The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Large Vision-Language Models (LVLMs) can reason effectively over both textual and visual inputs, but they tend to hallucinate syntactically coherent yet visually ungrounded contents. In this paper, we investigate the internal dynamics of hallucination by examining the tokens logits rankings throughout the generation process, revealing three key patterns in how LVLMs process information: (1) gradual visual information loss -- visually grounded tokens gradually become less favored throughout generation, and (2) early excitation -- semantically meaningful tokens achieve peak activation in the layers earlier than the final layer. (3) hidden genuine information -- visually grounded tokens though not being eventually decided still retain relatively high rankings at inference. Based on these insights, we propose VISTA (Visual Information Steering with Token-logit Augmentation), a training-free inference-time intervention framework that reduces hallucination while promoting genuine information. VISTA works by combining two complementary approaches: reinforcing visual information in activation space and leveraging early layer activations to promote semantically meaningful decoding. Compared to existing methods, VISTA requires no external supervision and is applicable to various decoding strategies. Extensive experiments show that VISTA on average reduces hallucination by abount 40% on evaluated open-ended generation task, and it consistently outperforms existing methods on four benchmarks across four architectures under three decoding strategies.

MLLM-as-a-Judge for Image Safety without Human Labeling

Image content safety has become a significant challenge with the rise of visual media on online platforms. Meanwhile, in the age of AI-generated content (AIGC), many image generation models are capable of producing harmful content, such as images containing sexual or violent material. Thus, it becomes crucial to identify such unsafe images based on established safety rules. Pre-trained Multimodal Large Language Models (MLLMs) offer potential in this regard, given their strong pattern recognition abilities. Existing approaches typically fine-tune MLLMs with human-labeled datasets, which however brings a series of drawbacks. First, relying on human annotators to label data following intricate and detailed guidelines is both expensive and labor-intensive. Furthermore, users of safety judgment systems may need to frequently update safety rules, making fine-tuning on human-based annotation more challenging. This raises the research question: Can we detect unsafe images by querying MLLMs in a zero-shot setting using a predefined safety constitution (a set of safety rules)? Our research showed that simply querying pre-trained MLLMs does not yield satisfactory results. This lack of effectiveness stems from factors such as the subjectivity of safety rules, the complexity of lengthy constitutions, and the inherent biases in the models. To address these challenges, we propose a MLLM-based method includes objectifying safety rules, assessing the relevance between rules and images, making quick judgments based on debiased token probabilities with logically complete yet simplified precondition chains for safety rules, and conducting more in-depth reasoning with cascaded chain-of-thought processes if necessary. Experiment results demonstrate that our method is highly effective for zero-shot image safety judgment tasks.

Implicit In-context Learning

In-context Learning (ICL) empowers large language models (LLMs) to adapt to unseen tasks during inference by prefixing a few demonstration examples prior to test queries. Despite its versatility, ICL incurs substantial computational and memory overheads compared to zero-shot learning and is susceptible to the selection and order of demonstration examples. In this work, we introduce Implicit In-context Learning (I2CL), an innovative paradigm that addresses the challenges associated with traditional ICL by absorbing demonstration examples within the activation space. I2CL first generates a condensed vector representation, namely a context vector, from the demonstration examples. It then integrates the context vector during inference by injecting a linear combination of the context vector and query activations into the model's residual streams. Empirical evaluation on nine real-world tasks across three model architectures demonstrates that I2CL achieves few-shot performance with zero-shot cost and exhibits robustness against the variation of demonstration examples. Furthermore, I2CL facilitates a novel representation of "task-ids", enhancing task similarity detection and enabling effective transfer learning. We provide a comprehensive analysis of I2CL, offering deeper insights into its mechanisms and broader implications for ICL. The source code is available at: https://github.com/LzVv123456/I2CL.

GAgent: An Adaptive Rigid-Soft Gripping Agent with Vision Language Models for Complex Lighting Environments

This paper introduces GAgent: an Gripping Agent designed for open-world environments that provides advanced cognitive abilities via VLM agents and flexible grasping abilities with variable stiffness soft grippers. GAgent comprises three primary components - Prompt Engineer module, Visual-Language Model (VLM) core and Workflow module. These three modules enhance gripper success rates by recognizing objects and materials and accurately estimating grasp area even under challenging lighting conditions. As part of creativity, researchers also created a bionic hybrid soft gripper with variable stiffness capable of gripping heavy loads while still gently engaging objects. This intelligent agent, featuring VLM-based cognitive processing with bionic design, shows promise as it could potentially benefit UAVs in various scenarios.

DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image

Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics. By leveraging a set of primitives to represent the target shape, recent methods have achieved promising results. However, these methods either use a relatively large number of primitives or lack geometric flexibility due to the limited expressibility of the primitives. In this paper, we propose a novel bi-channel Transformer architecture, integrated with parameterized deformable models, termed DeFormer, to simultaneously estimate the global and local deformations of primitives. In this way, DeFormer can abstract complex object shapes while using a small number of primitives which offer a broader geometry coverage and finer details. Then, we introduce a force-driven dynamic fitting and a cycle-consistent re-projection loss to optimize the primitive parameters. Extensive experiments on ShapeNet across various settings show that DeFormer achieves better reconstruction accuracy over the state-of-the-art, and visualizes with consistent semantic correspondences for improved interpretability.

Training Like a Medical Resident: Universal Medical Image Segmentation via Context Prior Learning

A major enduring focus of clinical workflows is disease analytics and diagnosis, leading to medical imaging datasets where the modalities and annotations are strongly tied to specific clinical objectives. To date, building task-specific segmentation models is intuitive yet a restrictive approach, lacking insights gained from widespread imaging cohorts. Inspired by the training of medical residents, we explore universal medical image segmentation, whose goal is to learn from diverse medical imaging sources covering a range of clinical targets, body regions, and image modalities. Following this paradigm, we propose Hermes, a context prior learning approach that addresses the challenges related to the heterogeneity on data, modality, and annotations in the proposed universal paradigm. In a collection of seven diverse datasets, we demonstrate the appealing merits of the universal paradigm over the traditional task-specific training paradigm. By leveraging the synergy among various tasks, Hermes shows superior performance and model scalability. Our in-depth investigation on two additional datasets reveals Hermes' strong capabilities for transfer learning, incremental learning, and generalization to different downstream tasks. The code is available: https://github.com/yhygao/universal-medical-image-segmentation.

Steering Prototype with Prompt-tuning for Rehearsal-free Continual Learning

Prototype, as a representation of class embeddings, has been explored to reduce memory footprint or mitigate forgetting for continual learning scenarios. However, prototype-based methods still suffer from abrupt performance deterioration due to semantic drift and prototype interference. In this study, we propose Contrastive Prototypical Prompt (CPP) and show that task-specific prompt-tuning, when optimized over a contrastive learning objective, can effectively address both obstacles and significantly improve the potency of prototypes. Our experiments demonstrate that CPP excels in four challenging class-incremental learning benchmarks, resulting in 4% to 6% absolute improvements over state-of-the-art methods. Moreover, CPP does not require a rehearsal buffer and it largely bridges the performance gap between continual learning and offline joint-learning, showcasing a promising design scheme for continual learning systems under a Transformer architecture.

Towards Self-supervised and Weight-preserving Neural Architecture Search

Neural architecture search (NAS) algorithms save tremendous labor from human experts. Recent advancements further reduce the computational overhead to an affordable level. However, it is still cumbersome to deploy the NAS techniques in real-world applications due to the fussy procedures and the supervised learning paradigm. In this work, we propose the self-supervised and weight-preserving neural architecture search (SSWP-NAS) as an extension of the current NAS framework by allowing the self-supervision and retaining the concomitant weights discovered during the search stage. As such, we simplify the workflow of NAS to a one-stage and proxy-free procedure. Experiments show that the architectures searched by the proposed framework achieve state-of-the-art accuracy on CIFAR-10, CIFAR-100, and ImageNet datasets without using manual labels. Moreover, we show that employing the concomitant weights as initialization consistently outperforms the random initialization and the two-stage weight pre-training method by a clear margin under semi-supervised learning scenarios. Codes are publicly available at https://github.com/LzVv123456/SSWP-NAS.

Contrastive and Selective Hidden Embeddings for Medical Image Segmentation

Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning. However, the laborious and expensive annotation process lags down the speed of further advances. Contrastive learning-based weight pre-training provides an alternative by leveraging unlabeled data to learn a good representation. In this paper, we investigate how contrastive learning benefits the general supervised medical segmentation tasks. To this end, patch-dragsaw contrastive regularization (PDCR) is proposed to perform patch-level tugging and repulsing with the extent controlled by a continuous affinity score. And a new structure dubbed uncertainty-aware feature selection block (UAFS) is designed to perform the feature selection process, which can handle the learning target shift caused by minority features with high uncertainty. By plugging the proposed 2 modules into the existing segmentation architecture, we achieve state-of-the-art results across 8 public datasets from 6 domains. Newly designed modules further decrease the amount of training data to a quarter while achieving comparable, if not better, performances. From this perspective, we take the opposite direction of the original self/un-supervised contrastive learning by further excavating information contained within the label.

Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation

Deep learning has demonstrated significant improvements in medical image segmentation using a sufficiently large amount of training data with manual labels. Acquiring well-representative labels requires expert knowledge and exhaustive labors. In this paper, we aim to boost the performance of semi-supervised learning for medical image segmentation with limited labels using a self-ensembling contrastive learning technique. To this end, we propose to train an encoder-decoder network at image-level with small amounts of labeled images, and more importantly, we learn latent representations directly at feature-level by imposing contrastive loss on unlabeled images. This method strengthens intra-class compactness and inter-class separability, so as to get a better pixel classifier. Moreover, we devise a student encoder for online learning and an exponential moving average version of it, called teacher encoder, to improve the performance iteratively in a self-ensembling manner. To construct contrastive samples with unlabeled images, two sampling strategies that exploit structure similarity across medical images and utilize pseudo-labels for construction, termed region-aware and anatomical-aware contrastive sampling, are investigated. We conduct extensive experiments on an MRI and a CT segmentation dataset and demonstrate that in a limited label setting, the proposed method achieves state-of-the-art performance. Moreover, the anatomical-aware strategy that prepares contrastive samples on-the-fly using pseudo-labels realizes better contrastive regularization on feature representations.