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

Lift, Associate, and Fuse: A Decision-Centric Framework for 2D-to-3D Foundation Model Transfer

Wentao Sun, Yiping Chen, John S. Zelek, Jonathan Li

Methods that transfer predictions from two-dimensional foundation models into three-dimensional segmentation are commonly grouped by task or representation. Those groupings obscure the decisions that determine whether a system remains coherent across views: where image evidence is grounded, when observations become one identity, how semantic and granularity conflicts are handled, which information is fused, and what state survives for later queries. We introduce \textbf{Lift, Associate, and Fuse (LAF)}, a decision-centric framework that represents a transfer system as five operators: \textbf{Generate, Associate, Reconcile, Fuse, and Persist/Query}. LAF defines an explicit contract for the persistent carrier---its spatial support, semantic state, identity state, uncertainty, provenance, and supported operations---and identifies the first stage at which discarded evidence becomes unrecoverable. We operationalize the framework as a structured audit protocol and apply it to 161 systems available through 7 August 2026, spanning point-, field-, Gaussian-, object-, graph-, and memory-based carriers. Representation, temporal, relational, and feed-forward stress tests required no additional analytical stage after the final confirmation pass. The resulting decision traces expose four recurring properties: association does not establish identity; carrier design fixes both the query interface and correction boundary; rendered-view, native-3D, and proposal-level evaluations are not interchangeable; and qualifiers such as \emph{training-free}, \emph{real-time}, \emph{open-vocabulary}, and \emph{generalizable} are meaningful only when attached to a stage and a complete cost ledger. LAF therefore supplies a representation-neutral method for comparing existing systems, diagnosing irreversible failures, and specifying revisable 3D perception for future agents.

arXiv

MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model

Taiga Yamane, Satoshi Suzuki, Ryo Masumura, Shota Orihashi, Tomohiro Tanaka, Mana Ihori, Naoki Makishima

Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view map from multi-view images. Recent MVPD methods adopt a unified framework that projects 2D image features into a 3D world space and aggregates them into a single feature. Although they are effective, they struggle to generalize to unseen camera configurations during training due to two main issues. First, they are difficult to capture accurate visual geometry across views in unseen camera configurations. Second, they make detection models highly dependent on distortion patterns during training arising from their image feature projection. To address these, we leverage a visual geometric foundation model and propose MV2GF. This foundation model has exhibited strong generalization in capturing visual geometry across views and predicting accurate 3D attributes in diverse camera configurations. MV2GF fuses task-specific features with general-purpose geometric features extracted by the foundation model to effectively capture the visual geometry even in unseen camera configurations. Furthermore, MV2GF projects each pixel in the image features to an appropriate 3D location using 3D pointmaps predicted by the foundation model, preventing the detection model from depending on distortion patterns during training. Our experiments demonstrate the effectiveness of leveraging a visual geometric foundation model for MVPD and that MV2GF generalizes better than existing methods.

arXiv

Exploring the Performance Frontier of Compact Unified Image Generation Models

taihang Hu, Zhao Wang, Zuan Gao, Tao Liu, Hao Yan, Zhengze Xu, Yuhang Yu, Yongchao Du, Xingjian Wang, Jun Zheng, Qinye Zhou, YaQi Cai, Zhengrui Chen, Chao Lin, Yefeng Shen, Yuan Wang, Zhengtao Wu, Ge Wu, Xiaoli Xu, Denghui Yang, Huayu Zhang, Mingzhou Zhang, Mengting Chen

We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a relatively small visual generator can be pushed through systematic training engineering under a constrained computational budget. Swift-Image adopts an efficient 6B single-stream DiT and a progressive training pipeline that evolves from broad semantic coverage to higher resolution, stronger visual quality, and unified generation-editing supervision. For post-training, we employ parallel expert reinforcement learning followed by multi-teacher on-policy distillation to alleviate interference among heterogeneous objectives. We further decouple high-level reasoning from pixel-level rendering with a Prompt Enhancer that translates user requests into generator-aligned visual specifications. For efficient deployment, structural pruning and few-step distillation produce 3B and accelerated variants. Swift-Image achieves leading aggregate performance among evaluated open-source models with only 6B parameters and 243K GPU training hours; the compressed 3B model incurs nearly no loss, while few-step distillation further improves aggregate editing performance with substantially fewer sampling steps. Our study also summarizes practical lessons for architecture, data curriculum, post-training, prompt enhancement, and model compression.

arXiv

ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval

Chunyi Peng, Zhipeng Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Sen Mei, Yubo Sun, Yongheng Zhang, Jie Zhou, Yu Gu, Ge Yu, Maosong Sun

Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document collections where evidence is distributed across text, layout, charts, and visual structures. Recent efforts toward finer-grained supervision primarily rely on textual descriptions or localized visual regions as evidence proxies. However, such supervision signals may either overlook complex visual structures or provide incomplete and inaccurate representations of the underlying evidence. To address these limitations, we propose ConceptFormer, a latent concept representation learning framework for visual document retrieval. ConceptFormer models query-relevant evidence as continuous, query-conditioned latent concepts that explicitly bridge localized visual evidence and semantic relevance, without requiring either textual intermediate representations or direct reliance on raw visual annotations. During training, ConceptFormer employs a strong vision-language model to dynamically determine the number of latent concept tokens and uses these concepts as an intermediate representation to bridge the semantic gap between queries and documents, thereby guiding the learning of the embedding space. Experiments on diverse visual document retrieval benchmarks demonstrate that ConceptFormer achieves 16.7\% and 22.1\% relative improvements in average NDCG@10 over the strongest visual retrieval baseline and the strongest OCR-based text retrieval baseline, respectively. Further analysis reveals that latent concepts effectively connect localized visual evidence with semantic relevance, enabling the retriever to capture both fine-grained textual cues and complex document-level visual structures while preserving strong retrieval alignment. Codes and data are available at https://github.com/Neuir/ConceptFormer.

arXiv

Instruction-Based Video Editing by Repurposing an Image Editing Model

Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi, Qixing Huang

Instruction-based video editing is commonly built on video-pretrained generative backbones: a video diffusion transformer is adapted, at considerable cost, to condition on a source video and an editing instruction. In this report we explore a different route and show that a strong instruction-based image editing model can edit videos by operating directly on video-VAE latents. Starting from Qwen-Image-Edit, we arrange the latent frames of a Wan~2.1 video VAE as tiles of one large virtual image, reuse the editor's image positional encoding for every tile, and bridge the two latent spaces with a pair of lightweight input/output projections warm-started from the editor's own patchify and unpatchify layers, so that at initialization a (static) video is embedded exactly as an image the model already understands. The whole system is then fine-tuned on the public Ditto-1M editing triplets, and a few denoising steps of Wan~2.2 serve as an optional temporal enhancer. We motivate the design with a chain of zero-training observations: the stock image editor already edits a video presented as a contact sheet; it is indifferent to whether the sheet's tokens come from one joint encode or from per-frame encodes stitched in latent space; and it even edits genuine video latents zero-shot to a clearly recognizable degree, leaving fine-tuning only a fidelity gap to close. Our results suggest that, despite the large investment in training video latent spaces, per-frame video latents remain close enough to the image domain that mature image editing priors transfer with minimal adaptation. Project Page: https://yunpeng1998.github.io/Qwen-Video-Edit-Page Code: https://github.com/yunpeng1998/Qwen-Video-Edit Model: https://huggingface.co/yunpeng1998/Qwen-Video-Edit

arXiv

Cloak of Invisibility: Real-Time Privacy-Preserving Volumetric Video Streaming

Hossein Khalili, Philip Do, Alexander Vilesov, Achuta Kadambi, Kittipat Apicharttrisorn, Nader Sehatbakhsh

Volumetric video streaming turns privacy into a 3D, multi-view problem. Unlike ordinary video, where sensitive content can often be redacted frame by frame, RGB-D volumetric pipelines capture people, rooms, and personal objects from multiple cameras and fuse them into a shared 3D representation. A private object missed in one view, or only partially removed before fusion, can therefore reappear in the reconstructed scene. This creates a privacy challenge for 3D telepresence, education, entertainment, and immersive applications: private content should be removed before raw visual and geometric data leave the camera side, while the public part of the scene should remain useful for real-time reconstruction. Existing volumetric streaming systems mainly optimize reconstruction, data movement, and latency, while privacy-preserving vision methods are designed for single-camera, single-frame images and do not directly address calibrated multi-view RGB-D fusion. We present InViStream, a real-time "privacy-from-source" system designed for this setting. InViStream addresses three challenges in volumetric capture: private objects may appear differently across views, RGB masking alone can leave geometric privacy leakage in depth, and public/private instances of the same class must be separated consistently before cloud-side fusion. To address these challenges, InViStream combines object detection with depth-aware masking, propagates public/private decisions across calibrated views, and fuses only sanitized point clouds. We evaluate InViStream on synthetic and real RGB-D scenes, including offices, conference rooms, living rooms, and settings with multiple public and private people and objects. InViStream achieves synthetic Dice/Recall of 0.799/0.891 and real Dice/Recall of 0.792/0.908, with synthetic SSIM above 0.98 and real-time streaming above 30 FPS.

arXiv

Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement

Uma Ranjan, Kunal Tilaganji, Aditya Koul, Anurag Mahipal, Dashpreet Singh, Hriday Rana, Manan Jain, Sidharth Gupta, Ajo Babu George, Vineeth Balasubramanian, Nagarajan Natarajan, Amit Sharma

Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models to abstain when uncertain improves reliability but introduces a coverage accuracy tradeoff. We propose a two-stage framework for medical hypothesis verification in multiple-choice settings that manages this tradeoff through targeted ontology grounding, applied only when the model abstains. We show that abstention is not random but reflects genuine uncertainty, with abstained predictions associated with lower confidence. Across two frontier models (GPT-5.5, accessed via the Azure OpenAI API, and DeepSeek-R1), the proposed framework improves question-level accuracy by 9.6 percentage points (82.9% to 92.5%) and hypothesis-level accuracy by 4.2 percentage points (92.0% to 96.2%). Our experiments conducted on MedReason and MedQA show that abstention can be repurposed as a control signal for selective reasoning refinement, achieving knowledge-graph-level performance without explicit knowledge graph construction.

arXiv

A continually expandable foundation model for brain MRI

Michail Mamalakis, Carmen Jimenez-Mesa, Yonghao Li, Hao Chen, Chao Li, Antonios Mamalakis, John Suckling, Richard Bethlehem, Stephen J. Price, Richard J. Gilbertson, Pietro Lio

Brain magnetic resonance imaging (MRI) is central to neuroscience and clinical assessment, but models are commonly developed for individual diseases, populations or imaging protocols. Foundation models promise more general representations, yet they are usually pretrained once and can lose earlier capabilities when updated with new data. Here we show that Alcmaeon, a three-dimensional brain MRI foundation model pretrained without manual labels on more than 425,000 volumes and derived imaging maps, can be expanded sequentially across clinical domains. Alcmaeon combines volumetric encoding and latent diffusion generation with Graph-Blueprint Pruning (GBP), which protects network modules important to earlier domains while leaving the remaining capacity trainable. Across expansion from healthy ageing and neurodegeneration to developmental, psychiatric and tumour imaging, GBP showed less forgetting than sequential adaptation and elastic weight consolidation across voxel-level reconstruction measures, with its largest advantage after adaptation to tumour imaging. The blueprints provided an inspectable record of how model capacity was protected and reused. Representations from different model levels supported image synthesis, disease classification, survival modelling and postoperative prediction, although no single representation was optimal for every task. These findings provide a route towards brain MRI foundation models that can grow with emerging data while retaining earlier capabilities.

arXiv

Generative Embedding Benchmark: How Much Information Survives in a Dense Embedding?

Yun Li, Biao Yang, Peixi Wu, Yunhao Zhou, Mingzhou Jiang, Wei Yuan, Fan Yang, Wenwu Ou

Embeddings have emerged as a standard representational interface linking foundation models with downstream systems. Most embedding benchmarks assess representations through discriminative tasks or geometric criteria centered on separability in embedding space. However, strong performance on such evaluations does not establish whether content compressed into an embedding remains accessible to a downstream generator. To address this gap, we introduce the Generative Embedding Benchmark (GEB), in which a decoder answers questions using only a frozen embedding and question text, without access to the original image or intermediate visual features. Answer quality under this readout measures generative information: the answer-relevant content recoverable from an embedding. GEB includes a curated visual-question-answering dataset with a 1,800-item development split and a held-out 900-item test split covering natural images, scene text, and visual documents. Using a common decoder and training recipe, we evaluate seven public embedding models in visual-only and vision-language joint modes. On the test set, visual-only scores range from 28.25 to 33.21; with image-question joint encoding, all five VLM-based embedding models score higher, and the best reaches 65.56. Matched embeddings also outperform text-only inputs, zero embeddings, and shuffled embeddings. Natural-image information is much easier to recover than scene text or visual-document information, while a Qwen3-VL-2B reference with access to the original image reaches 84.30. Together, these results show that generative readout exposes information bottlenecks that separability-based evaluation does not capture.

arXiv

A Distributional Robustness Margin For Pathology Foundation Models

Clément Grisi, Jeroen van der Laak, Geert Litjens

Pathology foundation models encode non-biological variation introduced by tissue preparation, staining and scanning, enabling shortcut learning that undermines generalisation across institutions. The Robustness Index (RI) was proposed to assess whether local representation geometry is dominated by biological or non-biological variation. However, its construction suffers from structural limitations that make cross-model comparison unreliable, calling for a more principled metric. We introduce the Cross-confounder Robustness Margin (CRoMa), a signed, per-sample margin that measures whether samples sharing the same biology but different confounder lie closer than samples sharing the same confounder but different biology. It is defined for every sample, allowing models to be compared on the same cohort and robustness to be analysed as a distribution rather than reduced to a single pooled score. We evaluated CRoMa across 20 tile-level encoders on three benchmarks. Rankings by median CRoMa were highly consistent across benchmarks (Spearman rho ~ 0.90), yet every encoder retained confounder-dominated samples, whose prevalence and severity varied markedly. Similar patterns emerged for four slide-level encoders evaluated on a separate benchmark, extending the analysis beyond tile-level representations. Higher median CRoMa was associated with smaller shortcut-induced performance losses in downstream linear probes, supporting its use as a representation-level indicator of shortcut susceptibility.

arXiv

MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents

Kaixin Ma, Di Feng, Alexander Metz, Jiarui Lu, Eshan Verma, Afshin Dehghan

We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful execution environment spanning 500+ tools across 16 application domains, supporting multi-image, multi-turn tasks where agents must ground progressively arriving visual inputs into executable tool calls while handling realistic conversational phenomena (goal revisions, error corrections, state mutations). An automated scenario generation pipeline produces diverse, visually grounded scenarios through information-flow-guided planning and multi-stage quality filtering, yielding 258 human-verified nominal scenarios and 50 variants targeting interactive UI applications. Evaluating 12 state-of-the-art models, from 4B open-weight to frontier proprietary systems, shows that current models still lack robust visual tool-calling capability: even the best model achieves below 50% success rate. Our failure analysis further reveals that visual precision, not only planning, is a primary bottleneck for capable models: 53% of failures stem from incorrect information extraction from images despite otherwise correct task workflows. A planning-to-precision crossover emerges with scale: smaller models fail at deciding what to do, while larger models fail at perceiving what they see, suggesting fundamentally different research directions for improving models at different capability levels. The framework and the benchmark are publicly available at https://github.com/apple/ml-mmtoolsandbox

arXiv

A Dual-domain Refinement Network with FBP-based Jacobian Learning for Sparse-view Dual-Energy CT Material Decomposition

Qian Liu, Xiaohong Fan, Ke Chen, Chong Chen, Shuaikang Wang, Jianping Zhang

Dual-energy CT (DECT) exploits attenuation differences across different X-ray spectra to provide richer material information and has been widely used in medical imaging. While sparse-view acquisition can lower radiation exposure, it makes DECT material decomposition even more challenging, as the problem is nonlinear and ill-posed. Existing deep unrolling approaches generally do not explicitly incorporate the Jacobian operator induced by the nonlinear forward model, and their sparsity priors are still mainly built on conventional convolutions, which are insufficient for modeling global structural information. This study addresses the challenge of DECT multi-material decomposition in sparse-view settings by representing it as a sparse-regularized nonlinear least-squares problem. To solve it, we propose an iterative dual-domain refinement network (DECT-DRNet). In each iteration, the filtered back-projection (FBP)-based Jacobian approximation module is used first to generate an intermediate material decomposition result. Here, we characterize the forward process of material decomposition using a nonlinear operator, and then construct a theoretically grounded learnable approximation of the adjoint Jacobian operator by integrating the FBP algorithm with a U-Net into the backward process. In addition, to address the limitation of existing deep learning-based decomposition methods in globally suppressing noise and artifacts, we introduce a learnable sparse dual domain regularization term that incorporates Fourier convolutional residual blocks. This refinement block combines geometric feature extraction in the image domain with noise suppression in the frequency domain, allowing the model to capture both global and local features while maintaining structural details. DECT-DRNet demonstrates its ability to achieve more accurate material decomposition under sparse-view conditions.

arXiv

MatMMExtract: An Open-Source Pipeline for Panel-Level Extraction of Grounded Image-Text Pairs from Materials Science Literature

Subham Ghosh, Shubham Tiwari, Mohammad Ibrahim, Abhishek Tewari

The materials science literature encodes decades of experimental knowledge in figures, yet this visual record remains locked away and inaccessible to AI at scale. The core difficulty is structural: most scientific figures are compound, with a single caption describing multiple sub-panels simultaneously, making direct image-text pairing unreliable. We present MatMMExtract, an end-to-end open-source pipeline that resolves this by decomposing compound figures into individual sub-panels and generating structured, grounded annotations using a large language model guided by a curated materials science taxonomy. Applied to 14,810 open-access articles, MatMMExtract produces MatSciFig; 391,606 panel-level image-text pairs from 180,571 figures, each annotated with a sub-caption, a two-level visualisation category spanning 19 classes and over 100 subtypes, and a scientific summary. To enable accurate panel localisation, we introduce MaterialScope, a domain-specific detection dataset of 2,811 manually annotated materials science figures, on which a fine-tuned YOLO12-m detector achieves mAP_50 of 0.9227. Among six benchmarked language models, Gemini 3.1 Flash Lite delivers the best cost-quality trade-off for annotation generation, with 82% of outputs rated good and a hallucination rate of 4.8%. A dual-encoder retrieval baseline on MatSciFig achieves a 4.4 times improvement in R@1 over zero-shot CLIP, demonstrating the dataset's immediate utility for vision-language learning. All resources are released openly to the community.

arXiv

MeshFlow: Mesh Generation with Equivariant Flow Matching

Qi Sun, Kiyohiro Nakayama, Jing Nathan Yan, Qixing Huang, Alexander Rush, Leonidas Guibas, Gordon Wetzstein, Jing Liao, Guandao Yang

Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains important symmetries, including permutation invariance of faces and vertices. MeshFlow learns to generate triangle meshes directly as triangle soups, avoiding the need to serialize meshes into long autoregressive sequences. We adopt equivariant optimal-transport flow matching models that respect the key symmetries of triangle soups: arbitrary permutations of faces and permutations of the vertices within each face. Toward this goal, we propose a simple yet effective modification to the Diffusion Transformer architecture, resulting in a scalable network capable of modeling a velocity field while maintaining the desired equivariance. We further introduce an optimal-transport-based training objective that improves convergence by eliminating supervision signals that violate these symmetries. MeshFlow achieves mesh quality comparable to state-of-the-art autoregressive mesh generators while providing about an 18$\times$ speedup during inference. Project page is at https://qiisun.github.io/MeshFlow/.

arXiv

Future Dynamic 3D Reconstruction: Toward 3D World Modeling with Disentangled Ego-Motion

Nils Morbitzer, Jonathan Evers, Artem Savkin, Thomas Stauner, Nassir Navab, Federico Tombari, Stefano Gasperini

Forecasting the evolution of dynamic environments is crucial for autonomous agents. While generative world models have achieved high photorealism in 2D video synthesis by mixing ego-motion and environmental dynamics within the image plane, they exhibit physical inconsistencies, such as morphing or vanishing objects, especially over long time horizons. In this paper, we propose FR3D, a world-modeling approach that predicts a persistent 3D latent representation for future dynamic 3D reconstruction. Unlike prior works that treat the world as a sequence of image-based features, FR3D explicitly decouples the 3D evolution of the scene from the agent's trajectory, treating the inferred ego-motion as a latent proxy for action. This disentanglement resolves ambiguities between self-motion and world-motion, ensuring geometric consistency into the future. Furthermore, we introduce a teacher-student distillation strategy that leverages the spatial "common sense" of off-the-shelf foundation models, leading to robust zero-shot generalization. Extensive experiments demonstrate FR3D's strong performance for future dynamic 3D reconstruction from monocular observations across multiple datasets, even 2 seconds into the future. Project page: https://fr3d-wm.github.io.

arXiv

CogCanvas: A Benchmark for Evaluating Multi-Subject Reference-Based Image Generation

Long-Bao Nguyen, Quang-Khai Le, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le

Multi-subject reference-based image generation requires jointly preserving multiple human identities, binding per-person objects and fashion items, and respecting a specified background scene, a regime where current diffusion models remain brittle. Existing benchmarks evaluate only one axis at a time and none jointly captures multi-identity composition with human-object interaction, background grounding, and spatial plausibility. We introduce CogCanvas, a benchmark of 1,952 curated reference images spanning 100 celebrity identities, 115 distinctive objects and fashion items, and 29 real-world background scenes including landmarks, from which we construct 1,361 compositional prompts covering 2-5 person group sizes. The curation pipeline combines DINOv2-based deduplication, two-stage aesthetic filtering, and automated derivation of structured interaction and position graphs that serve as ground-truth supervision. CogCanvas supports three tasks, reference-based multi-human-object generation (primary), text-to-image compositional generation, and reference retrieval, under a unified six-axis evaluation protocol. We introduce two metrics tailored to the multi-reference setting: BG-Sim, which scores background fidelity on SAM 3-masked regions via DINOv3 feature similarity, and Attr-VQA, which uses a multimodal LLM to verify per-subject attribute binding and inter-person interactions against the structured graphs. Benchmarking five SOTA methods reveals that every model degrades substantially as group size grows from 2 to 5, with near-complete failure on object/fashion binding beyond three subjects.

arXiv

Learning to Orchestrate Vision Foundation Models for Multi-Task Dense Prediction

Donghyun Han, Yuseok Bae, Jung Uk Kim, Hyung-Il Kim

Vision foundation models (VFMs) exhibit complementary strengths shaped by their pretraining objectives. Yet prevailing methods for multi-task dense prediction still train an entire backbone, either by fine-tuning it under multi-task supervision or by distilling multiple VFMs in an additional stage. We ask whether downstream learning can instead compose the frozen representations already available in foundation models. Dense tasks require composite representations that no individual expert provides alone. Realizing them is difficult: simple fusion yields only marginal gains over the best single expert, while learned routing tends to collapse toward candidates that are strong at initialization, starving newly initialized composers of training signal. We present COVE, which constructs pairwise composite candidates through Synergy Composers and routes among raw and composite candidates with a Task-Conditioned Router. To prevent this collapse, COVE combines Gaussian logit perturbation for exploration with counterfactual supervision that selectively increases under-credited routing allocations. On NYUD-v2 and PASCAL-Context, COVE matches or surpasses ViT-L-based methods on most tasks using a smaller frozen encoder pool and roughly half the computation of recent VFM-based competitors, while exceeding the best single frozen expert on every task.

arXiv

Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation

Xiaomeng Yang, Yanyu Li, Gordon Guocheng Qian, Ivan Skorokhodov, Viacheslav Ivanov, Avalon Vinella, Xuan Zhang, Yanzhi Wang, Sergey Tulyakov, Anil Kag

While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current practice requires training a separate Low-Rank Adaptation (LoRA) module for each effect, incurring substantial data curation and iterative optimization costs that hinder interactive control. We present Prompt2Effect, a weight-driven hypernetwork that amortizes per-effect training by directly synthesizing effect-specific LoRA weights in a single forward pass. Unlike prior hypernetworks that regress adapter weights purely from semantics, Prompt2Effect is explicitly conditioned on the frozen base model weights, grounding prediction in the structural geometry of each layer. Furthermore, instead of predicting raw LoRA matrices, we introduce an SVD-canonicalized parameterization that resolves factorization ambiguity and stabilizes large-scale synthesis. Extensive experiments demonstrate that Prompt2Effect achieves on-par or superior video quality and effect alignment compared to conventional LoRA fine-tuning, while reducing the computational cost from 56 GPU training hours to 3.3 seconds of hypernetwork inference. When used as initialization for subsequent fine-tuning, our predicted weights further improve final performance and accelerate optimization by approximately 10x.

arXiv

From Simulation to the Real-World: An In-Field 6D Pose Dataset and Baseline for Robotic Strawberry Harvesting

Woojung Son, Won Suk Lee, Zijing Huang, Daeun Choi, Catia Silva, Yu She, Yan Gu

Robotic strawberry harvesting requires precise 6D pose estimation; however, collecting 6D pose ground truth in real agricultural fields is inherently challenging. Existing strawberry 6D pose estimation studies have therefore relied mainly on synthetic data, leaving their in-field performance unquantified. In this work, we obtain ground truth indirectly, by recovering camera poses via PnP, reconstructing each scene at metric scale, and annotating a single 3D bounding box per strawberry that is propagated across all frames, yielding, to the best of our knowledge, the first real world 6D pose ground truth dataset of red-stage strawberries collected at an actual strawberry farm (12,040 images). We also introduce a synthetic dataset rendered in NVIDIA Isaac Sim, featuring scene-level realism and domainrandomization. Despite this improved simulation setup, models trained on synthetic data alone fail to transfer to in-field images, while introducing a small amount of real data improves both translation and rotation accuracy across all backbones. Under the monocular RGB setting evaluated here, rotation is largely recovered once real data is used, and depth is what limits pose accuracy. These baselines across backbone encoders serve as a reference for future work. The real-world dataset is publicly available at https://huggingface.co/datasets/WoojungSon/F ieldStraw6D, and the data-collection pipeline is available at https://github.com/wjson2435/FieldStraw6D-pipeline.

arXiv

Reason-Then-Retrieve for CoVR-R with Structured Edit Prompts and Dense-Sparse Fusion

Dongqing Liu, Mengshi Qi, Hongwei Ji

CoVR-R studies reason-aware composed video retrieval: given a reference video and an edit instruction, the system must retrieve the target video that satisfies the edit. The main difficulty is that the target is not described directly; it must be inferred from fine-grained changes in object identity, action order, final state, hand interaction, and scene transition. We build a zero-shot reason-then-retrieve pipeline around Qwen3.5-27B. For each gallery video, the model generates a retrieval-oriented structured description and a dense embedding by pooling generated-token hidden states with token-dependent weights. For each query, the model first performs edit reasoning over the reference video and instruction, then generates a target-video description whose hidden states serve as the query embedding. We complement dense retrieval with a TF-IDF branch over the generated texts and fuse the two rankings with split-specific weights. On validation, the current best submission reaches 80.81 at R@1, 94.86 at R@5, 97.11 at R@10, and 98.59 at R@50. On the blind test split, it reaches 89.73 at R@1, 95.79 at R@5, 96.63 at R@10, and 97.98 at R@50.

Keep browsing

More papers from top AI conferences

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