Search arXiv⌕ Search

arXiv subjects

Xiao Liang

Publications and source records attributed to Xiao Liang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Toponium Production at Future Muon Colliders and in heavy ion ultraperipheral collisions

In the framework of non-relativistic quantum chromodynamics (NRQCD), we systematically investigate the inclusive and exclusive production processes of spin-singlet \(^1S_0\) and spin-triplet \(^3S_1\) toponium at future muon colliders and in Pb--Pb ultraperipheral collisions (Pb--Pb UPC). Using the Coulomb-plus-linear potential and solving the Schrödinger equation, we obtain the wave function at the origin as $|R_{t\bar{t}}(0)|^2 = 2.507\ \text{GeV}^3$. The scattering cross sections and various kinematic distributions for two types of processes are calculated, and the corresponding event yields are estimated based on the expected integrated luminosities. Our study indicates that the detection prospects for toponium production through the aforementioned processes are unfavorable.

hep-ph↗
arXiv2026

Probing $d$-wave pairing in the $t$-$t'$-$U$ Hubbard model with tensor-backflow wave functions

Building on the recently developed tensor-backflow method, which accurately describes energies and stripe states in the Fermi-Hubbard model, we investigate $d$-wave pairing in the two-dimensional $t$-$t'$-$U$ Hubbard model. For the $8\times8$ lattice, we improve the wave function using symmetry projections followed by one Lanczos step, whereas for the $12\times 12$ and $16\times 16$ lattices, we apply one Lanczos step without symmetry projection. We focus primarily on the parameter regime with filling $n=0.875$, on-site repulsion $U=8$ and next-nearest-neighbor hopping $t'=-0.2t$, a regime in which enhanced $d$-wave pairing has been reported. The resulting energies are competitive with those obtained using state-of-the-art neural quantum states. For example, on a $16\times 16$ lattice with periodic boundary conditions, the tensor-backflow wave function after one Lanczos step without explicit symmetry enforcement achieves a relative energy difference of $4.4\times 10^{-3}$ from the symmetry-preserving neural quantum state result. From the real space pair correlations, for $t'=-0.2t$, we observe stronger $d$-wave pair correlations together with the characteristic relative sign between horizontal and vertical bond-pair components. Compared with $t'=0$, finite negative $t'$ increases the spectral weight of the corresponding pair-density matrix, which indicates the enhanced overall $d$-wave pair fluctuations. The leading eigenvalue is enhanced on the $8\times8$ lattice for both with and without symmetry projections. For larger lattices such as $12\times 12$ and $16\times 16$, the leading pair-density matrix spectral weight is distributed among several nearly degenerate eigenmodes rather than being concentrated in a single dominant mode. This indicates enhanced and more broadly distributed $d$-wave pair fluctuations, but no single eigenvalue exhibits the extensive scaling required for ODLRO.

cond-mat.str-el↗
arXiv2026

BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents

Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent gaps. Sandbox training produces a distribution mismatch with production environments; expensive real-device failures remain underutilized; and fixed benchmarks saturate, losing the power to guide iteration. We present BlueLM-GUI, a 35B-A3B mobile GUI agent built as a real-device-centric flywheel that closes these gaps through three principles. Every Sample Matters: a dual-track pipeline with Heterogeneous Triple-System Consensus evaluation and an Error Correction \& Derivation Module salvages every trajectory into usable supervision. Every Rollout Is Real: a three-stage recipe---continual pre-training, supervised fine-tuning, and agentic reinforcement learning on hundreds of real phones---grounds every rollout in real production environments, so the capability the model learns transfers directly to deployment. Every Query Evolves: a quota-driven benchmark methodology with three orthogonal axes enables precise attribution and allows the benchmark to be systematically upgraded as the model improves. BlueLM-GUI achieves 87.4 on MobileGUI-VBench, surpassing the best closed-source model by 5.1 points, and 84.9 on AndroidWorld, the best result among open-source models and competitive with closed-source models. These results demonstrate that grounding model training and iterative improvement in both real devices and the three Every principles yields strong, robust, and transferable mobile GUI capability.

cs.AI↗
arXiv2026

OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation

Generative recommendation (GR) relies on large-beam decoding to generate hundreds of candidate items, creating a new scaling challenge for recurrent linear attention. Existing linear attention serving systems either materialize a full recurrent state for every beam or repeatedly replay shared history, incurring substantial memory and traffic overhead. To address this, we present OneLA, a linear-attention decoding framework that exploits the shared prompt and short divergent suffixes of GR workloads. Specifically, OneLA represents all beam states using a single shared prompt-derived state and compact, append-only records of their divergent transitions. Using this representation, OneLA computes only the state information required at each decoding step, without reconstructing a full recurrent state for every beam. Furthermore, OneLA uses a lightweight ancestry index to track the transition records that make up each beam's history, allowing beams to be updated without moving or copying existing records. A fused GPU kernel further reuses the shared state across beams. Our analysis shows that OneLA achieves 1.54-2.46x end-to-end decode speedups while substantially reducing recurrent-state memory use and data movement.

cs.AI↗
arXiv2026

MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves

Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machine-checkable slice, not general capability where questions are open and correctness is settled by argument, replication, or measurement. We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable. To that end we present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm. Data-RSI amplifies existing competence and marks its boundary; Harness-RSI edits a five-slot scaffold without touching weights; Model-RSI internalizes capability into parameters through bounded training. Sharing one loop kernel and artifact vocabulary, they make data, scaffold, and model changes composable rather than exclusive. A two-axis optimizer jointly decides operator order and each operator's proposal policy, while a meta-level policy revises the schedule across terms. We validate MetaRSI-v1 under the field's standard evaluations, on code and closed-form science, with no external teacher: the target model plays every role in its own loop. MetaRSI-v1 reframes self-improvement from a single-surface edit to a composition across the full model-production pipeline, opening two paths: a model route internalizing capability through training, and a harness route leaving weights untouched and thus extending self-improvement to any model reachable through an interface, with Data-RSI redefined as the shared substrate feeding both. The framework further yields refutable laws on where loops exist, how operators compose, and what supervision buys.

cs.LG↗
arXiv2026

From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents

Computer-use agents can execute increasingly complex tasks in graphical interfaces, but their interaction experience is typically transient: procedural knowledge acquired from one rollout is not systematically retained, refined, and reused in later tasks. Existing skill libraries provide external procedural knowledge, yet their incremental value over the same agent operating without skills, as well as their longitudinal dynamics under repeated interaction, remain insufficiently characterized. We present an online skill-evolution framework that converts interaction trajectories and evaluator feedback into a persistent, versioned library of reusable procedures. Each iteration executes against a frozen library snapshot, and evidence-guided skill updates become available in subsequent iterations without changing model parameters. We compare the full evolving-library system with a configuration-matched empty-library control across four OSWorld application domains under the same fixed action-generation and GUI-grounding stack, task sets, and iteration horizons. Following a five-iteration empty-library warm-up, Full attains a higher post-warm-up mean evaluator score in all four observed domain runs, with mean differences ranging from 5.7 to 18.6 percentage points and domain-dependent temporal stability. In GIMP, provenance-aware analysis reveals retrieval across task-of-origin boundaries and revision churn, where repeated accepted edits fail to recover the originating task. These findings characterize evolving skill libraries as auditable, shared procedural memory that can improve a fixed computer-use stack, while showing that their benefits are conditional and repeated revision does not guarantee recovery. Code is released at https://github.com/LongtaoHu/Skill-Evo4GUI.

cs.AI↗
arXiv2026

EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems

Long-horizon interactions with LLM-based assistants require memory systems that preserve and update user states, preferences, and interaction histories. Existing evaluations report end-to-end QA accuracy and cannot determine whether errors arise from encoding, retrieval, or generation. We introduce EvalMem, an operation-level diagnostic framework with three parallel Examiners. For each query, the Encoding Examiner checks whether the target fact is stored, the Retrieval Examiner assesses whether the native retriever returns usable evidence, and the Generation Examiner tests whether the model can answer from oracle evidence. Their outputs form fine-grained multi-label defect codes. To improve store-level diagnosis, we adapt agentic RAG with a recall-first strategy that searches using both the query and source evidence, increasing recall of present evidence on LoCoMo from 70.2% to 95.6%. Evaluations of seven memory systems on LoCoMo, LongMemEval-S, and dynamic DynaMem-Bench identify retrieval as the most frequently attributed failure layer; in default LoCoMo, retrieval defects reach 22.1%, compared with 7.7% for encoding and 6.5% for generation. Guided by this diagnosis, MemWiki, a search-friendly auxiliary structure built from each system's memory export, improves mean accuracy by 2.5 and 2.3 percentage points on LoCoMo and LongMemEval-S, respectively.

cs.CL↗
arXiv2026

SIMPNet: Spatial-Informed Motion Planning Network

Current robotic manipulators require fast and efficient motion-planning algorithms to operate in cluttered environments. State-of-the-art sampling-based motion planners struggle to scale to high-dimensional configuration spaces and are inefficient in complex environments. This inefficiency arises because these planners utilize either uniform or hand-crafted sampling heuristics within the configuration space. To address these challenges, we present the Spatial-informed Motion Planning Network (SIMPNet). SIMPNet consists of a stochastic graph neural network (GNN)-based sampling heuristic for informed sampling within the configuration space. The sampling heuristic of SIMPNet encodes the workspace embedding into the configuration space through a cross-attention mechanism. It encodes the manipulator's kinematic structure into a graph, which is used to generate informed samples within the framework of sampling-based motion planning algorithms. We have evaluated the performance of SIMPNet using a UR5e robotic manipulator operating within simple and complex workspaces, comparing it against baseline state-of-the-art motion planners. The evaluation results show the effectiveness and advantages of the proposed planner compared to the baseline planners. Project website: \href{https://davoodsz.github.io/simpnet/}{https://davoodsz.github.io/simpnet/}

cs.RO↗
arXiv2026

PHR-VLA: Planning Horizon Reasoning for Vision-Language-Action Models

Vision-language-action models (VLAs) have shown strong promise for general-purpose robotic manipulation by mapping language instructions and vision observations directly to actions. However, most VLAs primarily condition action prediction on current observations and lack an explicit mechanism for reasoning over future task dynamics, which is particularly important for fine-grained, contact-rich manipulation. We present PHR-VLA, a framework that enables planning-horizon reasoning in VLAs through privileged latent representations of future dynamics. PHR-VLA introduces a lightweight auxiliary future head that, during training, aligns the VLA's internal representations with latent dynamics extracted from future observations. Evaluation results demonstrate that local, contact-centric, patch-level latent dynamics supervision from the wrist camera improves success rate on LIBERO from 84.1% to 88.4% and on real-world disassembly tasks from 63.3% to 82.5%. Patch-level supervision from a third-person camera also improves performance on Meta-World from 56.70% to 57.8%. These results demonstrate that privileged latent dynamics alignment provides an effective training signal for improving anticipatory reasoning in VLA policies. Project website: \href{https://davoodsz.github.io/PHR-VLA.github.io/}{https://davoodsz.github.io/PHR-VLA.github.io/}

cs.RO↗
arXiv2026

MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control

MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental challenges. First, structural misalignment between instance-level reasoning and pairwise contrastive supervision may lead to shortcut behavior, where the model merely learns the superficial format of reasoning. Second, reasoning is not universally beneficial for embedding tasks. Enforcing reasoning for all inputs may introduce unnecessary computation and latency, and can even obscure salient semantic signals for simple cases. To address these issues, we propose MMEmb-R1, an adaptive reasoning-based multimodal embedding framework. We formulate reasoning as a latent variable and introduce pair-aware reasoning selection that employs counterfactual intervention to identify reasoning paths beneficial for query-target alignment. Furthermore, we adopt reinforcement learning to selectively invoke reasoning only when necessary. Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency.

cs.CV↗
arXiv2026

NeurRAFT: Robot Motion Planning via Anchor-Level Flow Matching with Clearance-Aware Preference Tuning

Recent end-to-end neural motion planners generate trajectories from raw sensor observations, avoiding the privileged geometric models required by classical planners. However, collision-free planning in cluttered environments remains challenging. We present NeurRAFT, a generative planning framework based on anchor-level flow matching and clearance-aware preference tuning. Unlike prior neural planners that model dense waypoint sequences and spend capacity on redundant local details and smoothness, NeurRAFT operates on compact anchor waypoints. We train the planner using a Jacobian-weighted loss that accounts for the task-space impact of each anchor. At inference, the anchors are generated in two integration steps, followed by cubic-spline interpolation to recover a smooth, full-resolution trajectory. Since imitation learning from positive demonstrations cannot distinguish collision-free from near-collision trajectories, collision-prone behaviors persist at test time. Rather than relying on post-hoc corrections, we directly reshape the pretrained planner's distribution toward safer solutions without augmenting inference. Specifically, Direct Preference Optimization shifts probability mass toward trajectories with larger obstacle clearance, with the resulting improvement directly absorbed into the planner parameters. Experiments show substantial improvements over state-of-the-art planners, while real-world experiments demonstrate zero-shot transfer to a Franka robot under noisy and partially occluded depth observations. Video results available at https://neurraft.github.io/.

cs.RO↗
arXiv2026

PerFACT: Motion Policy with LLM-Powered Dataset Synthesis and Fusion Action-Chunking Transformers

Deep learning methods have significantly enhanced motion planning for robotic manipulators by leveraging prior experiences within planning datasets. However, state-of-the-art neural motion planners are primarily trained on small datasets collected in manually generated workspaces, limiting their deployment in various everyday scenarios. Additionally, these planners often rely on monolithic network architectures that struggle to encode critical planning information. To address these challenges, we introduce Motion Policy with Dataset Synthesis powered by large language models (LLMs) and Fusion Action-Chunking Transformers (PerFACT), which incorporates two key components. Firstly, a novel workspace generation method, PerFACT, enables large-scale planning data collection by leveraging procedural primitive generation, and LLM-powered primitive suggestion and placement. Secondly, we introduce Fusion Motion Policy Networks (M$π$NetsFusion), an end-to-end, open-loop neural motion planner that uses a fusion action-chunking transformer to better encode planning signals and attend to multiple feature modalities. Leveraging PerFACT, we collect a dataset of 3.5M trajectories to train and evaluate M$π$NetsFusion against state-of-the-art planners. Results show that M$π$NetsFusion achieves consistently low planning time with sub-second inference, while maintaining competitive performance compared to both sampling-based and end-to-end neural benchmark planners. Project website: \href{https://davoodsz.github.io/perfact.github.io/}{https://davoodsz.github.io/perfact.github.io/}

cs.RO↗
arXiv2026

Flow Motion Policy: Manipulator Motion Planning with Flow Matching Models

Open-loop end-to-end neural motion planners have recently been proposed to improve motion planning for robotic manipulators. These methods enable planning directly from sensor observations without relying on a privileged collision checker during motion planning. However, existing planners produce a single path for a given planning problem and cannot exploit their open-loop nature to propose multiple motion plans. To address this limitation, we introduce Flow Motion Policy, an open-loop neural motion planner that uses flow matching to generate a batch of motion plan proposals by learning a distribution over motion plans conditioned on the planning observation. At inference time, it samples multiple candidate motion plans to enable efficient best-of-$N$ inference while avoiding iterative collision checking during planning. We benchmark the Flow Motion Policy against representative sampling-based, optimization-based and neural motion planning methods. Evaluation results demonstrate that Flow Motion Policy improves planning success and efficiency, highlighting the effectiveness of stochastic generative policies for end-to-end motion planning and best-of-$N$ sampling. Project website: \href{https://davoodsz.github.io/FlowMotionPolicy.github.io/}{https://davoodsz.github.io/FlowMotionPolicy.github.io/}

cs.RO↗
arXiv2026

Learning When to See and When to Feel: Adaptive Vision-Torque Fusion for Contact-Aware Manipulation

Vision-based policies have achieved a good performance in robotic manipulation due to the accessibility and richness of visual observations. However, purely visual sensing becomes insufficient in contact-rich and force-sensitive tasks where force/torque (F/T) signals provide critical information about contact dynamics, alignment, and interaction quality. Although various strategies have been proposed to integrate vision and F/T signals, including auxiliary prediction objectives, mixture-of-experts architectures, and contact-aware gating mechanisms, a comparison of these approaches remains lacking. In this work, we provide a controlled comparison of different F/T-vision integration strategies within diffusion-based manipulation policies. In addition, we propose an adaptive integration strategy that ignores F/T signals during non-contact phases while adaptively leveraging both vision and torque information during contact. Experimental results demonstrate that our method outperforms the strongest baseline by 14% in success rate, highlighting the importance of contact-aware multimodal fusion for robotic manipulation.

cs.RO↗
arXiv2026

Transforming Remanufacturing Automation with Large Language Models: A Forward-Looking Analysis with Case Studies

With growing concerns about resource scarcity and environmental degradation, remanufacturing of end-of-life (EoL) products within the circular economy is attracting increasing attention. Remanufacturing can preserve most of the original manufacturing value and materials while transforming EoL products into like-new condition. However, the variability and uncertainty of EoL products make remanufacturing highly dependent on human expertise. Recently, large language models (LLMs) have demonstrated remarkable capabilities in learning from massive, unstructured datasets, generating expert-level output across various tasks, and communicating with humans in natural language for interpretation. These advantages can align closely with the complex demands of remanufacturing, thereby mitigating the reliance on specialized expertise. However, their roles and research progress in this domain remain underexplored. In this paper, we present a forward-looking review and analysis of the role of LLMs in remanufacturing automation, grounded in a brief critical review of existing LLM-related studies relevant to remanufacturing. Building on this foundation, we introduce ReManGPT as a conceptual framework and use three representative case studies to illustrate selected modules of the framework in practical remanufacturing scenarios. We also analyze three representative remanufacturing applications, electric vehicle batteries, electronic waste, and electric motors, to illustrate how the proposed framework could address their domain-specific challenges. Finally, we discuss the current barriers to deploying this framework in practice and outline future research directions, including LLM-assisted human operation and language-action models for robotic automation.

eess.SY↗
arXiv2026

Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in GUI Agents

Graphical User Interface (GUI) agents have made significant progress in automating digital tasks through the utilization of computer vision and language models. Nevertheless, existing agent systems encounter notable limitations. Firstly, they predominantly depend on trial and error decision making rather than progressive reasoning, thereby lacking the capability to learn and adapt from interactive encounters. Secondly, these systems are assessed using overly simplistic single step accuracy metrics, which do not adequately reflect the intricate nature of real world GUI interactions. In this paper, we present CogniGUI, a cognitive framework developed to overcome these limitations by enabling adaptive learning for GUI automation resembling human-like behavior. Inspired by Kahneman's Dual Process Theory, our approach combines two main components: (1) an omni parser engine that conducts immediate hierarchical parsing of GUI elements through quick visual semantic analysis to identify actionable components, and (2) a Group based Relative Policy Optimization (GRPO) grounding agent that assesses multiple interaction paths using a unique relative reward system, promoting minimal and efficient operational routes. This dual-system design facilitates iterative ''exploration learning mastery'' cycles, enabling the agent to enhance its strategies over time based on accumulated experience. Moreover, to assess the generalization and adaptability of agent systems, we introduce ScreenSeek, a comprehensive benchmark that includes multi application navigation, dynamic state transitions, and cross interface coherence, which are often overlooked challenges in current benchmarks. Experimental results demonstrate that CogniGUI surpasses state-of-the-art methods in both the current GUI grounding benchmarks and our newly proposed benchmark.

cs.AI↗
arXiv2026

LapSurgie: Humanoid Robots Performing Surgery via Teleoperated Handheld Laparoscopy

Robotic laparoscopic surgery has gained increasing attention in recent years for its potential to deliver more efficient and precise minimally invasive procedures. However, adoption of surgical robotic platforms remains largely confined to high-resource medical centers, exacerbating healthcare disparities in rural and low-resource regions. To close this gap, a range of solutions has been explored, from remote mentorship to fully remote telesurgery. Yet, the practical deployment of surgical robotic systems to underserved communities remains an unsolved challenge. Humanoid systems offer a promising path toward deployability, as they can directly operate in environments designed for humans without extensive infrastructure modifications -- including operating rooms. In this work, we introduce LapSurgie, the first humanoid-robot-based laparoscopic teleoperation framework. The system leverages an inverse-mapping strategy for manual-wristed laparoscopic instruments that abides to remote center-of-motion constraints, enabling precise hand-to-tool control of off-the-shelf surgical laparoscopic tools without additional setup requirements. A control console equipped with a stereo vision system provides real-time visual feedback. Finally, a comprehensive user study across platforms demonstrates the effectiveness of the proposed framework and provides initial evidence for the feasibility of deploying humanoid robots in laparoscopic procedures.

cs.RO↗
arXiv2026

AutoPath: Learning Transferable Goal-Conditioned Stochastic Path Prior for Safe Navigation Without Human Demonstrations

Real-time navigation in cluttered and dynamic environments requires collision-free and dynamically feasible motion under limited perception. However, feasible navigation behaviors are inherently multimodal because multiple paths may exist around obstacles. In this paper, we formulate navigation as learning a transferable goal-conditioned stochastic path prior that models a reusable distribution over goal-aligned geometry-consistent local paths conditioned on local observations. This formulation enables structured sampling of navigation candidates, allowing multiple feasible paths to be explored through sampling without relying on robot-specific motion constraints. To this end, we introduce a goal-aligned canonical state representation that removes in-plane rotational ambiguity and normalizes local geometry with respect to the goal, enabling rotation-invariant path distribution learning. We further develop a structured prior learning framework that parameterizes local paths using a geometry-aware polar action manifold and incorporates risk-sensitive utility shaping with multi-goal distributional rollouts for stable and safety-aware planning. Extensive experiments in dense static environments and dynamic pedestrian scenarios demonstrate that the proposed method achieves consistently high success rates with competitive efficiency while enabling cross-platform transfer of a single path prior learned on differential-drive robots to quadruped platforms without retraining.

cs.RO↗