BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Sen Hu

Sen Hu appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Artificial Intelligencemath-phmath.MPComputation and Languagehep-phmath.DGmath.GTmath.QAOperating Systemsphysics.gen-phastro-ph.EPCryptography and SecurityDistributed, Parallel, and Cluster Computinggr-qchep-thmath.CTnlin.SIphysics.geo-phSoftware Engineering

Catalog footprint

What is connected

22works
19topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

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

Published work

22 published item(s)

preprint2026arXiv

CloneMem: Benchmarking Long-Term Memory for AI Clones

AI Clones aim to simulate an individual's thoughts and behaviors to enable long-term, personalized interaction, placing stringent demands on memory systems to model experiences, emotions, and opinions over time. Existing memory benchmarks primarily rely on user-agent conversational histories, which are temporally fragmented and insufficient for capturing continuous life trajectories. We introduce CloneMem, a benchmark for evaluating longterm memory in AI Clone scenarios grounded in non-conversational digital traces, including diaries, social media posts, and emails, spanning one to three years. CloneMem adopts a hierarchical data construction framework to ensure longitudinal coherence and defines tasks that assess an agent's ability to track evolving personal states. Experiments show that current memory mechanisms struggle in this setting, highlighting open challenges for life-grounded personalized AI. Code and dataset are available at https://github.com/AvatarMemory/CloneMemBench

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences

While autonomous software engineering (SWE) agents are reshaping programming paradigms, they currently suffer from a "closed-world" limitation: they attempt to fix bugs from scratch or solely using local context, ignoring the immense historical human experience available on platforms like GitHub. Accessing this open-world experience is hindered by the unstructured and fragmented nature of real-world issue-tracking data. In this paper, we introduce MemGovern, a framework designed to govern and transform raw GitHub data into actionable experiential memory for agents. MemGovern employs experience governance to convert human experience into agent-friendly experience cards and introduces an agentic experience search strategy that enables logic-driven retrieval of human expertise. By producing 135K governed experience cards, MemGovern achieves a significant performance boost, improving resolution rates on the SWE-bench Verified by 4.65%. As a plug-in approach, MemGovern provides a solution for agent-friendly memory infrastructure.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction

As Large Language Models (LLMs) evolve from static dialogue interfaces to autonomous general agents, effective memory is paramount to ensuring long-term consistency. However, existing benchmarks primarily focus on casual conversation or task-oriented dialogue, failing to capture **"long-term project-oriented"** interactions where agents must track evolving goals. To bridge this gap, we introduce **RealMem**, the first benchmark grounded in realistic project scenarios. RealMem comprises over 2,000 cross-session dialogues across eleven scenarios, utilizing natural user queries for evaluation. We propose a synthesis pipeline that integrates Project Foundation Construction, Multi-Agent Dialogue Generation, and Memory and Schedule Management to simulate the dynamic evolution of memory. Experiments reveal that current memory systems face significant challenges in managing the long-term project states and dynamic context dependencies inherent in real-world projects. Our code and datasets are available at [https://github.com/AvatarMemory/RealMemBench](https://github.com/AvatarMemory/RealMemBench).

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents

As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, reusable, and executable skills from repositories and documents. Existing benchmarks primarily evaluate the efficacy of given skills or the ability of agents to solve downstream tasks from raw context, but they do not isolate skill generation itself as the object of study. We introduce SkillGenBench, a benchmark for evaluating skill generation pipelines under a unified and controlled protocol. In SkillGenBench, a generator receives raw corpora and produces standardized skill artifacts, which are then executed under fixed harnesses and assessed with unified evaluation procedures. The benchmark covers two generation regimes: task-conditioned generation, where a task-specific skill is synthesized after the task is revealed, and task-agnostic generation, where a reusable skill library must be distilled before downstream tasks are known. It also spans two complementary procedural sources: repository-grounded instances, where procedures are distributed across code, configuration, and scripts, and document-grounded instances, where procedures and constraints must be distilled from long-form text. We provide standardized task specifications, pinned environments, and evaluation protocols centered on deterministic execution-based checks, supplemented by auxiliary signals for diagnosis. Experiments across a range of skill-generation methods and backbones show substantial performance variation, highlight the difficulty of reusable skill distillation, and reveal distinct failure modes in skill generation from software repositories versus long-form documents. SkillGenBench establishes a reproducible testbed for studying skill generation as an independent research problem in agent systems.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

From Beginner to Expert: Modeling Medical Knowledge into General LLMs

Recently, large language model (LLM) based artificial intelligence (AI) systems have demonstrated remarkable capabilities in natural language understanding and generation. However, these models face a significant challenge when it comes to sensitive applications, such as reasoning over medical knowledge and answering medical questions in a physician-like manner. Prior studies attempted to overcome this challenge by increasing the model size (>100B) to learn more general medical knowledge, while there is still room for improvement in LLMs with smaller-scale model sizes (<100B). In this work, we start from a pre-trained general LLM model (AntGLM-10B) and fine-tune it from a medical beginner towards a medical expert (called AntGLM-Med-10B), which leverages a 3-stage optimization procedure, i.e., general medical knowledge injection, medical domain instruction tuning, and specific medical task adaptation. Our contributions are threefold: (1) We specifically investigate how to adapt a pre-trained general LLM in medical domain, especially for a specific medical task. (2) We collect and construct large-scale medical datasets for each stage of the optimization process. These datasets encompass various data types and tasks, such as question-answering, medical reasoning, multi-choice questions, and medical conversations. (3) Specifically for multi-choice questions in the medical domain, we propose a novel Verification-of-Choice approach for prompting engineering, which significantly enhances the reasoning ability of LLMs. Remarkably, by combining the above approaches, our AntGLM-Med-10B model can outperform the most of LLMs on PubMedQA, including both general and medical LLMs, even when these LLMs have larger model size.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Ancient and recent collisions revealed by phosphate minerals in the Chelyabinsk meteorite

The collision history of asteroids is an important archive of inner Solar System evolution. Evidence for these collisions is brought to Earth by meteorites, which can preserve impact-reset radioisotope mineral ages. However, as meteorites often preserve numerous mineral ages, their interpretation is controversial. Here, we combine analysis of phosphate U-Pb ages and mineral microtextures to construct a collision history for the highly shocked Chelyabinsk meteorite. We show that phosphate U-Pb ages in the meteorite are independent of thermal history at macro-to-microscales, correlating instead with phosphate microtexture. Isotopic data from pristine phosphate domains is largely concordant, whereas fracture-damaged domains universally display discordance. Combining both populations best constrains upper (4,473 +/- 11 Ma) and lower intercept (-9 +/- 55 Ma, i.e., within error of the present day) U-Pb ages for Chelyabinsk phosphates. We conclude that all phosphate U-Pb ages were completely reset during an ancient high energy collision. Fracture-damaged phosphate domains experienced further Pb-loss during mild collisional heating in the geologically recent past, and must be targeted to properly constrain a lower intercept age. Targeting textural sub-populations of phosphate grains can significantly improve the calculation and interpretation of U-Pb ages, permitting more robust reconstruction of both ancient and recent asteroidal collision histories.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Overview of the CCKS 2019 Knowledge Graph Evaluation Track: Entity, Relation, Event and QA

Knowledge graph models world knowledge as concepts, entities, and the relationships between them, which has been widely used in many real-world tasks. CCKS 2019 held an evaluation track with 6 tasks and attracted more than 1,600 teams. In this paper, we give an overview of the knowledge graph evaluation tract at CCKS 2019. By reviewing the task definition, successful methods, useful resources, good strategies and research challenges associated with each task in CCKS 2019, this paper can provide a helpful reference for developing knowledge graph applications and conducting future knowledge graph researches.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Symplectic group and Heisenberg group in p-adic quantum mechanics

This paper treats mathematically some problems in p-adic quantum mechanics. We first deal with p-adic symplectic group corresponding to the symmetry on the classical phase space. By the filtrations of isotropic subspaces and almost self-dual lattices in the p-adic symplectic vector space, we explicitly give the expressions of parabolic subgroups, maximal compact subgroups and corresponding Iwasawa decompositions of some symplectic groups. For a triple of Lagrangian subspaces, we associated it with a quadratic form whose Hasse invariant is calculated. Next we study the various equivalent realizations of unique irreducible and admissible representation of p-adic Heisenberg group. For the Schrodinger representation, we can define Weyl operator and its kernel function, while for the induced representations from the characters of maximal abelian subgroups of Heisenberg group generated by the isotropic subspaces or self-dual lattice in the p-adic symplectic vector space, we calculate the Maslov index defined via the intertwining operators corresponding to the representation transformation operators in quantum mechanics.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Two-Parameter Dynamics and Geometry

In this paper we present the two-parameter dynamics which is implied by the law of inertia in flat spacetime. A remarkable perception is that (A)dS4 geometry may emerge from the two-parameter dynamics, which exhibits some phenomenon of dynamics/ geometry correspondence. We also discuss the Unruh effects within the context of two-parameter dynamics. In the last section we construct various invariant actions with respect to the broken symmetry groups.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

HOMFLY polynomial from a generalized Yang-Yang function

Starting from the free field realization of Kac-Moody Lie algebra, we define a generalized Yang-Yang function. Then for the Lie algebra of type $A_{n}$, we derive braiding and fusion matrix by braiding the thimble from the generalized Yang-Yang function. One can construct a knots invariant $H(K)$ from the braiding and fusion matrix. It is an isotropy invariant and obeys a skein relation. From them, we show that the corresponding knots invariant is HOMFLY polynomial.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Schwarzschild-de Sitter Metric and Inertial Beltrami Coordinates

Under consideration of coordinate conditions, we get the Schwarzschild-Beltrami-de Sitter (S-BdS) metric solution of the Einstein field equations with a cosmological constant $Λ$. A brief review to the de Sitter invariant special relativity (dS-SR), and de Sitter general relativity (dS-GR, or GR with a $Λ$) is presented. The Beltrami metric $B_{μν}$ provides inertial reference frame for the dS-spacetime. By examining the Schwarzschild-de Sitter (S-dS) metric $g_{μν}^{(M)}$ existed in literatures since 1918, we find that the existed S-dS metric $g_{μν}^{(M)}$ describes some mixing effects of gravity and inertial-force, instead of a pure gravity effect arisen from "solar mass" $M$ in dS-GR. In this paper, we solve the vacuum Einstein equation of dS-GR, with the requirement of gravity-free metric $g_{μν}^{(M)}|_{M\rightarrow 0}=B_{μν}$. In this way we find S-BdS solution of dS-GR, written in inertial Beltrami coordinates. This is a new form of S-dS metric. Its physical meaning and possible applications are discussed.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Remark on "Pair Creation Constrains Superluminal Neutrino Propagation"

The concept of group velocity of a particle should be consistent with its Hamilton-Jacobi velocity. This point is missed in the work of Cohen, Glashow, "{\it Pair Creation Constrains Superluminal Neutrino Propagation}" (Phys. Rev. Lett. {\bf 107}, 181803 (2011)). It then leads to the conclusion of existence of Cherenkov-like radiation provided one sees superluminal neutrinos. We show that in the framework of Special Relativity with de Sitter space-time symmetry (dS-SR) the above Cohen-Glashow argument does not hold and the Cherenkov-like radiation is forbidden. Our result is consistent with the experimental results of the ICARUS Collaboration.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Superluminal Neutrinos from Special Relativity with de Sitter Space-time Symmetry

We explore the recent OPERA experiment of superluminal neutrinos in the framework of Special Relativity with de Sitter space-time symmetry (dS-SR). According to Einstein a photon is treated as a massless particle in the framework of Special Relativity. In Special Relativity (SR) we have the universal parameter $c$, the photon velocity $c_{photon}$ and the phase velocity of a light wave in vacuum $c_{wave}=λν$. Due to the null experiments of Michelson-Morley we have $c=c_{wave}$. The parameter $c_{photon}$ is determined by the Noether charges corresponding to the space-time symmetries of SR. In Einstein's Special Relativity (E-SR) we have $c=c_{photon}$. In dS-SR, i.e. the Special Relativity with SO(4,1) de Sitter space-time symmetry, we have $c_{photon}>c$. In this paper, the OPERA datum are examined in the framework of dS-SR. We show that OPREA anomaly is in agreement with the prediction of dS-SR with $R\simeq 1.95\times 10^{12}l.y.$ Based on the $p$-$E$ relation of dS-SR, we also prove that the Cohen and Glashow's argument of possible superluminal neutrino's Cherenkov-like radiation is forbidden. We conclude that OPERA and ICARUS results are consistent and they are explained in the dS-SR framework.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

Generalized Ricci flow I: Local existence and uniqueness

In this paper we investigate a kind of generalized Ricci flow which possesses a gradient form. We study the monotonicity of the given function under the generalized Ricci flow and prove that the related system of partial differential equations are strictly and uniformly parabolic. Based on this, we show that the generalized Ricci flow defined on a $n$-dimensional compact Riemannian manifold admits a unique short-time smooth solution. Moreover, we also derive the evolution equations for the curvatures, which play an important role in our future study.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

On determination of the geometric cosmological constant from the OPERA experiment of superluminal neutrinos

The recent OPERA experiment of superluminal neutrinos has deep consequences in cosmology. In cosmology a fundamental constant is the cosmological constant. From observations one can estimate the effective cosmological constant $Λ_{eff}$ which is the sum of the quantum zero point energy $Λ_{dark energy}$ and the geometric cosmological constant $Λ$. The OPERA experiment can be applied to determine the geometric cosmological constant $Λ$. It is the first time to distinguish the contributions of $Λ$ and $Λ_{dark energy}$ from each other by experiment. The determination is based on an explanation of the OPERA experiment in the framework of Special Relativity with de Sitter space-time symmetry.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

Determinating Timing Channels in Compute Clouds

Timing side-channels represent an insidious security challenge for cloud computing, because: (a) massive parallelism in the cloud makes timing channels pervasive and hard to control; (b) timing channels enable one customer to steal information from another without leaving a trail or raising alarms; (c) only the cloud provider can feasibly detect and report such attacks, but the provider's incentives are not to; and (d) resource partitioning schemes for timing channel control undermine statistical sharing efficiency, and, with it, the cloud computing business model. We propose a new approach to timing channel control, using provider-enforced deterministic execution instead of resource partitioning to eliminate timing channels within a shared cloud domain. Provider-enforced determinism prevents execution timing from affecting the results of a compute task, however large or parallel, ensuring that a task's outputs leak no timing information apart from explicit timing inputs and total compute duration. Experiments with a prototype OS for deterministic cloud computing suggest that such an approach may be practical and efficient. The OS supports deterministic versions of familiar APIs such as processes, threads, shared memory, and file systems, and runs coarse-grained parallel tasks as efficiently and scalably as current timing channel-ridden systems.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

Efficient System-Enforced Deterministic Parallelism

Deterministic execution offers many benefits for debugging, fault tolerance, and security. Running parallel programs deterministically is usually difficult and costly, however - especially if we desire system-enforced determinism, ensuring precise repeatability of arbitrarily buggy or malicious software. Determinator is a novel operating system that enforces determinism on both multithreaded and multi-process computations. Determinator's kernel provides only single-threaded, "shared-nothing" address spaces interacting via deterministic synchronization. An untrusted user-level runtime uses distributed computing techniques to emulate familiar abstractions such as Unix processes, file systems, and shared memory multithreading. The system runs parallel applications deterministically both on multicore PCs and across nodes in a cluster. Coarse-grained parallel benchmarks perform and scale comparably to - sometimes better than - conventional systems, though determinism is costly for fine-grained parallel applications.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

The "Ghost" Symmetry of the BKP hierarchy

In this paper, we systematically develop the "ghost" symmetry of the BKP hierarchy through its actions on the Lax operator $L$, the eigenfunctions and the $τ$ function. In this process, the spectral representation of the eigenfunctions and a new potential are introduced by using squared eigenfunction potential(SEP) of the BKP hierarchy. Moreover, the bilinear identity of the constrained BKP hierarchy and Adler-Shiota-van-Moerbeke formula of the BKP hierarchy are re-derived compactly by means of the spectral representation and "ghost" symmetry.

0 citations0 reviewsNo code linkedOpen access
preprint2004arXiv

Intersecting branes and adding flavors to the Maldacena-Nunez background

We study adding flavors into the Maldacena-Nŭnez background. It is achieved by introducing spacetime filling D9-branes or intersecting D5$'$-branes into the background with a wrapping D5-brane. Both D9-branes and D5$'$-branes can be spacetime filling from the 5D bulk point of view. At the probe limit it corresponds to introducing non-chiral fundamental flavors into the dual N=1 SYM. We propose a method to twist the fundamental flavor which has to involve open string charge. It reflects the fact that coupling fundamental matter to SYM in the dual string theory corresponds to adding an open string sector

0 citations0 reviewsNo code linkedOpen access