1 citations · 1 across the 17 of their papers we have counts for
20 papers
Outcome-Guided On-Policy Self-Distillation
ZheXu Wang, Mao-Lin Luo, Yankun Hong +6
On-policy self-distillation (OPSD) provides denser token-level supervision and better computational efficiency than Reinforcement Learning with Verifiable Rewards (RLVR). However,…
Learning Process Rewards via Reasoning State Propagation
Kai Gan, Zi-Hao Zhou, Bo Ye +3
Process reward models (PRMs) have demonstrated notable effectiveness in test-time scaling and reinforcement learning by providing fine-grained signals for evaluating intermediate r…
RL Forgets! Towards Continual Policy Optimization
Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou +4
Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent studies report that reinforcement learning is less prone to for…
KeepLoRA++: Continual Learning with Layer-Scaled Residual Gradient Adaptation
Mao-Lin Luo, Yi-Lin Zhang, Zi-Hao Zhou +5
Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of le…
SHED: Style-Homogenized Embedding Alignment for Domain Generalization
Kai Gan, Tong Wei
Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language models like CLIP exhibit strong…
Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery
Bo Ye, Kai Gan, Tong Wei +1
Generalized Category Discovery (GCD) seeks to identify novel categories from unlabeled data while retaining the classification ability of seen categories. Prior GCD methods commonl…
DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
Bo Ye, Xinyu Cui, Jian Zhao +2
Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks…
DC-Merge: Improving Model Merging with Directional Consistency
Han-Chen Zhang, Zi-Hao Zhou, Mao-Lin Luo +3
Model merging aims to integrate multiple task-adapted models into a unified model that preserves the knowledge of each task. In this paper, we identify that the key to this knowled…
Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
Hao Gu, Mao-Lin Luo, Zi-Hao Zhou +3
Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continu…
KeepLoRA: Continual Learning with Residual Gradient Adaptation
Mao-Lin Luo, Zi-Hao Zhou, Yi-Lin Zhang +3
Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of le…
Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition
Wei Tang, Zuo-Zheng Wang, Kun Zhang +2
Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased…
TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting
Zhiyuan Xu, Nan Min, Yuhang Guo +1
3D Gaussian Splatting offers a strong speed-quality trade-off but struggles to reconstruct semi-transparent surfaces because most methods assume a single depth per pixel, which fai…
Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
Jiajun Fan, Tong Wei, Chaoran Cheng +2
Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence…
Tuning the Right Foundation Models is What you Need for Partial Label Learning
Kuang He, Wei Tang, Tong Wei +1
Partial label learning (PLL) seeks to train generalizable classifiers from datasets with inexact supervision, a common challenge in real-world applications. Existing studies have d…
LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
Mao-Lin Luo, Zi-Hao Zhou, Tong Wei +1
Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-bas…
Weakly-Supervised Contrastive Learning for Imprecise Class Labels
Zi-Hao Zhou, Jun-Jie Wang, Tong Wei +1
Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. How…
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
Zi-Hao Zhou, Siyuan Fang, Zi-Jing Zhou +3
Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-ar…
Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning
Kai Gan, Tong Wei, Min-Ling Zhang
While long-tailed semi-supervised learning (LTSSL) has attracted growing attention in many real-world classification tasks, existing LTSSL algorithms typically assume that labeled…
Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning
Kai Gan, Tong Wei
Semi-supervised learning (SSL) has witnessed remarkable progress, resulting in the emergence of numerous method variations. However, practitioners often encounter challenges when a…
EAT: Towards Long-Tailed Out-of-Distribution Detection
Tong Wei, Bo-Lin Wang, Min-Ling Zhang
Despite recent advancements in out-of-distribution (OOD) detection, most current studies assume a class-balanced in-distribution training dataset, which is rarely the case in real-…