9 citations · 16 across the 15 of their papers we have counts for
16 papers
T-Rex: Tactile-Reactive Dexterous Manipulation
Dantong Niu, Zhuoyang Liu, Zekai Wang +31
The ability to react dynamically to tactile signals has long been considered crucial to agile human-level dexterity. Yet contemporary learning-based Vision-Language-Action (VLA) mo…
Contrastive Action-Image Pre-training for Visuomotor Control
Yuvan Sharma, Dantong Niu, Anirudh Pai +16
Existing vision encoders for robotics face a fundamental bottleneck: robotic datasets lack the scale necessary for large-scale pre-training. Prior work circumvents this data scarci…
Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization
Shufan Li, Konstantinos Kallidromitis, Akash Gokul +2
Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including mathematical reasoning and text-…
MobileWorldBench: Towards Semantic World Modeling For Mobile Agents
Shufan Li, Konstantinos Kallidromitis, Akash Gokul +3
World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world models, these approaches face prac…
Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
Yiming Qin, Bomin Wei, Jiaxin Ge +4
Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and g…
Learning to Grasp Anything by Playing with Random Toys
Dantong Niu, Yuvan Sharma, Baifeng Shi +11
Robotic manipulation policies often struggle to generalize to novel objects, limiting their real-world utility. In contrast, cognitive science suggests that children develop genera…
LaViDa: A Large Diffusion Language Model for Multimodal Understanding
Shufan Li, Konstantinos Kallidromitis, Hritik Bansal +7
Modern Vision-Language Models (VLMs) can solve a wide range of tasks requiring visual reasoning. In real-world scenarios, desirable properties for VLMs include fast inference and c…
Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection
Shufan Li, Konstantinos Kallidromitis, Akash Gokul +4
The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. W…
OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
Shufan Li, Konstantinos Kallidromitis, Akash Gokul +4
We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the r…
SegLLM: Multi-round Reasoning Segmentation
XuDong Wang, Shaolun Zhang, Shufan Li +5
We present SegLLM, a novel multi-round interactive reasoning segmentation model that enhances LLM-based segmentation by exploiting conversational memory of both visual and textual…
Hyperbolic Learning with Multimodal Large Language Models
Paolo Mandica, Luca Franco, Konstantinos Kallidromitis +2
Hyperbolic embeddings have demonstrated their effectiveness in capturing measures of uncertainty and hierarchical relationships across various deep-learning tasks, including image…
Aligning Diffusion Models by Optimizing Human Utility
Shufan Li, Konstantinos Kallidromitis, Akash Gokul +2
We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility. Since t…
Hierarchical Open-vocabulary Universal Image Segmentation
Xudong Wang, Shufan Li, Konstantinos Kallidromitis +3
Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomp…
Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
Luca Franco, Paolo Mandica, Konstantinos Kallidromitis +4
We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the h…
Refine and Represent: Region-to-Object Representation Learning
Akash Gokul, Konstantinos Kallidromitis, Shufan Li +4
Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondenc…
Contrastive Neural Processes for Self-Supervised Learning
Konstantinos Kallidromitis, Denis Gudovskiy, Kazuki Kozuka +2
Recent contrastive methods show significant improvement in self-supervised learning in several domains. In particular, contrastive methods are most effective where data augmentatio…