15 citations · 25 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…
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams
Cong Wan, Zeyu Guo, Zijian Cai +6
Raw multimodal streams are abundant but noisy, redundant, and unaligned with any particular training objective. Turning them into supervision today means either brittle heuristics…
CoRe: A Comprehensive Framework for Cross-Image Comparative Reasoning in Vision-Language Models
Lin Peng, Cong Wan, Zeyu Guo +2
Cross-image comparative reasoning remains challenging for vision-language models (VLMs), especially when correct prediction requires fine-grained attribute grounding and globally c…
ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
Jiangyang Li, Cong Wan, Changjie Wu +8
Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignme…
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…
Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
Jianchao Zhao, Huoren Yang, Yusong Hu +6
Vision-Language-Action (VLA) models show strong potential for general-purpose robotic manipulation, yet their closed-loop reliability often degrades under local deployment conditio…
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
Haisen He, Xiangyu Zou, SongLin Dong +3
Real-world image degradation is often unknown, spatially non-uniform, and compositional, requiring all-in-one restoration models to adapt a single set of weights to diverse local c…
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…
Trajectory-Diversity-Driven Robust Vision-and-Language Navigation
Jiangyang Li, Cong Wan, SongLin Dong +4
Vision-and-Language Navigation (VLN) requires agents to navigate photo-realistic environments following natural language instructions. Current methods predominantly rely on imitati…
Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models
Haoyun Liu, Jianzhuang Zhao, Xinyuan Chang +11
Despite the rapid progress of vision-language-action (VLA) models, the prevailing practice of predicting action chunks as discrete waypoints remains structurally misaligned with th…
ReMoT: Reinforcement Learning with Motion Contrast Triplets
Cong Wan, Zeyu Guo, Jiangyang Li +5
We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency -- a critical failure point in navigatio…
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…
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…
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…
Diversity Covariance-Aware Prompt Learning for Vision-Language Models
Songlin Dong, Zhengdong Zhou, Chenhao Ding +3
Prompt tuning can further enhance the performance of visual-language models across various downstream tasks (e.g., few-shot learning), enabling them to better adapt to specific app…
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…