January 2026

An in-depth look at database and cache internals, and the tradeoffs in each. ScyllaDB would like to publicly acknowledge dormando (Memcached maintainer) and Danny Kopping for their contributions to this project, as well as thank them for their support and patience. Engineers behind ScyllaDB – the database for predictable performance at scale – joined forces with Memcached maintainer dormando to compare both technologies head-to-head, in a collaborative vendor-neutral way. The results reveal that: Both Memcached and ScyllaDB maximized disks and network bandwidth […]

Ver mais

For most of the internet era, educational technology followed a familiar pattern: digitize the textbook, put worksheets on a screen, maybe add a video. The goal was efficiency. Faster distribution. Easier grading. More content, more quickly. But that model is starting to feel dated. Today’s learners don’t just want information delivered. They expect to interact with it. Remix it. Build on top of it. The question is no longer whether technology belongs in education; it’s whether our education […]

Ver mais

To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards that are commonly known as the fully cooperative setting. However, global rewards are usually noisy because they contain the contributions of all agents, which have to be resolved in the credit assignment process. On the other hand, using local reward benefits from faster learning due to the separation of agents’ contributions, but can be suboptimal as agents myopically […]

Ver mais

Many-Task Learning refers to the setting where a large number of related tasks need to be learned, the exact relationships between tasks are not known. We introduce the Cascaded Transfer Learning, a novel many-task transfer learning paradigm where information (e.g. model parameters) cascades hierarchically through tasks that are learned by individual models of the same class, while respecting given budget constraints. The cascade is organized as a rooted tree that specifies the order in which tasks are learned […]

Ver mais

Compositional reasoning is an important frontier for truly intelligent systems. While brute-force scaling has brought us far, the next leap in AI will come from models that don’t just memorize, but compose their existing knowledge to solve novel, complex problems! I am incredibly excited to share our latest research that addresses this head-on: Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning (https://arxiv.org/abs/2601.15160). 🚀 The core issue we tackle is reward design and assignment. Most RL-on-LLMs […]

Ver mais

Key results: – Takes 1M base pairs of DNA as input, predicts thousands of functional genomic tracks at single-base-pair resolution – Matches or exceeds best specialized models in 25 of 26 variant effect prediction evaluations – U-Net backbone with CNN + transformer layers, trained on human and mouse genomes – 1Mb context captures 99% of validated enhancer-gene pairs – Training took 4 hours (half the compute of Enformer) on TPUv3, inference under 1 second on H100 – Demonstrates […]

Ver mais

Victoria, Seychelles, January 29, 2026 MEXC, the fastest-growing global cryptocurrency exchange, redefining a user-first approach to digital assets through true zero-fee trading, today reported significant growth in precious metals futures trading, with gold futures market share reaching 47% on January 25, 2026, and single-day trading volume hitting $555 million. MEXC’s GOLD Futures market share grew from 2.4% in early December 2025 to 47% by January 25, 2026—a 20-fold increase over two months. The platform surpassed competitors to capture […]

Ver mais

Victoria, Seychelles, January 29, 2026 MEXC, the fastest-growing global cryptocurrency exchange, redefining a user-first approach to digital assets through true Zero-Fee trading, today released its 2025 Zero-Fee Strategy Annual Report. The ongoing commitment not only saved users a total of 1.1 billion USDT in fees but also bolsters both mainstream growth and emerging asset visibility, driving balanced development across the entire crypto landscape. The platform’s removal of fees across 3,026 spot trading pairs and 203 futures pairs resulted […]

Ver mais

Byline: Keith Belanger AI projects have a way of surfacing data problems that data teams used to be able to work around. That’s because analytical data allowed for a wide margin of error, and AI simply doesn’t. AI models don’t tolerate ambiguity, and decisions made at machine speed magnify every flaw hiding upstream. What once failed quietly now fails loudly, and often publicly. AI failures are often dismissed as experimental growing pains. In reality, they’re revealing the weakness […]

Ver mais