Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
Affiliation:
8
0
14
Most self-evolving LLM updates are useless, yet current methods inherit them all; new frameworks drastically cut harmful updates and preserve valuable experience.
A frozen video tokenizer's latent can be factored into controllable and reward-relevant components, unlocking significant downstream planning gains.
This work describes an automatic criterion for full-state rejuvenation of the Gibbs sampler, derived from the Gelman-Rubin statistic, which plays a key role in speeding up learning convergence.
Targeted non-literal suppression in LLMs reveals a critical trade-off between compliance and output quality that could redefine copyright defense strategies.
Compact retrievers can achieve nearly half the performance of larger models while being up to 9.7× faster, challenging the assumption that bigger is always better in retrieval tasks.
Transforming noisy web text into a high-quality petroleum engineering dataset boosts retrieval performance by over 44% on benchmark tasks.
Layer span variation can unlock a new dimension of deterministic rollout diversity, boosting performance by over 10 percentage points on reasoning tasks.
Forget retraining: HyperKKL uses a hypernetwork to dynamically condition KKL observers on exogenous inputs, enabling accurate state estimation for non-autonomous nonlinear systems.