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

JUMP-lite: Compact, reproducible benchmarking of cell representations

Alán F. Muñoz, Johan Fredin Haslum, Runxi Shen, Anne E Carpenter, Shantanu Singh

Image-based profiling captures rich phenotypic signatures for drug discovery and functional genomics. Large public datasets like JUMP Cell Painting now provide millions of images for systematic study. However, the scale of these resources, 115 TB for JUMP alone, and fragmented evaluation practices make systematic comparison of representation methods intractable for many researchers. Here we present Nahual, an open-source framework for reproducible model deployment, and JUMP-lite, a curated 116 GB subset of JUMP that is 1000 times smaller while preserving phenotypic diversity through careful selection of perturbations with high-confidence annotations and a storage reduction via lossy JPEG XL compression. With these, we benchmark five representation methods, including classical features (CellProfiler) and deep learning models (MorphEM, OpenPhenom, SubCell, DINOv2), and demonstrate that compression preserves downstream signal while standardized phenotypic activity and consistency metrics reveal meaningful performance differences across methods. Together, JUMP-lite and Nahual provide a foundation for accessible, reproducible benchmarking of image-based cell representations.

arXiv

CMU-Drive and V2V-VLA: Cooperative Multi-agent Unified Driving with Reasoning Benchmark and Vehicle-to-Vehicle Vision-Language-Action Models

Hsu-kuang Chiu, Stephen F. Smith

Vision-Language-Action (VLA) models have recently achieved impressive performance for end-to-end autonomous driving, yet existing approaches are primarily designed for an individual single autonomous driving agent with limited support for cooperative perception, reasoning, and planning. We present Cooperative Multi-agent Unified Driving with Reasoning (CMU-Drive), a closed-loop end-to-end benchmark for evaluating cooperative autonomous driving with multiple connected autonomous vehicles (CAVs) operating in safety-critical driving scenarios with background traffic participants. We further propose Vehicle-to-Vehicle Vision-Language-Action (V2V-VLA), a cooperative VLA model that integrates cooperative driving into a single forward pass by jointly generating driving actions, future waypoints, language reasoning, and communication policies. Experiments on CMU-Drive establish the first benchmark and baseline for cooperative VLA driving and provide a foundation for future research on multi-agent, closed-loop, end-to-end cooperative autonomous driving. Our code, benchmark, and model checkpoint will be publicly released to facilitate open-source research.

arXiv

FlowErase-OPD: Multi-Concept Erasure via Anchored On-Policy Distillation in Flow Matching Models

Yi Sun, Yimin Zhou, Xinhao Zhong, Zhiqi Zhang, Junhao Li, Bin CHEN

Recent advances in flow matching models have substantially improved the quality of text-to-image generation, but have also raised increasing safety concerns due to their potential to generate harmful or undesirable content. Existing concept erasure methods for flow matching models predominantly focus on removing individual concepts, while effectively erasing multiple concepts simultaneously remains challenging. We propose FlowErase-OPD, a framework for multi-concept erasure based on on-policy distillation (OPD). Our approach first distills multiple single-concept erased models into a unified LoRA module and introduces Anchored Multi-Teacher Distillation (AMTD), which incorporates a retention teacher to mitigate the trade-off between concept erasure and preservation of generative capabilities. To further improve the coordination of multiple erasure objectives, we develop Adaptive Retention Control (ARC), which dynamically adjusts the sampling frequency and loss weight of each erasure teacher, together with the relative contribution of erasure and retention teachers throughout training. Extensive experiments on nudity, object, and artistic-style erasure demonstrate that FlowErase-OPD consistently improves the trade-off between erasure effectiveness, image quality, and semantic alignment, achieving state-of-the-art performance across diverse multi-concept erasure settings. Furthermore, the resulting models exhibit strong robustness against adversarial attacks. These results highlight the potential of on-policy distillation as a principled framework for safe and controllable generation in flow matching models.

arXiv

RoboAtlas: Contextual Active SLAM

Alexander Schperberg, Shivam K. Panda, Abraham P. Vinod, Rokaha Bhagawan, M. K. Jawed, Stefano Di Cairano

We present RoboAtlas, a contextual Active SLAM framework that adaptively balances geometric exploration and semantic reasoning using a scalable 3D semantic mapping system, OpenRoboVox. RoboAtlas integrates frontier exploration, global semantic-map reasoning, and egocentric VLM-based reasoning through a contextual multi-armed bandit that transitions from exploration to semantically guided navigation as scene understanding improves. We evaluate the system in simulation and on a Unitree Go2 robot in large-scale real-world environments exceeding 1800 m2 with approx. 30k mapped semantic instances, achieving a 100% task success rate. On the GOAT-Bench "Val Unseen" benchmark, RoboAtlas achieves state-of-the-art performance with highest reported success rate (SR) of 90.6%, using GPT-4o, improving over the strongest prior baseline by 17.8 percentage points in SR. Using the much smaller Qwen2.5-VL-7B model, it still achieves 88.8% SR, outperforming all baselines using GPT-4o in SR, and revealing the importance of the information gained by our semantic mapping framework over simply replacing the underlying foundation model. The results demonstrate that grounding foundation models with large-scale 3D semantic maps enables robust and efficient contextual Active SLAM.

arXiv

Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation

Zhiyuan Yang, Jiahao Cheng, Vincent Quoc-Huy Trinh, Mahdi S. Hosseini

Generating clinically useful pathology reports for pathology cases from whole-slide images (WSIs) is challenging due to gigapixel resolution, long visual-token sequences, and the complexity of case-level reasoning, where a single case may contain multiple WSIs with heterogeneous tissues and ambiguous findings. We present a simple token-efficient vision--language model for case-level synoptic report generation that remains practical under constrained GPU memory. Our architecture follows a minimal three-component design: a frozen pathology patch encoder, a lightweight two-layer MLP vision-language aligner, and a large language model decoder, with an explicit WSI marker token to separate slides within a case. Training proceeds in two supervised stages: (1) aligner-only WSI captioning using heterogeneous WSI-text pairs, and (2) case-level supervised fine-tuning on case-report pairs for structured report generation. To reduce sequence length, we represent each slide using $512 \times 512$ patches at $5\times$ magnification, which reduces the average sequence length by up to $64\times$ times compared to the commonly used $20\times$ patches. Combined with efficient training techniques, we enable practical training with only half a NVIDIA H100 GPU. Across both training stages, our approach achieves high ROUGE-L/METEOR/BLEU-4 scores while being substantially more efficient in memory and runtime. In AI-based evaluations, our model is consistently preferred over strong baselines. Extensive ablations characterize performance-efficiency trade-offs and identify simple choices that improve robustness in multi-WSI settings. Overall, this work provides a strong, reproducible baseline for efficient pathology report generation, lowering the barrier to multi-WSI VLM research under limited compute. Code is available at https://github.com/AtlasAnalyticsLab/PathoSynVLM.

arXiv

FusionRelight: Relighting Portraits in Real Time via Hybrid Domain Knowledge Fusion

Qian Huang, Mayoore Selvarasa Jaiswal, Zhen Zhong, Rochelle Pereira, Jianyuan Min

Portrait relighting is a low-level vision problem in which physically plausible illumination transfer, identity preservation, and compact real-time inference must be considered together. Iterative diffusion-style methods can synthesize fine detail, but stochastic inference and cost complicate deterministic live video creation; physically grounded relighting preserves identity, but controlled synthetic or light-stage supervision transfers poorly to unconstrained cameras. We present Hybrid Domain Knowledge Fusion (HDKF), a relighting-specific training framework that learns complementary physics, reflectance, and realism priors from synthetic, One-Light-at-A-Time (OLAT), and in-the-wild data, then distills their source-routed supervision into a compact student with clean teacher labels and degraded student inputs. The framework is trained with pixel-aligned RGB, albedo, and normal supervision, providing a simulation substrate for physically grounded low-level relighting. On a held-out OLAT benchmark, HDKF obtains the best MSE, PSNR, and SSIM among evaluated methods while remaining competitive in LPIPS. The distilled model runs in real time at 512x512, reaching 11.89 ms on an RTX 2060 and 1.82 ms on an RTX 4090.

arXiv

Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders

Atahan Dokme, Sriram Vishwanath

We present the first systematic study of Sparse Autoencoders (SAEs) on video representations. Standard SAEs decompose video into interpretable, monosemantic features but destroy temporal coherence: hard TopK selection produces unstable feature assignments across frames, reducing autocorrelation by 36%. We propose spatio-temporal contrastive objectives and Matryoshka hierarchical grouping that recover and even exceed raw temporal coherence. The contrastive loss weight controls a tunable trade-off between reconstruction and temporal coherence. A systematic ablation on two backbones and two datasets shows that different configurations excel at different goals: reconstruction fidelity, temporal coherence, action discrimination, or interpretability. Contrastive SAE features improve action classification by +3.9 pp over raw features and text-video retrieval by up to 2.8 x R@1. A cross-backbone analysis reveals that standard monosemanticity metrics contain a backbone-alignment artifact: both DINOv2 and VideoMAE produce equally monosemantic features under an independent (CLIP) similarity space. Targeted feature ablation shows that contrastive training concentrates the probe's predictive signal into a small number of identifiable features. Supplementary material, code, configurations and evaluation scripts are available at https://github.com/atahandokme/spatio-temporal-sparse-autoencoders-video.

arXiv

Mask-aware inference with State-Space Models

Ignasi Mas, Ramon Morros, Javier-Ruiz Hidalgo, Ivan Huerta

Many real-world computer vision tasks, such as depth completion, must handle inputs with arbitrarily shaped regions of missing or invalid data. For Convolutional Neural Networks (CNNs), Partial Convolutions solved this by a mask-aware re-normalization conditioned only on valid pixels. Recently, State Space Models (SSMs) like Mamba have emerged, offering high performance with linear complexity. However, these architectures lack an inherent mechanism for handling such arbitrarily shaped invalid data at inference time. To bridge this gap, we introduce Partial Vision Mamba (PVM), a novel architectural component that ports the principles of partial operations to the Mamba backbone. We also define a series of rules to design architectures using PVM. We show the efficacy and generalizability of our approach in the tasks of depth completion, image inpainting, and classification with invalid data.

arXiv

SIP: Site in Pieces- A Dataset of Disaggregated Construction-Phase 3D Scans for Semantic Segmentation and Scene Understanding

Seongyong Kim, Yong Kwon Cho

Accurate 3D scene interpretation in active construction sites is essential for progress monitoring, safety assessment, and digital twin development. LiDAR is widely used in construction because it offers advantages over camera-based systems, performing reliably in cluttered and dynamically changing conditions. Yet most public datasets for 3D perception are derived from densely fused scans with uniform sampling and complete visibility, conditions that do not reflect real construction sites. Field data are often collected as isolated single-station LiDAR views, constrained by safety requirements, limited access, and ongoing operations. These factors lead to radial density decay, fragmented geometry, and view-dependent visibility-characteristics that remain underrepresented in existing datasets. This paper presents SIP, Site in Pieces, a dataset created to reflect the practical constraints of LiDAR acquisition during construction. SIP provides indoor and outdoor scenes captured with a terrestrial LiDAR scanner and annotated at the point level using a taxonomy tailored to construction environments: A. Built Environment, B. Construction Operations, and C. Site Surroundings. The dataset includes both structural components and slender temporary objects such as scaffolding, MEP piping, and scissor lifts, where sparsity caused by occlusion and fragmented geometry make segmentation particularly challenging. The scanning protocol, annotation workflow, and quality control procedures establish a consistent foundation for the dataset. SIP is openly available with a supporting Git repository, offering adaptable class configurations that streamline adoption within modern 3D deep learning frameworks. By providing field data that retain real-world sensing characteristics, SIP enables robust benchmarking and contributes to advancing construction-oriented 3D vision tasks.

arXiv

Score-based Membership Inference on Diffusion Models

Mingxing Rao, Bowen Qu, Daniel Moyer

Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set. While existing methods typically rely on measuring reconstruction error across multiple denoising steps as a test statistic, they often incur significant computational overhead. In this work, we present a simple yet successful attack statistic using only the predicted noise vectors from the DM's denoiser, or equivalently, the score. Specifically, we show that the expected denoiser output points toward a kernel-weighted local mean of nearby training samples, such that its norm encodes proximity to the training set and thereby reveals membership. Building on this observation, we propose SimA, a single-query attack that provides a principled, efficient alternative to existing multi-query methods. SimA consistently achieves highly competitive performance across variants of DMs and the Latent Diffusion Models (LDMs) on eight different datasets. Its Monte Carlo variant (SimA-MC) exhibits state-of-the-art performance in most experiments at 30 samples, significantly outperforming baseline methods in terms of TPR@1%FPR. These results demonstrate that complex reconstruction trajectories are unnecessary for effective membership inference, establishing SimA as a highly efficient benchmark for auditing privacy in DMs and LDMs.

arXiv

Topographic Constraints Shape Brain-Like Component Structure in Auditory Models

Haider Al-Tahan, Mayukh Deb, Jenelle Feather, N. Apurva Ratan Murty

If topography is a fundamental feature of the brain, it should influence both how neurons are arranged in space (i.e. explain brain maps) and how information is structured within the neural population. The human auditory cortex provides a strong, but previously underused test for the latter idea. Neural responses measured with both fMRI and ECoG can be decomposed into interpretable components corresponding to sound categories such as speech, music, and song, offering a view of how sound information is partitioned in the brain. Here we ask whether introducing topographic constraints into the training of audio neural network models shapes their internal representations to better match the component structure observed in the brain. To address this question, we introduce a new class of topographic auditory models, TopoAudio, which incorporate wiring-length constraints and encourage nearby units on a two-dimensional cortical sheet to develop similar response tuning. Despite these additional constraints we find that TopoAudio achieves comparable performance on standard speech and environmental sound classification tasks to standard non-topographic models and matches them in predicting human fMRI responses. Crucially however, topographic models develop more compact internal representations, and their inferred components align more closely with those derived from human ECoG recordings. These results provide initial evidence that topography offers a general mechanism for producing biologically aligned internal representations in artificial neural networks. More broadly, component-level alignment provides a complementary way for testing whether topography reshapes population responses in models to better match the representational structure observed in neural recordings. Our project page: https://topoaudio.github.io

arXiv

Ensemble learning of pathology foundation models for precision oncology

Xiangde Luo, Xiyue Wang, Feyisope Eweje, Xiaoming Zhang, Juan Luis Gomez Marti, Sarah Cascarino, Sen Yang, Yuchen Li, Ryan Quinton, Jinxi Xiang, Yuanfeng Ji, Zhe Li, Yijiang Chen, Colin Bergstrom, Ted Kim, Francesca Maria Olguin, Kelley Yuan, Matthew Abikenari, Andrew Heider, Sierra Willens, Sanjeeth Rajaram, Robert West, Joel Neal, Adam Schoenfeld, Maximilian Diehn, Chad Vanderbilt, Ruijiang Li

Histopathology is essential for cancer diagnosis and treatment selection, and pathology foundation models learn visual representations from whole-slide images (WSIs). However, existing foundation models are trained on disparate datasets using varying strategies, leading to inconsistent performance and limited generalizability. Here, we introduce ELF (Ensemble Learning of Foundation models), which integrates five pretrained pathology foundation models into unified slide-level representations. Trained on 53,699 WSIs spanning 20 anatomical sites, ELF leverages ensemble learning to capture complementary information across models. ELF's slide-level architecture is designed for data-efficient downstream evaluation, including settings with limited data such as therapeutic response prediction. We evaluate ELF for disease classification, biomarker detection, as well as anticancer and immunotherapy response prediction across multiple cancer types. ELF achieves higher performance than the evaluated constituent and slide-level foundation models across the tested tasks, supporting further evaluation of ensemble learning for pathology applications in oncology.

arXiv

NeuralDMD: Interpretable Neural Representation of Dynamics from Sparse and Noisy Measurements

Ali SaraerToosi, Renbo Tu, Esther Y. H. Lin, Kamyar Azizzadenesheli, Aviad Levis

Many challenges in scientific imaging involve solving ill-posed inverse problems, where the goal is to recover spatio-temporal fields from indirect, noisy, and highly sparse measurements - often without access to ground truth data or reliable simulators. To address this challenging scenario, we present NeuralDMD, an interpretable, untrained (per-instance) reconstruction framework that combines neural implicit representations with Dynamic Mode Decomposition (DMD) to reconstruct continuous spatio-temporal dynamics directly from measurements. NeuralDMD parameterizes DMD modes as continuous neural fields, and imposes a low-rank linear dynamics prior with spectral time evolution to enforce temporal continuity. This formulation enables both forecasting under sparsity, and yields interpretable modes and spectra. We find that NeuralDMD outperforms baselines on a wide variety of tasks: from weather data assimilation from sparse station observations to interferometric (Fourier domain) observations of Sagittarius A, the black hole at the center of our galaxy. Moreover, NeuralDMD remains stable when extrapolating into the future. While this framework is most naturally suited to linear dynamics, we show that it can be applied to nonlinear regimes, though with extrapolation performance that degrades with increasing nonlinearity. Together, these results show that NeuralDMD enables interpretable reconstruction and forecasting of spatio-temporal dynamics directly from sparse and indirect measurements without relying on numerical simulators or training data.

arXiv

Lying mirror using structured surfaces

Yuhang Li, Shiqi Chen, Bijie Bai, Aydogan Ozcan

We introduce an all-optical system, termed the "lying mirror", to hide input information by transforming it into misleading, ordinary-looking patterns that effectively camouflage the underlying image data and deceive the observers. This misleading transformation is achieved through passive light-matter interactions of the incident light with an optimized structured diffractive surface, enabling the optical concealment of any form of secret input data without any digital computing. These lying mirror designs were shown to camouflage different types of input image data, exhibiting robustness against a range of adversarial manipulations, including random image noise as well as unknown, random rotations, shifts, and scaling of the object features. The feasibility of the lying mirror concept was also validated experimentally using a structured micro-mirror array along with multi-wavelength illumination at 480, 550 and 600 nm, covering the blue, green and red image channels. Furthermore, we created a broadband lying mirror that operates across a continuous spectral range, enhancing its adaptability under diverse illumination conditions. This framework showcases the power of structured diffractive surfaces for visual information processing and might find various applications in defense, security and entertainment.

arXiv

MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation

Youjun Zhao, Alex Warren, Gary K. L. Tam, Rynson W. H. Lau

Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis. However, generating mirror reflections remains challenging because the content within a mirror must remain consistent with the surrounding scene. Existing VDMs are not specifically designed to model scene-to-mirror relationships, which can lead to reflections with incorrect content or inconsistent spatial arrangements. We observe that mirror reflection generation involves two complementary challenges: determining what scene content should be reflected and how the reflected content should be spatially arranged within the mirror region. Motivated by this observation, we propose MirrorWorld, a reflection-aware video inpainting framework that models scene-to-mirror relationships during generation. Specifically, we introduce Semantic Relation Distillation (SRD), which transfers relational information from a frozen visual foundation model to encourage semantic associations between visible scene content and mirror regions. We further propose Geometric Transformation Alignment (GTA), which learns a transformation that guides the spatial arrangement of reflected content. The two components play complementary roles, with SRD modeling what should be reflected and GTA modeling how it should be arranged. To facilitate research on this problem, we construct a benchmark for video mirror reflection generation by repurposing four existing video mirror datasets into a unified reflection reconstruction task. Experimental results show that MirrorWorld achieves improved reflection reconstruction quality over representative image-based reflection generation methods and strong video inpainting baselines.

arXiv

Conformal Coverage Guarantees for Any Video Temporal Grounder

Aseel Mohamed, Rasul Khanbayov, Erchin Serpedin, Hasan Kurban

Event boundaries in continuous video are ambiguous: re-annotate the same query-video pair and independent annotators mark moments that overlap by less than half on a large fraction of samples. The ground truth for video temporal grounding is therefore a distribution over intervals, yet every grounder returns a single interval with no statement of reliability, so at deployment a wrong interval is indistinguishable from a right one. COVER changes the output object: a post-hoc, model-agnostic wrapper that turns any grounder, a trained localizer or a black-box video--language model, into one that emits a temporal region containing the true moment with probability at least $1-α$, by calibrating the quantile of a temporal nonconformity score on held-out labels and widening the base prediction by that amount. The guarantee is finite-sample and distribution-free under exchangeability, and requires neither retraining nor white-box access. We give two score families, a two-sided boundary-widening score for grounders that emit an interval and a super-level-set score for grounders that emit a relevance signal, and develop theory specific to grounding that bounds how large the certified region becomes, when coverage survives conditioning on event length, and how it degrades when moments from one video break exchangeability. Across three benchmarks and five grounders, realized coverage tracks the target, and calibration exposes what point metrics hide.

arXiv

I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning

Shibo Gao, Chongxiao Wang, Chenglong Huang, Jie Ma, Haolin Shi, Fei Ding, Jing Li, Qiang Lyu, Yangyang Liu, Yang Liu, Jun Liu, Linlin Huang, Peipei Yang

Real-world video reasoning often involves multimodal, multi-source inputs, whereas existing video reasoning tasks typically assume a simplified video-text setting, limiting identity matching and person-centric reasoning. To bridge this gap, we introduce the Identity-conditioned Queries (ICQ) task, in which models are required to jointly associate and interpret an input video and a reference image of a person, and leverage this conditioning to address identity grounding, behavior understanding, and temporal reasoning, among other challenges. Building on ICQ, we present ISYV (I Seek You in Videos), a systematic solution comprising three components: (1) ISYV-Bench, a challenging evaluation benchmark with 1,377 real-world complex videos and 1,377 question-answer pairs, organized into six difficulty levels spanning capabilities from identity recognition to causal reasoning; (2) ISYV-75K, a large-scale training set of 75K high-quality samples constructed via automated annotation, multi-stage verification, and manual review; and (3) ISYV-Framework, containing an ICQ-oriented model and training strategy for learning to exploit informative video shots without additional shot-level annotations. Extensive experiments show that both mainstream closed-source and open-source MLLMs struggle on ISYV-Bench, especially in cross-domain identity matching and long-horizon tracking. ISYV-Model outperforms strong baselines and in some aspects approaches closed-source performance. Overall, ISYV provides a unified task definition, scalable datasets/benchmarks, and modeling insights for person-centric video reasoning.

arXiv

UniJEPA: A Unified Joint-Embedding Predictive Architecture for Task-Agnostic Visual World Modeling

An Lanji, Dawei Liu, Jin Li, Haoran Xu, Mei Chen, Yu Tian

Joint-Embedding Predictive Architectures (JEPAs) have emerged as a principled framework for self-supervised learning of world models in compact latent spaces, yet existing methods are fragmented: some predict masked parts of a single image in latent space (I-JEPA), others learn to predict global photometric transformations (Image World Models), while video-scale JEPAs predict future temporal states and are post-trained for action-conditioned planning (V-JEPA~2, DINO-World, DINO-WM). These objectives are treated as distinct recipes with separate encoders, predictors, and anti-collapse regularizers, hindering a single model from unifying image-level and video-level world modeling. We present UniJEPA, a unified JEPA that jointly learns photometric prediction (image-level transformations) and temporal prediction (video-level next-state dynamics) in one shared latent space. A single end-to-end objective, composed of a next-embedding prediction loss and a Gaussian regularizer, yields a provably anti-collapse encoder-predictor pair trainable from raw pixels without EMA, stop-gradient, or pre-trained encoders. We show that the same latent space supports controllable abstraction: photometric prediction learns invariant structure while temporal prediction learns equivariant dynamics. After action-conditioned post-training on offline trajectories, UniJEPA enables zero-shot planning by treating goal features as prediction targets. On image, video, and control benchmarks, UniJEPA matches or surpasses task-specific JEPAs while requiring a single loss hyperparameter, and plans up to tens of times faster than generative world models at comparable accuracy.

arXiv

Addressable Memory for Video World Models

Xindi Wu, Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taixé, Despoina Paschalidou, Jonathan Lorraine, Aljoša Ošep

We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames. However, we find that models can no longer reliably address stored content once rollouts extend beyond the training horizon, because temporal Rotary Positional Embeddings (RoPE) offsets then fall outside the range seen during training and the model struggles to retrieve the relevant visual information through attention. Moreover, naively compressing the cache in the RoPE-rotated space corrupts memory by averaging together incompatible positional phases. To address this, we propose WorldTrace, a training-free memory framework for long-horizon visual persistence. WorldTrace keeps compressed memory addressable by assigning each summary slot a distinct, in-distribution virtual position. Within this addressable cache, we study two memory compression approaches: WorldTrace-Field compresses history for temporal coherence, while WorldTrace-Landmark stores verbatim scene traces at detected transitions for episodic recall. We further introduce LoopBench, a benchmark evaluating whether a compressed cache can reconstruct a previously visited scene after a long detour. WorldTrace-Field improves temporal consistency by +15.5%, and WorldTrace-Landmark improves episodic recall by +19.5% on LoopBench, extending visually persistent generation without retraining.

arXiv

GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation

Yonglong zhang, Zongwu Xie, Yang Liu

Foundation segmentation models can provide supervision for spacecraft imagery without manual training masks, but their predictions vary with textual prompts and may contain geometric errors that are amplified during distillation. This paper presents GeoDistill-Refine, a two-stage framework that transfers offline SAM 3 pseudo-masks to a compact segmentation network. Six fixed prompts are fused by an unweighted 50% vote to stabilize the teacher output. The student first learns the foreground silhouette and is then refined with signed-distance-field, skeleton, and area objectives derived from the pseudo-mask. A sample-level gate, computed from prompt agreement, the valid-prompt ratio, and pseudo-mask area plausibility, reduces the influence of unreliable pseudo-geometry. On the SpaceSense-Bench HJM lockbox set, GeoDistill-Refine improves Image IoU and Boundary F1 by 0.0456 and 0.1380, respectively, over a plain pseudo-label student. External evaluations on the SPEED+ Lightbox and Sunlamp domains and on TANGO show competitive regional overlap together with gains in boundary quality or foreground precision. The deployed TinyUNet contains 0.263 M parameters and requires approximately 1.1 ms per image on an RTX 4090; SAM 3 pseudo-mask construction and the auxiliary geometry branches are used only during training.

Keep browsing

More papers from top AI conferences

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