Rule-VLN injects 177 regulatory signs into Touchdown-scale urban graphs; SNRM’s VLM perception plus mental-map detours cuts constraint violations ~19% and raises task completion ~6% zero-shot.
Benchmarking spatial relationships in text-to-image generation
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
Compositionality emerges in neural networks only in a narrow depth-connectivity regime, with gradient descent converging to fractured solutions outside it.
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.
ABSS ranks diffusion seeds by early cross-attention strength to prompt core tokens and retains only the top-k for full generation, yielding consistent gains in alignment and quality on Stable Diffusion variants.
EPIC introduces predicate-guided inference-time search that lifts compositional T2I prompt accuracy from 34% to 71% on GenEval2 with 31-81% lower execution costs.
Generative AI exhibits a paradox of simplicity where complex scene generation succeeds but deterministic tasks like pure color images fail, addressed via a new hierarchical obedience framework and Violin benchmark showing closed-source models outperform open-source ones.
ELDiff integrates evidential learning into T2I diffusion via pixel evidence loss and token conflict loss to improve object-wise semantic consistency.
CARINOX unifies noise optimization and exploration with human-correlated reward selection to boost compositional alignment in diffusion models, reporting +16% on T2I-CompBench++ and +11% on HRS while keeping quality and diversity.
citing papers explorer
-
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Rule-VLN injects 177 regulatory signs into Touchdown-scale urban graphs; SNRM’s VLM perception plus mental-map detours cuts constraint violations ~19% and raises task completion ~6% zero-shot.
-
Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds
Compositionality emerges in neural networks only in a narrow depth-connectivity regime, with gradient descent converging to fractured solutions outside it.
-
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.
-
Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection
ABSS ranks diffusion seeds by early cross-attention strength to prompt core tokens and retains only the top-k for full generation, yielding consistent gains in alignment and quality on Stable Diffusion variants.
-
EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
EPIC introduces predicate-guided inference-time search that lifts compositional T2I prompt accuracy from 34% to 71% on GenEval2 with 31-81% lower execution costs.
-
Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?
Generative AI exhibits a paradox of simplicity where complex scene generation succeeds but deterministic tasks like pure color images fail, addressed via a new hierarchical obedience framework and Violin benchmark showing closed-source models outperform open-source ones.
-
ELDiff: When Evidential Learning Meets Text-to-Image Diffusion
ELDiff integrates evidential learning into T2I diffusion via pixel evidence loss and token conflict loss to improve object-wise semantic consistency.
-
CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration
CARINOX unifies noise optimization and exploration with human-correlated reward selection to boost compositional alignment in diffusion models, reporting +16% on T2I-CompBench++ and +11% on HRS while keeping quality and diversity.