरुषोत्तमः॥ Mahabharata Tatparya Nirnaya 9.21
More from All
How can we use language supervision to learn better visual representations for robotics?
Introducing Voltron: Language-Driven Representation Learning for Robotics!
Paper: https://t.co/gIsRPtSjKz
Models: https://t.co/NOB3cpATYG
Evaluation: https://t.co/aOzQu95J8z
🧵👇(1 / 12)
Videos of humans performing everyday tasks (Something-Something-v2, Ego4D) offer a rich and diverse resource for learning representations for robotic manipulation.
Yet, an underused part of these datasets are the rich, natural language annotations accompanying each video. (2/12)
The Voltron framework offers a simple way to use language supervision to shape representation learning, building off of prior work in representations for robotics like MVP (https://t.co/Pb0mk9hb4i) and R3M (https://t.co/o2Fkc3fP0e).
The secret is *balance* (3/12)
Starting with a masked autoencoder over frames from these video clips, make a choice:
1) Condition on language and improve our ability to reconstruct the scene.
2) Generate language given the visual representation and improve our ability to describe what's happening. (4/12)
By trading off *conditioning* and *generation* we show that we can learn 1) better representations than prior methods, and 2) explicitly shape the balance of low and high-level features captured.
Why is the ability to shape this balance important? (5/12)
Introducing Voltron: Language-Driven Representation Learning for Robotics!
Paper: https://t.co/gIsRPtSjKz
Models: https://t.co/NOB3cpATYG
Evaluation: https://t.co/aOzQu95J8z
🧵👇(1 / 12)
Videos of humans performing everyday tasks (Something-Something-v2, Ego4D) offer a rich and diverse resource for learning representations for robotic manipulation.
Yet, an underused part of these datasets are the rich, natural language annotations accompanying each video. (2/12)
The Voltron framework offers a simple way to use language supervision to shape representation learning, building off of prior work in representations for robotics like MVP (https://t.co/Pb0mk9hb4i) and R3M (https://t.co/o2Fkc3fP0e).
The secret is *balance* (3/12)
Starting with a masked autoencoder over frames from these video clips, make a choice:
1) Condition on language and improve our ability to reconstruct the scene.
2) Generate language given the visual representation and improve our ability to describe what's happening. (4/12)
By trading off *conditioning* and *generation* we show that we can learn 1) better representations than prior methods, and 2) explicitly shape the balance of low and high-level features captured.
Why is the ability to shape this balance important? (5/12)
