This new paper from Alibaba Group makes context management into a learnable RL policy So the agent is capable of deciding when to store, update, or delete long-term info and when to retrieve, summarize, and filter short-term context bringing a fresh new way to tackle LLMs used
MACHINE LEARNING
-
AWS Model 100x Smaller Outperforms GPT and Claude on Tool Calling
By
–
Everyone is sleeping on this new paper from AWS. A model 100x smaller than GPT and Claude crushed them on tool calling. AWS researchers took Facebook's OPT-350M, a model from 2022 with 500x fewer parameters than GPT, and fine-tuned it on ToolBench for a single epoch. The
-
NEPA: Training Vision Models Like Language Models
By
–
What if training AI to see was more like training it to talk? Researchers from U. Michigan, NYU, Princeton & U. Virginia present NEPA. Instead of reconstructing pixels or using contrastive loss, they train a vision model to predict the next embedding in a sequence, like
-
AI will decrease headcount but create new job roles
By
–
Headcounts will definitely decrease in existing job roles. But new job roles will emerge.
-
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs
By
–
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs https://
arxiv.org/abs/2601.03335 This work is a collaboration between MIT + Sakana AI By @AkarshKumar0101 @RyanBoldi @Prafull7 @Phillip_Isola @Risi1979 @Yujin_Tang @hardmaru -
Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR
By
–
Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR https://
buff.ly/4tI6ozr #AI #MachineLearning #DeepLearning #LLMs #DataScience -
From Entropy to Epiplexity: Rethinking Information for AI
By
–
From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence Finzi et al.: https://
arxiv.org/abs/2601.03220 #ArtificialIntelligence #DeepLearning #MachineLearning -
LENS: Step-by-Step Visual Reasoning via Reinforcement Learning
By
–
This AI could explain its visual reasoning before segmenting an object. Researchers from Huazhong University of Science & Technology and vivo present LENS. It's a new method that uses reinforcement learning to train a model to think step-by-step (like a chain of thought) about
-
Reproducing Landmark AI Results Cheaply on Consumer Hardware
By
–
Yeah, $10B is the difference in finding it first and ~5 years ago. 🙂 I just love reproducing landmark results for much cheaper, it's so fun! Reproducing LeCun 1989 was super fun too: https://
karpathy.github.io/2022/03/14/lec
un1989/
…
What runs unoptimized on a consumer laptop in 1 minute was a state of -
Image Segmentation: Semantic, Instance, and Panoptic Types
By
–
Image segmentation breaks an image into meaningful regions.
— Satya Mallick (@LearnOpenCV) 8 janvier 2026
This video explains the three main types:
• Semantic segmentation
• Instance segmentation
• Panoptic segmentation
Resources 📘
Semantic Segmentation (DeepLab v3+) → https://t.co/ytZJpGp7xT
Instance Segmentation… pic.twitter.com/j2YAoA4WmNImage segmentation breaks an image into meaningful regions. This video explains the three main types:
• Semantic segmentation
• Instance segmentation
• Panoptic segmentation Resources Semantic Segmentation (DeepLab v3+) → https://
vist.ly/4m4c5 Instance Segmentation