4 citations · 9 across the 18 of their papers we have counts for
22 papers
Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation
Xuening Zhang, Qi Lv, Xiang Deng +3
View transformers process multi-view observations to predict actions and have shown impressive performance in robotic manipulation. Existing methods typically extract static visual…
TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models
Qianlong Xiang, Miao Zhang, Haoyu Zhang +3
Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for their safe deployment to prevent the creation of harmful c…
Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
Jiarui Jiang, Wei Huang, Miao Zhang +2
State-space models (SSMs), particularly Mamba, emerge as an efficient Transformer alternative with linear complexity for long-sequence modeling. Recent empirical works demonstrate…
GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning
Xiaojie Li, Bei Wang, Wei Liu +4
The success of contrastive learning depends on the construction and utilization of high-quality positive pairs. However, current methods face critical limitations on two fronts: on…
A Survey on Video Temporal Grounding with Multimodal Large Language Model
Jianlong Wu, Wei Liu, Ye Liu +4
The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs).…
PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling
Yuxuan Yue, Zukang Xu, Zhihang Yuan +3
Large Language Models (LLMs) face significant challenges in edge deployment due to their massive parameter scale. Vector Quantization (VQ), a clustering-based quantization method,…
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding
Xiao Wang, Qingyi Si, Jianlong Wu +3
Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos. Recent methods compress video…
MegaSR: Mining Customized Semantics and Expressive Guidance for Real-World Image Super-Resolution
Xinrui Li, Jinrong Zhang, Jianlong Wu +3
Text-to-image (T2I) models have ushered in a new era of real-world image super-resolution (Real-ISR) due to their rich internal implicit knowledge for multimodal learning. Although…
HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models
Xiao Wang, Jingyun Hua, Weihong Lin +5
Recent Multi-modal Large Language Models (MLLMs) have made great progress in video understanding. However, their performance on videos involving human actions is still limited by t…
Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis
Jiaqi Zhao, Ming Wang, Miao Zhang +5
Post-training Quantization (PTQ) technique has been extensively adopted for large language models (LLMs) compression owing to its efficiency and low resource requirement. However,…
Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning
Xiaojie Li, Jianlong Wu, Yue Yu +2
Few-Shot Class-Incremental Learning (FSCIL) faces a critical challenge: balancing the retention of prior knowledge with the acquisition of new classes. Existing methods either free…
ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding
Xiao Wang, Qingyi Si, Jianlong Wu +3
Video Large Language Models (VideoLLMs) have made significant strides in video understanding but struggle with long videos due to the limitations of their backbone LLMs. Existing s…
RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training
Muhe Ding, Yang Ma, Pengda Qin +3
Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tas…
Preview-based Category Contrastive Learning for Knowledge Distillation
Muhe Ding, Jianlong Wu, Xue Dong +4
Knowledge distillation is a mainstream algorithm in model compression by transferring knowledge from the larger model (teacher) to the smaller model (student) to improve the perfor…
Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding
Xiao Wang, Jianlong Wu, Zijia Lin +3
Recently, video-language understanding has achieved great success through large-scale pre-training. However, data scarcity remains a prevailing challenge. This study quantitatively…
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
Jiarui Jiang, Wei Huang, Miao Zhang +2
Transformers have demonstrated great power in the recent development of large foundational models. In particular, the Vision Transformer (ViT) has brought revolutionary changes to…
DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture
Qianlong Xiang, Miao Zhang, Yuzhang Shang +3
Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effective…
Social Debiasing for Fair Multi-modal LLMs
Harry Cheng, Yangyang Guo, Qingpei Guo +4
Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models oft…
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
Xiaojie Li, Yibo Yang, Jianlong Wu +4
Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes from limited examples while preserving knowledge of previously learned classes. Existing metho…
A Survey on Human Preference Learning for Large Language Models
Ruili Jiang, Kehai Chen, Xuefeng Bai +6
The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning, enhancin…
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning
Yibo Yang, Xiaojie Li, Zhongzhu Zhou +4
Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain.…
WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More
Yuxuan Yue, Zhihang Yuan, Haojie Duanmu +3
Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation pr…