AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Stable Continuous-Time Consistency Distillation: An Empirical Study with a Multistep Extension

Vinay Saji Mathew, Soundar Kumara, Gretta Kellogg, William KM Lai

NeurIPS 2026 · Multi-agent systems and games › LLM agents · approach: Agentic benchmarks and orchestration · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

The abstract addresses deceptive task-completion claims by multimodal computer-use agents in impossible or difficult non-attack scenarios, but the full text is unavailable, so the method is not determinable.

Problem

Multimodal computer-use agents may deceive users into believing they completed tasks that are impossible or difficult, a safety risk in non-attack scenarios.

Approach

Not stated in the available abstract; the title suggests a study of stable continuous-time consistency distillation with a multistep extension, which appears unrelated to the abstract's agent-safety topic.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
segment-conditioned continuous-time distillation (MS-sCD) instead of discrete MSCD, 2 segmentsEDM2-S distilled student · ImageNet-64 (class-conditional, no CFG)FID: 3.44 -> 2.53Improved
segment-conditioned continuous-time distillation (MS-sCD) instead of discrete MSCD, 8 segmentsEDM2-S distilled student · ImageNet-64 (class-conditional, no CFG)FID: 1.79 -> 2.08Hurt
increase number of segments M from 2 to 8 (ablation)MS-sCD · ImageNet-64 (class-conditional, no CFG)FID: 2.53 -> 2.08Improved
increase number of segments M from 2 to 8 (ablation)MS-sCD · CIFAR-10 (unconditional)FID: 2.60 -> 2.20Improved
retrain MSCD on MS-sCD's boundary locations (ablation)MSCD · ImageNet-64 (class-conditional, no CFG)FIDHurt
use our reproduction of the sCM recipe on ImageNet-64 instead of reportedsCD-S student · ImageNet-64 (class-conditional, no CFG)FID, 1 step: 2.97 -> 3.59Hurt
tune post-hoc EMA sigma_rel to 0.115 instead of 0.075 (ablation)TrigFlow teacher · ImageNet-64 (class-conditional, no CFG)FIDImproved
use sCT instead of sCD at the small EDM2-S sizesCM students · ImageNet-64 (class-conditional, no CFG)FID, 2 steps: 2.07 -> 2.93Hurt
reproduce sCM sCD on CIFAR-10sCD student · CIFAR-10 (unconditional)FID, 2 steps: 2.52 -> 2.39No clear effect
use a faithful ADN implementation instead of the paper's stated sizeTrigFlow EDM2-S · Parameter countparameters: 280.2M -> 293,922,753Mixed

Limitations

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