9 citations · 16 across the 15 of their papers we have counts for
9 papers · 1 filter
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-…
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…
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…
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…
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…