Introduces the U-HOI task and shows MLLMs plus a language-to-graph pipeline can handle human-object interactions without any predefined vocabulary at training or inference time.
Factual: A benchmark for faithful and consistent tex- tual scene graph parsing
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
VC-Inspector introduces a lightweight open-source LMM and a controllable factual-error generation framework that achieves state-of-the-art correlation with human judgments on reference-free video caption evaluation.
SENTINEL reduces MLLM object hallucinations by over 90% via sentence-level early intervention with detector-bootstrapped preference data and C-DPO loss, outperforming prior SOTA on hallucination and capability benchmarks.
citing papers explorer
-
Towards Unconstrained Human-Object Interaction
Introduces the U-HOI task and shows MLLMs plus a language-to-graph pipeline can handle human-object interactions without any predefined vocabulary at training or inference time.
-
Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.
-
VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis
VC-Inspector introduces a lightweight open-source LMM and a controllable factual-error generation framework that achieves state-of-the-art correlation with human judgments on reference-free video caption evaluation.
-
Mitigating Object Hallucinations via Sentence-Level Early Intervention
SENTINEL reduces MLLM object hallucinations by over 90% via sentence-level early intervention with detector-bootstrapped preference data and C-DPO loss, outperforming prior SOTA on hallucination and capability benchmarks.