11 papers
Correcting WHERE, Preserving HOW: Compositional Generalization for Vision-Language-Action Models via Referential Guidance
Yanyan Zhang, Disheng Liu, Xinpeng Li +8
While Vision-Language-Action (VLA) models enable flexible action generation, their generalization across diverse environmental elements, including manipulated objects, destinations…
Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models
Tuo Liang, Disheng Liu, Nengbo Wang +2
Grounding is a core capability of spatial vision-language models, yet most existing work focuses only on where a referred object is. Many 3D tasks also require knowing how it is or…
Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
Tuo Liang, Zhe Hu, Disheng Liu +2
Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural knowledge, and communic…
Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting
Disheng Liu, Tuo Liang, Chaoda Song +1
Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models. Existing approaches to exploiting this potentia…
Imagining Recovery: Inference-Time Counterfactual Realignment for Vision-Language-Action Models
Yanyan Zhang, Disheng Liu, Kai Ye +6
Vision-language-action (VLA) models have improved the flexibility and generality of robotic manipulation, yet they remain fragile to online disruptions, such as changes in task goa…
Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion
Yiran Qiao, Yiren Lu, Yunlai Zhou +5
3D asset generation plays a pivotal role in fields such as gaming and virtual reality, enabling the rapid synthesis of high-fidelity 3D objects from a single or multiple images. Bu…
GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning
Yiren Lu, Yi Du, Disheng Liu +3
Effective embodied exploration requires agents to accumulate and retain spatial knowledge over time. However, existing scene representations, such as discrete scene graphs or stati…
Counterfactual Visual Explanation via Causally-Guided Adversarial Steering
Yiran Qiao, Disheng Liu, Yiren Lu +3
Recent work on counterfactual visual explanations has contributed to making artificial intelligence models more explainable by providing visual perturbation to flip the prediction.…
BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting
Yiren Lu, Yunlai Zhou, Disheng Liu +2
3D Gaussian Splatting (3DGS) has shown remarkable potential for static scene reconstruction, and recent advancements have extended its application to dynamic scenes. However, the q…
When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?
Tuo Liang, Zhe Hu, Jing Li +8
Understanding humor-particularly when it involves complex, contradictory narratives that require comparative reasoning-remains a significant challenge for large vision-language mod…
CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data
Disheng Liu, Yiran Qiao, Wuche Liu +5
True intelligence hinges on the ability to uncover and leverage hidden causal relations. Despite significant progress in AI and computer vision (CV), there remains a lack of benchm…