Related papers: Evaluating Deep Human-in-the-Loop Optimization for Retinal Implants Using Sighted Participants

Related papers

P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization [55.74731799669337]
Hallucination has recently garnered significant research attention in Large Vision-Language Models (LVLMs)<n>Direct Preference Optimization (DPO) aims to learn directly from the corrected preferences provided by humans.<n>Existing preference pairs are often vision-agnostic and their inherently off-policy nature limits their effectiveness in guiding model learning.<n>We propose Perceptual Processing Direct Preference Optimization (P$2$-DPO), a novel training paradigm in which the model generates and learns from its own preference pairs.
arXiv Detail & Related papers (2026-06-02T09:22:53Z)
AI Outperforms Humans in Personalized Image Aesthetics Assessment via LLM-Based Interviews and Semantic Feature Extraction [2.905751301655124]
Accurately predicting individual aesthetic evaluation for images is a fundamental challenge for AI.<n>We develop an integrated DL-LLM system that elicits aesthetic preferences through semi-structured interviews.<n>Our results show that the proposed system outperforms all of them, with particularly strong performance on highly-rated images.
arXiv Detail & Related papers (2026-05-14T12:24:23Z)
Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models [53.15468578562038]
We propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for Multimodal Large Language Models (MLLMs)<n>We first quantify the uncertainty from the model's failure to ground token predictions in the given image.<n>We then encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples.
arXiv Detail & Related papers (2026-05-06T13:08:12Z)
Bridging Human Evaluation to Infrared and Visible Image Fusion [54.71406895277533]
Infrared and visible image fusion (IVIF) integrates complementary modalities to enhance scene perception.<n>Current methods predominantly focus on optimizing handcrafted losses and objective metrics, often resulting in fusion outcomes that do not align with human visual preferences.<n>We propose a feedback reinforcement framework that bridges human evaluation to infrared and visible image fusion.
arXiv Detail & Related papers (2026-03-04T09:23:57Z)
Bayesian Preference Elicitation: Human-In-The-Loop Optimization of An Active Prosthesis [3.6494031371026323]
We introduce a human-in-the-loop optimization (HILO) approach to personalize a standard four- parameter prosthesis controller efficiently.<n>We show efficient convergence, robust preference elicitation, and measurable biomechanical improvements.
arXiv Detail & Related papers (2026-02-26T12:11:51Z)
Preference is More Than Comparisons: Rethinking Dueling Bandits with Augmented Human Feedback [17.459431876117176]
Interactive preference elicitation (IPE) aims to substantially reduce human effort while acquiring human preferences in wide personalization systems.<n>Dueling bandit (DB) algorithms enable optimal decision-making in IPE building on pairwise comparisons.<n>We introduce an alternative perspective based on feedback augmentation, and introduce critical improvements to the model-free DB framework.<n>Our prototype algorithm achieves competitive performance across several IPE benchmarks, including recommendation, multi-objective optimization, and response optimization for large language models.
arXiv Detail & Related papers (2025-11-12T06:56:35Z)
MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
arXiv Detail & Related papers (2025-10-24T02:11:05Z)
ControlEchoSynth: Boosting Ejection Fraction Estimation Models via Controlled Video Diffusion [12.459487400882068]
We propose a novel approach for enhancing clinical diagnosis accuracy by synthetically generating echo views.<n>These views are conditioned on existing, real views of the heart, focusing specifically on the estimation of ejection fraction (EF)<n>Preliminary results indicate that our synthetic echoes, when used to augment existing datasets, not only enhance EF estimation but also show potential in advancing the development of more robust, accurate, and clinically relevant machine learning models.
arXiv Detail & Related papers (2025-08-25T03:27:25Z)
Human Scanpath Prediction in Target-Present Visual Search with Semantic-Foveal Bayesian Attention [49.99728312519117]
SemBA-FAST is a top-down framework designed for predicting human visual attention in target-present visual search.<n>We evaluate SemBA-FAST on the COCO-Search18 benchmark dataset, comparing its performance against other scanpath prediction models.<n>These findings provide valuable insights into the capabilities of semantic-foveal probabilistic frameworks for human-like attention modelling.
arXiv Detail & Related papers (2025-07-24T15:19:23Z)
Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization [58.64721525687295]
Direct Preference Optimization (DPO) has emerged as an effective approach for mitigating hallucination in Multimodal Large Language Models (MLLMs)<n>We propose a Symmetric Multimodal Preference Optimization (SymMPO) which conducts symmetric preference learning with direct preference supervision (i.e., response pairs)<n>In addition to conventional ordinal preference learning, SymMPO introduces a preference margin consistency loss to quantitatively regulate the preference gap between symmetric preference pairs.
arXiv Detail & Related papers (2025-06-13T12:29:15Z)
Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data [51.62162460809116]
We introduce Dynamic Noise Preference Optimization (DNPO) to ensure consistent improvements across iterations. In experiments with Zephyr-7B, DNPO consistently outperforms existing methods, showing an average performance boost of 2.6%. DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.
arXiv Detail & Related papers (2025-02-08T01:20:09Z)
Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment [73.14105098897696]
We propose Representation-Aligned Preference-based Learning (RAPL) to learn visual rewards from significantly less human preference feedback. RAPL focuses on fine-tuning pre-trained vision encoders to align with the end-user's visual representation and then constructs a dense visual reward via feature matching. We show that RAPL can learn rewards aligned with human preferences, more efficiently uses preference data, and generalizes across robot embodiments.
arXiv Detail & Related papers (2024-12-06T08:04:02Z)
A Topic-level Self-Correctional Approach to Mitigate Hallucinations in MLLMs [34.71750379630014]
We introduce Topic-level Preference Overwriting (TPO), a self-correctional approach that guide the model itself to mitigate its own hallucination at the topic level. Results show TPO achieves state-of-the-art performance in trustworthiness, significantly reducing the object hallucinations by 92% and overall hallucinations by 38%.
arXiv Detail & Related papers (2024-11-26T09:42:07Z)
VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment [55.7956150385255]
We investigate the efficacy of AI feedback to scale supervision for aligning vision-language models. We introduce VLFeedback, the first large-scale vision-language feedback dataset. We train Silkie, an LVLM fine-tuned via direct preference optimization on VLFeedback.
arXiv Detail & Related papers (2024-10-12T07:56:47Z)
Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
arXiv Detail & Related papers (2024-09-26T12:37:26Z)
Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
arXiv Detail & Related papers (2024-06-04T20:33:22Z)
LIRE: listwise reward enhancement for preference alignment [27.50204023448716]
We propose a gradient-based reward optimization approach that incorporates the offline rewards of multiple responses into a streamlined listwise framework. LIRE is straightforward to implement, requiring minimal parameter tuning, and seamlessly aligns with the pairwise paradigm. Our experiments demonstrate that LIRE consistently outperforms existing methods across several benchmarks on dialogue and summarization tasks.
arXiv Detail & Related papers (2024-05-22T10:21:50Z)
Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models [85.96013373385057]
Fine-tuning text-to-image models with reward functions trained on human feedback data has proven effective for aligning model behavior with human intent. However, excessive optimization with such reward models, which serve as mere proxy objectives, can compromise the performance of fine-tuned models. We propose TextNorm, a method that enhances alignment based on a measure of reward model confidence estimated across a set of semantically contrastive text prompts.
arXiv Detail & Related papers (2024-04-02T11:40:38Z)
Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation [46.61909578101735]
Adversarial Policy Optimization (AdvPO) is a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback. In this paper, we introduce a lightweight way to quantify uncertainties in rewards, relying solely on the last layer embeddings of the reward model.
arXiv Detail & Related papers (2024-03-08T09:20:12Z)
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases [76.9127853906115]
Bridging the gap between diffusion models and human preferences is crucial for their integration into practical generative. We propose Temporal Diffusion Policy Optimization with critic active neuron Reset (TDPO-R), a policy gradient algorithm that exploits the temporal inductive bias of diffusion models. Empirical results demonstrate the superior efficacy of our methods in mitigating reward overoptimization.
arXiv Detail & Related papers (2024-02-13T15:55:41Z)
Who Are We Missing? A Principled Approach to Characterizing the Underrepresented Population [5.568543786710628]
We introduce an optimization-based approach, Rashomon Set of Optimal Trees (ROOT), to characterize underrepresented groups. ROOT optimize the target subpopulation distribution by minimizing the variance of the target average treatment effect estimate. Our framework offers a systematic approach to enhance decision-making accuracy and inform future trials in diverse populations.
arXiv Detail & Related papers (2024-01-25T21:11:35Z)
Interactive Hyperparameter Optimization in Multi-Objective Problems via Preference Learning [65.51668094117802]
We propose a human-centered interactive HPO approach tailored towards multi-objective machine learning (ML) Instead of relying on the user guessing the most suitable indicator for their needs, our approach automatically learns an appropriate indicator.
arXiv Detail & Related papers (2023-09-07T09:22:05Z)
Preference Ranking Optimization for Human Alignment [90.6952059194946]
Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values. Reinforcement learning from human feedback (RLHF) has been employed to achieve this alignment. We propose Preference Ranking Optimization (PRO) as an efficient SFT algorithm to fine-tune LLMs for human alignment.
arXiv Detail & Related papers (2023-06-30T09:07:37Z)
Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses [2.7309692684728617]
Neuroprostheses show potential in restoring lost sensory function and enhancing human capabilities, but the sensations produced by current devices often seem unnatural or distorted. We propose a novel, practically feasible approach that overcomes both of these fundamental limitations. We show that our approach quickly learns a personalized stimulus encoder, leads to dramatic improvements in the quality of restored vision, and is robust to noisy patient feedback.
arXiv Detail & Related papers (2023-06-16T18:49:51Z)
Provable Reward-Agnostic Preference-Based Reinforcement Learning [61.39541986848391]
Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories. We propose a theoretical reward-agnostic PbRL framework where exploratory trajectories that enable accurate learning of hidden reward functions are acquired.
arXiv Detail & Related papers (2023-05-29T15:00:09Z)
Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles [16.916111322004557]
A black-box objective function can only be gauged via a ranking oracle. We introduce ZO-RankSGD, an innovative zeroth-order optimization algorithm. We show that ZO-RankSGD can significantly enhance the detail of generated images with only a few rounds of human feedback.
arXiv Detail & Related papers (2023-03-07T09:20:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.