Cognaptus Insights

What if your AI model isn’t just answering questions, but living in its own version of time? A new paper titled The Other Mind makes a bold claim: large language models (LLMs) exhibit temporal cognition that mirrors how humans perceive time — not through raw numbers, but as a subjective, compressed mental landscape. Using a cognitive science task known as similarity judgment, the researchers asked 12 LLMs, from GPT-4o to Qwen2.5-72B, to rate how similar two years (like 1972 and 1992) felt. The results were startling: instead of linear comparisons, larger models automatically centered their judgment around a reference year — typically close to 2025 — and applied a logarithmic perception of time. In other words, just like us, they feel that 2020 and 2030 are more similar than 1520 and 1530. ...

The promise of fully autonomous vehicles hinges on their ability to handle not just the average drive—but the unexpected. Yet, creating rare, safety-critical scenarios for testing autonomous driving (AD) systems has long been a bottleneck. Manual scene creation doesn’t scale. Generative models often drift away from real-world distributions. And collecting edge cases on the road? Too dangerous, too slow. Enter AGENTS-LLM, a deceptively simple yet powerful framework that uses Large Language Models (LLMs) not to solve traffic scenes, but to break them. The twist? These aren’t just static prompts or synthetic scripts. AGENTS-LLM organizes LLMs into a multi-agent, modular system that modifies real traffic scenarios with surgical precision—making them trickier, nastier, and far more useful for evaluating planning systems. ...

In an age where aging infrastructure meets accelerating AI, a new paper out of George Mason University proposes a novel question: Can large language models interpret what even seasoned engineers find difficult — NDE contour maps of bridges? The answer, based on this pilot study, is a cautious but resounding yes — with caveats that echo through the entire field of AI-assisted engineering. The Problem: Data Is There — Expertise Isn’t Always Bridges are scanned using advanced non-destructive evaluation (NDE) tools — Ground Penetrating Radar (GPR), Electrical Resistivity (ER), Impact Echo (IE), and Ultrasonic Surface Waves (USW) — but interpreting those outputs requires human expertise, which is not always available, especially during emergency assessments or in rural areas. Contour maps from these tools don’t speak for themselves. ...

The latest advancement in fake news detection doesn’t just analyze what is said—it also looks at how it feels. The SEER model (Semantic Enhancement and Emotional Reasoning Network) introduces an innovative approach that harnesses emotional reasoning and semantic depth to surpass existing benchmarks in multimodal fake news detection. 🧠 Beyond Consistency: The Emotional Gap in Fake News Traditionally, models focus on image-text consistency: does the photo match the caption? But this misses the forest for the trees. Fake news isn’t just mismatched—it’s emotionally manipulative. ...

What if we stopped asking language models to “be creative”—and instead let them explore creativity the way humans brainstorm: by remixing ideas, nudging boundaries, and iterating through meaningful variations? That’s exactly what Large Language Models as Innovators proposes: a novel framework that leverages the latent embedding space of ideas—not prompts—to drive controlled, domain-agnostic creativity. Rather than relying on handcrafted rules or complex prompting tricks, the authors show how LLMs can generate original and relevant ideas by interpolating between known concepts, evaluating results, and refining outputs over time. ...

It’s no secret that Vision-Language Models (VLMs) have dazzled us with their prowess—excelling at image captioning, chart understanding, and even medical diagnostics. But beneath the glitter of benchmark wins, a deeper flaw lurks: these models often suffer from what Berman and Deng (Princeton) have sharply diagnosed as “tunnel vision.” Their new paper, VLMs Have Tunnel Vision, introduces a battery of tasks that humans can breeze through but that leading VLMs—from Gemini 2.5 Pro to Claude Vision 3.7—fail to solve even marginally above chance. These tasks aren’t edge cases or contrived puzzles. They simulate basic human visual competencies like comparing two objects, following a path, and making discrete visual inferences from spatially distributed evidence. The results? A sobering reminder that state-of-the-art perception doesn’t equate to understanding. ...

In financial engineering, pricing exotic options often boils down to estimating one number: the expected payoff under a risk-neutral measure. But what if we’re asking the wrong question? That’s the provocative premise of a recent study by Ahmet Umur Özsoy, who reimagines option pricing as a distributional learning problem, not merely a statistical expectation problem. By combining insights from Distributional Reinforcement Learning (DistRL) with classical option theory, the paper offers a fresh solution to an old problem: how do we properly account for tail risk and payoff uncertainty in path-dependent derivatives like Asian options? ...

When electricity markets were deregulated across many U.S. states in the 1990s, economists and policymakers hoped competition would lower consumer prices. But for decades, the results remained ambiguous—until now. A new paper, Causality analysis of electricity market liberalization on electricity price using novel Machine Learning methods, offers the most precise evaluation yet. Using cutting-edge causal machine learning models, the authors demonstrate that liberalization led to a 7% decrease in residential electricity prices in the short term—a finding with major implications for regulatory policy and infrastructure reform. ...

When it comes to trading the S&P 500, tradition says: trust the chart. But a new study from UCLA researchers proposes a smarter compass—one that listens not only to price momentum but also to the tone of the news. By merging language model-powered sentiment scores with technical indicators and time-series forecasting, the authors build a hybrid strategy that outperforms a buy-and-hold baseline during a volatile 3-month window. ...

What if you could simulate thousands of realistic futures for the market, all conditioned on what’s happening today—and then train an investment strategy on those futures? That’s the central idea behind a bold new approach to portfolio optimization that blends score-based diffusion models with reinforcement learning, and it’s showing results that beat classic benchmarks like the S&P 500 and traditional Markowitz portfolios. ...