Searcharxiv⌕ Search

arXiv subjects

Ziyuan Qin

Publications and source records attributed to Ziyuan Qin.

At least 19 recordsLinked to original sources

TARGO and TARGO-Net: Benchmarking Target-driven Object Grasping under Occlusions

Predicting 6-DoF grasp poses from a single RGB-D frame has recently achieved impressive accuracy, yet performance can degrade significantly when the target object is heavily occluded by clutter. In this paper, we establish TARGO, the first benchmark dataset for TARget-driven Grasping under Occlusions, and introduce TARGO-Net, a grasp prediction model designed for visual occlusion. Our main contributions are fourfold: 1) We identify the visual occlusion challenge in single-view RGB-D 6-DoF grasping and show that current state-of-the-art models still suffer under severe occlusion. 2) We propose the TARGO dataset, which supports training and testing 6-DoF grasp models across different visual occlusion levels and enables robustness evaluation in real-world scenarios. 3) We devise TARGO-Net, a transformer-based grasping model with a target completion module and target-scene cross-attention, which achieves the most robust performance across all visual occlusion levels. 4) We show that target completion, number of occluders, and target minimum dimension also relate to grasp success in addition to visual occlusion.

cs.RO↗

Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation

We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete action-token pre-training, transfers these priors to continuous cross-embodiment control through flow-matching mid-training, and adapts the policy through real-world post-training. We introduce Rollback, which pairs replaced policy segments with human corrections to provide positive and negative supervision for CFG-DAgger without value learning or advantage labeling. A unified end-effector interface supports heterogeneous embodiments, while asynchronous action-chunk merging maintains smooth execution under variable inference latency. An event-driven agent maintains persistent task events and reassesses plans when progress or feasibility changes, enabling cross-task retrieval and conditional task resumption. MR0 achieves 93.6% success on RoboTwin 2.0 and ranks fifth in the RoboDojo VLA track. Under matched HG-DAgger post-training, MR0 achieves higher average success rate and progress score than $π_{0.5}$ across three real-robot tasks. On Ethernet insertion, CFG-DAgger trained with Rollback data reaches 70% success and a progress score of 0.90. Qualitative agent deployments demonstrate cross-task event retrieval and recovery from temporarily unsatisfied task conditions.

cs.RO↗

Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected?

Coding agents can now rewrite repository-scale codebases while preserving tested behavior, creating a new challenge for plagiarism detection, license auditing, and software provenance. We ask whether such rewrites can still be traced to their source. Existing clone benchmarks emphasize fragments and bounded edits, while repository-transformation benchmarks evaluate functional correctness rather than provenance. Moreover, ranking the most similar source does not establish derivation when independent implementations can be similarly close. We define repository-level agentic code laundering and introduce Launder-Bench, to our knowledge the first repository-level benchmark for provenance under agentic rewriting, constructed from 282 real-world repositories. A source-hidden reconstruction protocol decomposes source behavior, reconstructs modules and repository structure, and retains rewrites only after execution-based verification. We evaluate the same provenance problem in two complementary settings: Launder-Bench-Pair contains 1,128 pairwise instances asking whether two repositories share provenance, while Launder-Bench-Attr contains 229 source-attribution instances asking which candidate is the source, with abstention when evidence is insufficient. Measured same-domain independent repositories establish how much similarity can arise without shared provenance and provide detector-specific reference bands. Existing methods remain far from saturating Launder-Bench: the strongest static method reaches only 0.66 AUROC on pairwise detection, while repository encoders rank the true source first on up to 22% of attribution queries but earn calibrated attribution credit on only 1-2%. These results reveal a systematic gap between relative code similarity and source-specific provenance evidence, providing a reproducible target for provenance detection under agentic rewriting.

cs.SE↗

Accuracy is not compatibility: two Evo 2 checkpoints hinge on one FP8 matrix multiplication

FP8 formats specify how values are stored, not how products are summed; this gap can break checkpoints. Evo 2, a DNA language model, documents a Hopper FP8 requirement for its 1B and 40B checkpoints. On two Blackwell (sm_120) GPUs both fail the developers' forward test (the 7B passes); on an RTX 5070 Ti the 40B's next-base accuracy is 25.7%, near guessing. Greater accuracy breaks them, as BioNeMo saw for the 40B on Hopper: natively, 99.996% of one projection's outputs are correctly rounded (H100: about 30%), and fp32 accumulation of the same operands fails. Our H100 FP8 GEMM emulator, mmaemu (bit-exact on captured 1B projections), localises the dependence to the 1B's first projection (of 21), where exact sums fail but pass when shrunk by the H100's 1.4% (measured in-sample), not 2.1%. The 40B fails with only its first projection native. Emulating only that projection, weights unchanged, raises 40B BRCA1 variant-classification AUROC from 0.434 to 0.869 (H100: 0.868) on the RTX 5070 Ti, despite a narrow forward-test miss, and 0.481 to 0.867 on an RTX PRO 6000. We tested one model family but not training origin; releases should specify reference arithmetic.

cs.LG↗

From Bench-to-Bedside: A Review of Clinical Trials in Drug Discovery and Development

Clinical trials bridge basic research and clinical application, serving as essential steps in drug development. This review examines clinical trial phases (Phase I [safety assessment], Phase II [efficacy evaluation], Phase III [large-scale validation], and Phase IV [post-marketing surveillance]), highlighting the distinct characteristics and interconnections. Major challenges are identified, including ethical compliance, participant recruitment, and ensuring diversity and representativeness in trial populations, while proposing evidence-based mitigation strategies. To address these challenges, innovative technologies, such as artificial intelligence, big data analytics, and digital health tools, are transforming trial design and implementation, enhancing efficiency and data quality. Looking forward, the review explores how emerging therapies, including gene therapy and immunotherapy, are reshaping trial design requirements and emphasizes the growing importance of regulatory harmonization and global collaboration. Clinical trials remain central to advancing innovative drug development and improving patient outcomes.

cs.CY↗

From In Silico to In Vitro: A Comprehensive Guide to Validating Bioinformatics Findings

Translating computational predictions into experimentally validated biological knowledge remains one of the central challenges in modern bioinformatics. This review critically examines how in silico findings can be prioritized, tested, and interpreted through experimental validation. We organize the validation process around three recurring challenges: the specificity gap between genome-wide computational predictions and single-target experimental assays; the reproducibility-translatability tension, in which results validated in one model system may not generalize to another; and the scale-depth trade-off between high-throughput candidate discovery and the low-throughput nature of mechanistic validation. Rather than presenting an encyclopedic catalogue of techniques, we compare the strengths, limitations, and common failure modes of major validation approaches, including qPCR, RNA-seq, Western blotting, co-immunoprecipitation, luciferase reporter assays, CRISPR perturbation, and functional phenotypic assays. We also provide structured comparison tables for gene expression, protein-protein interaction, non-coding RNA, regulatory element, and pathway validation, together with decision-making frameworks to guide method selection according to prediction type, biological context, evidence stringency, throughput, and resource constraints. Case studies from cancer genomics, drug target discovery, miRNA regulation, and neurological disease illustrate how multi-step validation workflows can strengthen causal inference and reduce false-positive interpretation. Finally, we discuss how emerging technologies, including CRISPR screens, single-cell and spatial multi-omics, and AI-assisted experimental design, may reshape validation practice by improving scalability, context specificity, and reproducibility.

q-bio.GN↗

MedLoc-R1: Performance-Aware Curriculum Reward Scheduling for GRPO-Based Medical Visual Grounding

Medical visual grounding serves as a crucial foundation for fine-grained multimodal reasoning and interpretable clinical decision support. Despite recent advances in reinforcement learning (RL) for grounding tasks, existing approaches such as Group Relative Policy Optimization~(GRPO) suffer from severe reward sparsity when directly applied to medical images, primarily due to the inherent difficulty of localizing small or ambiguous regions of interest, which is further exacerbated by the rigid and suboptimal nature of fixed IoU-based reward schemes in RL. This leads to vanishing policy gradients and stagnated optimization, particularly during early training. To address this challenge, we propose MedLoc-R1, a performance-aware reward scheduling framework that progressively tightens the reward criterion in accordance with model readiness. MedLoc-R1 introduces a sliding-window performance tracker and a multi-condition update rule that automatically adjust the reward schedule from dense, easily obtainable signals to stricter, fine-grained localization requirements, while preserving the favorable properties of GRPO without introducing auxiliary networks or additional gradient paths. Experiments on three medical visual grounding benchmarks demonstrate that MedLoc-R1 consistently improves both localization accuracy and training stability over GRPO-based baselines. Our framework offers a general, lightweight, and effective solution for RL-based grounding in high-stakes medical applications. Code \& checkpoints are available at \hyperlink{}{https://github.com/MembrAI/MedLoc-R1}.

cs.CV↗

Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation

While recent advances in Reinforcement Fine-Tuning (RFT) have shown that rule-based reward schemes can enable effective post-training for large language models, their extension to cross-modal, vision-centric domains remains largely underexplored. This limitation is especially pronounced in the medical imaging domain, where effective performance requires both robust visual perception and structured reasoning. In this work, we address this gap by proposing VRFT-Aug, a visual reinforcement fine-tuning framework tailored for the medical domain. VRFT-Aug introduces a series of training strategies designed to augment both perception and reasoning, including prior knowledge injection, perception-driven policy refinement, medically informed reward shaping, and behavioral imitation. Together, these methods aim to stabilize and improve the RFT process. Through extensive experiments across multiple medical datasets, we show that our approaches consistently outperform both standard supervised fine-tuning and RFT baselines. Moreover, we provide empirically grounded insights and practical training heuristics that can be generalized to other medical image tasks. We hope this work contributes actionable guidance and fresh inspiration for the ongoing effort to develop reliable, reasoning-capable models for high-stakes medical applications.

cs.CV↗

Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges

This comprehensive review explores the intersection of Large Language Models (LLMs) and cognitive science, examining similarities and differences between LLMs and human cognitive processes. We analyze methods for evaluating LLMs cognitive abilities and discuss their potential as cognitive models. The review covers applications of LLMs in various cognitive fields, highlighting insights gained for cognitive science research. We assess cognitive biases and limitations of LLMs, along with proposed methods for improving their performance. The integration of LLMs with cognitive architectures is examined, revealing promising avenues for enhancing artificial intelligence (AI) capabilities. Key challenges and future research directions are identified, emphasizing the need for continued refinement of LLMs to better align with human cognition. This review provides a balanced perspective on the current state and future potential of LLMs in advancing our understanding of both artificial and human intelligence.

cs.AI↗

From Text to Multimodality: Exploring the Evolution and Impact of Large Language Models in Medical Practice

Large Language Models (LLMs) have rapidly evolved from text-based systems to multimodal platforms, significantly impacting various sectors including healthcare. This comprehensive review explores the progression of LLMs to Multimodal Large Language Models (MLLMs) and their growing influence in medical practice. We examine the current landscape of MLLMs in healthcare, analyzing their applications across clinical decision support, medical imaging, patient engagement, and research. The review highlights the unique capabilities of MLLMs in integrating diverse data types, such as text, images, and audio, to provide more comprehensive insights into patient health. We also address the challenges facing MLLM implementation, including data limitations, technical hurdles, and ethical considerations. By identifying key research gaps, this paper aims to guide future investigations in areas such as dataset development, modality alignment methods, and the establishment of ethical guidelines. As MLLMs continue to shape the future of healthcare, understanding their potential and limitations is crucial for their responsible and effective integration into medical practice.

cs.CY↗

Large Language Model Benchmarks in Medical Tasks

With the increasing application of large language models (LLMs) in the medical domain, evaluating these models' performance using benchmark datasets has become crucial. This paper presents a comprehensive survey of various benchmark datasets employed in medical LLM tasks. These datasets span multiple modalities including text, image, and multimodal benchmarks, focusing on different aspects of medical knowledge such as electronic health records (EHRs), doctor-patient dialogues, medical question-answering, and medical image captioning. The survey categorizes the datasets by modality, discussing their significance, data structure, and impact on the development of LLMs for clinical tasks such as diagnosis, report generation, and predictive decision support. Key benchmarks include MIMIC-III, MIMIC-IV, BioASQ, PubMedQA, and CheXpert, which have facilitated advancements in tasks like medical report generation, clinical summarization, and synthetic data generation. The paper summarizes the challenges and opportunities in leveraging these benchmarks for advancing multimodal medical intelligence, emphasizing the need for datasets with a greater degree of language diversity, structured omics data, and innovative approaches to synthesis. This work also provides a foundation for future research in the application of LLMs in medicine, contributing to the evolving field of medical artificial intelligence.

cs.CL↗

iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection

Existing prompt-based approaches have demonstrated impressive performance in continual learning, leveraging pre-trained large-scale models for classification tasks; however, the tight coupling between foreground-background information and the coupled attention between prompts and image-text tokens present significant challenges in incremental medical object detection tasks, due to the conceptual gap between medical and natural domains. To overcome these challenges, we introduce the \method~framework, which comprises two main components: 1) Instance-level Prompt Generation (\ipg), which decouples fine-grained instance-level knowledge from images and generates prompts that focus on dense predictions, and 2) Decoupled Prompt Attention (\dpa), which decouples the original prompt attention, enabling a more direct and efficient transfer of prompt information while reducing memory usage and mitigating catastrophic forgetting. We collect 13 clinical, cross-modal, multi-organ, and multi-category datasets, referred to as \dataset, and experiments demonstrate that \method~outperforms existing SOTA methods, with FAP improvements of 5.44\%, 4.83\%, 12.88\%, and 4.59\% in full data, 1-shot, 10-shot, and 50-shot settings, respectively.

cs.CV↗

Advanced Deep Learning Methods for Protein Structure Prediction and Design

After AlphaFold won the Nobel Prize, protein prediction with deep learning once again became a hot topic. We comprehensively explore advanced deep learning methods applied to protein structure prediction and design. It begins by examining recent innovations in prediction architectures, with detailed discussions on improvements such as diffusion based frameworks and novel pairwise attention modules. The text analyses key components including structure generation, evaluation metrics, multiple sequence alignment processing, and network architecture, thereby illustrating the current state of the art in computational protein modelling. Subsequent chapters focus on practical applications, presenting case studies that range from individual protein predictions to complex biomolecular interactions. Strategies for enhancing prediction accuracy and integrating deep learning techniques with experimental validation are thoroughly explored. The later sections review the industry landscape of protein design, highlighting the transformative role of artificial intelligence in biotechnology and discussing emerging market trends and future challenges. Supplementary appendices provide essential resources such as databases and open source tools, making this volume a valuable reference for researchers and students.

q-bio.BM↗

Guiding Medical Vision-Language Models with Explicit Visual Prompts: Framework Design and Comprehensive Exploration of Prompt Variations

While mainstream vision-language models (VLMs) have advanced rapidly in understanding image level information, they still lack the ability to focus on specific areas designated by humans. Rather, they typically rely on large volumes of high-quality image-text paired data to learn and generate posterior attention maps. To address this critical issue, we propose leveraging visual prompts:simple visual markers in various forms to guide and enhance the formation of region-specific attention. Thus, we introduce MedVP, a pioneering framework that integrates medical entity extraction, visual prompt generation, and dataset adaptation for visual prompt guided fine-tuning. We successfully outperform recent state-of-the-art large models across multiple medical VQA datasets. Extensive experiments and Human evaluation are conducted to analyze the impact of different visual prompt forms and how they contribute to performance improvement. The results demonstrate both the effectiveness and clinical significance of our approach.

cs.CV↗

Towards Explaining Uncertainty Estimates in Point Cloud Registration

Iterative Closest Point (ICP) is a commonly used algorithm to estimate transformation between two point clouds. The key idea of this work is to leverage recent advances in explainable AI for probabilistic ICP methods that provide uncertainty estimates. Concretely, we propose a method that can explain why a probabilistic ICP method produced a particular output. Our method is based on kernel SHAP (SHapley Additive exPlanations). With this, we assign an importance value to common sources of uncertainty in ICP such as sensor noise, occlusion, and ambiguous environments. The results of the experiment show that this explanation method can reasonably explain the uncertainty sources, providing a step towards robots that know when and why they failed in a human interpretable manner

cs.RO↗

Evaluating Hallucination in Text-to-Image Diffusion Models with Scene-Graph based Question-Answering Agent

Contemporary Text-to-Image (T2I) models frequently depend on qualitative human evaluations to assess the consistency between synthesized images and the text prompts. There is a demand for quantitative and automatic evaluation tools, given that human evaluation lacks reproducibility. We believe that an effective T2I evaluation metric should accomplish the following: detect instances where the generated images do not align with the textual prompts, a discrepancy we define as the `hallucination problem' in T2I tasks; record the types and frequency of hallucination issues, aiding users in understanding the causes of errors; and provide a comprehensive and intuitive scoring that close to human standard. To achieve these objectives, we propose a method based on large language models (LLMs) for conducting question-answering with an extracted scene-graph and created a dataset with human-rated scores for generated images. From the methodology perspective, we combine knowledge-enhanced question-answering tasks with image evaluation tasks, making the evaluation metrics more controllable and easier to interpret. For the contribution on the dataset side, we generated 12,000 synthesized images based on 1,000 composited prompts using three advanced T2I models. Subsequently, we conduct human scoring on all synthesized images and prompt pairs to validate the accuracy and effectiveness of our method as an evaluation metric. All generated images and the human-labeled scores will be made publicly available in the future to facilitate ongoing research on this crucial issue. Extensive experiments show that our method aligns more closely with human scoring patterns than other evaluation metrics.

cs.CV↗

EEG-DIF: Early Warning of Epileptic Seizures through Generative Diffusion Model-based Multi-channel EEG Signals Forecasting

Multi-channel EEG signals are commonly used for the diagnosis and assessment of diseases such as epilepsy. Currently, various EEG diagnostic algorithms based on deep learning have been developed. However, most research efforts focus solely on diagnosing and classifying current signal data but do not consider the prediction of future trends for early warning. Additionally, since multi-channel EEG can be essentially regarded as the spatio-temporal signal data received by detectors at different locations in the brain, how to construct spatio-temporal information representations of EEG signals to facilitate future trend prediction for multi-channel EEG becomes an important problem. This study proposes a multi-signal prediction algorithm based on generative diffusion models (EEG-DIF), which transforms the multi-signal forecasting task into an image completion task, allowing for comprehensive representation and learning of the spatio-temporal correlations and future developmental patterns of multi-channel EEG signals. Here, we employ a publicly available epilepsy EEG dataset to construct and validate the EEG-DIF. The results demonstrate that our method can accurately predict future trends for multi-channel EEG signals simultaneously. Furthermore, the early warning accuracy for epilepsy seizures based on the generated EEG data reaches 0.89. In general, EEG-DIF provides a novel approach for characterizing multi-channel EEG signals and an innovative early warning algorithm for epilepsy seizures, aiding in optimizing and enhancing the clinical diagnosis process. The code is available at https://github.com/JZK00/EEG-DIF.

eess.SP↗

TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation

This study presents a novel multimodal medical image zero-shot segmentation algorithm named the text-visual-prompt segment anything model (TV-SAM) without any manual annotations. The TV-SAM incorporates and integrates the large language model GPT-4, the vision language model GLIP, and the SAM to autonomously generate descriptive text prompts and visual bounding box prompts from medical images, thereby enhancing the SAM's capability for zero-shot segmentation. Comprehensive evaluations are implemented on seven public datasets encompassing eight imaging modalities to demonstrate that TV-SAM can effectively segment unseen targets across various modalities without additional training. TV-SAM significantly outperforms SAM AUTO and GSAM, closely matching the performance of SAM BBOX with gold standard bounding box prompts and surpasses the state-of-the-art methods on specific datasets such as ISIC and WBC. The study indicates that TV-SAM serves as an effective multimodal medical image zero-shot segmentation algorithm, highlighting the significant contribution of GPT-4 to zero-shot segmentation. By integrating foundational models such as GPT-4, GLIP, and SAM, the ability to address complex problems in specialized domains can be enhanced.

cs.CV↗