#uncertainty estimation

try —

13 papers match

cs.AI2026

The Geometry of Flow-Matching Uncertainty: A Cost-free Uncertainty Proxy and Its Application in Flow-based VLA Failure Detection

Ziyang Rao, Yiren Zhao, Weiyu Guo +3

The paper interprets uncertainty in flow‑matching based action models as geometric deviation in the velocity field and proposes a cost‑free proxy called denoising acceleration that…

#flow matching#uncertainty estimation#embodied AI#online failure detection
eess.IV2026

Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction

Gousia Habib, Laura Ruotsalainen

The paper presents Endo-NeRF++, a neural rendering system that uses multi-resolution hash encoding and uncertainty‑aware adaptive sampling to improve the reconstruction of dynamic,…

#neural rendering#surgical scene reconstruction#uncertainty estimation#hash-grid encoding
cs.LG2026

TIER-MoE: Trust-Informed Expert Routing via Conditional Modality Risk for Multimodal Fusion in Biomedical Classification

Yu Chang, Anzhe Cheng, Chenwei Wu +7

The paper proposes TIER-MoE, a risk‑guided mixture‑of‑experts framework that routes multimodal biomedical data to specialized experts based on estimated modality reliability, impro…

#multimodal fusion#mixture of experts#risk-aware routing#biomedical classification
cs.IR2026

NMKFR: A Robust Framework for Time-Aware Cold-Start Recommendation

Chengzhi Liu, Ning Zeng, Zehui Qu

The paper introduces NMKFR, a neural framework that fuses semantic text encoding with time-aware Kalman state tracking to improve recommendation of new items under changing tempora…

#cold-start recommendation#time-aware recommendation#semantic encoding#Kalman filter
stat.ML2026

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents

Amirmohammad Farzaneh, Osvaldo Simeone

The paper introduces Think Short, Defer Smart (TSDS), a framework for edge-deployed LLM agents that stops on-device reasoning when actions stabilize and defers uncertain actions to…

#large language models#edge computing#uncertainty estimation#deferral mechanisms
cs.CV2026

Schrödinger's Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics

Timy Phan, Jannik Wiese, Björn Ommer

The paper introduces GARFIELD, a probabilistic model that learns a structured spatio‑temporal latent representation of possible future scene motions from a single image and optiona…

#probabilistic motion prediction#scene kinematics#latent distribution modeling#video prediction