29 citations · 61 across the 17 of their papers we have counts for
17 papers · 1 filter
When Should the Count Change? Learning State Maintenance for Causal Video Counting
Pengyiang Liu, Dongyue Lyu, Junbo Niu +3
Continuous video counting requires distinguishing new observations from new objects or completed events. We introduce StaMina (State Maintenance), which learns to maintain counting…
MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning
Yingying Fan, Penghui Du, Leyan Zhu +10
Understanding tens-of-minutes surgical videos requires long-horizon temporal reasoning, answering what happens before, after, or across stages of a procedure by grounding the quest…
Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction
Zhongbin Guo, Jiahao Xie, Dongling Xiao +5
While Multimodal Large Language Models (MLLMs) have achieved remarkable progress, visual understanding and generation are typically treated as divergent objectives. Existing unifie…
DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes
Jiahao Xie, Zhongbin Guo, Qianle Wang +4
While data curation for Vision Language Models (VLMs) is increasingly active, public practice for constructing pretraining mixtures remains largely heuristic: practitioners stack d…
Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning
Hohin Kwan, Hongyu Li, Ray Zhang +5
Recent interest in multimodal large language models (MLLMs) raises a central question: can they reason over dynamic visual evidence rather than merely recognize objects or events i…
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
Sweta Mahajan, Sukrut Rao, Jiahao Xie +2
Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space. Despite this, the image and text embeddings are often poorly…
SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr +2
Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). Ho…
R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr +2
Large vision-language models (LVLMs) have demonstrated impressive performance in various multimodal understanding and reasoning tasks. However, they still struggle with object hall…
ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better
Mriganka Nath, Anurag Das, Jiahao Xie +1
Large vision-language models (LVLMs) tend to hallucinate, especially when visual inputs are corrupted at test time. We show that such corruptions act as additional distribution shi…
SemanticNVS: Improving Semantic Scene Understanding in Generative Novel View Synthesis
Xinya Chen, Christopher Wewer, Jiahao Xie +2
We present SemanticNVS, a camera-conditioned multi-view diffusion model for novel view synthesis (NVS), which improves generation quality and consistency by integrating pre-trained…
MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation
Jiahao Xie, Wei Li, Xiangtai Li +3
We present MosaicFusion, a simple yet effective diffusion-based data augmentation approach for large vocabulary instance segmentation. Our method is training-free and does not rely…
Correlational Image Modeling for Self-Supervised Visual Pre-Training
Wei Li, Jiahao Xie, Chen Change Loy
We introduce Correlational Image Modeling (CIM), a novel and surprisingly effective approach to self-supervised visual pre-training. Our CIM performs a simple pretext task: we rand…
Masked Frequency Modeling for Self-Supervised Visual Pre-Training
Jiahao Xie, Wei Li, Xiaohang Zhan +3
We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models. Instead of randomly inserting mask tokens t…
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
Zhaowen Li, Yousong Zhu, Fan Yang +9
Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images…
Unsupervised Object-Level Representation Learning from Scene Images
Jiahao Xie, Xiaohang Zhan, Ziwei Liu +2
Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNe…
Delving into Inter-Image Invariance for Unsupervised Visual Representations
Jiahao Xie, Xiaohang Zhan, Ziwei Liu +2
Contrastive learning has recently shown immense potential in unsupervised visual representation learning. Existing studies in this track mainly focus on intra-image invariance lear…
Online Deep Clustering for Unsupervised Representation Learning
Xiaohang Zhan, Jiahao Xie, Ziwei Liu +2
Joint clustering and feature learning methods have shown remarkable performance in unsupervised representation learning. However, the training schedule alternating between feature…