arXiv subjects

Beidi Zhao

Publications and source records attributed to Beidi Zhao.

13 recordsLinked to original sources

arXiv2026

SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning

Whole-slide images (WSIs) are challenging for vision-language reasoning because diagnostically relevant morphology is sparse, heterogeneous, and distributed across gigapixel-scale images and multiple spatial resolutions. Existing WSI models and pathology agents can aggregate slide features or actively acquire evidence, but the information retained after exploration is often difficult to access semantically while preserving its connection to the original visual evidence. We introduce SlideBank, a training-free framework that represents each WSI as a persistent, concept-indexed, and spatially grounded evidence bank. SlideBank performs question-independent coarse-to-fine exploration to identify informative regions and multi-scale views, converts them into explicit morphological observations, and grounds pathology signals to their supporting patches and WSI coordinates. At inference time, questions are routed to relevant signals and evidence scales, and the linked global, regional, and patch evidence is integrated through confidence-based cross-level consensus. Experiments on WSI-VQA and SlideBench-BCNB show that with Patho-R1, SlideBank reaches 52.77% on WSI-VQA and with Quilt-LLaVA, it reaches 50.92% average accuracy on SlideBench-BCNB, while structured signal-guided retrieval consistently outperforms random evidence sampling. Reusing the same bank across repeated queries further achieves over 99% rephrasing consistency and substantially reduces amortized inference cost through persistent evidence reuse.

cs.AI↗

arXiv2026

MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory

Long-horizon agents accumulate trajectories spanning hundreds of interleaved reasoning, action, and observation steps, where answering a query may depend on evidence buried far back in the history. External memory stores such trajectories as structured representations, yet each structure provides a distinct and incomplete view. Existing multi-memory systems either read a fixed set of structures for every query, inflating context and introducing noise, or route each query to a single structure, preventing the composition of complementary evidence. A controlled analysis on AMA-Bench shows that the optimal memory configuration is typically neither a single structure nor the full union, but a tailored composition of multiple structural memories that varies with query and task demands. Motivated by these findings, we formulate structure-level dynamic selection: selecting and fusing a query-adaptive subset from a library of specialized memory structures. We propose MESA (a Multi-structure Evidence Selection framework for long-horizon Agent), which builds five complementary structure views of each trajectory and learns from end-to-end answer-level feedback to select and fuse a query-specific subset for a frozen answer model. To learn under this weak supervision, MESA employs harness optimization with prior-guided search and UCB-guided scheduling to balance exploration and exploitation. On AMA-Bench, MESA outperforms the strongest baseline by 8.5% while using 41% fewer evidence tokens than the all-structure alternative.

cs.AI↗

arXiv2026

SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation

Although agent skills equip LLMs with reusable procedural knowledge, manual maintenance suffers from high costs, unscalability, and misalignment. Real-world deployments thus require autonomous, on-demand skill evolution at test time, constrained by limited interaction budgets and a lack of training or validation sets. This setting introduces a severe sparse reward challenge, where outcomes conflate multiple latent failure causes. Under such ambiguity, existing methods that greedily refine a single incumbent skill are particularly vulnerable to an exploitation trap, allowing early misdiagnoses to exhaust limited trials along unproductive trajectories. To address this, we introduce SkillHEX, a closed-loop framework coupling hypothesis-driven self-verification with evidence-guided tree search. SkillHEX translates falsifiable failure hypotheses into executable tests, producing diagnostic evidence as dense reward without additional environment attempts. This evidence guides a search over persistent skill-revision branches, dynamically balancing the exploitation of supported edits with the exploration of plausible alternatives. Evaluated on 87 tasks from SkillsBench, SkillHEX outperforms existing self-evolving methods and achieves an average pass rate of 55.9% and 57.9% using GPT-5.3-Codex and Claude Opus 4.7 under a five-iteration budget, respectively.

cs.AI↗

arXiv2026

UltraVR: A Diagnostic Ultra-Resolution Image-VQA Benchmark for Evidence-Grounded Reasoning

Vision-language models (VLMs) excel on visual question answering and multimodal reasoning benchmarks. Yet their capability on ultra-resolution images - where critical evidence is tiny, subtle, spatially distant, or distributed - remains unclear. Existing evaluations largely report final-answer accuracy, offering limited insight into whether models acquire and integrate the necessary visual evidence. We introduce UltraVR, a diagnostic benchmark for evidence-grounded visual reasoning over ultra-resolution images. UltraVR spans four high-value scenarios: CCTV surveillance, remote sensing (RS), whole-slide image (WSI) pathology, and industrial anomaly detection (AD). These domains pose complementary challenges: fine-grained object grounding in crowded CCTV scenes, long-range spatial comparison in RS, multi-scale evidence navigation in WSI, and subtle irregularity detection in repetitive industrial layouts. Beyond standard QA triples, each instance includes a structured ground-truth chain of thought with step-level questions, intermediate answers, and reasoning labels. These labels decompose reasoning into evidence grounding, local perception, quantification, evidence integration, and decision inference, enabling process-level diagnosis over black-box scoring. Using UltraVR, we evaluate frontier VLMs and show that current models remain far from reliable on ultra-resolution reasoning. Importantly, the structured annotations allow us to localize failures across the visual-to-decision pipeline: errors concentrate in evidence grounding and local perception, while downstream inference often recovers when intermediate visual facts are supplied. These findings demonstrate UltraVR as a diagnostic testbed for measuring not only whether VLMs answer correctly, but where their ultra-resolution reasoning process breaks.

cs.CV↗

arXiv2026

Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQA

Self-verification, re-invoking the same vision language model (VLM) in a fresh context to check its own generated answer, is increasingly used as a default safety layer for medical visual question answering (VQA). We argue that this practice is fundamentally unreliable. We introduce [METHOD NAME], a diagnostic framework for mapping the reliability boundary of medical VLM self-verification by decomposing verifier behavior into discrimination capability and agreement bias. Because the verifier and answer generator are capacity-coupled, the verifier can overly agree with the generator, creating a verification mirage: a regime with both high verifier error and high agreement bias, driven by false acceptance of incorrect answers. Evaluating six open-weight VLMs across five medical VQA datasets and seven medical tasks, we find that this boundary is strongly task-conditioned. Knowledge-intensive clinical tasks fall deepest into the mirage, simpler tasks are more resistant, and perceptual tasks lie in between. Verification also fails to provide an independent safety signal: logistic mixed-effects analysis shows that verifier error and agreement bias become more likely when the generator is wrong, while saliency analyses show that verifiers under-attend to image evidence relative to generators, a phenomenon we call the lazy verifier. Cross-verification reduces but does not eliminate the mirage. Moreover, when verification is reused in multi-turn actor-verifier loops, most initially wrong answers become locked in by false verification. Since our experiments use clean benchmarks, the observed reliability boundary likely underestimates failures in real clinical deployment.

cs.CV↗

arXiv2026

Plug-and-Play Logit Fusion for Heterogeneous Pathology Foundation Models

Pathology foundation models (FMs) have become central to computational histopathology, offering strong transfer performance across a wide range of diagnostic and prognostic tasks. The rapid proliferation of pathology foundation models creates a model-selection bottleneck: no single model is uniformly best, yet exhaustively adapting and validating many candidates for each downstream endpoint is prohibitively expensive. We address this challenge with a lightweight and novel model fusion strategy, LogitProd, which treats independently trained FM-based predictors as fixed experts and learns sample-adaptive fusion weights over their slide-level outputs. The fusion operates purely on logits, requiring no encoder retraining and no feature-space alignment across heterogeneous backbones. We further provide a theoretical analysis showing that the optimal weighted product fusion is guaranteed to perform at least as well as the best individual expert under the training objective. We systematically evaluate LogitProd on \textbf{22} benchmarks spanning WSI-level classification, tile-level classification, gene mutation prediction, and discrete-time survival modeling. LogitProd ranks first on 20/22 tasks and improves the average performance across all tasks by ~3% over the strongest single expert. LogitProd enables practitioners to upgrade heterogeneous FM-based pipelines in a plug-and-play manner, achieving multi-expert gains with $\sim$12$\times$ lower training cost than feature-fusion alternatives.

cs.CV↗

arXiv2026

When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs

While Retrieval-Augmented Generation (RAG) is one of the dominant paradigms for enhancing Large Vision-Language Models (LVLMs) on knowledge-based VQA tasks, recent work attributes RAG failures to insufficient attention towards the retrieved context, proposing to reduce the attention allocated to image tokens. In this work, we identify a distinct failure mode that previous study overlooked: Attention Distraction (AD). When the retrieved context is sufficient (highly relevant or including the correct answer), the retrieved text suppresses the visual attention globally, and the attention on image tokens shifts away from question-relevant regions. This leads to failures on questions the model could originally answer correctly without the retrieved text. To mitigate this issue, we propose MAD-RAG, a training-free intervention that decouples visual grounding from context integration through a dual-question formulation, combined with attention mixing to preserve image-conditioned evidence. Extensive experiments on OK-VQA, E-VQA, and InfoSeek demonstrate that MAD-RAG consistently outperforms existing baselines across different model families, yielding absolute gains of up to 4.76%, 9.20%, and 6.18% over the vanilla RAG baseline. Notably, MAD-RAG rectifies up to 74.68% of failure cases with negligible computational overhead.

cs.CV↗

arXiv2025

PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysis

Multiple Instance Learning (MIL) has advanced WSI analysis but struggles with the complexity and heterogeneity of WSIs. Existing MIL methods face challenges in aggregating diverse patch information into robust WSI representations. While ViTs and clustering-based approaches show promise, they are computationally intensive and fail to capture task-specific and slide-specific variability. To address these limitations, we propose PTCMIL, a novel Prompt Token Clustering-based ViT for MIL aggregation. By introducing learnable prompt tokens into the ViT backbone, PTCMIL unifies clustering and prediction tasks in an end-to-end manner. It dynamically aligns clustering with downstream tasks, using projection-based clustering tailored to each WSI, reducing complexity while preserving patch heterogeneity. Through token merging and prototype-based pooling, PTCMIL efficiently captures task-relevant patterns. Extensive experiments on eight datasets demonstrate its superior performance in classification and survival analysis tasks, outperforming state-of-the-art methods. Systematic ablation studies confirm its robustness and strong interpretability. The code is released at https://github.com/ubc-tea/PTCMIL.

cs.CV↗

arXiv2024

Learnable Community-Aware Transformer for Brain Connectome Analysis with Token Clustering

Neuroscientific research has revealed that the complex brain network can be organized into distinct functional communities, each characterized by a cohesive group of regions of interest (ROIs) with strong interconnections. These communities play a crucial role in comprehending the functional organization of the brain and its implications for neurological conditions, including Autism Spectrum Disorder (ASD) and biological differences, such as in gender. Traditional models have been constrained by the necessity of predefined community clusters, limiting their flexibility and adaptability in deciphering the brain's functional organization. Furthermore, these models were restricted by a fixed number of communities, hindering their ability to accurately represent the brain's dynamic nature. In this study, we present a token clustering brain transformer-based model ($\texttt{TC-BrainTF}$) for joint community clustering and classification. Our approach proposes a novel token clustering (TC) module based on the transformer architecture, which utilizes learnable prompt tokens with orthogonal loss where each ROI embedding is projected onto the prompt embedding space, effectively clustering ROIs into communities and reducing the dimensions of the node representation via merging with communities. Our results demonstrate that our learnable community-aware model $\texttt{TC-BrainTF}$ offers improved accuracy in identifying ASD and classifying genders through rigorous testing on ABIDE and HCP datasets. Additionally, the qualitative analysis on $\texttt{TC-BrainTF}$ has demonstrated the effectiveness of the designed TC module and its relevance to neuroscience interpretations.

q-bio.NC↗

arXiv2024

LLM-Assisted Content Conditional Debiasing for Fair Text Embedding

Mitigating biases in machine learning models has become an increasing concern in Natural Language Processing (NLP), particularly in developing fair text embeddings, which are crucial yet challenging for real-world applications like search engines. In response, this paper proposes a novel method for learning fair text embeddings. First, we define a novel content-conditional equal distance (CCED) fairness for text embeddings, ensuring content-conditional independence between sensitive attributes and text embeddings. Building on CCED, we introduce a content-conditional debiasing (CCD) loss to ensure that embeddings of texts with different sensitive attributes but identical content maintain the same distance from the embedding of their corresponding neutral text. Additionally, we tackle the issue of insufficient training data by using Large Language Models (LLMs) with instructions to fairly augment texts into different sensitive groups. Our extensive evaluations show that our approach effectively enhances fairness while maintaining the utility of embeddings. Furthermore, our augmented dataset, combined with the CCED metric, serves as an new benchmark for evaluating fairness.

cs.CL↗

arXiv2023

LESS: Label-efficient Multi-scale Learning for Cytological Whole Slide Image Screening

In computational pathology, multiple instance learning (MIL) is widely used to circumvent the computational impasse in giga-pixel whole slide image (WSI) analysis. It usually consists of two stages: patch-level feature extraction and slide-level aggregation. Recently, pretrained models or self-supervised learning have been used to extract patch features, but they suffer from low effectiveness or inefficiency due to overlooking the task-specific supervision provided by slide labels. Here we propose a weakly-supervised Label-Efficient WSI Screening method, dubbed LESS, for cytological WSI analysis with only slide-level labels, which can be effectively applied to small datasets. First, we suggest using variational positive-unlabeled (VPU) learning to uncover hidden labels of both benign and malignant patches. We provide appropriate supervision by using slide-level labels to improve the learning of patch-level features. Next, we take into account the sparse and random arrangement of cells in cytological WSIs. To address this, we propose a strategy to crop patches at multiple scales and utilize a cross-attention vision transformer (CrossViT) to combine information from different scales for WSI classification. The combination of our two steps achieves task-alignment, improving effectiveness and efficiency. We validate the proposed label-efficient method on a urine cytology WSI dataset encompassing 130 samples (13,000 patches) and FNAC 2019 dataset with 212 samples (21,200 patches). The experiment shows that the proposed LESS reaches 84.79%, 85.43%, 91.79% and 78.30% on a urine cytology WSI dataset, and 96.88%, 96.86%, 98.95%, 97.06% on FNAC 2019 dataset in terms of accuracy, AUC, sensitivity and specificity. It outperforms state-of-the-art MIL methods on pathology WSIs and realizes automatic cytological WSI cancer screening.

eess.IV↗

arXiv2022

Optimal Propagation for Graph Neural Networks

Graph Neural Networks (GNNs) have achieved tremendous success in a variety of real-world applications by relying on the fixed graph data as input. However, the initial input graph might not be optimal in terms of specific downstream tasks, because of information scarcity, noise, adversarial attacks, or discrepancies between the distribution in graph topology, features, and groundtruth labels. In this paper, we propose a bi-level optimization approach for learning the optimal graph structure via directly learning the Personalized PageRank propagation matrix as well as the downstream semi-supervised node classification simultaneously. We also explore a low-rank approximation model for further reducing the time complexity. Empirical evaluations show the superior efficacy and robustness of the proposed model over all baseline methods.

cs.LG↗

arXiv2020

A Framework of Combining Short-Term Spatial/Frequency Feature Extraction and Long-Term IndRNN for Activity Recognition

Smartphone sensors based human activity recognition is attracting increasing interests nowadays with the popularization of smartphones. With the high sampling rates of smartphone sensors, it is a highly long-range temporal recognition problem, especially with the large intra-class distances such as the smartphones carried at different locations such as in the bag or on the body, and the small inter-class distances such as taking train or subway. To address this problem, we propose a new framework of combining short-term spatial/frequency feature extraction and a long-term Independently Recurrent Neural Network (IndRNN) for activity recognition. Considering the periodic characteristics of the sensor data, short-term temporal features are first extracted in the spatial and frequency domains. Then the IndRNN, which is able to capture long-term patterns, is used to further obtain the long-term features for classification. In view of the large differences when the smartphone is carried at different locations, a group based location recognition is first developed to pinpoint the location of the smartphone. The Sussex-Huawei Locomotion (SHL) dataset from the SHL Challenge is used for evaluation. An earlier version of the proposed method has won the second place award in the SHL Challenge 2020 (the first place if not considering multiple models fusion approach). The proposed method is further improved in this paper and achieves 80.72$\%$ accuracy, better than the existing methods using a single model.

cs.CV↗