Agents of Disruption: How LLMs Became Adversarial Testers for Autonomous Driving
AGENTS-LLM shows how agentic LLM loops can turn real driving logs into harder autonomous-vehicle test scenarios without pretending to generate reality from scratch.
Cognaptus Insights
Industry thoughts, trends, and commentary.
Bridges and Biases: How LLMs Are Learning to Inspect Infrastructure
A mechanism-first reading of how multimodal LLMs can turn bridge NDE contour maps into inspection support, and why the real value is triage rather than autonomous certification.
Fake News Feels Different: How SEER Uses Emotion and Semantics to Spot Deception
A mechanism-first look at SEER, a multimodal fake-news detector that uses image captions, CLIP alignment, and emotion-aware reasoning to improve benchmark detection.
Latent Brilliance: Turning LLMs into Creativity Engines
A mechanism-first look at how continuous semantic conditioning can push LLMs beyond prompt-level diversity without retraining the base model.
Tunnel Vision: Why Vision-Language Models Still Miss the Bigger Picture
A mechanism-first reading of why leading vision-language models still fail at comparing, searching, and tracing visual evidence across an image.
Beyond the Mean: Teaching RL to Price the Entire Option Distribution
A mechanism-first reading of distributional RL for path-dependent option pricing, where the useful object is not one expected payoff but a state-conditioned payoff distribution.
Price Shock Therapy: Causal ML Reveals True Impact of Electricity Market Liberalization
A causal machine learning study finds that early electricity market liberalization reduced US residential power prices in the short term, while showing why the model choice matters almost as much as the policy result.
Signals & Sentiments: How GPT-2 and FinBERT Beat Buy-and-Hold on the S&P 500
A practical reading of how GPT-2, FinBERT, technical indicators, and time-series forecasts combined to outperform buy-and-hold in a short S&P 500 backtest.
Simulate First, Invest Later: How Diffusion Models Are Reinventing Portfolio Optimization
A mechanism-first reading of how adaptive diffusion models can generate market scenarios for dynamic portfolio learning without pretending that backtests are crystal balls.
Trading on Memory: Why Markov Models Miss the Signal
A practical reading of kernel-based mean-variance trading, where the value is not magic alpha but a better way to use temporal structure in signals and prices.