ROOT: Robust Orthogonalized Optimizer for Neural Network Training Huawei Noah's Ark Lab
Paper: https://
arxiv.org/abs/2511.20626
Code: https://
github.com/huawei-noah/no
ah-research/tree/master/ROOT
… Our report: https://
mp.weixin.qq.com/s/X7dNh8lwr0xV
W7TsuO4D2g
…
@jiqizhixin
-
ROOT: Robust Orthogonalized Optimizer for Neural Network Training
By
–
-
Huawei ROOT: Robust Orthogonalized Optimizer for LLM Training
By
–
This new optimizer can make training giant LLMs both more stable and more precise, even under noise and extreme scale! Huawei just introduces ROOT, a Robust Orthogonalized Optimizer that tackles two big weaknesses in recent momentum-orthogonalized methods: – Dimensional
-
Faster R-CNN Wins NeurIPS Test of Time Paper Award
By
–
Congratulations to Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun! Their paper “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” has been awarded the Test of Time Paper Award at NeurIPS 2025. The Faster R-CNN paper has been cited more than
-
ReSeek: Self-Correcting Search Agents with Dense Rewards
By
–
Search agents could notice their own mistakes and fix their reasoning mid-trajectory. ReSeek enables exactly that. With a JUDGE action for on the fly self correction and dense rewards for factual correctness plus real utility, it trains agents that outperform SOTA on complex
-
ScaleNet: Scaling Vision Transformers with Weight Sharing
By
–
What if you could scale up a ViT in minutes instead of training a giant one from scratch? ScaleNet makes it possible by inserting weight shared layers into pretrained ViTs with tiny adapter adjustments. It expands depth with almost no extra parameters, boosts a 2x depth DeiT
-
AI Agents Achieve Direct Mind-to-Mind Communication Framework
By
–
AI agents could skip language entirely and communicate mind to mind. This work introduces thought communication, a latent variable framework that identifies shared and private thoughts across agents and recovers the global structure of who shares what. The approach extracts
-
Vision Language Models Parse Floor Plan Maps Successfully
By
–
Vision Language Models Can Parse Floor Plan Maps! Paper: https://
arxiv.org/abs/2409.12842
Site: https://
sites.google.com/view/vlm-floor
plan/
… -
Rolling Forcing Enables Sharp, Coherent Long-Horizon Video Generation
By
–
AI can stream videos that stay sharp and coherent for minutes.
— 机器之心 JIQIZHIXIN (@jiqizhixin) 9 novembre 2025
Meet Rolling Forcing—a new technique for long-horizon video generation that slashes error accumulation.
It denoises multiple frames jointly, anchors long-term context via an attention sink, and trains efficiently… pic.twitter.com/E7QitWyGrDAI can stream videos that stay sharp and coherent for minutes. Meet Rolling Forcing—a new technique for long-horizon video generation that slashes error accumulation. It denoises multiple frames jointly, anchors long-term context via an attention sink, and trains efficiently
-
AI-Trader: Five AI Models Compete Autonomously in Market Trading
By
–
AI-Trader enables five distinct AI models, each employing unique investment strategies, to compete autonomously in the same market and determine which can generate the highest profits in NASDAQ 100 or SSE 50 trading! 9k stars already! AI-Trader: Can AI Beat the Market?
-
PhysToolBench: Testing MLLMs’ Physical Tool Understanding
By
–
Can AI truly understand tools like humans do? Researchers introduce PhysToolBench, the first benchmark testing MLLMs’ grasp of physical tools—from recognizing and explaining how they work to creatively inventing new ones when none are available. Tests on 32 leading models show