BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Yuyang Liu

Yuyang Liu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine LearningArtificial Intelligencecond-mat.mtrl-scieess.IVmath.NANumerical Analysisphysics.chem-phRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
8works
0followers
9topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

8 published item(s)

preprint2026arXiv

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment direction - defined by weight differences between aligned (safe) and unaligned models - rapidly compromise model safety. In contrast, updates along the alignment direction largely preserve it, revealing the parameter space as a "narrow safety basin". To address this, we propose AsFT (Anchoring Safety in Fine-Tuning) to maintain safety by explicitly constraining update directions during fine-tuning. By penalizing updates orthogonal to the alignment direction, AsFT effectively constrains the model within the "narrow safety basin," thus preserving its inherent safety. Extensive experiments on multiple datasets and models show that AsFT reduces harmful behaviors by up to 7.60%, improves task performance by 3.44%, and consistently outperforms existing methods across multiple tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

COLT: Enhancing Video Large Language Models with Continual Tool Usage

The success of Large Language Models (LLMs) has significantly propelled the research of video understanding. To harvest the benefits of well-trained expert models (i.e., tools), video LLMs prioritize the exploration of tool usage capabilities. Existing methods either prompt closed-source LLMs or employ the instruction tuning paradigm for tool-use fine-tuning. These methods, however, assume an established repository of fixed tools and struggle to generalize to real-world environments where tool data is perpetually evolving and streaming in. To this end, we propose to enhance open-source video LLMs with COntinuaL Tool usage (termed COLT), which automatically acquires tool-use ability in a successive tool stream without suffering 'catastrophic forgetting' of the past learned tools. Specifically, our COLT incorporates a learnable tool codebook as a tool-specific memory system. Then relevant tools are dynamically selected based on the similarity between user instruction and tool features within the codebook. To unleash the tool usage potential of video LLMs, we collect a video-centric tool-use instruction tuning dataset VideoToolBench. Extensive experiments on both previous video LLM benchmarks and the tool-use-specific VideoToolBench dataset demonstrate the state-of-the-art performance of our proposed COLT.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era

Vision-Language Models in Continual Learning (VLM-CL) aim to continuously adapt to new multimodal tasks while retaining prior knowledge. The emerging paradigm that couples Multimodal Large Language Models (MLLMs) with Reinforcement Learning with Verifiable Rewards (RLVR) calls for a new pattern to guide continual adaptation. Advances in reasoning capability now make it feasible to impose constraints at the reasoning level. We formalize portability, a sample-level measure of how reusable the previous policy's behavior is on a new task, and empirically show that reasoning-level signals remain reliable on out-of-distribution samples while answer-level signals do not. We instantiate this as Reasoning Portability (RP) and propose Reasoning-based Dynamic Balance Continual Learning (RDB-CL), which modulates the per-sample Kullback-Leibler regularization in RLVR according to RP: a tight anchor preserves reusable reasoning on high-RP samples, while a relaxed anchor on low-RP samples permits exploration of new reasoning pathways. Experiments show that RDB-CL consistently outperforms baselines, improving Last accuracy by +12.0% over the vanilla RLVR baseline.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SaddleScape V1.0: A Python Package for Constructing Solution Landscapes via High-index Saddle Dynamics

We present SaddleScape V1.0, a Python software package designed for the exploration and construction of solution landscapes in complex systems. The package implements the High-index Saddle Dynamics (HiSD) framework and its variants, including the Generalized HiSD for non-gradient systems and the Accelerated HiSD. SaddleScape V1.0 enables the systematic identification of critical points, including both local minima and high-index saddle points, by dynamically updating both the state estimate and an associated subspace characterizing the saddle's local manifold. It supports both gradient systems, defined by energy functions/functionals, and general non-gradient autonomous dynamical systems. Key features include automatic differentiation for symbolic inputs, numerical approximation techniques for Hessian-vector products, diverse eigenvalue solvers, and algorithms for constructing solution landscapes. The software offers a user-friendly interface with flexible parameter configuration, tools for trajectory and landscape visualization, and data export capabilities. By providing an efficient and accessible implementation of advanced saddle dynamics, SaddleScape V1.0 facilitates the construction of solution landscapes, empowering researchers in various scientific disciplines to gain deeper insights into the hierarchical structure of complex systems. The source code is available at the repository https://github.com/HiSDpackage/saddlescape. The package's introductory website is available at https://hisdpackage.github.io/saddlescape.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Generative Partial Visual-Tactile Fused Object Clustering

Visual-tactile fused sensing for object clustering has achieved significant progresses recently, since the involvement of tactile modality can effectively improve clustering performance. However, the missing data (i.e., partial data) issues always happen due to occlusion and noises during the data collecting process. This issue is not well solved by most existing partial multi-view clustering methods for the heterogeneous modality challenge. Naively employing these methods would inevitably induce a negative effect and further hurt the performance. To solve the mentioned challenges, we propose a Generative Partial Visual-Tactile Fused (i.e., GPVTF) framework for object clustering. More specifically, we first do partial visual and tactile features extraction from the partial visual and tactile data, respectively, and encode the extracted features in modality-specific feature subspaces. A conditional cross-modal clustering generative adversarial network is then developed to synthesize one modality conditioning on the other modality, which can compensate missing samples and align the visual and tactile modalities naturally by adversarial learning. To the end, two pseudo-label based KL-divergence losses are employed to update the corresponding modality-specific encoders. Extensive comparative experiments on three public visual-tactile datasets prove the effectiveness of our method.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation

Unsupervised domain adaptation without consuming annotation process for unlabeled target data attracts appealing interests in semantic segmentation. However, 1) existing methods neglect that not all semantic representations across domains are transferable, which cripples domain-wise transfer with untransferable knowledge; 2) they fail to narrow category-wise distribution shift due to category-agnostic feature alignment. To address above challenges, we develop a new Critical Semantic-Consistent Learning (CSCL) model, which mitigates the discrepancy of both domain-wise and category-wise distributions. Specifically, a critical transfer based adversarial framework is designed to highlight transferable domain-wise knowledge while neglecting untransferable knowledge. Transferability-critic guides transferability-quantizer to maximize positive transfer gain under reinforcement learning manner, although negative transfer of untransferable knowledge occurs. Meanwhile, with the help of confidence-guided pseudo labels generator of target samples, a symmetric soft divergence loss is presented to explore inter-class relationships and facilitate category-wise distribution alignment. Experiments on several datasets demonstrate the superiority of our model.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

L3DOC: Lifelong 3D Object Classification

3D object classification has been widely-applied into both academic and industrial scenarios. However, most state-of-the-art algorithms are facing with a fixed 3D object classification task set, which cannot well tackle the new coming data with incremental tasks as human ourselves. Meanwhile, the performance of most state-of-the-art lifelong learning models can be deteriorated easily on previously learned classification tasks, due to the existing of unordered, large-scale, and irregular 3D geometry data. To address this challenge, in this paper, we propose a Lifelong 3D Object Classification (i.e., L3DOC) framewor, which can consecutively learn new 3D object classification tasks via imitating 'human learning'. Specifically, the core idea of our proposed L3DOC model is to factorize PointNet in a perspective of lifelong learning, while capturing and storing the shared point-knowledge in a perspective of layer-wise tensor factorization architecture. To further transfer the task-specific knowledge from previous tasks to the new coming classification task, a memory attention mechanism is proposed to connect the current task with relevant previously tasks, which can effectively prevent catastrophic forgetting via soft-transferring previous knowledge. To our best knowledge, this is the first work about using lifelong learning to handle 3D object classification task without model fine-tuning or retraining. Furthermore, our L3DOC model can also be extended to other backbone network (e.g., PointNet++). To the end, comparisons on several point cloud datasets validate that our L3DOC model can reduce averaged 1.68~3.36 times parameters for the overall model, without sacrificing classification accuracy of each task.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Enhancing the understanding of hydrogen evolution and oxidation reaction on Pt(111) through ab initio simulations on electrode/electrolyte kinetics

The hydrogen oxidation reaction (HOR) and hydrogen evolution reaction (HER) play an important role in hydrogen based energy conversion. Recently, the frustrating performance in alkaline media raised debates on the relevant mechanism, especially on the role of surface hydroxyl (OH*). We present a full pH range electrode/electrolyte kinetics simulation for HER/HOR on Pt(111), with the potential-related rate constants been calculated with density functional theory methods. The polarization curves agree well with the experimental observations. The stability of OH* is found to be unlikely an effective activity descriptor since it is irrelevant to the onset potential of HOR/HER. Degree of rate control analyses reveal that the alkaline current is controlled jointly by Tafel and Volmer steps, while the acidic current solely by Tafel step, which explains the observed pH-dependent kinetics. Therefore, it is also possible to reduce the overpotential of alkaline HER/HOR by accelerating the Tafel step besides tuning the hydrogen binding energy.

0 citations0 reviewsNo code linkedOpen access