HumanMoveVQA is a new benchmark that generates 10K+ QA pairs from 3D-lifted video tracks to evaluate video MLLMs on global human trajectory and orientation reasoning.
Weld, Walter S
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
Introduces LP-anchored attribution for neural CO policies with CSP-certified counterfactuals and Bonferroni-PAC sufficient subsets, showing higher agreement with certified signals than gradient proxies on CVRPTW and OP.
IGT-OMD reduces gradient transport error from quadratic to linear in delay length for delayed bilevel optimization and achieves sublinear regret with adaptive steps.
GoD uses anatomy graphs and difference alignment to improve medical image re-identification accuracy and auditability, with +7.1 pp Rank-1 gains on fundus and +3.1 pp on CXR.
Higher generative AI error rates reduce user reliance, but task difficulty does not significantly moderate this effect.
Hiding generative AI use to signal expertise reduces knowledge sharing and transparency among workplace colleagues.
ProtDiS decomposes protein micro-environment embeddings into task-relevant dimensions via knowledge-guided methods, reporting gains on twelve downstream tasks especially under structure-based splits.
PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.
citing papers explorer
-
HumanMoveVQA: Can Video MLLMs reason about human movement in videos?
HumanMoveVQA is a new benchmark that generates 10K+ QA pairs from 3D-lifted video tracks to evaluate video MLLMs on global human trajectory and orientation reasoning.
-
Constraint-Anchored Attribution: Feasibility-Certified Counterfactuals and Bonferroni-PAC Sufficient Subsets for Neural CO Policies
Introduces LP-anchored attribution for neural CO policies with CSP-certified counterfactuals and Bonferroni-PAC sufficient subsets, showing higher agreement with certified signals than gradient proxies on CVRPTW and OP.
-
IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback
IGT-OMD reduces gradient transport error from quadratic to linear in delay length for delayed bilevel optimization and achieves sublinear regret with adaptive steps.
-
Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identification
GoD uses anatomy graphs and difference alignment to improve medical image re-identification accuracy and auditability, with +7.1 pp Rank-1 gains on fundus and +3.1 pp on CXR.
-
Effects of Generative AI Errors on User Reliance Across Task Difficulty
Higher generative AI error rates reduce user reliance, but task difficulty does not significantly moderate this effect.
-
"If You're Very Clever, No One Knows You've Used It": The Social Dynamics of Developing Generative AI Literacy in the Workplace
Hiding generative AI use to signal expertise reduces knowledge sharing and transparency among workplace colleagues.
-
Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition
ProtDiS decomposes protein micro-environment embeddings into task-relevant dimensions via knowledge-guided methods, reporting gains on twelve downstream tasks especially under structure-based splits.
-
PaliGemma: A versatile 3B VLM for transfer
PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.