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

Yuhan Liu

Yuhan Liu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningArtificial Intelligencecond-mat.str-elCryptography and Securityquant-phComputer Visioncond-mat.mes-hallData Structures and AlgorithmsInformation Theorymath.ITComputation and Languagecond-mat.mtrl-scicond-mat.otherDatabasesDistributed, Parallel, and Cluster Computingeess.SPHardware Architecturehep-thHuman-Computer Interactionmath-phmath.MPOperating SystemsPerformanceRoboticsSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
19works
0followers
25topics
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

19 published item(s)

preprint2026arXiv

AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving

Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which introduces significant redundant computation. Existing LLM serving systems address such redundant computation by storing the KV caches of processed context and loading the corresponding KV cache when a new request reuses the context. Further, as these LLM applications scale, the total size of KV caches becomes excessively large and requires both DRAM and SSD for full storage. However, prior work that stores KV caches in DRAM and SSD suffers from high loading delays, as most KV cache hits come from SSD, which is slow to load. To increase the KV cache hit rate on DRAM, we identify lossy KV cache compression as a promising approach. We design a lossy compression system that decides the compression algorithm, compression rate and device placement for each KV cache entry to maximise DRAM hits and minimise loading delay without significantly degrading generation quality. Compared to various static compression baselines across three tasks, our system AdaptCache achieves 1.43--2.4 x delay savings at the same quality and 6--55% quality improvements at the same delay.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Controllable Molecular Generative Foundation Models

Despite the success of foundation models in language and vision, molecular graph generation still lacks a unified framework for heterogeneous design tasks with reliable controllability. While reinforcement learning (RL) offers a natural post-training mechanism for task-specific optimization, applying it to graph generative models is hindered by the vast atom-wise action spaces and chemically invalid intermediate states. We propose \textbf{Co}ntrollable \textbf{Mole}cular Generative Foundation Models (CoMole), built with a unified motif-aware graph diffusion pipeline. By learning a motif-aware graph space, CoMole transfers pretrained structural priors into controllable generation, where RL optimizes conditional reverse policies over chemically meaningful decisions. We theoretically characterize the bottleneck of atom-level RL and justify motif-aware policy optimization. Across three heterogeneous benchmarks spanning materials and drug discovery, CoMole ranks first in controllability on all nine targets, reduces MAE by up to 48.2% relative to the strongest baselines, and maintains validity above 0.94 without rule-based correction or post-hoc filtering. We further show that CoMole transfers controllability to unseen properties by optimizing only task embeddings with the generator frozen, achieving performance competitive with strong task-specific baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

D$^3$R-DETR: DETR with Dual-Domain Density Refinement for Tiny Object Detection in Aerial Images

Detecting tiny objects plays a vital role in remote sensing intelligent interpretation, as these objects often carry critical information for downstream applications. However, due to the extremely limited pixel information and significant variations in object density, mainstream Transformer-based detectors often suffer from slow convergence and inaccurate query-object matching. To address these challenges, we propose D$^3$R-DETR, a novel DETR-based detector with Dual-Domain Density Refinement. By fusing spatial and frequency domain information, our method refines low-level feature maps and utilizes their rich details to predict more accurate object density map, thereby guiding the model to precisely localize tiny objects. Extensive experiments on the AI-TOD-v2 dataset demonstrate that D$^3$R-DETR outperforms existing state-of-the-art detectors for tiny object detection.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models

Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect privacy has become a pressing question. Membership inference attacks are the standard tool for this purpose, yet existing attacks assume a single-table setting and ignore the multi-relational structure of real sensitive data. A core challenge in assessing privacy risks from membership inference attacks in multi-table settings is how to leverage auxiliary information from relations associated with the target table, such as its parent tables. Particularly, we study a practical setting in which such auxiliary information is available only when training the attack model. At inference time, the attacker observes only the attribute values of the target record from the target table. We propose FERMI (FEature-mapping for Relational Membership Inference), which resolves this gap by enriching single-table features with relational membership signal. Across three tabular diffusion architectures and three real-world relational datasets, FERMI consistently improves attack performance over single-table baselines, with TPR@$0.1$FPR rising by up to 53% over the single-table baseline in the white-box setting and 22% in the black-box setting.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Governing Together: Toward Infrastructure for Community-Run Social Media

Decentralizing the governance of social computing systems to communities promises to empower them to make independent decisions, with nuance and in accordance with their values. Yet, communities do not govern in isolation. Many problems communities face are common, or move across their boundaries. We therefore propose designing for "inter-community governance:" mechanisms that support relationships and interactions between communities to coordinate on governance issues. Drawing from workshops with 24 individuals on decentralized, community-run social media, we present six challenges in designing for inter-community governance surfaced through ideas proposed in workshops. Together, these ideas come together as an ecosystem of resources, infrastructures, and tools that highlight three key principles for designing for inter-community governance: modularity, forkability, and polycentricity. We end with a discussion of how the ideas proposed in workshops might be implemented in future work aiming to support community governance in social computing systems broadly.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding

Although natural language is the default medium for Large Language Models (LLMs), its limited expressive capacity creates a profound bottleneck for complex problem-solving. While recent advancements in AI have relied heavily on scaling, merely internalizing knowledge does not guarantee its effective application. Defining language representation as the linguistic and symbolic constructs used to map and model the real world, this paper argues that shaping schemas through advanced language representation is the next frontier for expanding LLM intelligence. We posit that an LLM's knowledge activation and organization -- its schema -- depends heavily on the structural and symbolic sophistication of the language used to represent a given task. This paper contributes both a formalization of this claim and the empirical evidence to support it. With a new formalization, we present multiple lines of evidence to support our position: Firstly, we review recent empirical practices and emerging methodologies that demonstrate the substantial performance gains achievable through deliberate language representation design, even without modifying model parameters or scale. Secondly, we conduct controlled experiments showing that LLM performance and its internal feature activations vary under different language representations of the same underlying task. Together, these findings highlight language representation design as a promising direction for future research.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning

LLM/VLM-based digital agents have advanced rapidly thanks to scalable sandboxes for coding, web navigation, and computer use, which provide rich interactive training grounds. In contrast, embodied agents still lack abundant, diverse, and automatically generated 3D environments for interactive learning. Existing embodied simulators rely on manually crafted scenes or procedural templates, while recent LLM-based 3D generation systems mainly produce static scenes rather than deployable environments with verifiable tasks and standard learning interfaces. We introduce SimWorld Studio, an open-source platform built on Unreal Engine 5 for generating evolving embodied learning environments. At its core is SimCoder, a tool/skill-augmented coding agent that writes and executes engine-level code to construct physically grounded 3D worlds from language/image instructions. SimCoder self-evolves by using verifier feedback (e.g., compilation errors, physics checks, VLM critiques) to revise environments and autonomously add reusable tools and skills to its library. Generated worlds are exported as Gym-style environments for embodied agent learning. SimWorld Studio further enables co-evolution between environment generation and embodied learning: agent performance feedback guides SimCoder to generate adaptive curricula near the learner's capability frontier, so that environments become increasingly challenging as the embodied agent improves. Three case studies on embodied navigation show that self-evolution improves generation reliability, generated environments substantially improve embodied agent performance that generalizes to unseen benchmarks, and co-evolution yields an 18-point success-rate gain over fixed-environment learning and a 40-point gain over an untrained agent.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detection

Multimodal object detection leveraging RGB and Infrared (IR) images is pivotal for robust perception in all-weather scenarios. While recent adapter-based approaches efficiently transfer RGB-pretrained foundation models to this task, they often prioritize model efficiency at the expense of cross-modal structural consistency. Consequently, critical structural cues are frequently lost when significant domain gaps arise, such as in high-contrast or nighttime environments. Moreover, conventional static multimodal fusion mechanisms typically lack environmental awareness, resulting in suboptimal adaptation and constrained detection performance under complex, dynamic scene variations. To address these limitations, we propose SLGNet, a parameter-efficient framework that synergizes hierarchical structural priors and language-guided modulation within a frozen Vision Transformer (ViT)-based foundation model. Specifically, we design a Structure-Aware Adapter to extract hierarchical structural representations from both modalities and dynamically inject them into the ViT to compensate for structural degradation inherent in ViT-based backbones. Furthermore, we propose a Language-Guided Modulation module that exploits VLM-driven structured captions to dynamically recalibrate visual features, thereby endowing the model with robust environmental awareness. Extensive experiments on the LLVIP, FLIR, KAIST, and DroneVehicle datasets demonstrate that SLGNet establishes new state-of-the-art performance. Notably, on the LLVIP benchmark, our method achieves an mAP of 66.1, while reducing trainable parameters by approximately 87% compared to traditional full fine-tuning. This confirms SLGNet as a robust and efficient solution for multimodal perception.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

VeriCache: Turning Lossy KV Cache into Lossless LLM Inference

The large size of the KV cache has become a major bottleneck for serving LLMs with increasing context lengths. In response, many KV cache compression methods, such as token dropping and quantization, have been proposed. However, almost all of these methods are inherently lossy-despite minimal accuracy degradation for short outputs, their outputs increasingly diverge from full-KV-cache outputs as more tokens are decoded, which leads to catastrophic failures in code generation and tool calling. We present VeriCache, the first inference framework that ensures the same output as full-KV-cache decoding but largely preserves the high decoding throughput of a range of KV cache compression algorithms. VeriCache uses the compressed KV cache to draft tokens, then verifies them against the full KV cache. While it may seem like just speculative decoding, VeriCache requires addressing a key system challenge to work-keeping the full KV cache out of GPU memory and minimizing the overhead of swapping it in for verification. The insight is two-fold: (1) compressed-KV decoding can be parallelized with full-KV swap, because one is HBM-bandwidth-bound and the other is PCIe/network-bound, and (2) the compressed KV cache often produces output similar to the full KV cache, allowing a long drafting horizon to amortize each full-KV swap. VeriCache applies to both long-context decoding and remote prefix caching, supports a broad family of token-dropping and quantization methods through a uniform compressor interface, and composes with traditional speculative decoding. Experimental results show that VeriCache achieves up to 4X higher throughput than full-KV inference while producing identical outputs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Empathetic Response Generation with State Management

A good empathetic dialogue system should first track and understand a user's emotion and then reply with an appropriate emotion. However, current approaches to this task either focus on improving the understanding of users' emotion or on proposing better responding strategies, and very few works consider both at the same time. Our work attempts to fill this vacancy. Inspired by task-oriented dialogue systems, we propose a novel empathetic response generation model with emotion-aware dialogue management. The emotion-aware dialogue management contains two parts: (1) Emotion state tracking maintains the current emotion state of the user and (2) Empathetic dialogue policy selection predicts a target emotion and a user's intent based on the results of the emotion state tracking. The predicted information is then used to guide the generation of responses. Experimental results show that dynamically managing different information can help the model generate more empathetic responses compared with several baselines under both automatic and human evaluations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Human Behavior Recognition Method Based on CEEMD-ES Radar Selection

In recent years, the millimeter-wave radar to identify human behavior has been widely used in medical,security, and other fields. When multiple radars are performing detection tasks, the validity of the features contained in each radar is difficult to guarantee. In addition, processing multiple radar data also requires a lot of time and computational cost. The Complementary Ensemble Empirical Mode Decomposition-Energy Slice (CEEMD-ES) multistatic radar selection method is proposed to solve these problems. First, this method decomposes and reconstructs the radar signal according to the difference in the reflected echo frequency between the limbs and the trunk of the human body. Then, the radar is selected according to the difference between the ratio of echo energy of limbs and trunk and the theoretical value. The time domain, frequency domain and various entropy features of the selected radar are extracted. Finally, the Extreme Learning Machine (ELM) recognition model of the ReLu core is established. Experiments show that this method can effectively select the radar, and the recognition rate of three kinds of human actions is 98.53%.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning to Rearrange with Physics-Inspired Risk Awareness

Real-world applications require a robot operating in the physical world with awareness of potential risks besides accomplishing the task. A large part of risky behaviors arises from interacting with objects in ignorance of affordance. To prevent the agent from making unsafe decisions, we propose to train a robotic agent by reinforcement learning to execute tasks with an awareness of physical properties such as mass and friction in an indoor environment. We achieve this through a novel physics-inspired reward function that encourages the agent to learn a policy discerning different masses and friction coefficients. We introduce two novel and challenging indoor rearrangement tasks -- the variable friction pushing task and the variable mass pushing task -- that allow evaluation of the learned policies in trading off performance and physics-inspired risk. Our results demonstrate that by equipping with the proposed reward, the agent is able to learn policies choosing the pushing targets or goal-reaching trajectories with minimum physical cost, which can be further utilized as a precaution to constrain the agent's behavior in a safety-critic environment.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Accelerating Deep Learning Inference via Learned Caches

Deep Neural Networks (DNNs) are witnessing increased adoption in multiple domains owing to their high accuracy in solving real-world problems. However, this high accuracy has been achieved by building deeper networks, posing a fundamental challenge to the low latency inference desired by user-facing applications. Current low latency solutions trade-off on accuracy or fail to exploit the inherent temporal locality in prediction serving workloads. We observe that caching hidden layer outputs of the DNN can introduce a form of late-binding where inference requests only consume the amount of computation needed. This enables a mechanism for achieving low latencies, coupled with an ability to exploit temporal locality. However, traditional caching approaches incur high memory overheads and lookup latencies, leading us to design learned caches - caches that consist of simple ML models that are continuously updated. We present the design of GATI, an end-to-end prediction serving system that incorporates learned caches for low-latency DNN inference. Results show that GATI can reduce inference latency by up to 7.69X on realistic workloads.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Estimating Sparse Discrete Distributions Under Local Privacy and Communication Constraints

We consider the problem of estimating sparse discrete distributions under local differential privacy (LDP) and communication constraints. We characterize the sample complexity for sparse estimation under LDP constraints up to a constant factor and the sample complexity under communication constraints up to a logarithmic factor. Our upper bounds under LDP are based on the Hadamard Response, a private coin scheme that requires only one bit of communication per user. Under communication constraints, we propose public coin schemes based on random hashing functions. Our tight lower bounds are based on the recently proposed method of chi squared contractions.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Learning discrete distributions: user vs item-level privacy

Much of the literature on differential privacy focuses on item-level privacy, where loosely speaking, the goal is to provide privacy per item or training example. However, recently many practical applications such as federated learning require preserving privacy for all items of a single user, which is much harder to achieve. Therefore understanding the theoretical limit of user-level privacy becomes crucial. We study the fundamental problem of learning discrete distributions over $k$ symbols with user-level differential privacy. If each user has $m$ samples, we show that straightforward applications of Laplace or Gaussian mechanisms require the number of users to be $\mathcal{O}(k/(mα^2) + k/εα)$ to achieve an $\ell_1$ distance of $α$ between the true and estimated distributions, with the privacy-induced penalty $k/εα$ independent of the number of samples per user $m$. Moreover, we show that any mechanism that only operates on the final aggregate counts should require a user complexity of the same order. We then propose a mechanism such that the number of users scales as $\tilde{\mathcal{O}}(k/(mα^2) + k/\sqrt{m}εα)$ and hence the privacy penalty is $\tildeΘ(\sqrt{m})$ times smaller compared to the standard mechanisms in certain settings of interest. We further show that the proposed mechanism is nearly-optimal under certain regimes. We also propose general techniques for obtaining lower bounds on restricted differentially private estimators and a lower bound on the total variation between binomial distributions, both of which might be of independent interest.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Multipartitioning topological phases by vertex states and quantum entanglement

We discuss multipartitions of the gapped ground states of (2+1)-dimensional topological liquids into three (or more) spatial regions that are adjacent to each other and meet at points. By considering the reduced density matrix obtained by tracing over a subset of the regions, we compute various correlation measures, such as entanglement negativity, reflected entropy, and associated spectra. We utilize the bulk-boundary correspondence to show that such multipartitions can be achieved by using what we call vertex states in (1+1)-dimensional conformal field theory -- these are a type of state used to define an interaction vertex in string field theory and can be thought of as a proper generalization of conformal boundary states. This approach allows an explicit construction of the reduced density matrix near the entangling boundaries. We find the fingerprints of topological liquid in these quantities, such as (universal pieces in) the scaling of the entanglement negativity, and a non-trivial distribution of the spectrum of the partially transposed density matrix. For reflected entropy, we test the recent claim that states the difference between reflected entropy and mutual information is given, once short-range correlations are properly removed, by $(c/3)\ln 2$ where $c$ is the central charge of the topological liquid that measures ungappable edge degrees of freedom. As specific examples, we consider topological chiral $p$-wave superconductors and Chern insulators. We also study a specific lattice fermion model realizing Chern insulator phases and calculate the correlation measures numerically, both in its gapped phases and at critical points separating them.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Tidal surface states as fingerprints of non-Hermitian nodal knot metals

Non-Hermitian nodal knot metals (NKMs) contains intricate complex-valued energy bands gives rise to knotted exceptional loops and new topological surface states. We introduce a formalism that connects the algebraic, geometric, and topological aspects of these surface states with their parent knots, and provide an optimized constructive ansatz for tight-binding models for non-Hermitian NKMs of arbitrary knot complexity and minimal hybridization range. Specifically, various representative non-Hermitian torus knots Hamiltonians are constructed in real-space, and their nodal topologies studied via winding numbers that avoid the explicit construction of generalized Brillouin zones. In particular, we identify the surface state boundaries as "tidal" intersections of the complex band structure in a marine landscape analogy. Beyond topological quantities based on Berry phases, we further find these tidal surface states to be intimately connected to the band vorticity and the layer structure of their dual Seifert surface, and as such provide a fingerprint for non-Hermitian NKMs.

0 citations0 reviewsNo code linkedOpen access
preprint2018arXiv

Entanglement-guided architectures of machine learning by quantum tensor network

It is a fundamental, but still elusive question whether the schemes based on quantum mechanics, in particular on quantum entanglement, can be used for classical information processing and machine learning. Even partial answer to this question would bring important insights to both fields of machine learning and quantum mechanics. In this work, we implement simple numerical experiments, related to pattern/images classification, in which we represent the classifiers by many-qubit quantum states written in the matrix product states (MPS). Classical machine learning algorithm is applied to these quantum states to learn the classical data. We explicitly show how quantum entanglement (i.e., single-site and bipartite entanglement) can emerge in such represented images. Entanglement characterizes here the importance of data, and such information are practically used to guide the architecture of MPS, and improve the efficiency. The number of needed qubits can be reduced to less than 1/10 of the original number, which is within the access of the state-of-the-art quantum computers. We expect such numerical experiments could open new paths in charactering classical machine learning algorithms, and at the same time shed lights on the generic quantum simulations/computations of machine learning tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2018arXiv

Topological corner modes in a brick lattice with nonsymmorphic symmetry

The quest for new realizations of higher-order topological system has garnered much recent attention. In this work, we propose a paradigmatic brick lattice model where corner modes requires protection by nonsymmorphic symmetry in addition to two commuting mirror symmetries. Unlike the well-known square corner mode lattice, it has an odd number of occupied bands, which necessitates a different definition for the $\mathbb Z_2\times \mathbb Z_2$ topological invariant. By studying both the quadrupolar polarization and effective edge model, our study culminates in a phase diagram containing two distinct topological regimes. Our brick lattice corner modes can be realized in a RLC circuit setup and detected via collossal "topolectrical" resonances.

0 citations0 reviewsNo code linkedOpen access