online conformal prediction with nested sets
new methods produce nested prediction sets across multiple coverage levels for simultaneous uncertainty quantification in online settings.
aisummaries filed under research
new methods produce nested prediction sets across multiple coverage levels for simultaneous uncertainty quantification in online settings.
aia new framework learns latent user preferences from few conversations and applies them across tasks to improve human-aligned decision making.
aia test-time framework uses a generative verifier to pick the best action from multiple candidates, improving robustness of multimodal language model agents without retraining.
aia new metric called quide collapses compression, accuracy, and latency into one score to find optimal quantization levels for neural networks.
aiai analysis of natural speech patterns like pauses and filler words can predict executive function and may help detect early cognitive decline.
aiuniform control schedules hurt text quality in discrete diffusion models, but a new adaptive scheduler improves multi-attribute steering by aligning interventions with each attribute's unique denoising timeline.
aia new post-hoc layer gives frozen predictors a spatial view of errors and a closed-form covariance without retraining.
aia new framework enables valid statistical inference when reusing data from adaptive sampling methods like bayesian optimization.
ailarge-depth transformers trained with adamw converge uniformly to a forward-backward ode system, with explicit convergence rates.
ainew method finds exact softmax bounds from score intervals, reducing slack in transformer robustness checks.
aibalora extends lora with bayesian adaptation, improving accuracy and providing uncertainty estimates for large model fine-tuning.
aia method for decentralized novelty detection that controls false discovery rate without sharing raw data, using low-precision model exchange.
aia free-energy perspective distinguishes whether post-training reweights existing model behaviors or creates new ones.
aia new method routes each case to a cost-appropriate set of predictors and samples labels based on uncertainty, reducing variance under a fixed budget.
aia mechanistic study finds attention sharpness is a near-zero predictor of correctness in vision-language models, while hidden state geometry and self-consistency offer stronger reliability signals.
aistandard text embeddings capture semantics, not agreement, so new methods are needed to map free-text opinions for fair clustering and facility location.
aithinking machines lab announced interaction models, a full-duplex ai that processes input and generates responses simultaneously, aiming for natural conversation speed.
aia new framework combines flow matching and reinforcement learning to quickly generate valid kirigami cut patterns for target shapes.
aipathboost is a gradient tree boosting method for graph-level prediction that learns path-based features directly from graph structure, outperforming graph neural networks on half of benchmark datasets.
aimean-field theory reveals initialization-driven competition and decoupling regimes in online independent component analysis.
ai