Related papers: CLASP: Class-Adaptive Layer Fusion and Dual-Stage …

Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context…

For multimodal large language models (MLLMs), visual information is relatively sparse compared with text. As a result, research on visual pruning emerges for efficient inference. Current approaches typically measure token importance based…

Vision-Language-Action (VLA) models have shown remarkable promise in robotics manipulation, yet their high computational cost hinders real-time deployment. Existing token pruning methods suffer from a fundamental trade-off: aggressive…

Current structural pruning methods face two significant limitations: (i) they often limit pruning to finer-grained levels like channels, making aggressive parameter reduction challenging, and (ii) they focus heavily on parameter and FLOP…

Learning a versatile language-image model is computationally prohibitive under a limited computing budget. This paper delves into the \emph{efficient language-image pre-training}, an area that has received relatively little attention…

The high computational demands of Large Language Models (LLMs) motivate methods that reduce parameter count and accelerate inference. In response, model pruning emerges as an effective strategy, yet current methods typically focus on a…

Data-efficient learning aims to eliminate redundancy in large training datasets by training models on smaller subsets of the most informative examples. While data selection has been extensively explored for vision models and large language…

Large pre-trained vision-language models, such as CLIP, have demonstrated state-of-the-art performance across a wide range of image classification tasks, without requiring retraining. Few-shot CLIP is competitive with existing specialized…

Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and memory costs hinder deployment in resource-constrained settings. While Post-Training Quantization (PTQ) and vision token pruning…

Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in the real-world scenarios. To achieve…

Large vision-language models (LVLMs) employ multi-modal in-context learning (MM-ICL) to adapt to new tasks by leveraging demonstration examples. While increasing the number of demonstrations boosts performance, they incur significant…

Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategies, which can lead to…

Omni-modal large language models have demonstrated remarkable potential in holistic multimodal understanding; however, the token explosion caused by high-resolution audio and video inputs remains a critical bottleneck for real-time…

The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense…

Recently, multi-view learning (MVL) has garnered significant attention due to its ability to fuse discriminative information from multiple views. However, real-world multi-view datasets are often heterogeneous and imperfect, which usually…

Vision-Language Models (VLMs) process thousands of visual tokens per image alongside comparatively few text tokens, yet existing compression methods treat both modalities uniformly. We observe that the two modalities have fundamentally…

Pruning vision-language models (VLMs) for efficient deployment is challenging because compression can affect not only task utility but also visual grounding, often amplifying object hallucinations even at the same sparsity level. We present…

Vision-Language-Action (VLA) models have achieved significant breakthroughs by leveraging Large Vision Language Models (VLMs) to jointly interpret instructions and visual inputs. However, the substantial increase in visual tokens,…

While Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose significant barriers to practical deployment. Current parameter reduction techniques primarily…

While multi-modal large language models (MLLMs) have made significant progress in recent years, the issue of hallucinations remains a major challenge. To mitigate this phenomenon, existing solutions either introduce additional data for…