AIBullisharXiv – CS AI · Jun 257/10
🧠Researchers have developed the first formal convergence theorem for LLM-Verifier systems, proving that multi-stage software verification pipelines will reach completion with guaranteed termination. The 4/δ bound provides a precise latency prediction model validated across 90,000+ empirical trials, replacing heuristic approaches with mathematically rigorous resource planning for safety-critical applications.
AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers demonstrate that Mamba, a state space model alternative to transformers, efficiently learns optimal statistical estimators for Markov chains through in-context learning. The study reveals that single-layer Mamba discovers the Laplacian smoothing estimator—which is both Bayes and minimax optimal—and theoretically explains this capability through convolution-based representation.
AINeutralarXiv – CS AI · Mar 57/10
🧠Researchers introduce History-Echoes, a framework revealing how large language models become trapped by their conversational history, with past interactions creating geometric constraints in latent space that bias future responses. The study demonstrates that behavioral persistence in LLMs manifests as mathematical traps where previous hallucinations and responses influence subsequent model behavior across multiple model families and datasets.
AIBullisharXiv – CS AI · Feb 277/103
🧠Researchers introduce α-GFNs, an enhanced version of Generative Flow Networks that allows tunable control over exploration-exploitation dynamics through a parameter α. The method achieves up to 10× improvement in mode discovery across various benchmarks by addressing constraints in traditional GFlowNet objectives through Markov chain theory.
$LINK
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers introduce CogSpike, a formal verification tool for probabilistic spiking neural networks that addresses the state space explosion problem through weight-discretized quotient abstractions. The innovation enables verification of previously intractable neural network models by reducing computational complexity exponentially while maintaining mathematical fidelity guarantees.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers demonstrate that standard generative models cannot produce heavy-tailed distributions due to Gaussian decoder limitations and Lipschitz constraints. They propose replacing Gaussian decoders with Phase-Type distributions based on Markov chains, achieving up to 10x improvement in extreme quantile error for heavy-tailed data generation.
AINeutralarXiv – CS AI · Mar 34/103
🧠Researchers propose Phase-Type Variational Autoencoders (PH-VAE), a new deep learning model that uses Phase-Type distributions to better capture heavy-tailed data patterns where extreme events are critical. The approach outperforms standard VAE models with Gaussian decoders in modeling tail behavior and extreme quantiles, marking the first integration of Phase-Type distributions into deep generative modeling.
