Applying STP at consecutive semantic reasoning steps achieves 168x more accurate multi-step latent prediction on ProcessBench than frozen baselines, with trajectories forming smooth curves best captured by non-linear predictors.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Demonstrates direct comparison of observable compact-binary populations from GW data to astrophysical models, with unbiased inference shown possible and applied to O3 data.
SPLICE couples JEPA-based latent diffusion with adaptive conformal inference to deliver accurate time-series inpainting with 93-95% empirical coverage on load datasets.
Removing utility regression and rank supervision auxiliary losses improves language modeling performance and training efficiency for conditional depth routing gates, and eliminates the advantage of a more complex JEPA-guided gate over a simple MLP gate.
citing papers explorer
-
Semantic Step Prediction: Multi-Step Latent Forecasting in LLM Reasoning Trajectories via Step Sampling
Applying STP at consecutive semantic reasoning steps achieves 168x more accurate multi-step latent prediction on ProcessBench than frozen baselines, with trajectories forming smooth curves best captured by non-linear predictors.
-
Comparing astrophysical models to gravitational-wave data in the observable space
Demonstrates direct comparison of observable compact-binary populations from GW data to astrophysical models, with unbiased inference shown possible and applied to O3 data.
-
SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting
SPLICE couples JEPA-based latent diffusion with adaptive conformal inference to deliver accurate time-series inpainting with 93-95% empirical coverage on load datasets.
-
Revisiting Auxiliary Losses for Conditional Depth Routing: An Empirical Study
Removing utility regression and rank supervision auxiliary losses improves language modeling performance and training efficiency for conditional depth routing gates, and eliminates the advantage of a more complex JEPA-guided gate over a simple MLP gate.