相关论文: Interpretability Transfer from Language to Vision …

Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…

Large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks. Understanding how LLMs internally represent knowledge remains a significant challenge. Despite Sparse Autoencoders (SAEs) have…

Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dictionary of abstract, human-interpretable concepts. However, we…

Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific…

Recent transformer-based methods achieve notable gains in the Human-object Interaction Detection (HOID) task by leveraging the detection of DETR and the prior knowledge of Vision-Language Model (VLM). However, these methods suffer from…

Recently vision transformer models have become prominent models for a range of vision tasks. These models, however, are usually opaque with weak feature interpretability. Moreover, there is no method currently built for an intrinsically…

Large Vision-Language Models (LVLMs) have achieved remarkable success but continue to struggle with object hallucination (OH), generating outputs inconsistent with visual inputs. While previous work has proposed methods to reduce OH, the…

Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a…

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

Recent work shows that Sparse Autoencoders (SAE) applied to large language model (LLM) layers have neurons corresponding to interpretable concepts. These SAE neurons can be modified to align generated outputs, but only towards…

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

Variational Autoencoders (VAEs) are powerful generative models for learning latent representations. Standard VAEs generate dispersed and unstructured latent spaces by utilizing all dimensions, which limits their interpretability, especially…

Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto-regressive language…

Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous expression to its intended meaning. Although prior work has proposed…

Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…

Visual-Language Alignment (VLA) has gained a lot of attention since CLIP's groundbreaking work. Although CLIP performs well, the typical direct latent feature alignment lacks clarity in its representation and similarity scores. On the other…

3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence. Current 3D-VL models rely heavily on sophisticated modules,…

Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the…