2 citations · 4 across the 8 of their papers we have counts for
14 papers
SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages
Raja Kumar, Rajat Koner, Ritwick Chaudhry +3
Vision-Language (VL) reasoning requires a model to both extract relevant and accurate information from an image (visual reasoning, VR), and to infer the answer from it (language re…
DSV-Mem: Evaluating Multimodal Memory in Professional Workflows for MLLM Agents
Jike Zhong, Ritwick Chaudhry, Xuanbai Chen +4
Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management and business operations. Yet…
ALoDLM: Adaptively Looped Diffusion Language Models
Liancheng Fang, Zhuowei Li, Youngeun Kim +10
Diffusion language models (DLMs) enable fast generation by predicting multiple tokens in parallel, but their practical adoption remains limited by a persistent quality gap relative…
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
Xi Xiao, Tianchen Zhao, Youngeun Kim +10
Latent visual reasoning (LVR) enables multimodal large language models (MLLMs) to perform intermediate computation in continuous latent tokens rather than expressing every reasonin…
VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models
Soumya Suvra Ghosal, Youngeun Kim, Zhuowei Li +6
Advances in large reasoning models have shown strong performance on complex reasoning tasks by scaling test-time compute through extended reasoning. However, recent studies observe…
Salient Concept-Aware Generative Data Augmentation
Tianchen Zhao, Xuanbai Chen, Zhihua Li +5
Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essentia…
AuthGuard: Generalizable Deepfake Detection via Language Guidance
Guangyu Shen, Zhihua Li, Xiang Xu +6
Existing deepfake detection techniques struggle to keep-up with the ever-evolving novel, unseen forgeries methods. This limitation stems from their reliance on statistical artifact…
Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels
Yongshuo Zong, Qin Zhang, Dongsheng An +6
This work presents a simple yet effective workflow for automatically scaling instruction-following data to elicit pixel-level grounding capabilities of VLMs under complex instructi…
Open-World Dynamic Prompt and Continual Visual Representation Learning
Youngeun Kim, Jun Fang, Qin Zhang +7
The open world is inherently dynamic, characterized by ever-evolving concepts and distributions. Continual learning (CL) in this dynamic open-world environment presents a significa…
Threshold-Consistent Margin Loss for Open-World Deep Metric Learning
Qin Zhang, Linghan Xu, Qingming Tang +4
Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes an…
Learning for Transductive Threshold Calibration in Open-World Recognition
Qin Zhang, Dongsheng An, Tianjun Xiao +6
In deep metric learning for visual recognition, the calibration of distance thresholds is crucial for achieving desired model performance in the true positive rates (TPR) or true n…
Learning Hierarchical Graph Neural Networks for Image Clustering
Yifan Xing, Tong He, Tianjun Xiao +6
We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities using a training set of images annotated…
3D-Aided Data Augmentation for Robust Face Understanding
Yifan Xing, Yuanjun Xiong, Wei Xia
Data augmentation has been highly effective in narrowing the data gap and reducing the cost for human annotation, especially for tasks where ground truth labels are difficult and e…
A Self-Supervised Bootstrap Method for Single-Image 3D Face Reconstruction
Yifan Xing, Rahul Tewari, Paulo R. S. Mendonca
State-of-the-art methods for 3D reconstruction of faces from a single image require 2D-3D pairs of ground-truth data for supervision. Such data is costly to acquire, and most datas…