Schizophrenia

Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models

Although multimodal large language models (MLLMs) exhibit remarkable reasoning capabilities on complex multimodal understanding tasks, they still suffer from the notorious hallucination issue: generating outputs misaligned with obvious visual or factual evidence. Currently, training-based solutions, like direct preference optimization (DPO), leverage paired preference data to suppress hallucinat...

Perception in Reflection

We present a perception in reflection paradigm designed to transcend the limitations of current large vision-language models (LVLMs), which are expected yet often fail to achieve perfect perception initially. Specifically, we propose Reflective Perception (RePer), a dual-model reflection mechanism that systematically alternates between policy and critic models, enables iterative refinement of vi...

HalluciNot: Hallucination Detection Through Context and Common Knowledge Verification

This paper introduces a comprehensive system for detecting hallucinations in large language model (LLM) outputs in enterprise settings. We present a...

TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection

Large Vision-Language Models have demonstrated remarkable performance across various tasks; however, the challenge of hallucinations constrains thei...

Can ChatGPT Learn My Life From a Week of First-Person Video?

Motivated by recent improvements in generative AI and wearable camera devices (e.g. smart glasses and AI-enabled pins), I investigate the ability of...

A Memory-Augmented LLM-Driven Method for Autonomous Merging of 3D Printing Work Orders

With the rapid development of 3D printing, the demand for personalized and customized production on the manufacturing line is steadily increasing. E...

HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation

Text-to-video (T2V) generation has made tremendous progress in generating complicated scenes based on texts. However, human-object interaction (HOI)...

Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best?

This article surveys Evaluation models to automatically detect hallucinations in Retrieval-Augmented Generation (RAG), and presents a comprehensive ...

Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy

The rapid development of multimodal large language models has resulted in remarkable advancements in visual perception and understanding, consolidat...

Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering

Multimodal large language models (MLLMs) have demonstrated significant potential in medical Visual Question Answering (VQA). Yet, they remain prone ...

GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization

Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. W...

Bigger But Not Better: Small Neural Language Models Outperform Large Language Models in Detection of Thought Disorder

Disorganized thinking is a key diagnostic indicator of schizophrenia-spectrum disorders. Recently, clinical estimates of the severity of disorganize...

CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning

The rapid advancement of large vision-language models (LVLMs) has driven significant progress in multimodal tasks, enabling models to interpret, rea...

Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation

The hallucination of large multimodal models (LMMs), providing responses that appear correct but are actually incorrect, limits their reliability an...

LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text

This study addresses the technical bottlenecks in handling long text and the "hallucination" issue caused by insufficient short text information in ...

good4cir: Generating Detailed Synthetic Captions for Composed Image Retrieval

Composed image retrieval (CIR) enables users to search images using a reference image combined with textual modifications. Recent advances in vision...

Judge Anything: MLLM as a Judge Across Any Modality

Evaluating generative foundation models on open-ended multimodal understanding (MMU) and generation (MMG) tasks across diverse modalities (e.g., ima...

ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing

Recent approaches using large-scale pretrained diffusion models for image dehazing improve perceptual quality but often suffer from hallucination is...

FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs

Large Language Models (LLMs) frequently generate hallucinated content, posing significant challenges for applications where factuality is crucial. W...

REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models

The rapid evolution of Large Vision-Language Models (LVLMs) has highlighted the necessity for comprehensive evaluation frameworks that assess these ...