1 citations · 2 across the 10 of their papers we have counts for
12 papers
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
Junming Liu, Yuqi Li, Yifei Sun +6
Vision-Language Models (VLMs) have made striking progress, yet their spatial reasoning remains fragile. Models that answer an original input correctly can still fail under valid tr…
Artemis: Structured Visual Reasoning for Perception Policy Learning
Wei Tang, Yanpeng Sun, Shan Zhang +6
Recent reinforcement-learning frameworks for visual perception policy usually incorporate intermediate reasoning chains expressed in natural language. Empirical observations indica…
Amortized Active Generation of Pareto Sets
Daniel M. Steinberg, Asiri Wijesinghe, Rafael Oliveira +3
We introduce active generation of Pareto sets (A-GPS), a new framework for online discrete black-box multi-objective optimization (MOO). A-GPS learns a generative model of the Pare…
Noise Consistency Regularization for Improved Subject-Driven Image Synthesis
Yao Ni, Song Wen, Piotr Koniusz +1
Fine-tuning Stable Diffusion enables subject-driven image synthesis by adapting the model to generate images containing specific subjects. However, existing fine-tuning methods suf…
Math Blind: Failures in Diagram Understanding Undermine Reasoning in MLLMs
Yanpeng Sun, Shan Zhang, Wei Tang +5
Diagrams represent a form of visual language that encodes abstract concepts and relationships through structured symbols and their spatial arrangements. Unlike natural images, they…
Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs
Shan Zhang, Aotian Chen, Yanpeng Sun +6
Current multimodal large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding. The limitation is largely…
PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization
Yao Ni, Shan Zhang, Piotr Koniusz
Parameter-Efficient Fine-Tuning (PEFT) effectively adapts pre-trained transformers to downstream tasks. However, the optimization of tasks performance often comes at the cost of ge…
CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization
Yao Ni, Piotr Koniusz
Generative Adversarial Networks (GANs) significantly advanced image generation but their performance heavily depends on abundant training data. In scenarios with limited data, GANs…
Manifold Learning Benefits GANs
Yao Ni, Piotr Koniusz, Richard Hartley +1
In this paper, we improve Generative Adversarial Networks by incorporating a manifold learning step into the discriminator. We consider locality-constrained linear and subspace-bas…
Meta-Learning for Multi-Label Few-Shot Classification
Christian Simon, Piotr Koniusz, Mehrtash Harandi
Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address. This work targets the problem of multi-label meta-lear…
Towards a Robust Differentiable Architecture Search under Label Noise
Christian Simon, Piotr Koniusz, Lars Petersson +2
Neural Architecture Search (NAS) is the game changer in designing robust neural architectures. Architectures designed by NAS outperform or compete with the best manual network desi…
On Learning the Geodesic Path for Incremental Learning
Christian Simon, Piotr Koniusz, Mehrtash Harandi
Neural networks notoriously suffer from the problem of catastrophic forgetting, the phenomenon of forgetting the past knowledge when acquiring new knowledge. Overcoming catastrophi…