← Search

Zhuoran Zhang

30 accepted papers

2026

Beyond Fixed Biases: Decoding the Role of Reasoning Uncertainty in MLLM Modality Conflicts

ICML 2026poster

Multimodal Large Language Models (MLLMs) must resolve conflicts when modalities provide contradictory information, a process we term "modality following". We propose a framework that deconstructs this behavior into case-specific relative reasoning uncertainty and a model's stable inherent preference…

Cited by 0SourceScholar
2026

Fine-Grained Classification for Depth Estimation From Monocular Microscopy for Robotic Micromanipulation of Motile Cells

RA-L 2026

Manipulation of motile cells is crucial for biological research and clinical applications. However, obtaining Z-axis visual feedback under monocular microscopy remains a challenge for robotic micromanipulation. Traditional depth-from-focus and depth-from-defocus methods fail to handle motile cells d

Cited by 0SourceScholar
2026

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

CVPR 2026

The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this architectural unification actually enable synergetic interaction betwe

Cited by 0SourcecodeScholar
2026

Robotic Cell Manipulation at the Solid-Liquid Interface for Cryopreservation

ICRA 2026poster

Automating cell manipulation at a solid-liquid interface is a critical challenge for biomedical applications such as embryo cryopreservation. Unlike manipulation in a full liquid medium, the cell-substrate contact creates a significant static friction force that is not readily measurable with curren…

Cited by 0Scholar
2026

When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models

AAAI 2026technical

Large Language Models (LLMs) often exhibit sycophantic behavior, agreeing with user-stated opinions even when those contradict factual knowledge. While prior work has documented this tendency, the internal mechanisms that enable such behavior remain poorly understood. In this paper, we provide a mec

Cited by 0SourcePDFScholar
2025

COMPKE: Complex Question Answering under Knowledge Editing

ACL 2025finding

Knowledge Editing-Efficiently modifying the knowledge in large language models has gathered great attention. Current benchmarks primarily use multi-hop question answering to assess and analyze newly injected or updated knowledge. However, we argue that these benchmarks fail to effectively evaluate h…

Cited by 0SourcePDFScholar
2025

Continuous Convolution for Automated Measurement of Sperm Flagella

ICRA 2025

Quantifying sperm flagellar beating behavior (e.g., beating amplitude, frequency, and wavelength) plays a crucial role in biological research, clinical diagnostics, and the design of sperm-inspired microrobots. However, existing computational methods struggle to accurately and efficiently analyze th

Cited by 0SourcecodeScholar
2025

EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

NeurIPS 2025poster

Understanding the internal mechanisms of transformer-based language models remains challenging. Mechanistic interpretability based on circuit discovery aims to reverse engineer neural networks by analyzing their internal processes at the level of computational subgraphs. In this paper, we revisit ex…

Cited by 0SourceScholar
2025

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

ICML 2025poster

The locate-then-edit paradigm has shown significant promise for knowledge editing (KE) in Large Language Models (LLMs). While previous methods perform well on single-hop fact recall tasks, they consistently struggle with multi-hop factual recall tasks involving newly edited knowledge. In this paper,…

Cited by 4SourcePDFScholar
2025

MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios

NeurIPS 2025poster

Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is significantly diminished due to factors such as motion blur, temporal variations, and visual effects inherent in video conte…

Cited by 0SourceScholar
2025

VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs

EMNLP 2025

As demonstrated by the proprietary Large Language Models (LLMs) such as GPT and Claude series, LLMs have the potential to achieve remarkable proficiency across a wide range of domains, including law, medicine, finance, science, code, etc., all within a single model. These capabilities are further au

2024

Automated Non-invasive Analysis of Motile Sperms Using Cross-scale Guidance Network

ICRA 2024poster

Unbiased measurement of sperm morphometric and motility parameters is essential for assessing fertility potential and guiding visual feedback for microrobotic manipulation. Automated analysis of multiple sperms and selection of an optimal sperm is crucial for in vitro fertilisation treatment such as…

Cited by 0SourceScholar
2024

Automated Sperm Immobilization with a Clinically-Compatible and Compact XYZ Stage

ICRA 2024poster

Automated positioning systems play a pivotal role in micro-scale cell manipulation. In clinical intracytoplasmic sperm injection (ICSI) of in vitro fertilization (IVF) treatment, a motile sperm needs to be immobilized by glass micropipette tapping for subsequent surgical steps. The process requires…

Cited by 0SourceScholar
2024

Automated Sperm Morphology Analysis Based on Instance-Aware Part Segmentation

ICRA 2024poster

Traditional sperm morphology analysis is based on tedious manual annotation. Automated morphology analysis of a high number of sperm requires accurate segmentation of each sperm part and quantitative morphology evaluation. State-of-the-art instance-aware part segmentation networks follow a "detect-t…

Cited by 2SourceScholar
2022

Robotic Cell Manipulation for Blastocyst Biopsy

ICRA 2022poster

Soft tissue cutting is used for incision, separation and removal of tissues or cells. Due to high deformation of soft tissues resulting from their viscosity and elasticity, it is challenging to accurately cut the tissue along a desired path and control the force applied to the tissue for reducing in…

Cited by 6SourceScholar
2021

Automated End-Effector Alignment for Robotic Cell Manipulation

ICRA 2021poster

Cell manipulation is a key technology in many biomedical and clinical applications, in which end-effector alignment is a critical procedure. Presently, end-effector alignment is performed manually and suffers from large misalignment error and inconsistency. Manual alignment often undesirably moves t…

Cited by 3SourceScholar
2020

Design and Control of a Piezo Drill for Robotic Piezo-Driven Cell Penetration

RA-L 2020

Cell penetration is an indispensable step in many cell surgery tasks. Conventionally, cell penetration is achieved by passively indenting and eventually puncturing the cell membrane, during which undesired large cell deformation is induced. Piezo drills have been developed to penetrate cells with le

Cited by 28SourceScholar
2020

Model-Based Robotic Cell Aspiration: Tackling Nonlinear Dynamics and Varying Cell Sizes

RA-L 2020

Aspirating a single cell from the outside to the inside of a micropipette is widely used for cell transfer and manipulation. Due to the small volume of a single cell (picoliter) and nonlinear dynamics involved in the aspiration process, it is challenging to accurately and quickly position a cell to

Cited by 13SourceScholar
2020

Robotic Control of a Magnetic Swarm for On-Demand Intracellular Measurement

ICRA 2020poster

In biology, fluorescent dyes are routinely used for biochemical measurements such as pH and ion concentrations. They, especially when used for detecting a low concentration of ions, suffer from low signal-to-noise ratios (SNR); and increasing the concentration of fluorescent dyes causes more sever c…

Cited by 6SourceScholar
2019

Automated Laser Ablation of Motile Sperm for Immobilization

RA-L 2019

Automated manipulation of single cells is required in both biological and clinical applications. In clinical infertility treatments, a single motile sperm is immobilized and inserted into an egg cell for in vitro fertilization. Sperm immobilization is essential to ease the ensuing pick-up procedure,

Cited by 5SourceScholar
2019

Robotic Orientation Control of Deformable Cells

ICRA 2019poster

Robotic manipulation of deformable objects (vs. rigid objects) has been a classic topic in robotics. Compared to deformable synthetic objects such as rubber balls and clothes, biological cells are highly deformable and more prone to damage. This paper presents robotic manipulation of deformable cell…

Cited by 8SourceScholar
2018

Automated Non-Invasive Measurement of Sperm Motility and Morphology Parameters

ICRA 2018poster

Measuring the motility and morphology parameters of motile cells is important for revealing their functional characteristics. This paper presents automation techniques that, for the first time, enable automated, non-invasive measurement of motility and morphology parameters of individual sperms. Com…

Cited by 4SourceScholar
2018

Robotic Intracellular Manipulation: 3D Navigation and Measurement Inside a Single Cell

ICRA 2018poster

Magnetic micromanipulation is an untethered technique and has enabled numerous applications in the scale of millimeters to micrometers from the tissue level to cell level. However, existing systems are not capable of maneuvering a sub-micrometer object for precise force control, preventing the reali…

Cited by 8SourceScholar
2017

Robotic Pick-And-Place of Multiple Embryos for Vitrification

RA-L 2017

Embryo vitrification is an essential cryopreservation technique in IVF (in vitro fertilization) clinics. Vitrification involves pick-and-place of an embryo in multiple types of cryoprotectant solutions for processing before placing the embryo on a vitrification straw for cryopreservation in liquid n

Cited by 37SourceScholar
2017

Three-dimensional robotic control of a 5-micrometer magnetic bead for intra-embryonic navigation and measurement

ICRA 2017poster

Magnetic micromanipulation has the advantage of untethered control, high precision, and biocompatibility and has recently undergone great advances. The magnetic micromanipulation task to tackle in this work is to three-dimensionally navigate a 5-micrometer magnetic bead inside a mouse embryo and per…

Cited by 1SourceScholar
2016

An automated system for investigating sperm orientation in fluid flow

ICRA 2016

Mammalian sperms reorient against fluid flow in the female reproductive tract, known as rheotaxis. Compared to chemotaxis that provides short-distance guidance, rheotaxis provides long-distance guidance for a sperm to find the egg cell. However, only a low number of sperms are capable of rheotaxis a

Cited by 6SourceScholar