论文检索

Zhengxi Lu, Yuxiang Chai, Yaxuan Guo, Xi Yin, Liang Liu, Hao Wang, Han Xiao, Shuai Ren, Pengxiang Zhao, Guangyi Liu 等

The recent DeepSeek-R1 has showcased the emergence of reasoning capabilities in large language models (LLMs) through reinforcement learning (RL) with rule-based rewards. Despite its success in language tasks, its application in multimodal domains, particularly in graphic user interface (GUI) agent tasks, remains under-explored. To address this gap, we propose UI-R1, the first framework to investigate how rule-based RL can enhance the reasoning capabilities of multimodal large language models (MLLMs) for GUI action prediction tasks. UI-R1 introduces a novel rule-based action reward scheme, enabling model optimization via policy-based algorithms such as Group Relative Policy Optimization (GRPO). To further improve efficiency at inference time, we present UI-R1-Efficient, a two-stage training paradigm that reduces reasoning length while boosting overall performance. In addition, we construct a compact yet high-quality dataset containing 2K challenging tasks across five prevalent mobile device action types. Experiments show that our proposed models (e.g., UI-R1-3B) achieve substantial improvements over the base model (Qwen2.5-VL-3B) on both in-domain (ID) and out-of-domain (OOD) tasks, with average accuracy gains of 18.3% on ScreenSpot, 6.0% on ScreenSpot-Pro, and 10.9% on ANDROIDCONTROL. Moreover, our efficient versions deliver competitive performance compared to considerably larger state-of-the-art models, underscoring the potential of reinforcement learning to advance GUI control and paving the way for future research in Human-Computer Interaction (HCI).

Yu Liu, Cunrui Wang, Lin Feng, Jianxin Zhang, Bo Lu

Space computing devices expand handwritten input from two-dimensional screens into three-dimensional space, providing an unrestricted interactive experience. Due to the high degree of freedom and lack of tactile feedback in in-air handwriting, handwritten characters not only become less legible but also lose the writer's personal style. This paper proposes a method for reconstructing discrete in-air handwriting using continuous diffusion models, capturing the writing process and style from a small number of user-provided handwritten tracks and images, to restore the legibility of characters and mimics the writer's style. We represent handwritten track data in binary form and model it with continuous diffusion models, recovering discrete handwritten track data through threshold processing. Our approach reconstructs in-air handwritten characters in two stages. During the content preservation phase, we propose a partial noise injection strategy based on reference sequence modeling, using the content information of the original character as a guiding condition to maintain content consistency in handwritten character. In the style aggregation phase, we adaptively fuse the visual style of the handwritten in the image modality with the dynamic writing process in the sequence modality, overcoming issues of insufficient style capture due to noise interference in the backward process. Qualitative and quantitative experiments demonstrate the superiority of our method.

Xuan-Hao Liu, Yan-Kai Liu, Tianyi Zhou, Bao-Liang Lu, Wei-Long Zheng

Brain decoding aims to reconstruct video from brain signals. Existing brain decoding frameworks are primarily built on a subject-dependent paradigm, which requires large amounts of brain data for each subject. However, the expensive cost of collecting brain-video data causes severe data scarcity for brain decoding. Although some cross-subject methods being introduced, they often exhibit an excessive preoccupation with subject-invariant information while neglecting subject-specific information, resulting in slow fine-tune-based adaptation strategy. To achieve fast and data-efficient new subject adaptation, we propose **MindCross**, a novel cross-subject brain decoding framework. MindCross's *N* specific encoders and one shared encoder are designed to extract subject-specific and subject-invariant information, respectively. Additionally, a Top-*K* collaboration module is adopted to enhance new subject decoding with the knowledge learned from previous subjects' encoders. Extensive experiments on fMRI/EEG-to-video benchmarks demonstrate MindCross's efficacy and efficiency of cross-subject decoding and new subject adaptation using only one model. Code of our framework will be released upon publication.

Wenchao Liu, Hongwei Li, Zhouyang Xu, Lin Ma, Haifeng Li

In recent years, electroencephalography (EEG)-based visual decoding research has become a key direction for revealing brain processing mechanisms and realizing brain-computer interfaces. This emerging field has attracted extensive attention in the fields of brain science, cognitive neuroscience, and artificial intelligence. Among various approaches, contrastive learning has demonstrated strong performance in aligning multi-modal data, effectively enabling unified representations across modalities. However, during human visual perception, images are often subject to varying degrees of blurring due to the uneven distribution of retinal photoreceptor cells and the limited speed of lens accommodation. To address the mismatch between EEG and visual representations, we propose a novel visual decoding framework inspired by human perceptual blurring. Specifically, multi-level Gaussian blurring is applied to the visual stimuli to simulate human visual characteristics, followed by a feature selection module to construct robust visual representations. For EEG decoding, we design a lightweight and efficient network employing positively constrained spatial convolutions to identify channels associated with visual processing. The EEG and visual features are then aligned using contrastive learning. We evaluate the proposed framework on the Things-EEG dataset. Experimental results show significant improvements in the zero-shot brain-to-image retrieval task, achieving a top-1 accuracy of 80% and a top-5 accuracy of 96.9%, surpassing previous state-of-the-art methods by margins of 29.1% and 17.2%, respectively. These findings highlight the potential of incorporating perceptual properties into EEG-based visual decoding.

Le Liu, Yuhao Wang, Bohan Shen, Wei Zeng, Shizhou Zhang, Di Xu, Peng Wang

Uncertainty visualizations, such as hurricane cones and ensemble tracks, are essential for risk communication but are often misinterpreted, leading to harmful decisions. As AI assistants like large language models (LLMs) increasingly support understanding of graphics and decision-making, they offer a promising pathway to enhance the interpretation of complex visualizations and a new opportunity to examine and improve the interpretation of uncertainty. We introduce UnReason, the first benchmark that systematically compares how humans and LLMs reason about hurricane forecast uncertainty visualizations. UnReason spans two escalating phases, seven representative visualization formats, six real hurricane cases, and three agent types (humans, LLMs with context, and LLMs without context), including 880 visualizations and 117,600 structured question–answer pairs under matched evaluation conditions. Phase 1 evaluates reasoning across implicit and explicit uncertainty encodings; Phase 2 examines reasoning under single- versus multi-dimensional uncertainty representations. We thoroughly assess damage estimation, reasoning strategies, and comprehension patterns, revealing that LLMs have a stronger semantic and conceptual understanding of uncertainty, and are less misled by visual variability, but still replicate key human biases during decision-making. Our findings offer insights into aligning LLM behavior with human cognition in uncertainty-rich visual reasoning tasks.

Henglin Liu, Nisha Huang, Chang Liu, Jiangpeng Yan, Huijuan Huang, Jixuan Ying, Tong-Yee Lee, Pengfei Wan, Xiangyang Ji

The aesthetic quality assessment task is crucial for developing a human-aligned quantitative evaluation system for AIGC. However, its inherently complex nature—spanning visual perception, cognition, and emotion—poses fundamental challenges. Although aesthetic descriptions offer a viable representation of this complexity, two critical challenges persist: (1) data scarcity and imbalance: existing dataset overly focuses on visual perception and neglects deeper dimensions due to the expensive manual annotation; and (2) model fragmentation: current visual networks isolate aesthetic attributes with multi-branch encoder, while multimodal methods represented by contrastive learning struggle to effectively process long-form textual descriptions. To resolve challenge (1), we first present the Refined Aesthetic Description (RAD) dataset, a large-scale (70k), multi-dimensional structured dataset, generated via an iterative pipeline without heavy annotation costs and easy to scale. To address challenge (2), we propose ArtQuant, an aesthetics assessment framework for artistic image which not only couple isolated aesthetic dimensions through joint description generation, but also better model long-text semantics with the help of LLM decoders. Besides, theoretical analysis confirms this symbiosis: RAD's semantic adequacy (data) and generation paradigm (model) collectively minimize prediction entropy, providing mathematical grounding for the framework. Our approach achieves state-of-the-art performance on several datasets while requiring only 33% of conventional training epochs, narrowing the cognitive gap between artistic image and aesthetic judgment. We will release both code and dataset to support future research.

Xiang Li, Wenxi Li, Yuetong Wang, Chenyang Lyu, Haozhe Lin, Guiguang Ding, Yuchen Guo

Object detection in High-Resolution Wide (HRW) shots, or gigapixel images, presents unique challenges due to extreme object sparsity and vast scale variations. State-of-the-art methods like SparseFormer have pioneered sparse processing by selectively focusing on important regions, yet they apply a uniform computational model to all selected regions, overlooking their intrinsic complexity differences. This leads to a suboptimal trade-off between performance and efficiency. In this paper, we introduce GigaMoE, a novel backbone architecture that pioneers adaptive computation for this domain by replacing the standard Feed-Forward Networks (FFNs) with a Mixture-of-Experts (MoE) module. Our architecture first employs a shared expert to provide a robust feature baseline for all selected regions. Upon this foundation, our core innovation---a novel Sparsity-Guided Routing mechanism---insightfully repurposes importance scores from the sparse backbone to provide a "computational bonus,'' dynamically engaging a variable number of specialized experts based on content complexity. The entire system is trained efficiently via a loss-free load-balancing technique, eliminating the need for cumbersome auxiliary losses. Extensive experiments show that GigaMoE sets a new state-of-the-art on the PANDA benchmark, improving detection accuracy by 1.1% over SparseFormer while simultaneously reducing the computational cost (FLOPs) by a remarkable 32.3%.

Saisai Li, Bing Shi, Yiming Xia, Xiao Su

As intelligent systems advance rapidly, human-robot collaboration is becoming increasingly important. Ensuring that the intelligent agent's behaviors match human intentions and value preferences is crucial for effective collaboration, which is termed the value alignment problem. Within the Reinforcement Learning (RL) paradigm, value alignment typically relies on pre-designed reward functions, and Cooperative Inverse Reinforcement Learning (CIRL) is often used to model value alignment as a human-robot game. However, existing works often assume that human is perfectly rational, and can fully obtain robot’s belief on human’s preference. To address this limitation, we propose a Particle Filter-based Hierarchical Dynamic Programming algorithm (PFHDP). By modeling the robot's belief state, this algorithm ensures the correct updates of human's estimate of the robot's belief. This allows human to adopt more targeted pedagogical behaviors to guide the robot based on her understanding of the robot's current belief, achieving belief alignment between human and robot and thereby promoting value alignment more effectively. Furthermore, we run experiments to evaluate the proposed method in two cooperative scenarios against some typical benchmark approaches. The experimental results show that our method can strengthen the alignment of belief states between human and robot, leading to enhanced value alignment.

Ruochen Li, Zhanxing Zhu, Tanqiu Qiao, Hubert P. H. Shum

Pedestrian trajectory prediction is critical for ensuring safety in autonomous driving, surveillance systems, and urban planning applications. While early approaches primarily focus on one-hop pairwise relationships, recent studies attempt to capture high-order interactions by stacking multiple Graph Neural Network (GNN) layers. However, these approaches face a fundamental trade-off: insufficient layers may lead to under-reaching problems that limit the model's receptive field, while excessive depth can result in prohibitive computational costs. We argue that an effective model should be capable of adaptively modeling both explicit one-hop interactions and implicit high-order dependencies, rather than relying solely on architectural depth. To this end, we propose ViTE (Virtual graph Trajectory Expert router), a novel framework for pedestrian trajectory prediction. ViTE consists of two key modules: a Virtual Graph that introduces dynamic virtual nodes to model long-range and high-order interactions without deep GNN stacks, and an Expert Router that adaptively selects interaction experts based on social context using a Mixture-of-Experts design. This combination enables flexible and scalable reasoning across varying interaction patterns. Experiments on three benchmarks (ETH/UCY, NBA, and SDD) demonstrate that our method consistently achieves state-of-the-art performance, validating both its effectiveness and practical efficiency.

Jing Li, Yanxin Luo, Donghong Han, Yimeng Zhan, Xiaoming Fu, Baiyou Qiao, Gang Wu

Emotional Support Conversation (ESC) aims to alleviate individuals’ negative emotions through multi-turn dialogues, where effective strategy planning and response generation are essential. However, existing methods often suffer from limitations in both planning reasonable support strategies and effectively expressing them in responses. To the end, we propose a novel LLM-based Emotional Support Conversation Agent (ESCA) with a plug-in strategy planner and a strategy-aligned prompt generator. The strategy planner cooperates with four aspects of the seeker’s state, including emotion intensity, trust degree, dialogue behavior, and stage of change, to enhance the rationality and effectiveness of the strategy prediction. To ensure that predicted strategies are better conveyed, the prompt generator integrates strategy-aligned instructions, knowledge, and context to generate the soft prompt for guiding the LLM to generate supportive responses. In addition to supervised fine-tuning, the prompt generator is further optimized by reinforcement learning. Experimental results demonstrate that ESCA significantly improves both response quality and the success rate of achieving the ESC task goal.

Hyeonji Kim, Sujeong Oh, Sanghack Lee

Reinforcement learning from human feedback (RLHF) is widely used to align large language models (LLMs) with human preferences. However, RLHF-trained reward models often exhibit length bias—a systematic tendency to favor longer responses by conflating verbosity with quality. We propose a causal framework for analyzing and mitigating length bias in RLHF reward modeling. Central to our approach is a counterfactual data augmentation method that generates response pairs designed to isolate content quality from verbosity. These counterfactual examples are then used to train the reward model, enabling it to assess responses based on content quality independently of verbosity. Specifically, we construct (1) length-divergent pairs with similar content and (2) content-divergent pairs of similar length. Empirical evaluations show that our method reduces length bias in reward assignment and leads to more concise, content-focused outputs from the policy model. These findings demonstrate that the proposed approach effectively reduces length bias and improves the robustness and content sensitivity of reward modeling in RLHF pipelines.

Xuanming Jiang, Dingyu Nie, Baoyi An, Yuzhe Zheng, Yichuan Mao, Jialie Shen, Xueming Qian, Zhiwen Jin, Wei Lan, Guoshuai Zhao

The proliferation of collaborative training and multi-person sports has underscored the necessity for concurrent whole-field action sensing. However, Electromyography (EMG) recognition, which plays a pivotal role in Wearable Human Activity Recognition (WHAR) for analyzing muscle activity and decoding action intent, still faces challenges in achieving a balance between performance, cost, and efficiency in multi-person scenarios. Unlike current channel-expansion solutions, we propose a wireless wearable Single-Dimensional Sparse EMG (2SEMG) Sensor for efficient personal sampling. These action-unaffected sensors leverage the proposed lightweight One-Dimensional Motion Network (OMONet) to facilitate concurrent action sensing. Experiments demonstrate that OMONet achieves leading performance and efficiency in action signal recognition, and two real-world badminton matches further confirm the performance, robustness, and real-time efficiency of the whole-field action sensing network constructed via 2SEMG Sensors and OMONet.

Weiliang Huo, Shilin Zhang, Suixue Wang, Qingchen Zhang

The continuous advancements in life science technology have enabled spatial transcriptome technology to achieve an impressive level of resolution at the single-cell level. This technology has emerged as a crucial method for studying the cellular composition and differentiation states of tissues, investigating cell-cell interactions, and unraveling the molecular mechanisms underlying diseases and developmental processes. A key component in this analysis is the accurate segmentation of cells. However, existing segmentation methods often fail to fully leverage the valuable information provided by spatial transcriptomics, leading to inaccurate cell segmentation. In this study, we introduce SSL-CST, a cell segmentation for single-cell spatial transcriptome method based on self-supervised learning. SSL-CST employs a pre-trained model for foundational contour segmentation. Following the denoising process, it utilizes a self-supervised neural network to correct the cell boundaries to obtain accurate cell boundaries. Through this approach, SSL-CST outperforms other state-of-the-art methods in various tests conducted on multiple datasets. The improved segmentation provided by SSL-CST further enhances the analysis of single-cell spatial expression, providing effective tools for biological discovery.

De Hu, Junsheng Hu, Cuicui Jiang

To achieve immersive spatial audio rendering on VR/AR devices, high-quality Head-Related Transfer Functions (HRTFs) are essential. In general, HRTFs are subject-dependent and position-dependent, and their measurement is time-consuming and tedious. To address this challenge, we propose the Graph Neural Field with Spatial-Correlation Augmentation (GraphNF-SCA) for HRTF personalization, which can be used to generate individual HRTFs for unseen subjects. The GraphNF-SCA consists of three key components: an HRTF personalization (HRTF-P) module, an HRTF upsampling (HRTF-U) module, and a fine-tuning stage. In the HRTF-P module, we predict HRTFs of the target subject via the Graph Neural Network (GNN) with an encoder-decoder architecture, where the encoder extracts universal features and the decoder incorporates the target-relevant features and produces individualized HRTFs. The HRTF-U module employs another GNN to model spatial correlations across HRTFs. This module is fine-tuned using the output of the HRTF-P module, thereby enhancing the spatial consistency of the predicted HRTFs. Unlike existing methods that estimate individual HRTFs position-by-position without spatial correlation modeling, the GraphNF-SCA effectively leverages inherent spatial correlations across HRTFs to enhance the performance of HRTF personalization. Experimental results demonstrate that the GraphNF-SCA achieves state-of-the-art results.

He-Yen Hsieh, Wei-Te Mark Ting, H. T. Kung

Pre-trained gaze models learn to identify useful patterns commonly found across users, but subtle user-specific variations (i.e., eyelid shape or facial structure) can degrade model performance. Test-time personalization (TTP) adapts pre-trained models to these user-specific domain shifts using only a few unlabeled samples. Efficient fine-tuning is critical in performing this domain adaptation: data and computation resources can be limited-especially for on-device customization. While popular parameter-efficient fine-tuning (PEFT) methods address adaptation costs by updating only a small set of weights, they may not be taking full advantage of structures encoded in pre-trained filters. To more effectively leverage existing structures learned during pre-training, we reframe personalization as a process to reweight existing features rather than learning entirely new ones. We present Attentive Low-Rank Filter Adaptation (Alfa) to adapt gaze models by reweighting semantic patterns in pre-trained filters. With Alfa, singular value decomposition (SVD) extracts dominant spatial components that capture eye and facial characteristics across users. Via an attention mechanism, we need only a few unlabeled samples to adjust and reweight pre-trained structures, selectively amplifying those relevant to a target user. Alfa achieves the lowest average gaze errors across four cross-dataset gaze benchmarks, outperforming existing TTP methods and low-rank adaptation (LoRA)-based variants. We also show that Alfa's attentive low-rank methods can be applied to applications beyond vision, such as diffusion-based language models.

Celine Hocquette, Johannes Langer, Andrew Cropper, Ute Schmid

The goal of inductive program synthesis is for a machine to automatically generate a program from user-supplied examples. A key underlying assumption is that humans can provide sufficient examples to teach a concept to a machine. To evaluate the validity of this assumption, we conduct a study where human participants provide examples for six programming concepts, such as finding the maximum element of a list. We evaluate the generalisation performance of five program synthesis systems trained on input-output examples (i) from a human group, (ii) from a gold standard set, and (iii) randomly sampled. Our results suggest that human-provided examples are typically insufficient for a program synthesis system to learn an accurate program.

Wen-Jue He, Xiaofeng Zhu, Zheng Zhang

Incomplete multi-modal emotion recognition (IMER) aims at understanding human intentions and sentiments by comprehensively exploring the partially-observed multi-source data. Although the multi-modal data is expected to provide more abundant information, the performance gap and modality under-optimization problem hinder effective multi-modal learning in practice, and are exacerbated in the confrontation of the missing data. To address this issue, we devise a novel Cross-modal Prompting (ComP) method, which emphasizes coherent information by enhancing modality-specific features and improves the overall recognition accuracy by boosting each modality's performance. Specifically, a progressive prompt generation module with a dynamic gradient modulator is proposed to produce concise and consistent modality semantic cues. Meanwhile, cross-modal knowledge propagation selectively amplifies the consistent information in modality features with the delivered prompts to enhance the discrimination of the modality-specific output. Additionally, a coordinator is employed to dynamically re-weight the modality outputs as a complement to the balance strategy to improve the model's efficacy. Extensive experiments on 4 datasets with 7 SOTA methods under different missing rates validate the effectiveness of our proposed method.

Haoran Gu, Handing Wang, Yi Mei, Mengjie Zhang, Yaochu Jin

Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context algorithm have shown strong performance and efficiency. However, inappropriate preference representations and training with imbalanced reward scores limit the performance of such algorithms. In this work, we introduce ParetoHqD that addresses the above issues by representing human preferences as preference directions in the objective space and regarding data near the Pareto front as ''high-quality'' data. For each preference, ParetoHqD follows a two-stage supervised fine-tuning process, where each stage uses an individual Pareto high-quality training set that best matches its preference direction. The experimental results have demonstrated the superiority of ParetoHqD over five baselines on two multiobjective alignment tasks.

Caterina Fregosi, Lucia Vicente, Andrea Campagner, Federico Cabitza

Achieving appropriate human reliance on Artificial Intelligence (AI) systems remains a central challenge in Human-Computer Interaction. Confidence scores—indicators of an AI system’s certainty in its recommendations—have been proposed as a means to help users calibrate their trust and reliance on AI Decision Support Systems (DSS). However, limited research has explored how well-calibrated versus miscalibrated confidence scores affect human decision-making. We report a study examining the effects of confidence calibration on user reliance, decision accuracy, and perceived utility of an AI DSS. In a within-subjects experiment involving 184 participants solving logic puzzles, we found that well-calibrated confidence scores significantly improved decision accuracy (+20%, 95% CI: [0.18, 0.23]), whereas miscalibrated scores yielded minimal accuracy gains (+2%, 95% CI: [-0.00, 0.04]) and increased vulnerability to automation bias and conservatism bias. Participants were more likely to accept AI recommendations when high confidence was expressed, even when those recommendations were incorrect, resulting in errors. Conversely, miscalibrated and low-confidence recommendations increased conservatism bias, leading users to reject even accurate AI suggestions. Perceived utility of the AI system was higher when confidence levels were high (p < 0.001) and when confidence was well-calibrated (p = 0.002). These findings underscore the importance of designing AI systems with properly calibrated confidence cues to improve human-AI collaboration and mitigate reliance-related biases.

Qiaohui Chu, Haoyu Zhang, Meng Liu, Yisen Feng, Haoxiang Shi, Liqiang Nie

Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assistance. However, existing approaches suffer from three key limitations: 1) underutilization of fine-grained visual cues from hand-object interactions, 2) neglect of semantic dependencies between verbs and nouns, and 3) lack of explicit cognitive reasoning, limiting generalization and long-term forecasting ability. To overcome these challenges, we propose INSIGHT, a unified two-stage framework for egocentric action anticipation. In the first stage, INSIGHT focuses on extracting semantically rich features from hand-object interaction regions and enhances action representations using a verb-noun co-occurrence matrix. In the second stage, it introduces a reinforcement learning-based module that simulates explicit cognitive reasoning through a structured process: visual perception (think) → intention inference (reason) → action anticipation (answer). Extensive experiments on Ego4D, EPIC-Kitchens-55, and EGTEA Gaze+ benchmarks show that INSIGHT achieves state-of-the-art performance, demonstrating its effectiveness and strong generalization capability.