Heterogeneous Graph Neural Networks(HGNNs) have advanced mainly through better encoders, yet their decoding/projection stage still relies on a single shared linear head, assuming it can map rich node embeddings to labels. We call this the Linear Projection Bottleneck: in heterogeneous graphs, contextual diversity and long-tail shifts make a global head miss fine semantics, overfit hub nodes, and underserve tail nodes. While Mixture-of-Experts(MoE) could help, naively applying it clashes with structural imbalance and risks expert collapse. We propose a […]

Ver mais

Three-year-old startup Mercor has become a $10 billion middleman in AI’s data gold rush. The company connects AI labs like OpenAI and Anthropic with former employees of Goldman Sachs, McKinsey, and white-shoe law firms, paying them up to $200 an hour to share their industry expertise and train the AI models that could eventually automate their former employers out of business.   Today we’re bringing […]

Ver mais

Humanity isn’t raw clay, but a living, evolving organism shaped by deep cosmic laws. As consciousness and complexity entwine, the human mass tightens, organizes, and spiritualizes itself. Diversity must be honored, unity embraced. Any blueprint for the future that ignores these biological forces is doomed from the start.

Ver mais

Candide de Copilot In a century where dashboards replace stained glass and algorithms preach sermons, Candide wanders through clouds, Silicon Valley, Davos, and quantum labs, asking naïve yet devastating questions: If machines think for us, what remains for humans? Can optimization cheat death? Can AGI write a constitution for intentions it does not have? This tale, sharpened with irony and polished with paradox, exposes our cult of metrics, our dream of perfect convergence, and our terror of imperfection. […]

Ver mais

Abstract-style summary We introduce a closed-loop method for guiding LLM-based agents using explicit game-theoretic feedback. Agent interaction logs are transformed into structured graphs, a zero-sum attacker–defender game is solved on the graph (Nash equilibrium), and the resulting equilibrium statistics are injected back into the agent’s system prompt as a strategic control signal. Method • Automatic graph extraction from agent logs • Effort-based scoring replacing static probabilities • Nash equilibrium computation on dynamically inferred graphs • Periodic feedback into […]

Ver mais

arXiv:2601.00156v1 Announce Type: new Abstract: In this paper, we introduce an underexplored problem in facial analysis: generating and recognizing multi-attribute natural language descriptions, containing facial action units (AUs), emotional states, and age estimation, for arbitrarily selected face regions (termed FaceFocalDesc). We argue that the system’s ability to focus on individual facial areas leads to better understanding and control. To achieve this capability, we construct a new multi-attribute description dataset for arbitrarily selected face regions, providing rich region-level annotations […]

Ver mais

Clark Packard Last week, Disney+ released a restored version of The Beatles Anthology, the landmark 1995 ABC eight-part documentary series that remains the closest thing to a definitive account of the band’s extraordinary journey. I binge-watched the updated Anthology over the Thanksgiving holiday weekend, which brought back memories of watching the original with my parents 30 years ago. Now I’m the parent, though my wife and four-year-old son were less enthusiastic about the marathon viewing sessions. Last year, I […]

Ver mais

By Michael Nielsen Status: Rough and speculative working notes, very quickly written – basically, a little raw thinking and exploration. Knowledgeable corrections welcome! William James wrote a book with the marvellous title “The Varieties of Religious Experience”. I like the title because it emphasizes just how many and varied are the ways in which a human being can experience religion. And it invites followup questions, like how aliens would experience religion, whether other animals could have religious experiences, […]

Ver mais

arXiv:2601.00092v1 Announce Type: new Abstract: 4D spatial intelligence involves perceiving and processing how objects move or change over time. Humans naturally possess 4D spatial intelligence, supporting a broad spectrum of spatial reasoning abilities. To what extent can Multimodal Large Language Models (MLLMs) achieve human-level 4D spatial intelligence? In this work, we present Spatial4D-Bench, a versatile 4D spatial intelligence benchmark designed to comprehensively assess the 4D spatial reasoning abilities of MLLMs. Unlike existing spatial intelligence benchmarks that are often […]

Ver mais