Information Retrieval
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Monday 31 August
Embedding-based retrieval is at the core of industrial recommender systems, but a single user embedding is often too limited to capture a user's diverse interests. Multi-interest retrieval addresses this by using multiple user embeddings, yet existing methods still suffer from two issues: interest collapse, where different embeddings learn the same interest, and static dispatch, where serving uses a fixed retrieval budget even when some embeddings are unnecessary. We propose SetMIR, which treats multi-interest retrieval as a set prediction problem. SetMIR encodes a user's behavior history with a transformer and uses K learnable queries to decode a set of user interests, each producing a retrieval embedding and a presence score. During training, Hungarian matching assigns targets to queries one-to-one, so matched queries learn distinct interests and the presence head learns which queries are active. At serving time, SetMIR uses presence scores and query-level Non-Maximum Suppression (NMS) to issue only active, non-redundant ANN queries. On Snap's Dynamic Product Ads (DPA) data, SetMIR outperforms four learned multi-interest retrievers on every metric while issuing 33% fewer ANN queries per request. Deployed as a new retrieval source in the DPA production stack, SetMIR lifts overall CVR by 3.1%, while lifting CTR by 44% and CVR by 51% over the item-to-item retrieval source with the same item embeddings, ANN index, and retrieval quota.
Artificial Intelligence
Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs
This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers. Each target is a directed acyclic graph (DAG) of conditional actions with parallel branches, hit-first fallback chains, and per-branch Boolean predicates, encoded in the JSON dialect of a commercial routing platform. We show that neuro-symbolic decomposition enables lower-cost, non-reasoning large language models to generate complex workflow DAGs at production-relevant quality without expensive extended-reasoning models. Our central diagnostic is an emission-density bottleneck: on a 635-rule benchmark of manufactured synthetic data, models select the correct graph nodes with high accuracy but increasingly misconfigure attributes and Boolean grouping as the number of interdependent nodes emitted in one pass grows. We therefore move combinatorial graph construction from the model into a deterministic compiler driven by a compact intermediate representation, with a learned registry-selection front end that focuses generation on relevant vocabulary. Across four models, the full system reaches approximately 89% LLM-judge validity, approximately 90% exact-match condition accuracy, and 99-100% valid JSON while using roughly half the per-rule prompt tokens of a monolithic prompt. On GPT-5.3-chat, the method improves judge validity by 24 percentage points and achieves statistical equivalence to a reasoning model's out-of-the-box quality, although an approximately 8-point frontier gap remains. We also present a deployment path and transferable lessons for structured-generation applications.
Read the full abstract
Differential Geometry
The Grassmannian of indefinite subspaces
The homogeneous space $\operatorname{O}_{m,n}(\mathbb{R})/(\operatorname{O}_{p,q}(\mathbb{R}) \times \operatorname{O}_{m-p,n-q}(\mathbb{R}))$ is an object that has received scant attention, with just two brief mentions in existing literature, and christened the indefinite Grassmannian in one of them. In this article, we develop some of its basic properties, building it from ground up. We will see that, aside from its homogeneous space description, the indefinite Grassmannian may be characterized in several other ways: set-theoretically, it is the manifold of indefinite $(p+q)$-dimensional subspaces in $(m +n)$-dimensional space; it is an adjoint orbit of a Lie group; a semialgebraic smooth manifold of matrices; a base space of a principal bundle whose total space is the indefinite Stiefel manifold, a natural corresponding notion. It may also be naturally equipped with various structures, turning the indefinite Grassmannian into a pseudo-Riemannian manifold; a Einstein manifold; a symplectic manifold; and a pseudo-Kähler manifold (last two only over $\mathbb{C}$). As a centerpiece of this article, we establish two attributes of the indefinite Grassmannian in relation to the standard Grassmannian: (i) any Grassmannian has a Whitney stratification whose highest dimensional strata are indefinite Grassmannians; (ii) the indefinite Grassmannian is a strong deformation retract of a product of two Grassmannians, thereby allowing us to completely ascertain the topology of the former. We will also determine some of the indefinite Grassmannian's features that are within reach — both geometric (Riemann, Ricci, sectional, and scalar curvatures; second fundamental form) and topological (cohomology ring, homotopy groups, characteristic classes).
Read the full abstract
Software Engineering
DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation
Current data science (DS) code generation benchmarks equate correctness with quality, overlooking execution time differences that span orders of magnitude between correct solutions. We introduce DSEffi-Bench, the first benchmark specifically targeting execution efficiency in LLM-generated DS code, comprising 1,000 instances across 10+ DS libraries with stress-testing harnesses and human-validated references. Evaluating 16 models across 3 tiers, we find that correctness alone fails to characterize efficiency: GPT-5.4 leads in correctness (Pass, 66.9%) but its efficiency score (B$|$P, 71.7%) nearly matches GPT-5.4-mini (71.6%), which solves 47 fewer tasks; Kimi-K2.5 ranks lowest in correctness among frontier models (40.2%) yet achieves the highest efficiency score (73.6%) across all 16 models. A human-annotated five-category taxonomy reveals that 79.1% of efficiency deficits extend beyond algorithmic complexity to domain-specific root causes, with distinct failure profiles across model tiers and libraries. Two exploratory experiments provide initial evidence that these diagnostics can guide improvement, yielding up to +14.7% efficiency gains via taxonomy-guided optimization and approaching Claude-Opus-4.6 Best@3 in efficiency at 13.0$\times$ lower cost via library-conditioned routing.
Read the full abstract
Computer Vision
OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection
Recent unified open-vocabulary detection (OVD) supports heterogeneous prompts, including text queries, visual exemplars, and their combinations, but often rely on increasingly complex designs such as heavy cross-modal fusion, staged training, and iterative annotation pipelines. We revisit whether such complexity is necessary in the era of stronger foundation models. Our finding is that unified OVD can be made substantially simpler with semantic-rich visual representations and scalable grounding supervision. We present OPUS (Open-vocabulary, Prompt-Unified, Simple), a unified detector supporting text, interactive visual, generic visual, and mixed prompting within one framework. OPUS adopts a simple three-part design. Its model architecture combines a semantic-rich visual encoder, built on a DINOv3-ConvNeXt-B backbone with efficient hybrid encoding, with a prompt-aware decoder that avoids prompt-specific branches for unified prompt reasoning. OPUS is trained with a one-stage text-visual training strategy with Instance-level Contrastive Alignment (ICA), and is supported by a SAM3-based single-pass data engine for heterogeneous grounding supervision. Experiments on COCO, LVIS-minival, and ODinW35 show that OPUS achieves state-of-the-art Visual-I performance, reaching 68.1/69.2/54.7 AP, while maintaining balanced Text and Visual-G accuracy. OPUS also turns mixed prompting from interference into complementarity, improving over text or visual prompt alone. These results show that simplicity and strong unified prompting capability can be achieved together.
Read the full abstract
Logic
A Borel Concept Class of VC Dimension One with a Non-PAC Consistent Learner in ZFC
The fundamental theorem of statistical learning states that, under suitable measurability assumptions, finite Vapnik–Chervonenkis (VC) dimension guarantees that every proper consistent learning rule is probably approximately correct (PAC). Blumer, Ehrenfeucht, Haussler, and Warmuth showed, assuming the Continuum Hypothesis, that the "well-behavedness" condition of the concept class cannot be omitted: they constructed a concept class of Borel sets of VC dimension one admitting a consistent learning rule that is not PAC. We show that the Continuum Hypothesis is unnecessary. Working in Zermelo–Fraenkel set theory with the Axiom of Choice (ZFC) alone, we construct a concept class of Borel sets on $[0,1]$ of VC dimension one and a proper consistent learning rule that is not PAC. More precisely, for a suitable Borel probability measure and target concept, the rule has true risk one at every sample size on a set of samples of outer probability one. Consequently, finite VC dimension and Borel measurability of the individual concepts do not suffice to guarantee that every proper consistent learning rule is PAC. The result shows, with no need of extra set-theoretical assumptions, that the additional regularity assumption in the fundamental theorem cannot in general be omitted.
Read the full abstract
Representation Theory
ABRR Summation Formulas for Relative Extremal Projectors
In 2004, Khoroshkin proved that the extremal projector is equivalent to the dynamical twist. The Arnaudon-Buffenoir-Ragoucy-Roche (ABRR) equation, satisfied by the dynamical twist, yields a recursive formula for the coefficients in the extremal projector. The resulting summation formula is uniform and powerful in its applications to representation theory and Mickelsson-Zhelobenko reduction algebras. In this paper we generalize this recursive formula to the relative extremal projector, introduced by Conley and Sepanski in 2003. When the Levi subalgebra is the Cartan subalgebra, we recover the usual ABRR recursion. We also find a compact and explicit expression for the solution to the recursion. Our setting includes infinite-dimensional contragredient Lie superalgebras, Kac-Moody algebras, basic classical Lie superalgebras, and finite-dimensional reductive Lie algebras.
Read the full abstract
Optimization and Control
Decentralized Strategies for Finite Population LQG Social Control: A Reinforcement Learning Approach
This paper presents a novel model-free algorithm for the finite-population linear quadratic Gaussian (LQG) decentralized social control problem with multiplicative noise. The state and control weights in the cost functional are not limited to be positive semidefinite. For both finite-horizon and infinite-horizon cases, the goal is to obtain a social optimum by solving two algebraic Riccati equations (AREs), without requiring prior knowledge of the system matrices. Then, we complete the design of a model-free algorithm for solving the decentralized social control problem. Especially, in the infinite-horizon case, the algorithm's convergence is based on analyzing the spectral property of the Lyapunov-type operator. The differences of reinforcement learning (RL) solutions between the finite-horizon and infinite-horizon cases are compared. Finally, the effectiveness of the proposed algorithm is demonstrated by a numerical example.
Read the full abstract
Solar and Stellar Astrophysics
Systematic and Statistical Properties of Prominence Eruptions on the M-dwarf YZ CMi
M-dwarfs produce frequent flares, and their associated mass ejections are expected to significantly affect the habitability of close-in exoplanets. Recent spectroscopic observations have revealed several prominence eruptions-indicative of stellar mass ejections-on M-dwarfs through Doppler shifts of the H$\alpha$ line. However, systematic and statistical studies, particularly regarding their association with white-light flares, have been limited due to the lack of intensive and continuous simultaneous photometric and spectroscopic monitoring of the same target star. We conducted one month of continuous spectroscopic observations of the active M-dwarf YZ CMi using the 3.8-m Seimei telescope with an unprecedentedly high time cadence of $\sim$1 min, simultaneously with TESS. We detected four prominence eruptions, among which two events showed rapid, short-duration eruptions with velocities of $\sim$300-500 km s$^{-1}$ and durations of $\sim$5 min. Such short-duration events may have been missed in previous observations due to insufficient time cadence. We further performed a systematic analysis using 35 H$\alpha$ flares on YZ CMi observed simultaneously with TESS. Notably, most prominence eruptions (6 out of 7) were not associated with detectable white-light flares. This result suggests that most observed prominence eruptions on M-dwarfs may have occurred near the stellar limb, where white-light flares are difficult to detect, which may imply a potential observational bias in their detectability due to low contrast with the background emission. These first statistical constraints, together with the discovery of rapid, short-duration prominence eruptions, indicate that previous observations may have underestimated both the frequency and velocities of mass ejections on M-dwarfs due to observational biases and highlight the necessity of reassessing their impact on close-in exoplanets.
Read the full abstract
Robotics
CanonNav: Disentangling Navigation Behavior from Camera Geometry in Cross-Platform Visual Navigation
While visual navigation has advanced through imitation learning from cross-platform demonstrations, fully leveraging such data remains challenging. First, directly learning from image-trajectory pairs entangles navigation behavior with platform-dependent camera geometry. This hinders consistent learning by forcing the policy to implicitly infer camera geometry from visual observations, an inherently ill-posed problem. Second, imitation learning from demonstrated trajectories captures the expert's chosen motion but leaves the intermediate decisions underlying that motion implicit. To address these issues, we propose CanonNav, a visual navigation framework that disentangles navigation behavior from camera geometry and incorporates complementary planning supervision into learning from cross-platform demonstrations. CanonNav introduces camera geometry canonicalization, which transforms visual observations and trajectories into a camera-consistent representation space. Building on this representation, we derive safety and local-progress supervision using pseudo-labels from an offline traversability estimator. Safety supervision penalizes unsafe trajectories, while local-progress supervision guides where the robot should advance. Experiments across diverse camera configurations and environments show that, despite using only RGB at inference, CanonNav consistently outperforms RGB-based baselines and even surpasses RGB-D-based methods in challenging scenarios.
Read the full abstract
Computation and Language
PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback
Recent efforts have aimed to automate scientific diagram generation from paper content (Lin et al., 2026; Zhu et al., 2026a). However, fully satisfying an author's visual and communicative preferences in a single turn is challenging: in our formative user study (N = 14), all participants requested further revisions after viewing an initial draft, and 86% of them rated the refined diagrams as more satisfactory. Despite the clear demand, the multi-turn workflow remains largely underexplored. To bridge this gap, we present MTPaperBananaBench, a benchmark for multi-turn diagram generation containing 292 images annotated with 3,518 user requirements. To reduce expensive human studies and enable scalable benchmarking, we construct a user simulator that, at each turn, identifies unsatisfied requirements and converts k of them into natural language feedback. Evaluating both requirement satisfaction and overall diagram quality reveals two key failure modes shared across baseline multiturn systems: (1) quality drift, where diagram quality progressively declines over turns, and (2) forgetting, where previously implemented features are lost in subsequent turns. To address these issues, we introduce PaperBanana-Interact, a multi-agent system that refines diagrams via an internal critique-and-refine loop. PaperBanana-Interact consistently improves rather than degrades diagram quality across turns, outperforming baselines by 11.9-18.6 points in quality score and reducing forgetting by 3.7-6.2 points.
Read the full abstract
High Energy Physics (Phenomenology)
Spin-dependent fermion potentials from mixed tensor couplings of massive spin-1 and spin-2 bosons
Searches for weak spin-dependent forces are commonly interpreted in terms of a basis of sixteen rotationally invariant two-fermion potentials, including potentials which violate parity (P) and time-reversal (T) invariance. We derive finite-range coordinate-space potentials generated by a massive spin-1 boson with vector, axial-vector, tensor, and pseudotensor couplings to Dirac fermions. In addition to the familiar vector–vector, vector–axial-vector, and axial-vector–axial-vector interactions, we obtain the mixed vector–tensor, vector–pseudotensor, axial-vector–tensor, and axial-vector–pseudotensor potentials, together with tensor–tensor, tensor–pseudotensor, and pseudotensor–pseudotensor terms. We retain the contact terms needed in atomic-scale applications and give compact expressions that include both orderings of inequivalent fermion vertices. We then extend the analysis to a massive spin-2 mediator described by a symmetric Fierz–Pauli field. Besides the conventional coupling to the conserved fermion energy–momentum tensor, we consider a symmetric axial-tensor current. Its nonconservation for massive fermions makes the longitudinal spin-2 helicities contribute to axial-tensor–axial-tensor exchange. The leading minimal spin-2 interactions are either P,T even or P odd and T even; in particular, they do not generate a T-odd potential. We map the resulting interactions onto the sixteen-potential Dobrescu–Mocioiu basis and use this mapping to translate existing experimental constraints into numerical limits on spin-1 and spin-2 coupling products in the small- and large-mediator-mass regimes, together with representative limits at finite mediator masses. The derived relations between the boson-exchange coupling constants and the coefficients of the basis potentials also allow published exclusion curves to be rescaled to arbitrary mediator masses.
Read the full abstract
Statistical Computation
GPU-Parallelization of Markov Chain Pool Decoding with Unbiased MCMC
Markov chain pool decoding (MCPD) devised by Knill et al. (1996) identifies likely positive clones from noisy pooled-test results. The standard MCPD estimates clone-wise posterior probabilities using Gibbs sampling, but it may allocate excessive computational effort to low-scoring clones. This paper focuses on parallelizing MCPD on GPU architectures. Whereas the standard MCPD employs systematic-scan updates, we propose a score-weighted update scheme that updates high-scoring clones more frequently. We prove that the stationary distribution of the proposed Markov chain coincides with the target posterior distribution. To enable efficient GPU parallelization, we further incorporate the unbiased MCMC framework of Jacob et al. (2020) and employ a slot-refilling technique based on the arguments by Glynn and Heidelberger (1991) about the coupling of Markov chains. Experiments involving 1,298 clones, 97 pools, and three true positives demonstrate improved recovery compared with uniform decoders, while maintaining high overlap under high-noise conditions.
Read the full abstract
Computational Complexity
Unrestricted Boolean Multiplicative Complexity of Four-Term Binary Polynomial Multiplication: Rational Places, Hasse Jets, and the Failure of Nonlinear Feedback
Classical lower bounds show that multiplying two degree-three polynomials over $\mathbb F_2$ requires nine scalar products in bilinear or quadratic models. They do not settle unrestricted Boolean multiplicative complexity: an XOR–AND circuit may reuse nonlinear intermediate wires, and Boolean equality is taken modulo $x_i^2=x_i$, so a multiplication can lower algebraic degree. Let $\operatorname{Mul}_4:\mathbb F_2^8\to\mathbb F_2^7$ output the seven coefficients of the product of two four-term binary polynomials. We prove that its unrestricted XOR–AND multiplicative complexity is exactly nine. This resolves, for a natural vector-valued quadratic function, the Boyar–Find question of whether a quadratic-circuit lower bound can persist against unrestricted nonlinear reuse. The proof is structural rather than exhaustive. A useful purely quadratic prefix is forced onto the three rational places of $\mathbb P^1(\mathbb F_2)$. In a hypothetical eight-AND circuit, the unique non-useful gate must carry a cubic high part. Any useful continuation then forces a rational tangent and exposes a first Hasse jet, while exterior jet separation together with Boolean idempotence prevents the same defect from exposing the second Hasse jet. The required useful suffix therefore cannot exist. A complete Lean 4 formalization verifies the Boolean-ANF semantics, the unrestricted circuit model, and the exact theorem; it uses no project-specific axiom or native decision procedure. The same zero-defect flag argument gives multiplicative complexity six for three-term multiplication, and the method isolates the multi-defect obstruction for five terms.
Read the full abstract
Robotics
Motus2: A Self-Evolving General World Model for Dexterous Manipulation
General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in building such agents, yet existing models typically append an action output head to a world simulator, without coupling them into a closed decision-and-learning loop for policy improvement. We present Motus2, a self-evolving general world model for dexterous manipulation. Motus2 advances world modeling through model scaling and data scaling. For model scaling, a single model with shared weights exposes three control interfaces: a policy (world-action model), a simulator (action-conditioned world model), and an evaluator (value model). The policy proposes candidate action chunks, the simulator predicts their visual consequences, and the evaluator assesses the predicted outcomes. Their coupling forms a closed decision-and-learning loop for policy improvement. This formulation uses curated expert demonstrations for action learning, while failed and suboptimal interactions provide valuable evidence for dynamics modeling and value learning. For data scaling, Motus2 progresses from large-scale monocular egocentric data to synchronized stereo egocentric data, followed by robot-domain adaptation with robot trajectories and supplementary human-robot alignment data. Motus2 further studies global-autoregressive and hybrid-memory extensions of its sliding-window context, adds tactile feedback for contact-aware control, and is instantiated on a fully biomimetic platform with stereo vision, dual arms, dual dexterous hands, and tactile sensing. Together, egocentric data scaling and closed-loop general world model scaling provide a general path toward self-evolving dexterous manipulation.
Read the full abstract
Algebraic Geometry
A Note On the moduli space of rank two vector bundles on Hirzebruch surfaces
The aim of this paper is to study the Segre invariant for rank $2$ vector bundles on Hirzebruch surfaces $\mathbb{F}_e$, $e \geq 0$. We give necessary conditions in order to determine what numbers can appear as the Segre Invariant of a rank $2$ vector bundle on $\mathbb{F}_e$ with fixed Chern classes. We compute a bound of the dimensions of the strata whenever are non-empty. Finally, we present applications to Brill-Noether Theory and describe differences between moduli spaces under change of polarization for rank $2$ vector bundles on $\mathbb{F}_e$.
Read the full abstract
Artificial Intelligence
LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information
Knowledge graph completion requires models to use both textual descriptions and relational structure. Existing LLM-based methods either encode KG structure as discrete tokens or refine a restricted set of candidate entities, and these two directions have largely been studied separately. We propose CoSC for LLM-based KGC, which combines discrete structural coding with similar entity information. Specifically, an LLM generates an initial candidate entity ranking from discrete structural codes, after which information from entities with structures similar to that of the query entity refines the ranking. Experiments on FB15k-237 show that CoSC outperforms existing baselines on MRR and Hits@10 while remaining competitive on Hits@1.
Read the full abstract
Artificial Intelligence
CoLa-ICD: A Knowledge-Enhanced Framework for Long-Tail Automated Medical Coding
Automatic medical coding assigns ICD codes to clinical notes, but it remains challenging due to long documents, imbalanced label distributions, and diverse terms. These challenges are especially severe for rare codes, which have limited training instances and are easily confused with semantically similar labels. We introduce CoLa-ICD, a knowledge-enhanced framework for long-tail prediction. CoLa-ICD enriches ICD labels with external terms, models dependencies among related codes, and learns stronger alignment between label semantics and clinical evidence for long-tail prediction. Experiments show that CoLa-ICD improves long-tail prediction with larger gains in larger and sparser label spaces and achieves state-of-the-art performance in AUC, F1, and P@k. Our code is available at https://github.com/youwillbethebest/Cola-ICD.
Read the full abstract
Computer Vision
Semantic-Spatial Discriminability Enhancement for Generalized Visual Grounding
Generalized Visual Grounding (GVG) task aims to localize targets in an image based on referring expressions, extends the classical visual grounding paradigm by integrating multi-target and non-target scenarios. Previous methods typically rely on global semantic matching or coarse-grained region interactions for localization, where the discriminative cues are primarily derived from sentence-level semantics or regional context. In complex multi-target scenarios, such approaches tend to confuse visually similar targets, making it difficult to establish stable instance-level decision boundaries. To address these limitations, this paper proposes a novel Semantic-Spatial Discriminability Enhancement (SSDE) framework for generalized visual grounding, which aims to enhance the discriminative ability on fine-grained semantics and spatial localization, improving both cross-modal understanding and instance-level grounding. Specifically, to enhance the semantic discriminability of query representations at the fine-grained level, we propose a Semantic Discriminability Enhancement (SeDE) module, which leverages spatially guided cross-attention to disentangle fine-grained target-relevant visual attributes and integrates them with the textual subject semantics. Furthermore, to strengthen the spatial discriminability of the referred targets, we introduce a Spatial Discriminability Enhancement (SpDE) module, which models an instance center density map to characterize the spatial distribution of targets, and explicitly constructs instance separation structures in the spatial domain by employing them as an auxiliary supervision signal. Extensive experiments show that SSDE achieves superior performance on ten datasets across both classic and generalized visual grounding tasks.
Read the full abstract
Analysis of PDEs
Strong Unique Continuation for Fractional Schrödinger Operators
We prove the strong unique continuation property for the fractional Schrödinger equation \[ (-\Delta)^s u=Vu \] with scaling-critical potentials $ V\in L^{\frac{n}{2s}}_{\mathrm{loc}}$ for all $0<s<1$. Our result constitutes the nonlocal counterpart to the classical Jerison–Kenig result for Schrödinger operators.
Read the full abstract
Neurons and Cognition
"More Is Different” in Neural Circuits: Algebraic Emergence of Effective Theories in Canonical Recurrent Motifs of Biological Neuronal Networks
Canonical neural circuit motifs are usually described functionally: divisive normalization rescales population activity by a pooled signal, and winner-take-all competition selects one pattern through recurrent excitation and shared inhibition. We represent them, and their compositions, algebraically as finite transformation systems and analyze the transition monoids generated by their input-conditioned updates, distinguishing structure already present in a generator from structure that appears only through composition, and, on a joint state space, structure inherited from one factor from structure that lives on a joint configuration. Individually aperiodic updates can generate non-aperiodic monoids. In the WTA, every frozen-drive generator collapses to fixed points, yet short input sequences create local cycles of winner-dependent inhibitory gating: globally dissipative dynamics with a reversible action. The strongest result arises in WTA-to-DN composition. The composed monoid then contains a genuinely composite local cycle in which normalization state and the winner's gating state change together, although every primitive generator is aperiodic. Holonomy analysis certifies this as a group component of the Krohn-Rhodes cascade rather than an incidental cycle, and finds most group-carrying image sets on joint configurations, whereas the uncoupled product has none. An exhaustive interface sweep shows that the composite cycle is a property of the coupling rather than of a chosen map. If motifs are building blocks of neural computation, composing them is a form of programming: one chooses primitives and interfaces so that the generated algebra has the intended repertoire. The transition monoid is that repertoire - what a primitive presents to any later construction. Recurrent circuits are compositional transformation systems; their algebra constrains what they can be programmed to compute.
Read the full abstract
Artificial Intelligence
Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration
Test-time prompt tuning (TPT) has emerged as a powerful paradigm, refining prompts for each test sample via entropy minimization (EM) over multiple augmented views. However, we identify a limitation in the standard EM-based adaptation: it inherently drives the model toward overconfident predictions disregarding sample-specific uncertainty, leading to significant calibration degradation. To address these limitations, we propose a new objective that replaces the conventional EM loss by aligning the original-view prediction with a target distribution derived from augmented views via cross-entropy, while adversarially incorporating the entropy of the target distribution to capture sample-specific uncertainty. Furthermore, to better construct this target distribution, we apply confidence-aware temperature scaling to each augmented-view prediction according to its confidence, sharpening confident predictions while softening uncertain ones. This formulation allows the model to increase confidence only when the target distribution is reliable, while preserving uncertainty when it reflects ambiguous or conflicting augmented-view predictions. Extensive experiments across diverse benchmarks demonstrate that our approach not only achieves state-of-the-art accuracy but also significantly improves model calibration.
Read the full abstract
Computation and Language
Quantifying and Mitigating Korean Jamo-Level Typographical Vulnerabilities in Large Language Models
Korean introduces an additional typographical perturbation level not captured by ordinary character-level edit models: because syllable blocks are internally composed of sub-character units called jamo, keyboard-level errors can occur within a syllable, either producing a valid but semantically altered character or exposing raw jamo on the surface. Both outcomes disrupt sub-word tokenization and are not reliably corrected by existing grammatical error correction pipelines, leaving LLMs directly exposed to corrupted inputs. To quantify this vulnerability, we apply five jamo-level perturbation types to the KMMLU benchmark and evaluate four language models, finding that accuracy declines monotonically with perturbation intensity and that parameter scaling does not confer robustness against intra-syllabic noise. We further show that typo-corrupted inputs induce a distinct shift in internal representations that is not reducible to ordinary answer incorrectness, and that a simple linear probe trained on these representations detects unseen perturbation types with high AUROC. Motivated by this signal, we propose Typo-Aware Chain-of-Thought (TACoT), which routes inputs to chain-of-thought inference only when the probe detects a likely typo, recovering a substantial portion of the CoT accuracy gain at a fraction of the inference cost.
Read the full abstract
Quantum Physics
SpiderLS: Leveraging Full ZX Reduction for Lattice Surgery Compilation
Lattice surgery compilation plays a central role in translating fault-tolerant quantum programs into efficient surface code realizations, where both spatial and temporal resources directly determine the cost of execution. Recent work has demonstrated the benefits of using ZX-diagrams as an intermediate representation for lattice surgery compilation, enabling semantics-preserving transformations that reduce spacetime cost. However, existing compilation restricts ZX reduction to preserve diagram structures that can be directly embedded as lattice surgery junctions. We present SpiderLS, which extends prior approach by leveraging full ZX reduction. To translate the resulting diagram into executable lattice surgery operations, SpiderLS applies a sequence of compiler passes that derives an execution order, generates target code by grouping compatible interactions into multi-target operations, and lowers the target code to Pauli-product measurements. The resulting explicit patch and Pauli-boundary requirements guide logical scheduling and structure-aware spacetime routing. Across representative algorithmic and random workloads, SpiderLS achieves average reductions of 49.2% in spacetime volume and 99.8% in compilation time compared with the prior ZX-based compiler.
Read the full abstract
Databases
ELASTIC: Trajectory-Based Synchronization of Event and Tracking Data in Soccer
Combining event and tracking data is fundamental to modern soccer analytics, yet the two sources are rarely well aligned: event timestamps recorded by human annotators often miss the true moment of the action, distorting the spatiotemporal context that downstream models rely on. Existing synchronization methods depend on noisy human-annotated event locations and fail to detect ball receptions, obscuring when each player gains ball possession. To address these limitations, we propose ELASTIC (Event-Location-AgnoSTIC synchronizer), a framework that infers the start and end timestamps of events solely from player and ball trajectories, without relying on annotated event locations. To recover ball receptions, ELASTIC enriches the event sequence by inserting virtual termination events between consecutive events, so that the end of each event is detected jointly with its start. It then extracts a sparse set of candidate frames where ball touches are physically plausible, and aligns the termination-inserted event sequence with the candidate-frame sequence using an extended Needleman-Wunsch algorithm. For reproducible evaluation, we construct a publicly available benchmark by annotating ground-truth timestamps on the Sportec Open DFL Dataset, on which ELASTIC substantially outperforms existing methods. Through downstream task evaluation, we further show that improved synchronization translates into measurable gains in soccer analytics. The source code and benchmark are available at https://github.com/hyunsungkim-ds/elastic.git.
Read the full abstract
Artificial Intelligence
LaMoC: Loss-Aware Modular Compression for LLMs
Modular compression has enabled considerable parameter reduction in LLMs while preserving strong language understanding and downstream task accuracy. However, existing joint modular compression methods primarily rely on activation statistics, leaving loss-sensitivity information and its module-level characterization underexplored. We investigate addressing this gap with LaMoC, a loss-aware modular compression methodology that blends activation and Empirical Fisher statistics through gradient-error alignment. LaMoC improves joint compression by selecting compression statistics that better align local module reconstruction error with the downstream loss. Our contributions are three-fold: (1) We characterize the Empirical Fisher as a module-level loss-aware proxy that can be blended with the activation statistics required for compression. (2) We reformulate joint modular compression as a two-tiered optimization problem that minimizes module reconstruction error while tuning the activation and gradient information blending rate. (3) We implement an empirically driven methodology with statistical validation to solve the resulting compression problem. We evaluate LaMoC across four model families spanning eight models. On the 4-8B models, LaMoC achieves an average 2.5% reduction in perplexity and a 1% relative improvement in task accuracy over state-of-the-art modular compression methods.
Read the full abstract
Computational Engineering
Redefining Stablecoins from Nominal to Real Value: A Maximum Likelihood Approach
Stablecoins, typically pegged to fiat currencies, cannot achieve true stability because they inherit fluctuations in the underlying unit of account. To overcome this limitation, we introduce a stablecoin pegged to the Maximum Likelihood Value (MLV), a newly defined unit of account derived as the most probable configuration of latent real-value movements that explains observed nominal-value (price) changes. Grounded in inferential statistics and modern portfolio theory, MLV represents the most stable unit of account, as it enforces a zero real return on the minimum-variance portfolio. Empirical results confirm the operational viability of an MLV-pegged stablecoin: MLV can be computed in real time from 500 asset price series and improves annualized returns and Sharpe ratios while substantially reducing turnover in portfolio optimization.
Read the full abstract
Computation and Language
The Differential Reasoning Router: Operationalizing Cost-Aware LLM Annotation in E-commerce
Large Language Models (LLMs) are increasingly used to annotate structured product data in e-commerce, but early deployment often begins as a cold-start problem: only limited pre-launch labels are available, the value of expensive reasoning is unknown, and human review is needed before the system can be trusted at scale. This challenge is especially common in rule-based annotation workflows, where each item must satisfy multiple business rules and both model errors and ambiguous rule boundaries affect final decisions. We introduce the Differential Reasoning Router (DRR), a cost-aware framework for cold-start LLM annotation that jointly optimizes model selection and human escalation. Rather than treating a reasoning model as a default fallback, DRR estimates separate success probabilities for a direct model and a reasoning model at both the sample and business-rule levels, enabling adaptive routing: easy cases are handled directly, reasoning is reserved for cases where it is expected to improve the decision, and likely double-failure or rule-disagreement cases are escalated to human annotators. The resulting labels provide targeted ground truth for prompt engineering, supervised fine-tuning, calibration, and rule refinement, enabling a gradual shift from human-heavy cold-start annotation toward high-confidence automated routing. In a production e-commerce workflow, DRR reaches accuracy parity with the strongest confidence-based router while achieving more than 60% reasoning-token cost savings.
Read the full abstract
Machine Learning (Statistics)
Fairness in multi-class multi-group classification problems via contextial coherent risk measures
We propose a new design of fair classifiers for multi-class classification problems in the presence of vector-valued sensitive attributes. In that scenario each sensitive attribute has multiple values and forms several groups relevant to the fairness consideration. Naturally those groups are overlapping and one should also analyze the interaction of factors. Additionally, the decision makers aided by the classification should not violate individual rights at the expense of satisfying fairness metrics at the group level. We propose an approach using the theory and methods of coherent measures of risk aiming at resolving the fairness challenges. Further, we propose a specialized numerical method for solving the resulting optimization problem. The method scales well with the increase of the number of observations. Additionally, we note that the obtained classifier is robust with respect to corrupted data or to situation when data is scarce. We demonstrate the advantages of the proposed framework in comparison to the support-vector machine framework and other methods handling fairness.
Read the full abstract
Robotics
Optimized Modular Design and Development of a Tilt-Rotor Bicopter Drone
Hybrid systems like tilt-rotor bicopter drones combine the beneficial characteristics of both fixed-wing and rotary-wing technology, enabling long endurance and VTOL capability. However, such drones also require an optimum design to ensure both static and dynamic stability. The modular design of a traditional bicopter is developed in this paper based on extensive analysis and in-depth structural and aerodynamic simulations. The structural analysis has been performed to ensure that the aircraft's structure withstands the stresses encountered during different flight modes. Controlling the relative positions of the Center of Gravity (CG) and Neutral Point (NP) is an essential aspect of the design, ensuring stability during hover and positive stability during forward flight. The thrust and power analyses have been conducted to assess the flight performance and endurance. After analysis, the drone has been developed, and flight tests with a basic flight controller were conducted to validate the performance metrics obtained in the simulation.