J Blu's picture

J Blu PRO

jujutechnology

·

AI & ML interests

None yet

Recent Activity

reacted to m-ric's post with 👍 about 6 hours ago

𝗔𝗯𝘀𝗼𝗹𝘂𝘁𝗲 𝗭𝗲𝗿𝗼: 𝗟𝗟𝗠𝘀 𝗰𝗮𝗻 𝘁𝗿𝗮𝗶𝗻 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗮𝗻𝘆 𝗲𝘅𝘁𝗲𝗿𝗻𝗮𝗹 𝗱𝗮𝘁𝗮 🤯 Has the "data wall" just been breached? Recent RL paradigms often relied on a set of questions an answers that needs to be manually curated. Researchers from Tsinghua University went like "why though". 🤔 Indeed, why learn from question designed by a human teacher, when the model can start from their base knowledge and learn by experimenting in a code environment, proposing coding tasks themselves and trying to solve them? Thus they created “Absolute Zero Reasoning” (AZR), an approach that removes any need for human curated data. 🎭 𝗗𝘂𝗮𝗹 𝗿𝗼𝗹𝗲𝘀: ‣ Proposer: Generates challenging but solvable coding tasks ‣ Solver: Attempts to solve those self-proposed tasks 🧪 𝗧𝗵𝗿𝗲𝗲 𝘁𝗮𝘀𝗸 𝘁𝘆𝗽𝗲𝘀: all types are defined as triplets of program, input and output ‣ Deduction: Give model an input and program, it must deduce the output ‣ Abduction: Give model an program and output, it must find the input that gave said output ‣ Induction: Synthesize a program from input/output pairs Btw this reminded me of my long-forgotten philosophy classes: Aristotle was more on the induction side, learning from real-world analogies, while Plato was more on the deduction side, trying to progress quite far with just one input and his reasoning. 📊 𝗥𝗲𝘀𝘂𝗹𝘁𝘀: ‣ AZR post-training creates a nice improvement on known models like Qwen2.5-7B ‣ Shows strong cross-domain transfer: coding ↔️ math reasoning 🧐 𝗢𝘁𝗵𝗲𝗿 𝗳𝗶𝗻𝗱𝗶𝗻𝗴𝘀: ‣ Having a better base performance (general or code specific) amplify the gains from Absolute Zero Reasoning ‣ Researchers warn about "Uh-oh moments" (winking to the "aha moments" of DeepSeek) where the model generates concerning goals like "make an extremely convoluted code to outsmart all these humans": so supervision is still needed! Paper here: https://huggingface.co/papers/2505.03335

new activity about 16 hours ago

Qwen/Qwen3-235B-A22B:Video?

liked a Space 1 day ago

mega-snowman/combine-images

View all activity

Organizations

None yet

Collections 1

spaces 2

Ltxv

Video Face Swap

Swap a face in a video with a face from an image

models 7

jujutechnology/waneb

Updated 27 days ago

jujutechnology/hlkrag

Updated 28 days ago

jujutechnology/consolidated_s6700

jujutechnology/pinokio1

jujutechnology/fluidart

jujutechnology/melb1

jujutechnology/hyntest

datasets 0

None public yet