arXiv subjects

Yezhou Yang

Publications and source records attributed to Yezhou Yang.

At least 19 recordsLinked to original sources

arXiv2026

PRISM: Principled Reference Identification for Schrodinger Bridge Model

Schr\"odinger bridge models restore a clean signal from a degraded observation by following the conditional bridges of a reference process, yet this reference is chosen heuristically, typically white noise with a hand-tuned schedule. We develop PRISM, a theory of bridge reference design. We characterize the time-varying Gaussian references that remain exactly tractable with per-mode schedules: precisely those whose instantaneous covariances commute. We then prove an invisibility principle: with the exact drift and unlimited solver steps, every admissible reference recovers the true posterior. The choice of reference therefore matters only under finite computational resources. For a fixed step budget, we derive the finite-step objective in closed form and prove that every optimal noise spectrum is proportional to Pk, the spectrum of information destroyed by the sensor, with a mode-independent constant x*(T) = (2 ln T)^-1/2 (1 + o(1)). The analysis shows that noise color and temporal scheduling are interchangeable, and regularization provably shifts the optimal reference toward white noise. Experiments in Gaussian settings confirm the predicted orderings and the closed-form loss floors. On FFHQ, the distortion-- perception trade-off and spectral localization transfer, but white noise outperforms the matched reference; a pre-registered study that changes the training regime refutes ridge whitening as the explanation. A 2x2 mechanism study then traces the inversion to the non-Gaussian per-mode statistics of real images. PRISM turns reference design from a hyperparameter sweep into a calculation in the Gaussian regime, and locates exactly where real images break it.

cs.LG↗

arXiv2026

SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction

Relational reasoning requires the process of perceptual understanding, comparing, and integrating the underlying relationships between concepts. This ability consists of multiple categories, such as analogical, structural, and cause-effect, each capturing a different aspect of higher-order understanding. To examine the performance of multimodal large language models (MLLM) on these relational inference tasks, we developed SciReC, a model-adaptive multimodal academic dialog benchmark. As the relational reasoning process involves multiple representations and various factors (visual understanding, exhibiting knowledge, and memory recall), we propose DMRA, a deficit-based diagnostic framework that quantifies the contribution of these components to identify the primary cause of unsuccessful cases. Claude 4.6 achieved the best performance on the overall relational score with 73\%, followed by GPT 5.4 with 68\%. Performance trends indicate that open-source models achieve their lowest scores on spatial relations, while proprietary models struggle more with hierarchical and sequential relations. Across domains, model performance is lowest on Astronomy and highest on Psychology. The results of DMRA reveal that relational reasoning is the primary source of error across all models, followed by memory limitations.

cs.CL↗

arXiv2026

Asynchronous Remote Sensing Time-Series Fusion for Cloud Removal and Anytime Reconstruction

Frequent cloud cover severely limits the usability of Sentinel-2 (S2) optical time series for Earth surface monitoring. Sentinel-1 (S1) SAR provides all-weather complementary observations, but practical S1/S2 fusion remains difficult because acquisitions are irregular and asynchronous. Many existing approaches assume temporally aligned inputs (or require external nearest-date matching) and typically restore only observed timestamps, limiting reconstruction under long gaps and preventing on-demand synthesis. We propose AGFlow (Time Aligned Generative Flow Matching), a spatiotemporal flow-matching model for S1/S2 cloud removal and time-series reconstruction with three capabilities: (1) timestamp-conditioned internal alignment that fuses asynchronous S1 and cloudy S2 observations without preprocessing-based pairing; (2) spatiotemporal, context-aware denoising that models spatial structure jointly with temporal dynamics (rather than independent per-pixel time series); and (3) anytime querying, enabling generation of cloud-free S2 frames at both observed and user-specified timestamps within the monitoring window. We evaluate on the RESTORE-DiT benchmark protocol with quantitative metrics, qualitative comparisons, and component ablations. AGFlow notably improves fully missing-frame reconstruction (MAE and RMSE reduce by 16-19% over RESTORE-DiT) and provides reliable reconstructions under persistent gaps, while also yielding competitive cloud removal performance and flexible temporal querying for downstream tasks such as dense vegetation monitoring.

cs.CV↗

arXiv2026

ShadeBench: A Benchmark Dataset for Building Shade Simulation in Sustainable Society

Urban heat exposure is becoming an increasingly critical challenge due to the intensifying urban heat island effect. Fine-grained shade patterns, especially those induced by urban buildings, strongly influence pedestrians' thermal exposure and outdoor activity planning. However, accurately modeling and analyzing urban shade at scale remains difficult because of the lack of large-scale datasets and systematic evaluation frameworks. To address this challenge, we present ShadeBench, a comprehensive dataset and benchmark for urban shade understanding. ShadeBench contains geographically diverse urban scenes with temporally varying simulated shade maps and textual descriptions, together with aligned satellite imagery, building skeleton representations, and 3D building meshes. Built upon this multimodal dataset, ShadeBench supports a range of downstream tasks, including shade generation, shade segmentation, and 3D building reconstruction. We further establish standardized evaluation protocols and baseline methods for these tasks. By enabling scalable and fine-grained shade analysis, ShadeBench provides a foundation for data-driven urban climate research and supports future studies in heat-resilient urban planning and decision-making. The code and dataset are publicly available at https://darl-genai.github.io/shadebench/.

cs.CV↗

arXiv2026

The Unwritten Benchmark: A New Challenge for Multimodal Machine Learning in Abstract Perceptual Reasoning

Current multimodal models have demonstrated remarkable proficiency in recognizing static visual and auditory content. However, their capacity for abstract perceptual reasoning, inferring unseen information from dynamic, generative processes, remains a critical and underexplored frontier. In this paper, we introduce The Unwritten Benchmark, a new challenge designed to probe this abstract perceptual and cognitive ability. We define the core task as acousto-kinematic word inference: models must decipher words, across 3 different writing styles, being written solely from the audio of pen scratches and the video of hand movements, without any visible ink trace. Our evaluation results reveal a profound gap between human and machine performance: while human participants achieve high ordered letter accuracy (over 80%), leading Multimodal Machine Learning Models, including GPT-4o and Gemini 2.5-Pro, struggle significantly, failing to surpass 10%. Furthermore, we identify a paradoxical fusion effect in the models, where providing both modalities often degrades performance rather than improving it. This finding indicates a fundamental breakdown in their ability to synthesize complementary perceptual cues for this cognitive task. These findings highlight significant limitations in both cross-modal causal reasoning and the understanding of the micro-kinematics essential for such cognitive and intuitive perceptual reasoning.

cs.AI↗

arXiv2026

VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations

We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffusion models at scale. At its core is VibeToken, a novel resolution-agnostic 1D Transformer-based image tokenizer that encodes images into a dynamic, user-controllable sequence of 32-256 tokens, achieving a state-of-the-art efficiency and performance trade-off. Building on VibeToken, we present VibeToken-Gen, a class-conditioned AR generator with out-of-the-box support for arbitrary resolutions while requiring significantly fewer compute resources. Notably, VibeToken-Gen synthesizes 1024x1024 images using only 64 tokens and achieves 3.94 gFID; by comparison, a diffusion-based state-of-the-art alternative requires 1,024 tokens and attains 5.87 gFID. In contrast to fixed-resolution AR models such as LlamaGen -- whose inference FLOPs grow quadratically with resolution (11T FLOPs at 1024x1024) -- VibeToken-Gen maintains a constant 179G FLOPs (63.4x efficient) independent of resolution. We hope VibeToken can help unlock the wide adoption of AR visual generative models in production use cases.

cs.CV↗

arXiv2026

eNavi: Event-based Imitation Policies for Low-Light Indoor Mobile Robot Navigation

Event cameras provide high dynamic range and microsecond-level temporal resolution, making them well-suited for indoor robot navigation, where conventional RGB cameras degrade under fast motion or low-light conditions. Despite advances in event-based perception spanning detection, SLAM, and pose estimation, there remains limited research on end-to-end control policies that exploit the asynchronous nature of event streams. To address this gap, we introduce a real-world indoor person-following dataset collected using a TurtleBot 2 robot, featuring synchronized raw event streams, RGB frames, and expert control actions across multiple indoor maps, trajectories under both normal and low-light conditions. We further build a multimodal data preprocessing pipeline that temporally aligns event and RGB observations while reconstructing ground-truth actions from odometry to support high-quality imitation learning. Building on this dataset, we propose a late-fusion RGB-Event navigation policy that combines dual MobileNet encoders with a transformer-based fusion module trained via behavioral cloning. A systematic evaluation of RGB-only, Event-only, and RGB-Event fusion models across 12 training variations ranging from single-path imitation to general multi-path imitation shows that policies incorporating event data, particularly the fusion model, achieve improved robustness and lower action prediction error, especially in unseen low-light conditions where RGB-only models fail. We release the dataset, synchronization pipeline, and trained models at https://eventbasedvision.github.io/eNavi/

cs.RO↗

arXiv2026

Domain Expansion: A Latent Space Construction Framework for Multi-Task Learning

Training a single network with multiple objectives often leads to conflicting gradients that degrade shared representations, forcing them into a compromised state that is suboptimal for any single task--a problem we term latent representation collapse. We introduce Domain Expansion, a framework that prevents these conflicts by restructuring the latent space itself. Our framework uses a novel orthogonal pooling mechanism to construct a latent space where each objective is assigned to a mutually orthogonal subspace. We validate our approach across diverse benchmarks--including ShapeNet, MPIIGaze, and Rotated MNIST--on challenging multi-objective problems combining classification with pose and gaze estimation. Our experiments demonstrate that this structure not only prevents collapse but also yields an explicit, interpretable, and compositional latent space where concepts can be directly manipulated.

cs.LG↗

arXiv2026

UDVideoQA: A Traffic Video Question Answering Dataset for Multi-Object Spatio-Temporal Reasoning in Urban Dynamics

Understanding the complex, multi-agent dynamics of urban traffic remains a fundamental challenge for video language models. This paper introduces Urban Dynamics VideoQA, a benchmark dataset that captures the unscripted real-world behavior of dynamic urban scenes. UDVideoQA is curated from 16 hours of traffic footage recorded at multiple city intersections under diverse traffic, weather, and lighting conditions. It employs an event-driven dynamic blur technique to ensure privacy preservation without compromising scene fidelity. Using a unified annotation pipeline, the dataset contains 28K question-answer pairs generated across 8 hours of densely annotated video, averaging one question per second. Its taxonomy follows a hierarchical reasoning level, spanning basic understanding and attribution to event reasoning, reverse reasoning, and counterfactual inference, enabling systematic evaluation of both visual grounding and causal reasoning. Comprehensive experiments benchmark 10 SOTA VideoLMs on UDVideoQA and 8 models on a complementary video question generation benchmark. Results reveal a persistent perception-reasoning gap, showing models that excel in abstract inference often fail with fundamental visual grounding. While models like Gemini Pro achieve the highest zero-shot accuracy, fine-tuning the smaller Qwen2.5-VL 7B model on UDVideoQA bridges this gap, achieving performance comparable to proprietary systems. In VideoQGen, Gemini 2.5 Pro, and Qwen3 Max generate the most relevant and complex questions, though all models exhibit limited linguistic diversity, underscoring the need for human-centric evaluation. The UDVideoQA suite, including the dataset, annotation tools, and benchmarks for both VideoQA and VideoQGen, provides a foundation for advancing robust, privacy-aware, and real-world multimodal reasoning. UDVideoQA is available at https://ud-videoqa.github.io/UD-VideoQA/UD-VideoQA/.

cs.CV↗

arXiv2026

MentalBlackboard: Evaluating Spatial Visualization via Mathematical Transformations

Spatial visualization is the mental ability to imagine, transform, and manipulate the spatial characteristics of objects and actions. This intelligence is a part of human cognition where actions and perception are connected on a mental level. To explore whether state-of-the-art Vision-Language Models (VLMs) exhibit this ability, we develop MentalBlackboard, an open-ended spatial visualization benchmark for Paper Folding and Hole Punching tests within two core tasks: prediction and planning. Our prediction experiments reveal that models struggle with applying symmetrical transformations, even when they predict the sequence of unfolding steps correctly. Also, rotations introduce a significant challenge to the physical situational awareness for models. The planning task reveals limitations of models in analyzing symmetrical relationships and in implementing the multi-stage symmetry process, with Claude Opus 4.1 achieving the highest planning score at an accuracy of 10\%. The top-performing model, o3, attains a peak performance of 71.6\% on the generalization task, which does not require spatial visualization but transfers spatial data; however, it achieves only 25\% accuracy on text-based prediction tasks.

cs.CV↗

arXiv2026

Hi-Light: A Path to high-fidelity, high-resolution video relighting with a Novel Evaluation Paradigm

Video relighting offers immense creative potential and commercial value but is hindered by challenges, including the absence of an adequate evaluation metric, severe light flickering, and the degradation of fine-grained details during editing. To overcome these challenges, we introduce Hi-Light, a novel, training-free framework for high-fidelity, high-resolution, robust video relighting. Our approach introduces three technical innovations: lightness prior anchored guided relighting diffusion that stabilises intermediate relit video, a Hybrid Motion-Adaptive Lighting Smoothing Filter that leverages optical flow to ensure temporal stability without introducing motion blur, and a LAB-based Detail Fusion module that preserves high-frequency detail information from the original video. Furthermore, to address the critical gap in evaluation, we propose the Light Stability Score, the first quantitative metric designed to specifically measure lighting consistency. Extensive experiments demonstrate that Hi-Light significantly outperforms state-of-the-art methods in both qualitative and quantitative comparisons, producing stable, highly detailed relit videos.

cs.CV↗

arXiv2026

VOCAL: Visual Odometry via ContrAstive Learning

Breakthroughs in visual odometry (VO) have fundamentally reshaped the landscape of robotics, enabling ultra-precise camera state estimation that is crucial for modern autonomous systems. Despite these advances, many learning-based VO techniques rely on rigid geometric assumptions, which often fall short in interpretability and lack a solid theoretical basis within fully data-driven frameworks. To overcome these limitations, we introduce VOCAL (Visual Odometry via ContrAstive Learning), a novel framework that reimagines VO as a label ranking challenge. By integrating Bayesian inference with a representation learning framework, VOCAL organizes visual features to mirror camera states. The ranking mechanism compels similar camera states to converge into consistent and spatially coherent representations within the latent space. This strategic alignment not only bolsters the interpretability of the learned features but also ensures compatibility with multimodal data sources. Extensive evaluations on the KITTI dataset highlight VOCAL's enhanced interpretability and flexibility, pushing VO toward more general and explainable spatial intelligence.

cs.CV↗

arXiv2026

eSkiTB: A Synthetic Event-based Dataset for Tracking Skiers

Tracking skiers in RGB broadcast footage is challenging due to motion blur, static overlays, and clutter that obscure the fast-moving athlete. Event cameras, with their asynchronous contrast sensing, offer natural robustness to such artifacts, yet a controlled benchmark for winter-sport tracking has been missing. We introduce event SkiTB (eSkiTB), a synthetic event-based ski tracking dataset generated from SkiTB using direct video-to-event conversion without neural interpolation, enabling an iso-informational comparison between RGB and event modalities. Benchmarking SDTrack (spiking transformer) against STARK (RGB transformer), we find that event-based tracking is substantially resilient to broadcast clutter in scenes dominated by static overlays, achieving 0.685 IoU, outperforming RGB by +20.0 points. Across the dataset, SDTrack attains a mean IoU of 0.711, demonstrating that temporal contrast is a reliable cue for tracking ballistic motion in visually congested environments. eSkiTB establishes the first controlled setting for event-based tracking in winter sports and highlights the promise of event cameras for ski tracking. The dataset and code will be released at https://github.com/eventbasedvision/eSkiTB.

cs.CV↗

arXiv2026

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models

Video-language models (VLMs) achieve strong multimodal understanding but remain prone to hallucinations, especially when reasoning about actions and temporal order. Existing mitigation strategies, such as textual filtering or random video perturbations, often fail to address the root cause: over-reliance on language priors rather than fine-grained visual dynamics. We propose a scalable framework for counterfactual video generation that synthesizes videos differing only in actions or temporal structure while preserving scene context. Our pipeline combines multimodal LLMs for action proposal and editing guidance with diffusion-based image and video models to generate semantic hard negatives at scale. Using this framework, we build CounterVid, a synthetic dataset of ~26k preference pairs constructed from short counterfactual action clips and targeting both action recognition and controlled action-sequence ordering. We further introduce MixDPO, a unified Direct Preference Optimization approach that jointly leverages textual and visual preferences. Across Qwen2.5-VL and InternVL3 backbones, MixDPO substantially improves action recognition and temporal ordering, yields gains on most standard video hallucination benchmarks, and largely preserves general video understanding. Our source code, trained models, and dataset are available at https://aimagelab.github.io/CounterVid.

cs.CV↗

arXiv2025

Foundation Model in Biomedicine

Foundation models, first introduced in 2021, refer to large-scale pretrained models (e.g., large language models (LLMs) and vision-language models (VLMs)) that learn from extensive unlabeled datasets through unsupervised methods, enabling them to excel in diverse downstream tasks. These models, like GPT, can be adapted to various applications such as question answering and visual understanding, outperforming task-specific AI models and earning their name due to broad applicability across fields. The development of biomedical foundation models marks a significant milestone in the use of artificial intelligence (AI) to understand complex biological phenomena and advance medical research and practice. This survey explores the potential of foundation models in diverse domains within biomedical fields, including computational biology, drug discovery and development, clinical informatics, medical imaging, and public health. The purpose of this survey is to inspire ongoing research in the application of foundation models to health science.

cs.LG↗

arXiv2025

EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment

Erasing harmful or proprietary concepts from powerful text to image generators is an emerging safety requirement, yet current "concept erasure" techniques either collapse image quality, rely on brittle adversarial losses, or demand prohibitive retraining cycles. We trace these limitations to a myopic view of the denoising trajectories that govern diffusion based generation. We introduce EraseFlow, the first framework that casts concept unlearning as exploration in the space of denoising paths and optimizes it with GFlowNets equipped with the trajectory balance objective. By sampling entire trajectories rather than single end states, EraseFlow learns a stochastic policy that steers generation away from target concepts while preserving the model's prior. EraseFlow eliminates the need for carefully crafted reward models and by doing this, it generalizes effectively to unseen concepts and avoids hackable rewards while improving the performance. Extensive empirical results demonstrate that EraseFlow outperforms existing baselines and achieves an optimal trade off between performance and prior preservation.

cs.LG↗

arXiv2025

Semantic-Guided Cross-Sensor Super Resolution of Remote Sensing Images: A Gated Dual Conditioning Flow Matching Model

High spatial resolution satellite imagery is critical for monitoring fine-scale Earth surface processes, but is often limited by cost and revisit time. This work studies cross-sensor super-resolution (SR) to reduce this gap by translating 10 m Sentinel-2 imagery into 2 m Maxar-like imagery in a data-scarce, domain-shifted setting, with a focus on rare geomorphic features such as retrogressive thaw slumps (RTS). We propose RareFlow, a semantic-guided generative AI framework for cross-sensor super-resolution based on a flow-matching formulation, designed to produce visually plausible and physically reliable high-resolution images. RareFlow uses dual conditioning to guide the generation process: (1) a gated ControlNet that preserves scene geometry from low-resolution (LR) input, and (2) text-based semantic guidance that injects contextual information when the target phenomenon is rare. To ensure high-fidelity outputs, we introduce a multifaceted loss function that anchors the output to the high-resolution (HR) ground truth by jointly enforcing frequency alignment, perceptual similarity, and color consistency. RareFlow's performance is systematically evaluated on a newly curated benchmark of multi-sensor satellite imagery for rare Earth feature detection, and its generalizability is demonstrated on two public remote sensing benchmarks, SEN2NAIP and BreizhSR. Human evaluation with domain experts is also conducted to further verify RareFlow's effectiveness in generating high-fidelity super-resolved images for scientific analysis.

cs.CV↗

arXiv2025

Chimera: Compositional Image Generation using Part-based Concepting

Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple source images without user specified masks or annotations. To address this, we introduce Chimera, a personalized image generation model that generates novel objects by combining specified parts from different source images according to textual instructions. To train our model, we first construct a dataset from a taxonomy built on 464 unique (part, subject) pairs, which we term semantic atoms. From this, we generate 37k prompts and synthesize the corresponding images with a high-fidelity text-to-image model. We train a custom diffusion prior model with part-conditional guidance, which steers the image-conditioning features to enforce both semantic identity and spatial layout. We also introduce an objective metric PartEval to assess the fidelity and compositional accuracy of generation pipelines. Human evaluations and our proposed metric show that Chimera outperforms other baselines by 14% in part alignment and compositional accuracy and 21% in visual quality.

cs.CV↗