3 citations · 11 across the 32 of their papers we have counts for
32 papers
BPG: Balancing Plasticity and Generalization for Domain Incremental Learning
Qiang Wang, Songlin Dong, Shaokun Wang +5
Deep neural networks excel in various tasks but struggle to generalize across evolving data distributions, leading to significant performance degradation under domain shifts. Domai…
SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication
Xinyi Fang, Kejian Tong, Jiabei Liu +2
Large scale document deduplication must preserve semantic equivalence while remaining efficient over massive corpora. We present SemHash LLM, a multi granularity framework that uni…
SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference
Amirhossein Abaskohi, Giuseppe Carenini, Peter West +1
Large language models increasingly operate over long contexts, where the KV cache becomes a dominant memory bottleneck: its size grows linearly with sequence length and must be ret…
ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction
Amirhossein Abaskohi, Yuhang He, Peter West +3
Computer-use agents (CUAs) rely on visual observations of graphical user interfaces, where each screenshot is encoded into a large number of visual tokens. As interaction trajector…
Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models
Huoren Yang, Jianchao Zhao, Hu Yusong +7
Vision-Language-Action (VLA) models have advanced rapidly with stronger backbones, broader pre-training, and larger demonstration datasets, yet their action heads remain largely ho…
Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
Jizhou Han, Chenhao Ding, Yuhang He +4
Generalized Category Discovery (GCD) seeks to uncover novel categories in unlabeled data while preserving recognition of known categories, yet prevailing visual-only pipelines and…
GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Task
Shiwei Lu, Yuhang He, Jiashuo Li +2
Federated learning (FL) facilitates the secure utilization of decentralized images, advancing applications in medical image recognition and autonomous driving. However, conventiona…
GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery
Jizhou Han, Chenhao Ding, SongLin Dong +4
Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typic…
Is Parameter Isolation Better for Prompt-Based Continual Learning?
Jiangyang Li, Chenhao Ding, Songlin Dong +4
Prompt-based continual learning methods effectively mitigate catastrophic forgetting. However, most existing methods assign a fixed set of prompts to each task, completely isolatin…
IOTA: Corrective Knowledge-Guided Prompt Learning via Black-White Box Framework
Shaokun Wang, Yifan Yu, Yuhang He +2
Recently, adapting pre-trained models to downstream tasks has attracted increasing interest. Previous Parameter-Efficient-Tuning (PET) methods regard the pre-trained model as an op…
P2L-CA: An Effective Parameter Tuning Framework for Rehearsal-Free Multi-Label Class-Incremental Learning
Songlin Dong, Jiangyang Li, Chenhao Ding +4
Multi-label Class-Incremental Learning aims to continuously recognize novel categories in complex scenes where multiple objects co-occur. However, existing approaches often incur h…
VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection
Qiang Wang, Xinyuan Gao, Yuhang He +5
Existing Video Detailed Captioning (VDC) methods predominantly rely on costly human annotations or distillation from powerful proprietary models, creating a dependency on external…
Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery
Jizhou Han, Shaokun Wang, Yuhang He +5
Generalized Category Discovery (GCD) focuses on classifying known categories while simultaneously discovering novel categories from unlabeled data. However, previous GCD methods fa…
Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptation
JianChao Zhao, Chenhao Ding, Songlin Dong +4
This paper focuses on the Continual Test-Time Adaptation (CTTA) task, aiming to enable an agent to continuously adapt to evolving target domains while retaining previously acquired…
Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation
Jizhou Han, Chenhao Ding, SongLin Dong +3
Visual-language models (VLMs) like CLIP exhibit strong generalization but struggle with distribution shifts at test time. Existing training-free test-time adaptation (TTA) methods…
Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need
Qiang Wang, Xiang Song, Yuhang He +4
Deep neural networks (DNNs) often underperform in real-world, dynamic settings where data distributions change over time. Domain Incremental Learning (DIL) offers a solution by ena…
Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models
Songlin Dong, Chenhao Ding, Jiangyang Li +4
This study aims to address the problem of multi-domain task incremental learning~(MTIL), which requires that vision-language models~(VLMs) continuously acquire new knowledge while…
DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype
Qiang Wang, Yuhang He, SongLin Dong +4
Domain-Incremental Learning (DIL) enables vision models to adapt to changing conditions in real-world environments while maintaining the knowledge acquired from previous domains. G…
Learn by Reasoning: Analogical Weight Generation for Few-Shot Class-Incremental Learning
Jizhou Han, Chenhao Ding, Yuhang He +4
Few-shot class-incremental Learning (FSCIL) enables models to learn new classes from limited data while retaining performance on previously learned classes. Traditional FSCIL metho…
Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning
Chenhao Ding, Songlin Dong, Zhengdong Zhou +4
Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as…
Space Rotation with Basis Transformation for Training-free Test-Time Adaptation
Chenhao Ding, Xinyuan Gao, Songlin Dong +5
With the development of visual-language models (VLM) in downstream task applications, test-time adaptation methods based on VLM have attracted increasing attention for their abilit…
Grid: Omni Visual Generation
Cong Wan, Xiangyang Luo, Hao Luo +7
Visual generation has witnessed remarkable progress in single-image tasks, yet extending these capabilities to temporal sequences remains challenging. Current approaches either bui…
LPT: Less-overfitting Prompt Tuning for Vision-Language Model
Chenhao Ding, Xinyuan Gao, Songlin Dong +5
Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more eff…
Dynamic Integration of Task-Specific Adapters for Class Incremental Learning
Jiashuo Li, Shaokun Wang, Bo Qian +4
Non-exemplar class Incremental Learning (NECIL) enables models to continuously acquire new classes without retraining from scratch and storing old task exemplars, addressing privac…