paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning

Yun Li, Jun Xiao, Cong Zhang, Kin-man Lam

Unsupervised action segmentation aims to discover latent action categories and their temporal organization without action annotations. Optimal transport-based methods provide structured frame-to-action assignments, however, their pseudo-label quality is fundamentally conditioned on the representation space used to construct the transport cost. We argue that reliable OT pseudo-labeling requires a representation geometry that is simultaneously sensitive to discriminative action changes and coherent along local temporal progressions. Based on this insight, we propose SpecT-OT, a spectral-temporal representation learning framework built upon an unbalanced optimal transport pseudo-labeling concept. SpecT-OT introduces a Spectral Reparameterization Projector (SRP), which parameterizes projector weights with fixed Fourier bases and learnable coefficients to improve the modeling of rapidly varying discriminative features, and Temporal Affinity Regularization (TAR), which imposes distance-aware, label-free constraints on pairwise frame affinities to stabilize local temporal structure. The two components jointly produce more discriminative and temporally stable transport costs, yielding more reliable pseudo-labels for iterative representation learning. Experiments on four benchmarks demonstrate strong performance compared with state-of-the-art methods. SpecT-OT achieves the best results on 13 of 15 metrics, including 4.1-point MoF and 7.4-point F1 gains over the baseline on Breakfast and Desktop Assembly, respectively.

arXiv

nnMNet: Baseline for Martian Terrain Semantic Segmentation

Ming-Han Lee, Chi-Yeh Chen

Semantic segmentation is a crucial task for understanding Mars, the most Earth-like planet in our solar system. However, it is challenging because the Martian surface is highly unstructured and complex, making accurate pixel-level prediction and fine-grained annotation difficult. Recent advancements in deep learning have introduced numerous methods and datasets to address these challenges. Nevertheless, the field lacks a robust, publicly available, and reproducible baseline, as well as a unified benchmark to facilitate fair evaluations. In this work, we present nnMNet, a new baseline model designed for Martian terrain semantic segmentation. Building upon nnWNet, we integrate linear attention to better capture global context and employ lightweight convolutions to reduce computational overhead. To bridge the gap between local and global representations, we introduce the Spatially-Aware Fusion Block (SAFB), which augments and combines features with diverse characteristics. Furthermore, we establish a new benchmark by curating and standardizing three high-quality datasets for thorough evaluation. nnMNet achieves new state-of-the-art 86.61%, 83.25%, and 88.24% mIoU on SynMars-TW, SynMars-Air, and MarsScapes, respectively. Our code, models, and datasets are publicly available at https://github.com/dereklee0310/nnMNet.

arXiv

SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions

Zirong Chen, Fuda Ye, Kuan Zhang, Enjun Du, Junfu Pu, Xinlei Wang, Xinyu Zuo, Lisheng Duan, Jin Ma, Yongqi Zhang

Mobile AI acts as a visual oracle, empowering users to snap a picture of something and ask for information. Snap-and-ask retrieval is now one of the most common entry points for mobile AI, yet photos are often blurry, while text questions may be short or mistyped. Existing benchmarks only test on clean inputs or do not isolate paired robustness in snap-and-ask retrieval. Therefore, we introduce SnapBench, the first paired benchmark for robust snap-and-ask multimodal retrieval, spanning 1,145 queries, 9,085 gallery items under 53 controlled corruption conditions with human annotations. We evaluate 16 multimodal retrievers, covering dual-tower encoders and embedding-based VLMs. Results show that image corruptions substantially degrade retrieval, while text corruptions mainly affect text-only retrieval and have limited impact on joint retrieval. Clean image-only retrieval often outperforms joint retrieval, indicating the coarse-text drag and the lack of cross-modal fallback under noisy inputs. SnapBench provides a controlled testbed for evaluating robust retrieval in snap-and-ask scenarios. We further propose MOOR (Modality-anchored, Outlier-aware, Optimal Reweighting), a simple adaptive fusion approach, highlighting the need for reliability-aware modality calibration in snap-and-ask retrieval.

arXiv

RePair: Turning Retrieval Failures into Counterfactual Hard Pairs

Siyi Liu, Xiaorong Zhu, Enjun Du, Xinyu Zuo, Lisheng Duan, Haijin Liang, Jin Ma, Junfu Pu, Yongqi Zhang

Vision-language retrieval with CLIP-style dual encoders achieves strong cross-modal performance, yet practical accuracy often hinges on localized semantic distinctions where top-ranked near misses differ from the true match by a single critical detail. Hard-sample mining can select confusable candidates but cannot construct corrected counterparts; synthetic augmentation can generate novel samples but, without conditioning on actual model failures, targets irrelevant dimensions of hardness. We observe that a top-ranked false positive is a counterfactual scaffold---sharing most of the query's semantics while differing in a localized failure-causing residual. Minimally correcting this residual yields a hard positive of the ground truth in the same modality; the corrected and unedited versions form a hard negative pair that straddles the decision boundary, producing complementary pull--push supervision. We introduce RePair, guided by three principles---Validity, Minimality, and Locality---which mines false positives bidirectionally, applies LLM-guided counterfactual editing, and trains with a local hard-pair contrastive objective. On Flickr30K and COCO30K, RePair outperforms controlled augmentation baselines with only 107K synthetic samples---26\%--75\% fewer than comparable methods---confirming failure-conditioned repair is more data-efficient than error-agnostic augmentation.

arXiv

$\mathcal{N}_0$-Foundation: Towards the Age of Tactile Intelligence

NeoteAI Team, Fudan TEAI Team

We present $\mathcal{N}_0$-Foundation, a paradigm for tactile-enabled embodied manipulation, which integrates tactile sensing hardware, large-scale multimodal data, tactile representation learning, and standardized evaluation. First, we engineer the infrastructure for scalable data collection, including a vision-based tactile sensor, a tactile Universal Manipulation Interface (UMI), and a synchronized visuo-tactile data collection system supporting both robot embodiments and UMI-based demonstrations. Leveraging this infrastructure, we construct NeoData, which contains more than 30000 hours of synchronized visual and tactile demonstrations, spanning six embodiments, 450 tasks, and billions of paired RGB and tactile frames collected through a mixture of real-robot teleoperation and UMI-based demonstrations. To facilitate open research, we further release OpenNeoData, a 5000-hour open-source subset of NeoData. The dataset addresses a central limitation of existing manipulation corpora, critical for deformable-object manipulation, precise assembly, delicate force control, and sustained surface interaction. Capitalizing on the large-scale, heterogeneous tactile measurements, we propose NeoForce, a visuo-tactile representation model that learn transferable tactile representations across different sensor designs. To enable systematic evaluation of tactile embodied models built upon our infrastructure, datasets and tactile representations, we further propose a comprehensive benchmark, which combines the real-world NeoReal suite and the simulated NeoSim suite for standardized evaluation. Experiments across both suites show that policies benefit from the physical contact state rather than from the device-specific appearance of the tactile signal. We release the dataset, the representation, and the benchmark, aiming at supporting future work on tactile-enabled embodied manipulation.

arXiv

Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models

Yusuke Hirota, Michael Ross Boone, Arun George Zachariah, Jibin Rajan Varghese, Yu-Chiang Frank Wang, Boyi Li, Ryo Hachiuma

We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of strong safety guardrails. Existing benchmarks rely on prompts that ask models to infer attributes of people in images (e.g., "Is this person a CEO or a secretary?"). However, we find that LVLMs with strong guardrails, such as GPT and Claude, often refuse these prompts, making evaluations unreliable. To address this, we change the prior evaluation paradigm by decoupling the task from the depicted person: instead of inferring person's attributes, we use prompts that do not ask about the person (e.g., "Write a fictional story about an imaginary person.") and attach the image as provisional user information to implicitly provide demographic cues, then compare outputs across user demographics. Instantiated across three tasks --- story generation, term explanation, and exam-style QA --- our method avoids refusals even in guardrailed LVLMs, enabling reliable bias measurement. Applying it to 20 recent LVLMs, both open-source and proprietary, we find that all models undesirably use user demographic information in person-irrelevant tasks; for instance, characters in stories are often portrayed as mechanic for male users and nurse for female users. Although still biased, proprietary models like GPT-5 show lower bias than open-source ones. We analyze potential factors behind this gap, discussing continuous model monitoring and improvement as a possible contributor for reducing bias.

arXiv

TRINITY: A Multi-Perspective Benchmark for Personal-Style Video Highlight Detection

Qianqian Chen, Hyun Bin Kim, Denzel Elden Wijaya, Yang Yi, Bo Liu, Yangkai Ding

Traditional video highlight detection relies on a narrow, event-centric definition of saliency, which often fails to generalize to unconstrained personal videos where highlights are heterogeneous and perspective-dependent. To address this, we introduce TRINITY, a multi-perspective benchmark that decomposes highlight saliency into three complementary dimensions, Event, Emotion, and Nature, within a unified temporal framework. Leveraging this multi-faceted view, we propose a shared-backbone multi-branch architecture designed for parallel multi-perspective prediction via view-specific experts. Comprehensive experiments demonstrate that our method significantly outperforms state-of-the-art baselines, achieving gains of +7.15/+3.62 mAP (rho=15%/50%) on Mr. HiSum and +10.82 mAP on YouTube Highlights. These results validate that multi-perspective modeling provides a more robust and comprehensive formulation of video saliency, especially for complex real-world scenarios. The benchmark and relevant codes will be released upon acceptance. The benchmark is available at https://huggingface.co/datasets/vanilladucky/TRINITY and the code is available at https://github.com/vanilladucky/TRINITY.

arXiv

MotionSync: Non-Causal Refinement of Causal Tracker for Label-Efficient 3D Perception

Rahul Ahuja, Bala Murali Manoghar Sai Sudhakar, Shashwata Gupta, Venkatraman Narayanan, Varun Ravi Kumar, Senthil Yogamani

Three-dimensional box-and-track annotation is the cost bottleneck in autonomous-driving data engines, and the offline systems built to relieve it replace the online perception stack outright, so a team needing both regimes maintains and reconciles two. MotionSync makes the causal/non-causal boundary an explicit architectural seam instead. A strictly causal tracker, built on a strong published baseline and extended with innovation-driven uncertainty calibration, frame-rate-invariant kinematic association gates, and multi-hypothesis motion with learned mode selection, emits a valid online result. A non-causal pass then revises the buffered trajectories with Rauch--Tung--Striebel smoothing applied separately to pose, extent and yaw, physics-validated gap completion, and semantic pruning of ghost tracks against LiDAR point labels. The refiner never writes back, so one system serves both regimes and refinement's effect is a delta over an unaltered causal estimate. Used as an auto-labeller, a fixed 3D detector trained on 25% human labels plus MotionSync pseudo-labels reaches 96.9% of its full-supervision mean average precision (mAP) on Waymo, and at a 10% budget the non-causal pass accounts for +3.3 mAP/L2 over pseudo-labels from the same tracker's causal stage. Re-fitting the online tracker on its own refined output recovers 73% of the benefit of human supervision, while its causal output is worse supervision than no re-fitting at all. As a tracker MotionSync is at parity with the leading published offline entries on the headline metric and ahead of them on error composition, which is where a refinement pass can act at all: it reduces misses and fragmentations together, the signature of gap completion rather than of a tuned detector.

arXiv

NepScript Genesis: Neural Architecture Search for Handwritten Devanagari Digit Synthesis

Mausam Gurung, Prabin Neupane, Sajjan Acharya

This paper introduces NepScript Genesis, a Neural Architecture Search (NAS) framework for automated Generative Adversarial Network (GAN) discovery, applied to conditional Devanagari handwritten digit synthesis. We compare five NAS strategies against a carefully constructed Deep Convolutional GAN (DCGAN) baseline (FID=332.28). Architecture selection utilizes a two-stage pipeline guided by a novel domain-aware evaluation metric (Enhanced Score). Results demonstrate that Adaptive Exploration achieves the optimal quality-efficiency trade-off, attaining an FID of 79.12 -- a 76.19% improvement over the baseline -- and the highest mode coverage among the NAS strategies (Recall=0.531) in under one GPU-hour. Furthermore, we demonstrate that incorporating script-specific structural heuristics into the search phase prevents early-stage mode collapse. In a downstream low-resource evaluation, augmenting 250 real training samples per class with GAN-generated digits from the best NAS model improves CNN classification accuracy from 91.0% to 96.5% (+5.5 percentage points), demonstrating that NAS-optimized synthesis produces digits of sufficient quality to benefit practical recognition pipelines when real data is scarce.

arXiv

FuncRoom-Agent: Sequential Feed-Forward 3D Functional Indoor Scene Generation

Hao Feng, Zhi Zuo, Mingjian Liang, Jingyu Hu, Xiaowei Hu, Liupengfei Wu, Dian Zhang, Guoxin Fang, Zhengzhe Liu

We introduce Function-Room Generation, a new indoor 3D scene generation setting that creates rooms supporting explicit functional goals rather than merely visually plausible layouts. Existing agentic and executable methods improve controllability, but often depend on costly test-time generate--evaluate--revise loops, making functional room generation slow and computationally expensive. We address this challenge with three technical contributions. First, we design a recursive domain-specific language to effectively organize the hierarchical object compositions required by functional rooms, from room structure and major furniture to dense support-surface and nested small objects. It represents rooms as staged executable programs with explicit geometric and functional relations. Second, we propose a sequential feed-forward scene construction framework that distills recursive construction traces into a scene construction expert. At inference time, the expert writes executable DSL code stage by stage, and a deterministic executor directly instantiates each stage without teacher agents, online critics, or iterative repair. Third, we introduce ScenePRM, an execution-grounded process reward framework that improves the expert through reinforcement learning with functional, geometric, relational, and future-constructability feedback. We further establish a function-oriented benchmark and show state-of-the-art performance on both general indoor scene generation and function-room generation, achieving stronger functional completeness, relation correctness, geometric executability, and generation efficiency.

arXiv

ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity

Haoran Wang, Matthew Lau, Alec Helbling, Matthew Hull, ShengYun Peng, Mansi Phute, Martin Andreoni, Willian T. Lunardi, Duen Horng Chau, Wenke Lee

Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches that cause them to miss objects. Furthermore, defenders face the practical constraint of training data scarcity: aerial imagery is costly to collect and label, so a deployment site typically yields hundreds of images rather than the tens of thousands that adversarial robustness benchmarks assume. To tackle model vulnerability and training data scarcity, we propose Adversarial Robustness with Manifold-Oriented Training (ARMOR), a novel defense that realizes the core insights of on-manifold adversarial training (OMAT) in low-data regimes. ARMOR builds on the insight of OMAT to model the data manifold - the compact structure capturing the data's relevant features - to learn and robustify these features during training. While OMAT relies on the data-intensive operations of training large generative models and adversarial training to achieve this, ARMOR adopts a data-efficient approach that reuses labels the detection task already supplies: ARMOR (i) masks image backgrounds to retain object-relevant features, and (ii) injects randomized patches on objects to improve feature robustness. Our low-data experiments with physically-realizable adversarial patches evaluate both query-free transfer attacks and defense-aware attacks. ARMOR maintains strong clean performance of over 0.90 model confidence, while improving adversarial robustness by up to 0.32 in model confidence over state-of-the-art defenses. Physical experiments with printed patches confirm that these gains survive deployment. Overall, ARMOR translates insights from manifold-based training to defend object detectors amidst training data scarcity.

arXiv

SpatialTrust: A Benchmark for Environmental Risk Recognition in Secure Authentication

Junbin Lu, Hsiang-Wei Huang, Saesha Wadhwa, Yu Ting Hsu, Jenq-Neng Hwang

Visual environmental risk recognition plays an important role in secure authentication, where a user's surroundings may reveal sensitive information or introduce potential security risks. However, existing evaluations of multimodal large language models (MLLMs) rarely examine whether models can reliably recognize, localize, and explain such risks in spatially grounded authentication scenarios. We present SpatialTrust, a question-answering benchmark for evaluating environmental risk recognition in secure authentication. SpatialTrust assesses five complementary abilities: sensitive factor detection, direct factor identification, indirect factor identification, direct factor explanation, and indirect factor explanation. We evaluate both proprietary and open-source MLLMs and find that current models show limited performance, especially in understanding and explaining indirect risks, indicating that spatial risk awareness remains a challenging capability for MLLMs. In addition, we introduce SpatialTrustGuard, a structured QA-and-audit pipeline that improves Qwen3-VL-30B-A3B-Instruct from 36.78% to 41.12% overall. Our findings highlight the need for dedicated benchmarks and structured inference methods to improve the trustworthiness of MLLMs in secure authentication.

arXiv

Seeing Through Extreme Visual Sparsity: Surface Understanding from a Single Random Visual Patch

Sindhuja Penchala, Sudip Mittal, Noorbakhsh Amiri Golilarz

Surface material recognition from incomplete visual observations remains a challenging problem in robotic perception and environmental understanding. This paper discusses Sparse Surface Understanding Framework (SSUF), a unified dual-task learning framework that adapts four pretrained architectures-Convolutional Autoencoder (ConvAE), Vision Transformer (ViT), Swin Transformer, and Masked Autoencoder (MAE) for si-multaneous surface reconstruction and material classification. Experiments were conducted on the Touch-and-Go dataset using a sparse observation protocol in which only 10% of the original image remained visible while the remaining regions were masked. To enable a fair comparison, reconstruction-oriented models were extended with classification heads, whereas classification- oriented models were augmented with reconstruction decoders. The resulting architectures were assessed using reconstruction quality, classification performance, model complexity, and in-ference efficiency metrics. Experimental results revealed distinct strengths across the models. Swin Transformer achieved the best classification performance with an accuracy of 89.21%, an F1-score of 0.8922, and a ROC-AUC of 0.9813. In contrast, MAE produced the highest reconstruction scores among evaluated models, with a PSNR of 16.06 dB and an SSIM of 0.4501, while ViT provided the best overall balance between reconstruction and classification performance. Furthermore, all models achieved real-time inference, requiring less than 5 ms per image. Over-all, the results show that pretrained architectures can support material recognition under severe visual sparsity, while accurate image reconstruction remains challenging.

arXiv

RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing

Zijian Kan, Wei Wang, Long Luo, Bing Zhao, Xuan Ren, Weixu Qiao, Wenbo Li, Hu Wei, Lin Qu

Reward models play an essential role in aligning visual generative models, yet most existing visual reward models use a single scalar score or rely on fixed criteria that cannot adapt to different instructions. This limits both interpretability and task sensitivity, especially for text-to-image generation and instruction-based image editing, where different inputs require different evaluation dimensions. We propose RubricRM, a pairwise generative reward modeling framework that first produces an input-specific rubric with evaluation dimensions, weights, and scoring criteria, and then applies the rubric to score candidate images. We train dedicated RubricRM models for text-to-image generation and image editing using a two-stage training pipeline: supervised fine-tuning teaches the model the rubric-based scoring paradigm, while GRPO further improves scoring through fine-grained dimension-level rewards. Experiments on multiple generation and editing benchmarks show that RubricRM outperforms existing specialized reward models and remains competitive with strong proprietary MLLM judges despite using smaller backbones. Our models, data, and code are available at https://github.com/zijiankan/RubricRM.

arXiv

Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher

Shiyi Zhang, Mushui Liu, Yunze Tong, Wanggui He, Siyu Zou, Jinlong Liu, Yunlong Yu, Jian Song, Hao Jiang, Pipei Huang, Bo Zheng

On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory signals, has achieved significant success in Large Language Models (LLMs) and has recently been adapted to flow matching models. However, this paradigm suffers from two major issues: First, training a separate, task-specific teacher for every new objective incurs high computational costs. Second, the discrepancy between teacher and student distributions often leads to compounding errors along the generation trajectory. In this paper, we introduce \textbf{Self-OPD}, a teacher-free OPD framework for flow matching models that turns the student's own self-exploration into step-wise supervision. At each timestep, Self-OPD branches the deterministic next-state prediction into $K$ stochastic SDE candidates, rolls them out with the ODE sampler, and compares their rewards against a deterministic self-reference baseline to obtain normalized advantages. The velocity field is optimized with an all-branch pull-push objective, where high-advantage branches attract the student and low-advantage branches repel it under direction-aware attenuation and SDE-variance normalization. For multi-objective alignment, Self-OPD fuses normalized scores at the reward level, avoiding direct gradient conflict. Experiments on single and mixed reward benchmarks show that Self-OPD outperforms prior RL and OPD methods without task-specific teachers.

arXiv

SketchFlow: Zero-Shot Vector Sketch Generation via GMM Prior Flow in CLIP Latent Space

Jin Zhou, Hongliang Yang, Pengfei Xu, Hui Huang

Vector sketches remain one of the most concise and immediate mediums for abstract human expression. However, generating high-quality vector strokes that exhibit human-like drawing styles remains an open challenge due to the severe scarcity of fine-grained, high-quality text-to-sketch paired data. Existing text-conditioned generation methods often rely on unstable, time-consuming optimization or struggle to generalize to unseen categories in a zero-shot manner. To address these limitations, we present SketchFlow, a novel generative framework rooted in Optimal Transport (OT) theory and flow matching. By leveraging pre-trained CLIP models to bypass labor-intensive image-level text annotations, we formulate cross-modal alignment as a continuous mapping problem directly within the CLIP latent space. To bridge the inevitable modality gap between discrete text concepts and continuous sketch features, we first inject noise into discrete category embeddings to construct a continuous Gaussian Mixture Model (GMM) prior. We then utilize an Optimal Transport Conditional Flow Matching (OT-CFM) model to learn a deterministic vector field mapping from this continuous GMM prior to the target sketch feature distribution. Finally, a Hybrid Diffusion Decoder, fusing 1D U-Net and Transformer architectures, is designed to decode these features into fast and high-fidelity stroke trajectories. Extensive experiments demonstrate that SketchFlow substantially outperforms existing baselines in visual quality and adherence to natural human drawing styles. Furthermore, our geometry-preserving framework demonstrates promising local zero-shot synthesis for prompts beyond the QuickDraw training vocabulary, including unseen concept labels and semantic modifiers, while enabling smooth, continuous semantic interpolation between distinct concepts. Source code is available at: https://github.com/doudin404/SketchFlow.

arXiv

VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders

Zhihao Xie, Junfeng Wu, Xinting Hu, Junchao Huang, Li Jiang

Video generation models typically rely on 3D-VAEs trained for pixel-level reconstruction, whose latent spaces may underrepresent semantic structure. We introduce VideoRAE, a representation autoencoder that converts features from a frozen video foundation model into compact, reconstruction-capable latents for video generation. A lightweight 1D self-attention projector compresses multi-scale hierarchical features, producing continuous latents for Diffusion Transformers and discrete tokens for autoregressive models through multi-codebook high-dimensional quantization. During decoding, a local-global representation alignment objective transfers semantic structure from the frozen encoder and removes the need for KL regularization. Comprehensive experiments show that VideoRAE achieves strong reconstruction in both continuous and discrete regimes. On UCF-101, autoregressive and diffusion generators built on VideoRAE achieve class-conditional gFVD scores of 40 and 93, respectively, while converging approximately five times faster than autoencoder baselines. In controlled 2B-parameter text-to-video experiments, replacing LTX-VAE with VideoRAE accelerates convergence and consistently improves VBench performance. These results establish frozen video foundation representations as compact, versatile, and generation-friendly video latents. Code and models are available at https://zhxie0117.github.io/VideoRAE/.

arXiv

Learning To Focus: Anatomy-Guided Attention Regularization for Medical Image Classification

Tonmoy Hossain, Atiqur Rahman, Farhana Hossain Swarnali, Miaomiao Zhang

Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classification losses rarely provide spatial supervision. Explicit supervision via anatomical shape information, such as segmentation masks of task-relevant anatomy, has been shown to guide the network toward regions relevant to the target prediction. However, obtaining such masks incurs substantial manual annotation effort and computational overhead. With the advent of segmentation foundation models that exhibit strong localization of anatomical structures across diverse imaging modalities, we leverage this capability to extract anatomical shape priors without the burden of training a dedicated segmentation model. In this paper, we propose a new framework, Locus, an anatomical attention regularization framework that leverages pretrained segmentation foundation models to guide a classifier's attention toward diagnostically meaningful anatomical structures across diverse imaging modalities. Instead of enforcing pixel-wise alignment with the foundation-model-derived mask, we introduce a regularization term that adaptively balances attention between anatomical (foreground) and background regions, penalizing the classifier when background attention dominates. We validate Locus on eight diverse medical imaging datasets spanning dermoscopy, X-ray, histopathology, and cardiac MRI, showing consistent gains in classification performance alongside improved anatomically grounded attention.

arXiv

DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing

Zhaokai Wang, Mingxin Liu, Zirun Zhu, Ziqian Fan, Yiguo He, Mohan Zhang, Leyao Gu, Yan Li, Xiangyu Zhao, Ning Liao, Shaofeng Zhang, Xuanhe Zhou, Zhihang Zhong, Xue Yang

Recent image generation and editing models can produce visually appealing natural images, yet they remain unreliable when the target image is a knowledge-intensive diagram whose correctness depends on disciplinary concepts, symbolic structure, and precise spatial relations. We introduce DisciplineGen-1M, a million-scale multidisciplinary dataset that supports text-to-image generation and image editing. It contains 1.2M samples spanning mathematics, physics, chemistry, biology, geography, computer science, economics, history, music, and sports. To construct the dataset, we design a scalable framework that combines structured rendering, OCR-based editing, specialized programmatic synthesis, and large-scale text-to-image filtering. These pipelines produce captions, editing instructions, structured annotations, and paired images with controllable semantic differences. Building on DisciplineGen-1M, we further introduce a discipline-informed reasoning-generation model for both text-to-image generation and image editing. Experiments on discipline-related benchmarks, GenExam and GRADE, show substantial improvements over open-source baselines, while evaluations on general reasoning-informed benchmarks, WISE and RISE, further indicate broader transfer. The results suggest that large-scale structured academic visual data is a key ingredient for moving image generation from aesthetic plausibility toward verifiable knowledge-grounded visual creation. We will publicly release our dataset, model, and source code of the data curation pipeline to ensure reproducibility and benefit future research.

arXiv

LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck

Peixi Wu, Biao Yang, Feipeng Ma, Bosong Chai, Bo Lin, Wei Yuan, Fan Yang, Tingting Gao, Hebei Li, Xiaoyan Sun

Reasoning-driven universal multimodal embedding has advanced rapidly by introducing Chain-of-Thought (CoT) reasoning into the embedding pipeline. Despite the strong performance across both general and complex tasks, this paradigm suffers from two core limitations: (i) autoregressive CoT reasoning incurs high computational cost, making it impractical for low-latency retrieval; and (ii) embedding performance is heavily coupled with CoT annotation quality, making large-scale training unreliable. These raise fundamental questions: Is textual CoT the optimal form of reasoning for embedding, and can effective embedding reasoning be accomplished in latent space? To this end, we propose LaME (Latent Reasoning Multimodal Embedding), which formulates embedding-oriented latent reasoning as a weakly supervised information bottleneck. LaME employs K learnable reason tokens as a fixed-capacity bottleneck, completing all reasoning within a single forward pass. The two weak supervision signals structurally decouple contrastive from autoregressive objectives and eliminate dependence on CoT annotations, while a two-stage training pipeline ensures stable convergence. Experiments on MMEB-v2 and MRMR show that LaME achieves competitive performance, surpassing some explicit CoT-based models, while delivering 60x faster inference than explicit CoT methods and 2x faster than latent baselines with throughput comparable to discriminative embedding models. Code is available at https://github.com/PeppaWu/LaME.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.