63 citations · 235 across the 69 of their papers we have counts for
82 papers
Conflict-Aware Logit Adapters for Utility-Preserving Anti-Distillation
Quoc Phong Dao, Binh Anh Nguyen, Linh Ngo Van +3
While reasoning traces improve model capability, they also provide supervision signals for downstream distillation. Initial efforts to mitigate this issue rely on decoding-time int…
VGGA: Geometry-Grounded Autoencoder for Video Generation
Chaofan Gan, Yian Zhao, Shijie Li +4
Autoencoders are the core component of latent video generative models, compressing high-dimensional videos into compact latent spaces for downstream generation. However, existing v…
Open Vocabulary Domain Unlearning
Sumanth Udupa, Mehrtash Harandi, Yadan Luo +1
Vision-Language Models (VLMs) exhibit remarkable zero-shot generalization, yet they often encode unwanted or hazardous stylistic domains such as idealized textbook diagrams in medi…
Reliability-Prioritized Fine-Grained Generation in Multimodal Large
Xiaomeng Fan, Wei Wu, Yuwei Wu +9
Multimodal large language models (MLLMs) are increasingly expected to generate fine-grained descriptions of visual content. However, we observe and theoretically show that generati…
Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation
Chaofan Gan, Zicheng Zhao, Yuanpeng Tu +6
Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiTs) remain insufficiently und…
Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modeling
Minh-Tuan Tran, Xuan-May Le, Quan Hung Tran +3
Existing generative models, such as diffusion and auto-regressive networks, are inherently static, relying on a fixed set of pretrained parameters to handle all inputs. In contrast…
Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
Haocheng Luo, Zehang Deng, Thanh-Toan Do +3
Direct Preference Optimization (DPO) has emerged as a popular algorithm for aligning pretrained large language models with human preferences, owing to its simplicity and training s…
Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
Quoc Minh Nguyen, Trung Le, Jing Wu +2
Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as…
Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers
Chaofan Gan, Zicheng Zhao, Yuanpeng Tu +5
Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for visual generation. Recent observations reveal \emph{Massive Activations} (MAs) in their internal feat…
Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds
Wei Wu, Xiaomeng Fan, Yuwei Wu +4
Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features fro…
Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise
Haocheng Luo, Mehrtash Harandi, Dinh Phung +1
Sharpness-aware minimization (SAM) has emerged as a highly effective technique to improve model generalization, but its underlying principles are not fully understood. We investiga…
Curvature Learning for Generalization of Hyperbolic Neural Networks
Xiaomeng Fan, Yuwei Wu, Zhi Gao +2
Hyperbolic neural networks (HNNs) have demonstrated notable efficacy in representing real-world data with hierarchical structures via exploiting the geometric properties of hyperbo…
Advancements and Challenges in Continual Reinforcement Learning: A Comprehensive Review
Amara Zuffer, Michael Burke, Mehrtash Harandi
The diversity of tasks and dynamic nature of reinforcement learning (RL) require RL agents to be able to learn sequentially and continuously, a learning paradigm known as continuou…
Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spaces
Pengxiang Li, Yuwei Wu, Zhi Gao +5
Learning in hyperbolic spaces has attracted increasing attention due to its superior ability to model hierarchical structures of data. Most existing hyperbolic learning methods use…
A Set-to-Set Distance Measure in Hyperbolic Space
Pengxiang Li, Wei Wu, Zhi Gao +6
We propose a hyperbolic set-to-set distance measure for computing dissimilarity between sets in hyperbolic space. While point-to-point distances in hyperbolic space effectively cap…
Flashbacks to Harmonize Stability and Plasticity in Continual Learning
Leila Mahmoodi, Peyman Moghadam, Munawar Hayat +2
We introduce Flashback Learning (FL), a novel method designed to harmonize the stability and plasticity of models in Continual Learning (CL). Unlike prior approaches that primarily…
Exemplar-Free Continual Learning for State Space Models
Isaac Ning Lee, Leila Mahmoodi, Trung Le +1
State-Space Models (SSMs) excel at capturing long-range dependencies with structured recurrence, making them well-suited for sequence modeling. However, their evolving internal sta…
Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations
Chaofan Gan, Yuanpeng Tu, Xi Chen +4
Pre-trained stable diffusion models (SD) have shown great advances in visual correspondence. In this paper, we investigate the capabilities of Diffusion Transformers (DiTs) for acc…
MoKD: Multi-Task Optimization for Knowledge Distillation
Zeeshan Hayder, Ali Cheraghian, Lars Petersson +1
Compact models can be effectively trained through Knowledge Distillation (KD), a technique that transfers knowledge from larger, high-performing teacher models. Two key challenges…
Optimizing Specific and Shared Parameters for Efficient Parameter Tuning
Van-Anh Nguyen, Thanh-Toan Do, Mehrtash Harandi +2
Foundation models, with a vast number of parameters and pretraining on massive datasets, achieve state-of-the-art performance across various applications. However, efficiently adap…
PCGS: Progressive Compression of 3D Gaussian Splatting
Yihang Chen, Mengyao Li, Qianyi Wu +3
3D Gaussian Splatting (3DGS) achieves impressive rendering fidelity and speed for novel view synthesis. However, its substantial data size poses a significant challenge for practic…
Learning from Noisy Labels with Contrastive Co-Transformer
Yan Han, Soumava Kumar Roy, Mehrtash Harandi +1
Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the prese…
Why Domain Generalization Fail? A View of Necessity and Sufficiency
Long-Tung Vuong, Vy Vo, Hien Dang +5
Despite a strong theoretical foundation, empirical experiments reveal that existing domain generalization (DG) algorithms often fail to consistently outperform the ERM baseline. We…
HAC++: Towards 100X Compression of 3D Gaussian Splatting
Yihang Chen, Qianyi Wu, Weiyao Lin +2
3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians an…