VLMs formulate differentiable rewards from task-specific rules to enable test-time online LoRA optimization of VGMs, delivering 16.7-point gains on symbolic and general video reasoning benchmarks over VLM-as-solver and Best-of-N baselines.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Simulated fidelity quantum kernels achieve competitive or better accuracy than RBF kernels on Indian Pines binary and multiclass tasks and Methane Detection data without heavy dimensionality reduction.
Extends Cover's separation capacity to scattering networks by counting realizable dichotomies and identifies governing factors in network building blocks.
A Bayesian classifier that fuses direct, indicative, and OSINT-derived contextual evidence improves simulated CBRNE threat-type classification accuracy by up to 15.8 percentage points over a late-fusion majority-vote baseline.
A multi-view evidential framework combines semantic and reasoning information to improve accuracy and provide trustworthy uncertainty estimates for mental health prediction on text data.
citing papers explorer
-
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
VLMs formulate differentiable rewards from task-specific rules to enable test-time online LoRA optimization of VGMs, delivering 16.7-point gains on symbolic and general video reasoning benchmarks over VLM-as-solver and Best-of-N baselines.
-
Large-Scale Quantum Kernels for Hyperspectral Data Classification
Simulated fidelity quantum kernels achieve competitive or better accuracy than RBF kernels on Indian Pines binary and multiclass tasks and Methane Detection data without heavy dimensionality reduction.
-
Separation Capacity of Scattering Networks
Extends Cover's separation capacity to scattering networks by counting realizable dichotomies and identifies governing factors in network building blocks.
-
An Evidence Hierarchy for Bayesian Object Classification via OSINT-Aided Heterogeneous Sensor Fusion
A Bayesian classifier that fuses direct, indicative, and OSINT-derived contextual evidence improves simulated CBRNE threat-type classification accuracy by up to 15.8 percentage points over a late-fusion majority-vote baseline.
-
Beyond Semantics: An Evidential Reasoning-Aware Multi-View Learning Framework for Trustworthy Mental Health Prediction
A multi-view evidential framework combines semantic and reasoning information to improve accuracy and provide trustworthy uncertainty estimates for mental health prediction on text data.