Search arXiv⌕ Search

arXiv subjects

Yuchen Guo

Publications and source records attributed to Yuchen Guo.

At least 19 recordsLinked to original sources
arXiv2026

BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots

Recent advances in gigapixel-level imaging have brought High-Resolution Wide shots to the forefront of research. However, these images present significant challenges: extreme sparsity of foreground, gigapixel-level resolutions and interleaving of foreground and background. This causes traditional detectors and attention mechanisms to be hindered by background, resulting in inefficiency and inaccuracy. To tackle this problem, we propose BiHashFormer, a dual sparsified branch transformer built on hashing. RoI Selector will predict the foreground proportion for top-k selecting target-containing windows. The compression branch processes windows selected and refines attention into HashAttention by discarding half of the key-value pairs, reducing cost and improving efficiency. The compensation branch uses HashMiner to perform low-cost hash searches in the remaining regions, recovering features of missed objects. Experiments confirm that the selection relationship in HashAttention is one-way and reveal the preference of different queries for keys. In experiments on the gigapixel benchmark PANDA, BiHashFormer reduces 37.5% backbone FLOPs while improving AP50 to 81.0%. Moreover, this parallel dual-branch structure allows the model to avoid inference delays caused by inter-branch dependencies, while achieving much greater stability than single-branch models, specially with low rates of RoI selection.

cs.CV↗
arXiv2026

ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer

Recent advances in gigapixel-level imaging have brought High-Resolution Wide shots to the forefront of research. However, these images present significant challenges: extreme sparsity of foreground, gigapixel-level resolutions and diverse target counts. This makes traditional close-up detectors inaccurate and slow as they are overwhelmed by the background. Although previous research has explored sparse backbones, their fixed sparsity patterns lack the adaptability required to handle diverse target numbers. To address this, we introduce ElasticFormer, a sparse backbone that dynamically allocates computational resources based on foreground proportion. After scoring windows based on variance, proposed ElasticSelector module will predict the foreground proportion for top-k selection. The mechanism guides the model to select target-containing windows, scaling resources in areas where objects are clustered. We introduce a novel loss function combined with the 3-phase training strategy for ElasticSelector, allowing it to function properly when bounding box annotations are missing. A WSOD study is carried on PASCAL VOC 2007 to evaluate its extensibility. Further, ElasticNet is created to verify its backbone-agnostic nature. In experiments on the PANDA gigapixel benchmark, ElasticFormer reduces backbone FLOPs by 80% while achieving a significant improvement in AP50 when compared to fixed-ratio sparse methods.

cs.CV↗
arXiv2026

Non-associative Hopf Algebra on Dyck Paths Arising from the Shuffle-insertion Product

In this paper, we define a shuffle-insertion product and a cut-box coproduct on the vector space spanned by Dyck paths, where the product is commutative but non-associative. We prove that the product and coproduct are compatible, making the space a non-associative bialgebra. This bialgebra is connected and bigraded by path degree and peak number, and hence is a non-associative Hopf algebra. Its primitive subspace is spanned by atoms, and associators of primitive elements are primitive. Furthermore, we provide closed-form formulas for its left and right antipodes. We also define the convolution product on the space of linear transformations of the non-associative Hopf algebra, which equips this space with a non-associative algebra structure. Finally, we construct a one-parameter deformation preserving the cut-box coproduct. Its zero specialization is the ordinary shuffle Hopf algebra, which is also the associated graded algebra for the atom filtration, while every nonzero specialization is isomorphic to the shuffle-insertion algebra.

math.CO↗
arXiv2026

Factual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and Retrieval

Factual recall is a lookup: some representation inside the network serves as the key, and what that key is made of decides which queries can retrieve the fact, what an edit must cover, and what a retriever can read. We call it the factual access state. In autoregressive (AR) models the subject position enriches attributes largely independently of the relation, and relation-specific selection happens later, at the readout position. In masked diffusion language models (DLMs) we find the state is assembled differently, and much earlier: in the first attention layer the wording of the relation is routed into the position of whichever entity is visible and the early feed-forward layers look the fact up on this fused representation. The state therefore varies with the relation's surface form and with the query direction, so the queries about one fact occupy a region of state space rather than a point, and an operation on the fact succeeds only for queries that enter it. We treat the state as an interface to a DLM's factual knowledge, and put it to two uses. Writing to the state gives a knowledge editor: from one declarative statement, Multi-View Edit fits one shared value per direction across that region and installs it in the early-MLP block, preserving source-prompt reliability while substantially improving paraphrase and reverse question answering, where AR editors gain near zero. Reading it suggests a complementary use: the state at each entity position can serve as a relation-specific retrieval vector with no training, returning both pieces of evidence for two-entity queries on which pooled, prompted and lexical retrievers almost never return both.

cs.CL↗
arXiv2026

Role-Aware Artificial Intelligence Across Augmentation and Automation in Human-Machine Symbiosis

The evolution of artificial intelligence (AI) has rendered the boundary between humanity and computational machinery increasingly ambiguous. In the presence of more interwoven relationships within human-machine symbiosis, the very notion of AI-generated information becomes difficult to define, as such information arises not from either humans or machines in isolation, but from their mutual shaping. At times AI acts in place of the human, automating the task; at others it extends what the human can do, augmenting their capability. Therefore, a more pertinent question lies not merely in whether AI has participated, but in how it has participated. In general, the role assumed by AI is often specified, either implicitly or explicitly, in the input prompt, yet becomes less apparent or altogether unobservable when the generated content alone is available. Once detached from the dialogue context, the functional role may no longer be traceable. This study considers the problem of tracing the functional role played by AI in natural language generation. A methodology is proposed to infer the latent role specified by the prompt, embed this role into the content during the probabilistic generation process and subsequently recover the nature of AI participation from the resulting text. Experimentation is conducted under a representative scenario in which AI acts either as an assistive agent that edits human-written content or as a creative agent that generates new content from a brief concept. The experimental results support the validity of the proposed methodology in terms of discrimination between roles, robustness against perturbations and preservation of linguistic quality. We envision that this study may contribute to future research on the ethics of AI with regard to whether AI has been used fairly, transparently and appropriately.

cs.AI↗
arXiv2026

Observation of electron spin interactions between Rydberg atoms

We report the observation of electron spin interactions between Rydberg atoms, which are driven by spin-orbit coupling through second-order dipole perturbation and exhibit a spatial anisotropy governed by the atomic configuration. Specifically, we observe coherent electron spin exchange dynamics, with the measured coupling strength agreeing well with both numerical calculations and theoretical models. Furthermore, we show that global microwave dressing enables active engineering and dynamical freezing of the spin exchange by introducing a differential AC Stark shift between the participating states. Additionally, we achieve tunability of the interaction by applying a stronger magnetic field, which effectively modifies the energy contributions of the underlying spin-orbit coupling channels. Finally, measuring spin dynamics in one-dimensional multi-atom chains aligned parallel or perpendicular to the magnetic field provides a self-consistent validation of the anisotropic XXZ framework. This electron spin interaction natively features spin-position coupling and enables a natural mapping onto the Heisenberg-Kitaev model. Our findings reveal a new class of electron spin-spin interactions among Rydberg atoms, expanding the scope of quantum simulation with Rydberg atom arrays.

cond-mat.quant-gas↗
arXiv2026

When Trust Meets Truth: Trust-Truth Separability in LLM-as-Judge

LLM-as-Judge systems can produce multi-dimensional evaluations, such as trustworthiness, reliability, and factuality, and these outputs are often interpreted as independent evidence. We test this assumption for a common pair of judgments: trust scoring and binary truth classification. On correctness-controlled QA, LLM judges align trust scores with truth verdicts more tightly than human behavioral reference, suggesting weaker separations between trust and truth judgment. We then apply stress tests by changing only source cues of identical QA between Human and AI. Source attribution shifts not only trust scores but also truth verdicts and logit-derived correct-side probabilities. Results show that current LLM-as-Judge protocols should not treat trust scores as independent evidence for truth judgments.

cs.AI↗
arXiv2026

Discovery of a Barred-Spiral Galaxy at $z_{spec}$ = 3.16 I: Bar Identification and Properties

The formation of stellar bars is an important milestone in the secular evolution of spiral galaxies, which typically indicates the presence of a massive rotationally supported disk. Determining when these structures first appeared in the early universe is crucial to constraining the timeline of galactic disk assembly. Here, we report the discovery of COSMOS-74706, a barred spiral galaxy at $z_{spec} = 3.159$. Imaging of COSMOS-74706 with JWST/NIRCam indicates a disk-like morphology and spiral structure with an elongated central feature aligned between the spiral arms, most conspicuously visible in the F200W, F277W, and F356W filters. Three independent methods all support the presence of a bar: visual inspection of residuals from Sérsic-profile fitting shows a linear structure, isophotal ellipse-fitting displays characteristic profiles of ellipticity and position angle consistent with a bar signature, and Fourier decomposition of the galaxy produces a central bisymmetric mode above a threshold strength calibrated to $z=1-3$ barred spirals. Leveraging archival Keck/MOSDEF spectroscopy overlapping with a blue clump on the edge of the galaxy, a robust redshift is inferred, with photometric constraints indicating that this structure lies at the same redshift as the main spiral. This spectroscopic evidence, placing an unlensed barred spiral at $z>3$ supports the idea that galaxies with rotationally supported disks and disk-halo properties that are conducive to bar formation were already in place within 2 Gyr after the Big Bang.

astro-ph.GA↗
arXiv2026

Rigorous Statements and Proofs of the Lemmas in Simon's Algorithm for the Dihedral Coset Problem and Their Underlying Hypothesis

In a recent preprint, Simon proposed a polynomial-time quantum algorithm for the Dihedral Coset Problem and rested the analysis on four lemmas. Three of them carry only proof sketches, and this paper gives each of those three a statement that admits a single reading together with a complete proof. Lemma 1 follows from an exact second-moment computation for the subset-sum counts, and it holds with probability tending to one in place of the constant originally claimed. The amplitude bound of Lemma 3 follows from an exact Parseval identity on the cube of measurement outcomes and holds at every threshold with no well-behavedness hypothesis, so that predicate leaves the argument entirely. For Lemma 4, we compute both balls-in-bins covariances exactly and find that the second carries a term a fixed ball count leaves out. The assumption that the distinguished group contains no faulty samples can also be dropped. The two branch amplitudes share a signed prefactor, so the counting estimates control their difference and not the ratio the lemma states. We prove the additive form and show that the closing argument consumes nothing more than that. A single hypothesis survives all of this. It asks that the partition into the two sides be fixed independently of the measured string, and the rule the algorithm gives for choosing that partition does not supply it. Establishing these four lemmas therefore does not by itself establish the correctness of the algorithm.

cs.CR↗
arXiv2026

Parent Hamiltonian and intrinsic phase transition in non-Hermitian photonic systems

Non-Hermitian systems host phenomena absent in Hermitian physics, but realizing Hamiltonians with intrinsic non-Hermitian properties remains challenging. The theoretical method of non-Hermitian parent Hamiltonian (NH-PH) enables the construction of a non-Hermitian system from a pair of matrix product states (MPSs) with tailored properties. Here, we report the first experimental generation of NH-PHs. This generation starts from MPSs that represent asymmetric Affleck--Kennedy--Lieb--Tasaki (AKLT) states. The construction is validated with single photons via imaginary-time evolution of the generated NH-PH to obtain its left and right ground states. We then characterize the properties of the system by measuring four different order parameters that probe non-reciprocal correlations, chiral imbalance, and conventional antiferromagnetic correlations. Furthermore, extending the framework to a larger system with a different model, we observe an intrinsic non-Hermitian phase transition, manifested by abrupt jumps of an order parameter when the designated zero-energy modes cease to be the globally lowest-energy states. Our work provides the first experimental realization and characterization of non-Hermitian Hamiltonians with controllable and customizable properties, opening new avenues for exploring intrinsic non-Hermitian phenomena across diverse physical platforms.

quant-ph↗
arXiv2026

Tensor network characterization and mitigation of readout errors

Readout errors are a major bottleneck to extracting reliable information from near-term quantum processors, especially when spatial correlations are non-negligible. We present a unified tensor-network framework that models the readout process as a matrix product operator (MPO), enabling efficient characterization and mitigation beyond uncorrelated approximations. The MPO model is trained via likelihood optimization on calibration data and applies to multiple tasks, including nonlocal observable estimation, random circuit sampling, and random-measurement protocols, such as classical shadows and learning-based tomography. Experiments on a superconducting processor and numerical simulations up to 20 qubits show that the MPO model captures correlated readout errors that uncorrelated models miss, with a sample cost that grows only near-linearly with system size. When extended to two-dimensional systems, the framework can also be integrated with tensor-network quantum error-correction decoders by performing joint inference over data and readout errors. These results establish tensor-network readout error mitigation as a scalable and versatile approach for noise-aware quantum data processing.

quant-ph↗
arXiv2026

Discovery of a Barred-Spiral Galaxy at $z_{spec}$ = 3.16 II. The Star Formation History

We present a detailed analysis of a massive barred galaxy at $z_{spec}=3.1591$ using deep multi-band imaging from HST and JWST. For the first time, we resolve its morphology and stellar structures thanks to the JWST/NIRCam NIR and MIR photometry. The galaxy possesses two distinct components with significantly different colors. Through careful image decomposition and masking, we isolate and characterize the flux contribution from each component. The galaxy exhibits a clear spiral morphology, and in a separate companion paper, we present evidence suggesting the presence of a stellar bar. Based on spatially resolved spectral energy distribution modeling with Prospector, we derive the star formation history and other physical properties of the bar and the surrounding regions. The total stellar mass of the galaxy is constrained as $\log(M_*/M_{\odot}) = 10.63\pm0.13$. We find that the bar region contains around 30% of the total stellar mass, but only accounts for around 8% of the recent star formation rate. The region containing the potential bar shows a significantly older mass-weighted stellar age, supporting the inside-out scenario for galaxy formation, and providing tentative evidence for bar quenching in the early stage. The quick onset of a stellar bar at this redshift requires a low dark matter fraction, suggesting the baryon-dominated nature of high-$z$ massive galaxies, and offering rare insight into galaxy evolution at around two billion years after the Big Bang.

astro-ph.GA↗
arXiv2026

Model Merging to Evolution: Parameter Space Exploration for Expert Models

Model merging integrates the capabilities of multiple expert models to create strong models for multiple tasks without additional training, thereby reducing computational resource requirements. However, existing methods operate within the convex combination space of expert models, failing to explore high-performance regions outside this space. This paper proposes the MERGEvolve framework, which unifies model merging and evolution within an evolution strategy by treating the merged model as the initialization for evolutionary exploration of the parameter space. During the merging phase, expert models act as deterministic sources to build a strong initial point. The evolution phase then explores the parameter space using random noise. Theoretical analysis shows that MERGEvolve explores regions outside the convex combination space. Extensive experiments on single-task and multi-task benchmarks demonstrate that MERGEvolve consistently achieves performance competitive with advanced model merging baselines. Ablation studies confirm that a high-quality initial point is critical for efficient exploration of the parameter space.

cs.NE↗
arXiv2026

All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution

Lifelong interactive agents are expected to assist users over months or years, which requires continually writing long term memories while retrieving the right evidence for each new query under fixed context and latency budgets. Existing memory systems often degrade as histories grow, yielding redundant, outdated, or noisy retrieved contexts. We present \textbf{All-Mem}, an online/offline lifelong memory framework that maintains a topology structured memory bank via explicit, non destructive consolidation, avoiding the irreversible information loss typical of summarization based compression. In online operation, it anchors retrieval on a bounded visible surface to keep coarse search cost bounded. Periodically offline, an LLM diagnoser proposes confidence scored topology edits executed with gating using three operators: Split, Merge, and Update, while preserving immutable evidence for traceability. At query time, typed links enable hop bounded, budgeted expansion from active anchors to archived evidence when needed. Experiments on \textbf{LoCoMo} and \textbf{LongMemEval-s} show improved retrieval and QA over representative baselines. The code is available at https://github.com/LvCan926/All-Mem.

cs.IR↗
arXiv2026

Exploring the Relationship Between Bars, Star Formation Activity, and Host Galaxy Properties from $\mathbf{z \sim 0}$ to $\mathbf{z \sim 2}$

We present the most comprehensive study to date of the relationship between bars, star formation, and galaxy properties from $z \sim$ 0 to $z \sim$ 2. We use a mass-complete sample of 1,171 galaxies from the JWST CEERS survey with $M_\star > 10^{10} M_\odot$ and repeat the analysis using COSMOS-Web data. Our results are: 1) At high redshift ($z \sim$ $1-2$) barred galaxies tend to have high sSFRs and low Sérsic indices ($n \leq 2$), while at low redshifts barred galaxies emerge with both low sSFR and higher $n$, suggestive of quiescent galaxies with bulges. 2) The fractional contribution of barred quiescent galaxies to the bar fraction rises steeply from $z \sim$ 2 to $z \sim$ 0, while that of barred actively star-forming galaxies falls. 3) The fraction of quiescent galaxies that are barred rises steeply over the last 10 Gyr. 4) Our empirical results show good agreement with the TNG50-1 simulations for bars with $a_{\mathrm{bar}}$ $>$ 1.5 kpc. Our results allow for the possibility that bar-driven secular evolution may lead to quiescence and/or that bars are more likely to persist and grow in gas-poor, quiescent galaxies. The steep rise in the quiescent bar fraction over 10 Gyr may represent an evolutionary sequence whereby gas-rich disks at high redshift first develop short, dynamically young bars and over time, repeated bar-driven gas inflows lead to central starbursts and declining gas fractions that strengthen the bar as the galaxy transitions toward quiescence.

astro-ph.GA↗
arXiv2026

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized through experience. PEAM pairs a slow deliberative LLM for open-ended reasoning with a fast parametric module for reflexive execution of consolidated skills. The fast module is a multimodal Mixture-of-Experts LoRA architecture with per-category physically isolated adapters, enabling parameter-level continual learning without catastrophic forgetting. We treat failure as a first-class training signal: failure--correction trajectory pairs are internalized through a joint behavioral-cloning and contrastive objective, so the agent learns not only what succeeds but also how corrected actions differ from failed ones. To govern consolidation, PEAM introduces a parameterization-worthiness score for deciding which experience should be internalized, and a scale-free self-triggered consolidation mechanism for deciding when to internalize without task-specific hand-tuned thresholds, making the agent self-evolving as the trigger transfers across task distributions without re-tuning. Experiments in Minecraft show that PEAM improves long-horizon task performance, mitigates forgetting on previously consolidated skills, and improves parametric-versus-retrieval efficiency over retrieval-based embodied agents and parametric memory variants.

cs.AI↗
arXiv2026

Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought

Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instructions remain target-referential: they describe, constrain, or imply the region to be segmented. However, in real-world embodied interaction, human instructions are often at the intent-level, which includes the desired outcome without naming the region that enables it. To bridge this gap, we introduce SegWorld, where the model reasons about the scene through a multi-level visual chain-of-thought (CoT) before committing to a mask. Before receiving any instructions, it proactively observes the scene, describing visible objects and inferring plausible events they may support. Given an instruction, it continues the chain: from the object relevant to the intent, through the action that satisfies it, to the physical interaction site, the object part that affords the action. We formalize SegWorld as probabilistic inference, in which proactive observation supplies a linguistic scene context that improves mask prediction when instructions are given at the level of intent. We construct an intent-to-part benchmark for evaluating affordance-bearing part segmentation from high-level goals. Experiments show SegWorld matches instruction-driven baselines on target-referential instructions and improves substantially on intent-level ones.

cs.CV↗
arXiv2026

Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMs

Surgical scene understanding is a cornerstone of computer-assisted intervention. While recent advances, particularly in surgical image segmentation, have driven progress, real-world clinical applications require a more holistic understanding that jointly captures procedural context, semantic reasoning, and precise visual grounding. However, existing approaches typically address these components in isolation, leading to fragmented representations and limited semantic consistency. To address this limitation, we propose SurgMLLM, a unified surgical scene understanding framework that bridges high-level reasoning and low-level visual grounding within a single model. Given surgical videos, SurgMLLM fine-tunes a multimodal large language model (MLLM) to support structured interpretability reasoning, which is used to jointly model phases, instrument-verb-target (IVT) triplets, and triplet-entity segmentation tokens. These tokens are then temporally aggregated and serve as prompts for a segmentation network, enabling accurate pixel-wise grounding of triplet instruments and targets. The entire framework is trained end-to-end with a unified objective that couples language-based reasoning supervision with visual grounding losses, promoting coherent cross-task learning and clinically consistent scene representations. To facilitate unified evaluation, we introduce CholecT45-Scene, extending CholecT45 dataset with 64,299 frames of pixel-level mask annotations for instruments and targets, aligned with existing triplet labels. Extensive experiments show that SurgMLLM significantly advances surgical scene understanding, improving the primary triplet recognition metric AP_IVT from 40.7% to 46.0% and consistently outperforming prior methods in phase recognition and segmentation. These results highlight the effectiveness of unified reasoning-and-grounding for reliable, context-aware surgical assistance.

cs.CV↗