12 citations · 27 across the 12 of their papers we have counts for
12 papers
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Meituan LongCat Team, Bin Xiao, Chao Wang +86
The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal syste…
Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
Jinhu Fu, Yihang Lou, Qingyi Si +3
Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and reasoning tasks, yet their internal safety mechanisms remain opaque an…
VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining
Xuanyu Zhu, Yuhao Dong, Rundong Wang +9
Recent advancements extend Multimodal Large Language Models (MLLMs) beyond standard visual question answering to utilizing external tools for advanced visual tasks. Despite this pr…
Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation
Yulu Gan, Yan Bai, Yihang Lou +4
Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly foc…
Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning
Jinze Li, Yan Bai, Yihang Lou +4
Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old one…
Bayesian Evidential Learning for Few-Shot Classification
Xiongkun Linghu, Yan Bai, Yihang Lou +4
Few-Shot Classification(FSC) aims to generalize from base classes to novel classes given very limited labeled samples, which is an important step on the path toward human-like mach…
Switchable Representation Learning Framework with Self-compatibility
Shengsen Wu, Yan Bai, Yihang Lou +3
Real-world visual search systems involve deployments on multiple platforms with different computing and storage resources. Deploying a unified model that suits the minimal-constrai…
Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning
Yan Bai, Jile Jiao, Shengsen Wu +4
Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the…
Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation
Shengsen Wu, Liang Chen, Yihang Lou +4
In object re-identification (ReID), the development of deep learning techniques often involves model updates and deployment. It is unbearable to re-embedding and re-index with the…
Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
Yongxing Dai, Jun Liu, Yan Bai +2
Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. To handle this problem, some rece…
Compact Descriptors for Video Analysis: the Emerging MPEG Standard
Ling-Yu Duan, Vijay Chandrasekhar, Shiqi Wang +6
This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG). MPEG-CDVA targets at d…
Improving Object Detection with Region Similarity Learning
Feng Gao, Yihang Lou, Yan Bai +3
Object detection aims to identify instances of semantic objects of a certain class in images or videos. The success of state-of-the-art approaches is attributed to the significant…