Junlong Gao

Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning

Shihao Hou, Chikai Shang, Zhiheng Yang, Jiacheng Yang et autres

Personalized federated learning (PFL) with foundation models has emerged as a promising paradigm enabling clients to adapt to heterogeneous data distributions. However, real-world scenarios often face the co-occurrence of non-IID data and long-tailed class distributions, presenting unique challenges that remain underexplored in …

Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning

Shihao Hou, Chikai Shang, Zhiheng Yang, Jiacheng Yang et autres

Personalized federated learning (PFL) with foundation models has emerged as a promising paradigm enabling clients to adapt to heterogeneous data distributions. However, real-world scenarios often face the co-occurrence of non-IID data and long-tailed class distributions, presenting unique challenges that remain underexplored in …

cn, gb (code pays fourni par la source)

Decision Boundary-aware Generation for Long-tailed Learning

Jiacheng Yang, Ruichi Zhang, Chikai Shang, Mengke Li et autres

Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this problem by generating additional data, while head-to-tail transfer further mitigate the generator bias inherit from long-tailed dataset. However, we show that while head-to-tail transfer …

CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning

Ruichi Zhang, Chikai Shang, Jiacheng Yang, Mengke Li et autres

Long-tailed distributions are common in real-world recognition tasks, where a few head classes have many samples while most tail classes have very few. Recently, fine-tuning foundation models for long-tailed learning has gained attention due to their excellent performance. However, most existing methods …

Decision Boundary-aware Generation for Long-tailed Learning

Jiacheng Yang, Ruichi Zhang, Chikai Shang, Mengke Li et autres

Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this problem by generating additional data, while head-to-tail transfer further mitigate the generator bias inherit from long-tailed dataset. However, we show that while head-to-tail transfer …

cn, gb, hk (code pays fourni par la source)

CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning

Ruichi Zhang, Chikai Shang, Jiacheng Yang, Mengke Li et autres

Long-tailed distributions are common in real-world recognition tasks, where a few head classes have many samples while most tail classes have very few. Recently, fine-tuning foundation models for long-tailed learning has gained attention due to their excellent performance. However, most existing methods …

cn, sg (code pays fourni par la source)

SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning

Hezhao Liu, Jiacheng Yang, Junlong Gao, Mengke Li et autres

In open-world semi-supervised learning (OWSSL), a model learns from labeled data and unlabeled data containing both known and novel classes. In practical OWSSL applications, models are expected to perform rigorous classification by directly selecting the most semantically relevant label from a candidate …

SECOS: Semantic Capture for Rigorous Classification in Open-World Semi-Supervised Learning

Hezhao Liu, Jiacheng Yang, Junlong Gao, Mengke Li et autres

In open-world semi-supervised learning (OWSSL), a model learns from labeled data and unlabeled data containing both known and novel classes. In practical OWSSL applications, models are expected to perform rigorous classification by directly selecting the most semantically relevant label from a candidate …

cn, gb (code pays fourni par la source)

Prompt-Optimization with Contextual Mining for Cross-Modal Image Compression

Shenpeng Song, Zhimeng Huang, Junlong Gao, Chuanmin Jia et autres

Recent advances in cross-modal compression(CMC) have opened new horizons for perceptual image coding at ultra-low bitrates (below 0.1 bpp) within a generative compression paradigm, but reconstruction fidelity is often compromised, yielding visually plausible yet semantically inconsistent reconstructions. While prompt engineering with contextual …

cn (code pays fourni par la source)

RynnBrain: Open Embodied Foundation Models

Ronghao Dang, Jiayan Guo, Bohan Hou, Sicong Leng et autres

Despite rapid progress in multimodal foundation models, embodied intelligence community still lacks a unified, physically grounded foundation model that integrates perception, reasoning, and planning within real-world spatial-temporal dynamics. We introduce RynnBrain, an open-source spatiotemporal foundation model for embodied intelligence. RynnBrain strengthens four …

RynnBrain: Open Embodied Foundation Models

Ronghao Dang, Jiayan Guo, Bohan Hou, Sicong Leng et autres

Despite rapid progress in multimodal foundation models, embodied intelligence community still lacks a unified, physically grounded foundation model that integrates perception, reasoning, and planning within real-world spatial-temporal dynamics. We introduce RynnBrain, an open-source spatiotemporal foundation model for embodied intelligence. RynnBrain strengthens four …

ART-VOD: Adaptive Relational Distillation and Temporal Modeling for Open-Vocabulary Video Object Detection

Yang Cao, Junlong Gao, Yan Yan, Hanzi Wang

cn (code pays fourni par la source)