Stories by che_shr_cat

LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures

Review: SpikingBrain Technical Spiking Brain-Inspired Large Models

K2-Think: A Parameter-Efficient Reasoning System

Canaries in the Coal Mine? Six Facts about the Recent Employment Effects of AI

Fantastic Pretraining Optimizers and Where to Find Them

Solving the compute crisis with physics-based ASICs

Critiques of World Models

DeepConf: Scaling LLM reasoning with confidence, not just compute

V-JEPA 2: Scaling V-JEPA

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

Tversky Neural Networks

Einstein Fields: A Neural Perspective to Computational General Relativity

Tversky Neural Networks: Psychologically Plausible Deep Learning With

GEPA: Reflective prompt evolution can outperform reinforcement learning

Subliminal Learning: Language models transmit behavioral traits via hidden

AlphaGo Moment for Model Architecture Discovery

Paper FOMO and ICML 2025 Outstanding Papers

Early Signs of Steganographic Capabilities in Frontier LLMs

Musicality in Animals

Text-to-LoRA Enables On-the-Fly Model Adaptation

1
2
3
4
5