Search papers, labs, and topics across Lattice.
10 papers published across 2 labs.
Omni-modal foundation models achieve self-improvement via RL compute scaled to 1M context, leveraging asynchronous training and agentic grading for enhanced intelligence.
Innate robot reflexes, designed for solitary tasks, actively impede the evolution of effective communication strategies in social foraging.
Looped Transformers can achieve tens of thousands of effective reasoning steps without performance collapse by learning to selectively retain and decay intermediate states.
Quantum classifiers grow to unpredictable depths regardless of training data size, and their generalization is not explained by active gate count alone.
Noise in Gaussian regression on Boolean cube polynomials can necessitate an exponential increase in sample complexity, requiring $(m+t)4^k\exp\{-O(k^{1/3})\}$ samples for parametric rates, a stark contrast to the $O((m+t)2^k)$ needed for noiseless identification.
Innate robot reflexes, designed for solitary tasks, actively impede the evolution of effective communication strategies in social foraging.
Looped Transformers can achieve tens of thousands of effective reasoning steps without performance collapse by learning to selectively retain and decay intermediate states.
Quantum classifiers grow to unpredictable depths regardless of training data size, and their generalization is not explained by active gate count alone.
Noise in Gaussian regression on Boolean cube polynomials can necessitate an exponential increase in sample complexity, requiring $(m+t)4^k\exp\{-O(k^{1/3})\}$ samples for parametric rates, a stark contrast to the $O((m+t)2^k)$ needed for noiseless identification.
Spectral analysis reveals that increasing latent dimensions in Koopman autoencoders improves dynamics learning by concentrating learned eigenvalues in low-residual regions, not just by reducing one-step prediction error.
Omni-modal foundation models achieve self-improvement via RL compute scaled to 1M context, leveraging asynchronous training and agentic grading for enhanced intelligence.
Softmax attention selectively exploits latent structure in Gaussian mixtures, solving nonlinear tasks beyond linear attention's reach while matching linear performance on tractable problems.
Latent world models scale predictably with compute via a second-order power law, enabling accurate forecasting of robotic planning performance and zero-shot task execution on real hardware.
LLM capabilities diverge under latent sequence compression; language modeling, decodability, and reasoning do not share a single compression threshold.
LLMs develop inherent fault tolerance as they scale, learning to compute within error-correcting codes that remain efficient even for massive models.
