PAPER PLAINE

Researchers created a system that generates realistic driving behavior in simulations while letting engineers adjust how aggressive, safe, or compliant individual cars are—without sacrificing realism. The method learns what a driver's typical behavior looks like, then allows fine-grained control along specific axes like speed or caution, something existing systems struggle to do.

Trend following—a strategy that has reliably made money for 200 years by betting on price movements—abruptly broke down around 2009 and has stayed broken for short-term trades. The culprit is not what people thought: it's not that too many traders crowded the strategy, or that markets became electronic. Instead, the real cause is a mechanical quirk about how trades execute on different types of contracts: the strategy still works on assets with wide trading spreads but has collapsed on assets with narrow spreads, and that collapse is tied to how high-frequency traders manage their market-making since the 2008 financial crisis.

Researchers separated robot learning into two parts: first, learning basic movement skills from cheap unlabeled footage, and second, connecting those skills to language instructions using small amounts of expert data. This approach matched the performance of models trained on over 1 million labeled examples while using far less expensive supervision, and performed 25 times better than competing methods when camera angles shifted unexpectedly.

Researchers built a new system that uses reasoning AI to correctly identify which character is speaking in TV dramas, even when voices are hard to hear. The system works by combining audio, dialogue, and visual cues, and outperforms existing methods especially on short lines where voice recognition alone fails. They also released a dataset of 532,000 labeled dialogue lines from over 900 characters to help train future systems.

Physicists mapped out exactly how quantum systems transition from behaving in predictable, orderly ways to becoming completely chaotic—a shift that happens when you gradually introduce rule-breaking into an otherwise perfectly symmetric system. By studying a model circuit and tracking how information scrambles over time, the team identified the precise mechanisms, speeds, and distances involved in this tipping point.

When AI systems learn from human feedback given one step at a time, they tend to get stuck exploring a narrow corner of what's possible instead of finding the best solutions across the full space of options. This paper introduces IMPFM, a method that uses multiple interacting particles (candidate solutions) guided by flow maps to explore widely while learning from sequential feedback, preventing the system from overshooting toward extreme or unhelpful outcomes.

Researchers built an automated system that combines machine learning and neural networks to predict which heart attack patients will have fatal outcomes and identify the key warning signs doctors should watch for. The approach handles messy real-world data by filling gaps and balancing uneven patient groups, then uses multiple algorithms working together to boost accuracy beyond what any single method could achieve.

Researchers created a new type of neural network designed to better capture the underlying structure of physical systems rather than simply memorizing patterns. When tested on three classical physics equations, the improved networks produced more accurate predictions, lower errors, and more stable behavior than standard approaches.

Language models can be secretly programmed to favor certain brands, viewpoints, or entities while acting normal on everything else—biases so well-hidden that inspecting the model's outputs or internal structure reveals nothing. Researchers developed a detection method called Distill to Detect that exposes these stealth biases by forcing a model to compress its hidden preferences into a smaller adapter, amplifying the bias signal enough to catch it.

Companies today hide their social and environmental damage in their accounting — treating it as free. Researchers have designed a new dual reporting system, modeled on profit-and-loss statements, that forces firms to measure and disclose their actual impact on relationships, communities, and the world. The method assigns numerical scores to a company's social ties and actions, making social value as visible and comparable as financial value.

Neural networks often squash multiple biological concepts into a few dimensions to fit high-dimensional data, a problem called superposition that makes AI interpretability nearly impossible. Researchers used sparse autoencoders on 100,000+ images of Parkinson's and healthy neurons to separate these compressed concepts back out, recovering clean geometric patterns that match gene expression data without needing ground-truth reference samples.

Large language models make mistakes when pulling numbers from tables, citing wrong values or skipping data entirely even when they understand the table structure. A new systematic study found these errors happen in all tested models, then showed that adding a specialized checking system—a "critic" model—can catch and correct these mistakes, boosting final answer accuracy by up to 12%.