AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

ANTiC: Adaptive Neural Temporal In Situ Compressor

Sandeep Suresh Cranganore, Andrei Bodnar, Gianluca Galletti, Fabian Paischer, Johannes Brandstetter

ICML 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed operator learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use PATS temporal selection instead of dense sampling (ablation)ANTiC-LoRA · 2D Kolmogorov flows (16.8 GiB)total compression: 47x -> 435xImproved
use PATS temporal selection instead of dense sampling (ablation)ANTiC-LoRA · 3D BSSN simulations (4.2 TiB)total compression: 3744x -> 6807xImproved
use PATS (physics-aware) instead of sparse sampling (ablation)ANTiC-LoRA · 2D Kolmogorov flows (16.8 GiB)temporal retention: 20% -> 37%Improved
replace ZFP with neural field continual fine-tuningPATS · 3D BSSN simulations (4.2 TiB)spatial compression: 27x -> 471xImproved
replace full fine-tuning with LoRA in CFT (ablation)ANTiC · 3D BSSN simulations (4.2 TiB)total compression: 860x -> 6807xImproved
use continual fine-tuning instead of training from scratch (ablation)Neural field · 2D Kolmogorov flows (16.8 GiB)mean relative l2: 1.7e-3 -> 6.1e-4Improved
use continual fine-tuning instead of training from scratch (ablation)Neural field · 3D BSSN simulations (4.2 TiB)mean relative l2: 6.2e-4 -> 4.6e-4Improved
use LoRA rank 64 instead of full FT (ablation)Neural field · 2D Kolmogorov flows (16.8 GiB)mean relative l2: 6.1e-4 -> 4.3e-4Improved
use LoRA rank 8 instead of full FT (ablation)Neural field · 2D Kolmogorov flows (16.8 GiB)mean relative l2: 6.1e-4 -> 6.9e-2Hurt
increase LoRA rank from 8 to 64 (ablation)Neural field · 3D BSSN simulations (4.2 TiB)mean relative l2: 6.0e-4 -> 4.6e-4Improved
use CFT instead of cold start for training (ablation)Neural field · 3D BSSN simulations (4.2 TiB)wallclock (s), H200: ~183-187 -> ~21-24Improved
use LoRA rank 8 instead of full FT (ablation)Neural field · 3D BSSN simulations (4.2 TiB)time per snapshot (s): ~162 -> ~131Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy