PAPER PLAINE

When countries sever trade relationships, the pain is rarely equal. Using data from the entire global supply network in 2022, researchers measured how much economic damage each country would suffer from breaking ties with major partners—and found stark imbalances: the United States has leverage over all its trading partners, China over all but one, and countries on the economic periphery like Belarus face devastating losses from severing ties with neighbors while barely denting those neighbors' economies. The asymmetry stems not from trade imbalances but from a country's position in the global network: central hubs can easily find alternatives, while dependent nations cannot.

Drug-discovery AI models perform much worse than expected when tested on chemically unusual molecules, even when using supposedly rigorous evaluation methods. Researchers found that standard testing approaches hide these "structural frontier" failures — inflating measured accuracy by 87% to 130% — and that adding penalty-based safeguards to training doesn't fix the underlying problem.

Small vision-language models can match larger ones on multilingual image questions through test-time scaling, but not in the way researchers expected. The real bottleneck isn't choosing between different reasoning paths—it's simply giving the model enough tokens to finish writing its answer. Fixing how the model formats its response and doubling the thinking budget from 1,000 to 2,000 tokens recovered most gains, while elaborate verification methods added almost nothing.

Researchers tested 13 different methods for measuring how mirror-symmetric an image is, comparing traditional computer vision techniques against modern deep learning approaches. Deep learning won on harder tasks, but a classical method called HOG came surprisingly close while running 300 times faster on standard computers—suggesting that for practical symmetry measurement, the speed advantage of classical methods may outweigh deep learning's modest performance gains.

When Bitcoin and Ethereum futures markets are about to change character—from stable to stressed, or vice versa—the current state of the order book is far more predictive than what's actually being bought and sold. A model based only on order-book snapshots beat interpretable trading models, and adding trade flow helped only modestly for Bitcoin and inconsistently for Ethereum, suggesting market microstructure models should start with liquidity state, not order flow.

A two-agent system won a competition for answering trivia questions with both text and images by learning to judge its own confidence. The key insight: instead of trying to be right about everything, one agent learned when to answer risky questions fast (Tossup rounds) while the other focused on getting the exact answer correct when time wasn't critical (Bonus rounds)—achieving the highest overall score without needing large model ensembles or search tools.

Physicists discovered that certain quantum detectors fail catastrophically when they cross the edge of a black hole, producing mathematical infinities that can't be resolved. The breakdown happens specifically when detectors measure nonlinear properties like momentum or energy density, suggesting the popular "firewall" model of black hole boundaries may be fundamentally incompatible with how these detectors work.

Researchers have discovered how to plant hidden backdoors in neural networks that are mathematically invisible — even when someone inspects the entire trained model with complete access. Someone with this backdoor can instantly break the network's security, while people trying to attack the model without the backdoor would need longer than the age of the universe to do the same thing.

Researchers created SLORR, a lightweight method that nudges neural networks toward simpler, more compressible structures during training—without requiring expensive mathematical operations or architectural changes. When tested on image recognition and large language models, SLORR let researchers compress models by significant amounts while keeping performance intact and adding less than 1% to training time.

Raft is a popular system for coordinating data across multiple computers, but it assumes failures are honest mistakes—it can't handle nodes that deliberately forge elections or tamper with data. Researchers added a trust-and-reputation layer that tracks each node's behavior, penalizes dishonest actions, and blocks untrustworthy nodes from leadership. In testing with 40% malicious nodes, the system kept bad leaders below 5% while losing less than 10% speed.

Mathematicians have proven sharp bounds on how well stochastic methods can approximate solutions to convex optimization problems—the kind used constantly in machine learning and engineering. The work uses a technique called radial dominance to show exactly how the error shrinks as you add more random samples, and proves these rates are the best possible.

Researchers created a new dataset and video generation model that teaches AI systems to solve reasoning problems by generating sequences of video frames rather than text explanations. The model, called Wan-CoF, substantially outperformed existing video generators on four reasoning benchmarks by learning from diverse examples of visual problem-solving and using special tokens to track reasoning across frames.