Searcharxiv⌕ Search

arXiv subjects

Jiaxin Yin

Publications and source records attributed to Jiaxin Yin.

At least 19 recordsLinked to original sources
arXiv2026

Bridging the Gap Between Semantics and Reconstruction:Unifying Sign Language Translation and Production

Recent advances in sign language (SL) research have shown a trend toward unifying multiple sign language understanding (SLU) subtasks, such as isolated sign language recognition (ISLR), continuous sign language recognition (CSLR), and sign language translation (SLT), within a single framework, leading to substantial progress. Meanwhile, sign language production (SLP), which generates sign sequences from text, has also attracted growing attention. This naturally raises an important question: can sign language understanding and production be unified within a single framework? Compared with unifying SLU subtasks, this problem is substantially more challenging. Existing SLU tasks largely share the same direction of mapping, namely from sign inputs to linguistic outputs, whereas SLT and SLP lie in opposite directions of sign-text mapping. A unified framework must therefore address two key challenges: (1) bridging the modality gap between continuous sign motions and discrete text tokens through a shared sign tokenizer that supports both linguistic abstraction and motion reconstruction; and (2) learning a single conditional autoregressive model that can take either sign or text as input and generate the corresponding target sequence in the opposite modality. To this end, we propose Uni-SLTP, a unified framework for SLT and SLP with two key components: (1) a shared sign tokenizer that converts sign sequences into discrete tokens and latent representations, capturing both semantic and reconstructive information; and (2) a unified autoregressive generation model that formulates both tasks as conditional sequence generation. Experiments on widely used public datasets show that Uni-SLTP achieves superior motion accuracy for SLP while maintaining competitive SLT performance.

cs.CL↗
arXiv2026

Retrospective Progress-Aware Self-Refinement for LLM Agent Training

LLM-based agents trained with reinforcement learning optimize step-wise action prediction but lack metacognitive awareness of task progress, inducing a gap that hinders long-horizon scaling. A pilot study reveals that online progress prompting hurts performance while retrospective demonstrations help, yet this capability cannot emerge from outcome-reward training alone. We present RePro, Retrospective Progress-Aware Training, a framework that trains agents to self-generate progress signals via a forward-then-reflect rollout paradigm: the agent executes actions online, then retrospectively reassesses its step-wise progress given the completed trajectory and known outcome. RePro initializes with a Retrospection Warmup that teaches reflection format from minimal external demonstrations, then further trains through RePro-PO with a composite reward that produces self-generated signals without continuous external supervision. Experiments on WebShop, ALFWorld, and Sokoban show that RePro enhances the Qwen family's performance, with up to $12\%$ absolute success rate gains.

cs.CL↗
arXiv2026

Communication Policy Evolution for Proactive LLM Agents

LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas, and model combinations. Building information asymmetry for proactive agents, we set up two complementary settings, User-Agent and Planner-Executor. Experimental results reveal complementary strengths between interaction channels: text-based interaction often facilitates task performance, while structured UI improves agents' response quality and persona compliance. Motivated by that, a hybrid method combines these advantages. We further propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving. Without model modification, CPE achieves the best task success across multiple settings using prompt refinement alone. Our findings identify communication behavior as a critical yet underexplored design dimension for LLM agents.

cs.AI↗
arXiv2026

TopoClaw: A Human-Centric and Topology-Aware Agent Operating System

Large language models (LLMs) have evolved AI assistants into autonomous reasoning engines that maintain context, invoke tools, and pursue long-horizon tasks. This has spurred Agent Operating Systems (Agent OS) as kernel-like layers for lifecycle management, memory, scheduling, and access control. Yet most designs remain agent-centric, treating the OS as a single-host runtime for internal reasoning and tool use, leaving open how autonomous actions integrate with distributed, collaborative, permission-sensitive workflows. TopoClaw is an open-source, human-centric, topology-aware Agent OS modeling the user's ecosystem as two coupled structures: a physical device topology of heterogeneous surfaces and a social relationship topology of shared spaces, teams, and delegated roles. It unifies device operation, messaging, and skills around accountable cross-boundary execution, with three core contributions: (1) cross-device action placement, decoupling intent from actuation and routing distributed actions across the device cluster based on hardware affordances and user context; (2) cross-user identity attribution, treating agents as socially situated "Digital Twins" that coordinate in multi-user spaces while preserving provenance, role-aware permissions, and human accountability; (3) cross-context authority governance, pairing broad capability with distributed, context-aware policy enforcement across physical and social trust boundaries to bound proactive autonomy at the OS layer. This report presents TopoClaw as an engineering-oriented reference architecture, covering its design principles, runtime, cross-device execution, collaboration mechanisms, security model, and deployment outlook.

cs.HC↗
arXiv2025

Ultrafast μeV-Precision Bandgap Engineering in Low-Dimensional Topological Insulators

Precise and ultrafast control of electronic band structures is a central challenge for advancing quantum functional materials and devices. Conventional approaches--such as chemical doping, lattice strain, or external gating--offer robust stability but remain confined to the quasi-static regime, far from the intrinsic femto- to picosecond dynamics that govern many-body interactions. Here, using cryogenic transient reflectance spectroscopy, we realize dynamic bandgap engineering in the anisotropic topological insulator $α$-Bi$_4$Br$_4$ with unprecedented micro-electron-volt ($μ$eV) precision. The exceptional sensitivity arises from the cooperative action of long-lived topological carriers, stabilized by restricted bulk-to-edge scattering phase space, together with symmetry-resolved coherent phonons that modulate inter-chain hopping. These channels jointly modify Coulomb screening and interband transitions, enabling both gradual and oscillatory control of the electronic structure. Supported by first-principles and tight-binding theory, we further demonstrate a dual-pump coherent control strategy for continuous, mode-selective tuning of electronic energies with $μ$eV accuracy. This framework paves the way for ultrafast on-demand band-structure engineering, pointing toward new frontiers in quantum optoelectronics, precision measurement in molecular and biological systems, and attosecond control of matter.

cond-mat.mes-hall↗
arXiv2025

ColorAgent: Building A Robust, Personalized, and Interactive OS Agent

With the advancements in hardware, software, and large language model technologies, the interaction between humans and operating systems has evolved from the command-line interface to the rapidly emerging AI agent interactions. Building an operating system (OS) agent capable of executing user instructions and faithfully following user desires is becoming a reality. In this technical report, we present ColorAgent, an OS agent designed to engage in long-horizon, robust interactions with the environment while also enabling personalized and proactive user interaction. To enable long-horizon interactions with the environment, we enhance the model's capabilities through step-wise reinforcement learning and self-evolving training, while also developing a tailored multi-agent framework that ensures generality, consistency, and robustness. In terms of user interaction, we explore personalized user intent recognition and proactive engagement, positioning the OS agent not merely as an automation tool but as a warm, collaborative partner. We evaluate ColorAgent on the AndroidWorld and AndroidLab benchmarks, achieving success rates of 77.2% and 50.7%, respectively, establishing a new state of the art. Nonetheless, we note that current benchmarks are insufficient for a comprehensive evaluation of OS agents and propose further exploring directions in future work, particularly in the areas of evaluation paradigms, agent collaboration, and security.

cs.MA↗
arXiv2024

Non-Hermitian Boundary in a Surface Selective Reconstructed Magnetic Weyl Semimetal

Non-Hermitian physics, studying systems described by non-Hermitian Hamiltonians, reveals unique phenomena not present in Hermitian systems. Unlike Hermitian systems, non-Hermitian systems have complex eigenvalues, making their effects less directly observable. Recently, significant efforts have been devoted to incorporating the non-Hermitian effects into condensed matter physics. However, progress has been hindered by the absence of a viable experimental approach. Here, the discovery of surface-selectively spontaneous reconstructed Weyl semimetal NdAlSi provides a feasible experimental platform for studying non-Hermitian physics. Utilizing angle-resolved photoemission spectroscopy measurements, surface-projected density functional theory calculations, and scanning tunneling microscopy measurements, we demonstrate that surface reconstruction in NdAlSi alters surface Fermi arc connectivity and generates new isolated non-topological surface Fermi arcs. In the presence of a magnetic field, the surface-selective spontaneous reconstructed Weyl semimetal NdAlSi can be viewed as a Hermitian bulk--non-Hermitian boundary system. The isolated non-topological surface Fermi arcs on the reconstructed surface act as a loss mechanism and open boundary condition for the topological electrons and bulk states, serving as non-Hermitian boundary states. This discovery provides a good experimental platform for exploring new physical phenomena and potential applications based on boundary non-Hermitian effects, extending beyond purely mathematical concepts.

cond-mat.mtrl-sci↗
arXiv2024

Disorder Driven Non-Anderson Transition in a Weyl Semimetal

For several decades, it was widely believed that a non-interacting disordered electronic system could only undergo an Anderson metal-insulator transition due to Anderson localization. However, numerous recent theoretical works have predicted the existence of a disorder-driven non-Anderson phase transition that differ from Anderson localization. The frustration lies in the fact that this non-Anderson disorder-driven transition has not yet been experimentally demonstrated in any system. Here, using angle-resolved photoemission spectroscopy, we present a case study of observing the non-Anderson disorder-driven transition by visualizing the electronic structure of the Weyl semimetal NdAlSi on surfaces with varying amounts of disorder. Our observations reveal that strong disorder can effectively suppress all surface states in the Weyl semimetal NdAlSi, including the topological surface Fermi arcs. This disappearance of surface Fermi arcs is associated with the vanishing of the bulk topological invariant, indicating a quantum phase transition from a Weyl semimetal to a diffusive metal. By analyzing the changes in the electronic structure of NdAlSi, as the surface degrades, we provide a physical picture of this non-Anderson transition from a Weyl semimetal to a diffuse metal. These observations provide the first direct experimental evidence of the non-Anderson disorder-driven transition, a discovery long anticipated by theoretical physicists. The finding dispels longstanding suspicions among researchers that non-Anderson transitions exist in real quantum systems.

cond-mat.mtrl-sci↗
arXiv2023

Phonon promoted charge density wave in topological kagome metal ScV$_{6}$Sn$_{6}$

Charge density wave (CDW) orders in vanadium-based kagome metals have recently received tremendous attention due to their unique properties and intricate interplay with exotic correlated phenomena, topological and symmetry-breaking states. However, the origin of the CDW order remains a topic of debate. The discovery of ScV$_{6}$Sn$_{6}$, a vanadium-based bilayer kagome metal exhibiting an in-plane $\sqrt{3}$ x $\sqrt{3} $ $\textit{R}$30$°$ CDW order with time-reversal symmetry breaking, provides a novel platform to explore the underlying mechanism behind the unconventional CDW. Here, we combine high-resolution angle-resolved photoemission spectroscopy, Raman scattering measurements and density functional theory to investigate the electronic structures and phonon modes of ScV$_{6}$Sn$_{6}$ and their evolution with temperature. We identify topologically nontrivial Dirac surface states and multiple van Hove singularities (VHSs) in the vicinity of the Fermi level, with one VHS near the K point exhibiting nesting wave vectors in proximity to the $\sqrt{3}$ x $\sqrt{3}$ $\textit{R}$30$°$ CDW wave vector. Additionally, Raman measurements indicate a strong intrinsic electron-phonon coupling in ScV$_{6}$Sn$_{6}$, as evidenced by the presence of a two-phonon mode and a large frequency amplitude mode. Our findings highlight the fundamental role of lattice degrees of freedom in promoting the CDW in ScV$_{6}$Sn$_{6}$ and provide important insights into the fascinating correlation phenomena observed in kagome metals.

cond-mat.str-el↗
arXiv2023

Survey of Deep Learning for Autonomous Surface Vehicles in the Marine Environment

Within the next several years, there will be a high level of autonomous technology that will be available for widespread use, which will reduce labor costs, increase safety, save energy, enable difficult unmanned tasks in harsh environments, and eliminate human error. Compared to software development for other autonomous vehicles, maritime software development, especially on aging but still functional fleets, is described as being in a very early and emerging phase. This introduces very large challenges and opportunities for researchers and engineers to develop maritime autonomous systems. Recent progress in sensor and communication technology has introduced the use of autonomous surface vehicles (ASVs) in applications such as coastline surveillance, oceanographic observation, multi-vehicle cooperation, and search and rescue missions. Advanced artificial intelligence technology, especially deep learning (DL) methods that conduct nonlinear mapping with self-learning representations, has brought the concept of full autonomy one step closer to reality. This paper surveys the existing work regarding the implementation of DL methods in ASV-related fields. First, the scope of this work is described after reviewing surveys on ASV developments and technologies, which draws attention to the research gap between DL and maritime operations. Then, DL-based navigation, guidance, control (NGC) systems and cooperative operations, are presented. Finally, this survey is completed by highlighting the current challenges and future research directions.

cs.RO↗
arXiv2022

Signatures of a topological Weyl loop in Co$_3$Sn$_2$S$_2$

The search for novel topological phases of matter in quantum magnets has emerged as a frontier of condensed matter physics. Here we use state-of-the-art angle-resolved photoemission spectroscopy (ARPES) to investigate single crystals of Co$_3$Sn$_2$S$_2$ in its ferromagnetic phase. We report for the first time signatures of a topological Weyl loop. From fundamental symmetry considerations, this magnetic Weyl loop is expected to be gapless if spin-orbit coupling (SOC) is strictly zero but gapped, with possible Weyl points, under finite SOC. We point out that high-resolution ARPES results to date cannot unambiguously resolve the SOC gap anywhere along the Weyl loop, leaving open the possibility that Co$_3$Sn$_2$S$_2$ hosts zero Weyl points or some non-zero number of Weyl points. On the surface of our samples, we further observe a possible Fermi arc, but we are unable to clearly verify its topological nature using the established counting criteria. As a result, we argue that from the point of view of photoemission spectroscopy the presence of Weyl points and Fermi arcs in Co$_3$Sn$_2$S$_2$ remains ambiguous. Our results have implications for ongoing investigations of Co$_3$Sn$_2$S$_2$ and other topological magnets.

cond-mat.str-el↗
arXiv2020

Orbital-selective Dirac fermions and extremely flat bands in frustrated kagome-lattice metal CoSn

Layered kagome-lattice 3d transition metals are emerging as an exciting platform to explore the frustrated lattice geometry and quantum topology. However, the typical kagome electronic bands, characterized by sets of the Dirac-like band capped by a phase-destructive flat band, have not been clearly observed, and their orbital physics are even less well investigated. Here, we present close-to-textbook kagome bands with orbital differentiation physics in CoSn, which can be well described by a minimal tight-binding model with single-orbital hopping in Co kagome lattice. The capping flat bands with bandwidth less than 0.2 eV run through the whole Brillouin zone, especially the bandwidth of the flat band of out-of-plane orbitals is less than 0.02 eV along G-M. The energy gap induced by spin-orbit interaction at the Dirac cone of out-of-plane orbitals is much smaller than that of in-plane orbitals, suggesting orbital-selective character of the Dirac fermions.

cond-mat.mtrl-sci↗
arXiv2020

Discovery of topological Weyl fermion lines and drumhead surface states in a room temperature magnet

Topological matter is known to exhibit unconventional surface states and anomalous transport owing to unusual bulk electronic topology. In this study, we use photoemission spectroscopy and quantum transport to elucidate the topology of the room temperature magnet Co$_2$MnGa. We observe sharp bulk Weyl fermion line dispersions indicative of nontrivial topological invariants present in the magnetic phase. On the surface of the magnet, we observe electronic wave functions that take the form of drumheads, enabling us to directly visualize the crucial components of the bulk-boundary topological correspondence. By considering the Berry curvature field associated with the observed topological Weyl fermion lines, we quantitatively account for the giant anomalous Hall response observed in our samples. Our experimental results suggest a rich interplay of strongly correlated electrons and topology in this quantum magnet.

cond-mat.mtrl-sci↗
arXiv2019

Magnetic-field control of topological electronic response near room temperature in correlated Kagome magnets

Strongly correlated Kagome magnets are promising candidates for achieving controllable topological devices owing to the rich interplay between inherent Dirac fermions and correlation-driven magnetism. Here we report tunable local magnetism and its intriguing control of topological electronic response near room temperature in the Kagome magnet Fe3Sn2 using small angle neutron scattering, muon spin rotation, and magnetoresistivity measurement techniques. The average bulk spin direction and magnetic domain texture can be tuned effectively by small magnetic fields. Magnetoresistivity, in response, exhibits a measurable degree of anisotropic weak localization behavior, which allows the direct control of Dirac fermions with strong electron correlations. Our work points to a novel platform for manipulating emergent phenomena in strongly-correlated topological materials relevant to future applications.

cond-mat.mtrl-sci↗
arXiv2019

Topological photocurrent responses from chiral surface Fermi arcs

The nonlinear optical responses from topological semimetals are crucial in both understanding the fundamental properties of quantum materials and designing next-generation light-sensors or solar-cells. However, previous work was focusing on the optical effects from bulk states only, disregarding topological surface responses. Here we propose a new (hitherto unknown) surface-only topological photocurrent response from chiral Fermi arcs. Using the ideal topological chiral semimetal RhSi as a representative, we quantitatively compute the topologically robust photocurrents from Fermi arcs on different surfaces. By rigorous crystal symmetry analysis, we demonstrate that Fermi arc photocurrents can be perpendicular to the bulk injection currents regardless of the choice of materials' surface. We then generalize this finding to all cubic chiral space groups and predict material candidates. Our theory reveals a powerful notion where common crystalline-symmetry can be used to induce universal topological responses as well as making it possible to completely disentangle bulk and surface topological responses in many conducting material families.

cond-mat.mes-hall↗
arXiv2017

Topological Hopf and chain link semimetal states and their application to Co2MnGa (Theory and Materials Prediction)

Topological semimetals can be classified by the connectivity and dimensionality of the band cross- ing in momentum space. The band crossings of a Dirac, Weyl, or an unconventional fermion semimet- al are 0D points, whereas the band crossings of a nodal-line semimetal are 1D closed loops. Here we propose that the presence of perpendicular crystalline mirror planes can protect 3D band crossings characterized by nontrivial links such as a Hopf link or a coupled-chain, giving rise to a variety of new types of topological semimetals. We show that the nontrivial winding number protects topolog- ical surface states distinct from those in previously known topological semimetals with a vanishing spin-orbit interaction. We also show that these nontrivial links can be engineered by tuning the mirror eigenvalues associated with the perpendicular mirror planes. Using first-principles band structure calculations, we predict the ferromagnetic full Heusler compound Co2MnGa as a candidate. Both Hopf link and chain-like bulk band crossings and unconventional topological surface states are identified.

cond-mat.mes-hall↗
arXiv2017

Mirror protected Dirac fermions on a Weyl semimetal NbP surface

The first Weyl semimetal was recently discovered in the NbP class of compounds. Although the topology of these novel materials has been identified, the surface properties are not yet fully understood. By means of scanning tunneling spectroscopy, we find that NbPs (001) surface hosts a pair of Dirac cones protected by mirror symmetry. Through our high resolution spectroscopic measurements, we resolve the quantum interference patterns arising from these novel Dirac fermions, and reveal their electronic structure, including the linear dispersions. Our data, in agreement with our theoretical calculations, uncover further interesting features of the Weyl semimetal NbPs already exotic surface. Moreover, we discuss the similarities and distinctions between the Dirac fermions here and those in topological crystalline insulators in terms of symmetry protection and topology.

cond-mat.mes-hall↗