Articles
In-depth research, comprehensive guides, and long-form thoughts on modern technology.
CHMAS Framework Bridges Centralized Strategy and Distributed Execution in Multi-Agent RL
CHMAS introduces bidirectional coupling between strategic and tactical layers in multi-agent systems, using asynchronous updates to solve the non-stationarity problem that breaks most hierarchical approaches.
Autonomous Vehicle Drifting Emerges as Real-World Winter Safety Tool
A drift-capable MPC system shows that controlled sliding can outperform electronic stability control in real-world winter collision scenarios, with drifting emerging naturally at higher speeds.
ModPack Offers Modular Wearable Teleoperation for Bimanual Robots
ModPack introduces a backpack-based teleoperation system with plug-and-play modules for joint-level control, haptic feedback, and mobile manipulation across diverse robot platforms.
LLM Reasoning Can Collapse Decision Diversity, Study Finds
New research reveals that reasoning-mode generation in LLMs suppresses action diversity without improving accuracy, while standard SFT causes premature diversity collapse beyond what the accuracy tradeoff requires.
Stateful Guardrails for Multi-Turn LLMs Catch Hidden Risks
CRA-Bench tests LLM safety across multi-turn sessions, tracking semantic drift, sensitivity accumulation, and compliance gradients that single-turn checks miss.
Bayesian Wind Tunnels: Tiny Transformers Match Bayesian Inference
A 2.8M-parameter transformer matches the Bayesian optimum on involution model selection, but fails on arithmetic tasks with opaque symbols, even at 316M.
Input-Dependent Long Convolutions as an Attention Alternative
A new architecture uses input-dependent long convolutions to handle multi-dimensional data without the global field or rasterization tradeoffs of prior work.
Selective Fact-Checking with Evidence Chain Evaluation
ECE is a selective fact-checking framework that lets LLM verification agents abstain on weak evidence while hitting 97.8% accuracy on claims it does answer.
SysAdmin Benchmark: Power-Seeking in Frontier LLMs, Measured
The SysAdmin benchmark puts frontier LLMs in a Linux sandbox to test power-seeking across self-preservation, autonomy, resource acquisition, and concealment.
How Chinese AI Labs and Hardware Vendors Go Global at Once
Chinese AI labs, optical-module makers, and warehouse-robot vendors are taking different routes to global markets, across software, hardware, and robotics.
Splatoon Raiders Review: Nintendo's Weirdly Good Looter Shooter
PCMag's review of Splatoon Raiders says Nintendo's $49.99 Switch 2 game keeps the inking chaos of the series and ditches Turf War for solo and co-op raids.
Colossus: The Computer That Helped Win World War II
Built in secret by engineer Tommy Flowers, Colossus was the world's first large-scale programmable electronic computer — and it helped break Hitler's most secure ciphers.