Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (quant-ph) 2026-06-25

How to improve the accuracy of semiclassical and quasiclassical dynamics with and without generalized quantum master equations

arXiv:2603.04563v2 Announce Type: replace-cross Abstract: Semi- and quasi-classical (SC) theories can handle arbitrary interatomic interactions and are thus well-suited to predict quantum dynamics in condensed phases that encode energy and charge transport, spectroscopic responses, and chemical reactivity. However, SC theories can be computationally expensive and inaccurate. When combined with generalized quantum master equations (GQMEs), the resulting SC-GQMEs have been observed to enhance the efficiency and accuracy of SC dynamics. Yet, while the mechanism responsible for improved efficiency is clear, the underlying improved accuracy remains elusive. What is worse, SC-GQMEs can yield unphysical dynamics in challenging parameter regimes – a shortcoming that might be avoided if the mechanism of accuracy improvement were understood. Here, we uncover this mechanism. We leverage short-time analyses to prove that exact, "left-handed" time-derivatives delay the onset of SC inaccuracy, and show that their numerical integration yields dynamics with improved accuracy, even without the GQME. We find, however, that these derivatives are a double-edged sword: while offering greater short-time accuracy, they become unphysical in challenging parameter regimes. Because short-lived memory kernels can leverage short-time accuracy while circumventing long-time instability, we develop a protocol to unambiguously determine the memory kernel cutoff, even in challenging regimes where previous treatments had failed. Our insights into accuracy improvement and kernel cutoff protocol can be expected to apply to complex systems that go beyond simple models.

02.
arXiv (CS.AI) 2026-06-17

Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategies

作者:

arXiv:2502.17518v3 Announce Type: replace-cross Abstract: This paper presents a comprehensive study on the use of ensemble Reinforcement Learning (RL) models in financial trading strategies, leveraging classifier models to enhance performance. By combining RL algorithms such as A2C, PPO, and SAC with traditional classifiers like Support Vector Machines (SVM), Decision Trees, and Logistic Regression, we investigate how different classifier groups can be integrated to improve risk-return trade-offs. The study evaluates the effectiveness of various ensemble methods, comparing them with individual RL models across key financial metrics, including Cumulative Returns, Sharpe Ratios (SR), Calmar Ratios, and Maximum Drawdown (MDD). Our original experimental results demonstrate that ensemble methods often outperform base models in terms of risk-adjusted returns, providing better management of drawdowns and overall stability. However, both the original analysis and the additional reproduction reported in this version show that ensemble performance is sensitive to the choice of variance threshold \(\tau\), classifier group, RL-agent pair, and market universe. The reproduction evidence strengthens the conclusion that classifier-assisted ensemble selection can improve robustness, while also clarifying that the advantage is conditional rather than automatic across all datasets. This study emphasizes the value of combining RL with classifiers for adaptive decision-making, with implications for financial trading, robotics, and other dynamic environments.

03.
arXiv (CS.LG) 2026-06-19

Minimal Filling Architectures of Polynomial Neural Networks: Counterexamples, Frontier Search, and Defects

arXiv:2605.09609v2 Announce Type: replace Abstract: We provide counterexamples to the unimodal minimal filling architecture conjecture for polynomial neural networks (PNNs) with power activation functions. Fixing the input and output widths, the conjecture states that any minimal filling architecture has unimodal widths for the hidden layers. We found counterexamples via a frontier search, recursive dimension bounds on neurovarieties, and symbolic computation. Notably, several subarchitectures of our main example exhibit large defect, in contrast with the predominantly small-defect behavior observed in prior literature.

04.
arXiv (CS.CL) 2026-06-18

PragReST: Self-Reinforcing Counterfactual Reasoning for Pragmatic Language Understanding

Natural language understanding often depends on meanings that are implied rather than explicitly stated, requiring pragmatic reasoning. Despite strong performance on math and logical reasoning, large language models (LLMs) still struggle with making pragmatic inferences, often choosing literal interpretations. To improve LLM pragmatic reasoning, we introduce PragReST, a self-supervised framework that constructs pragmatic QA data, generates counterfactual reasoning traces, and trains models to internalize them through supervised fine-tuning and reinforcement learning, without human-labeled training data or distillation from a stronger teacher. Across four pragmatic benchmarks (PragMega, Ludwig, MetoQA, and AltPrag), PragReST improves over backbone models, task-specific pragmatic tuning baselines, and non-counterfactual variants of the same pipeline. On accuracy-based benchmarks, PragReST improves over the instruct backbone by 5.37 and 5.50% (absolute) for Qwen3-8B and Qwen3-14B, respectively. Our error analysis and ablations underscore the importance of counterfactual reasoning: PragReST primarily reduces errors caused by failures to contrast observed utterances with plausible alternatives, and removing counterfactual reasoning substantially reduces performance. Moreover, our training preserves out-of-domain performance on general-knowledge and mathematical reasoning benchmarks.

05.
arXiv (math.PR) 2026-06-17

How long does it take to train an Elephant Random Walk

作者:

arXiv:2509.15049v2 Announce Type: replace Abstract: We study how conditioning on the first $k$ steps, which we think of as training, affects the long-term behavior of the Elephant Random Walk. When the elephant is conditioned to be at position $k$ at time $k$, the first return time to the origin scales as $k^{(4-4p)/(3-4p)}$ in the diffusive regime, and grows exponentially in the critical regime. We loosely interpret this as a measurement of the rate at which the elephant forgets its training.

06.
arXiv (quant-ph) 2026-06-19

$K$-Theoretic Obstructions to Linearizing QCA Representations

arXiv:2606.19657v1 Announce Type: cross Abstract: Projective representations arise naturally in physics and representation theory, and determining whether they can be linearized has been a fundamental problem. In this work, we study the analogous problem for quantum cellular automata (QCA) representations, which incorporate locality constraints imposed by a metric space $X$. Over an arbitrary field $\mathbb{F}$, we develop an obstruction theory for the linearization of QCA representations, using the algebraic $K$-theory spectrum of QCA constructed in previous work of the authors. The resulting obstructions are governed by the homotopy type of the QCA spaces, from which we extract universal obstruction classes to linearization. In the complex algebraic and unitary case, we also fully compute the homotopy types of the QCA spaces over a point, a line, and a plane.

07.
arXiv (quant-ph) 2026-06-19

Complexity of detecting large coefficients in the Pauli basis

arXiv:2606.19545v1 Announce Type: new Abstract: We study the problem of deciding, given a mechanism to prepare a quantum state $\rho$ and a value $\varepsilon > 0$, whether there is some non-identity Pauli matrix $P$ such that $|Tr(P \rho)| \geq \varepsilon$. We consider that the state $\rho$ is described as the result of tracing out some of the qubits of a pure state prepared by a circuit $C$, and we assume the promise that either there is a Pauli matrix satisfying the stated condition or, instead, that for all non-identity Pauli matrices $P$ it is the case that $|Tr(P\rho)|\leq \varepsilon/2$. The problem is in $QCMA$, and we prove that if it belongs to $BQP$ then $NP \subseteq BQP$. The result is obtained through a reduction from the minimum-weight code problem, and it holds even when $\rho$ is assumed to be a pure state (i.e. when no qubits are discarded) and $\varepsilon$ is constant. This resolves an open question regarding the existence of efficient tomographic procedures to find the largest coefficients of a quantum state in the Pauli basis: namely, they do not exist under the standard hypothesis $NP \nsubseteq BQP$.

08.
arXiv (CS.CL) 2026-06-16

The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages

Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, forming distinct model lineages. It remains unclear whether a fundamental behavioral link exists between the foundational LLMs and downstream variants. We investigate this question by quantifying head-level context-truthfulness scores. Across diverse LLM and MLLM lineages, including Vicuna-, Qwen2.5-, LLaMA2-, and Mistral-based models, we find that Truth Scores are strongly preserved within model families, even after instruction tuning or multimodal adaptation. We further show that this inheritance is consistent with attention-head weight preservation, and that context-truthful heads attend to query-relevant evidence. Building on this finding, we propose TruthProbe, a soft-gating strategy that amplifies context-truthful heads while preserving other head contributions. TruthProbe improves contextual truthfulness on HaluEval and reduces multimodal hallucination on POPE and CHAIR, with base-LLM Truth Scores transferring effectively to their fine-tuned LLM and MLLM descendants. Code is available at https://github.com/miso-choi/TruthProbe.

09.
arXiv (CS.CL) 2026-06-16

FinBalance: A Multi-Document Accounting Reconciliation Benchmark

Existing financial-NLP benchmarks mostly evaluate prepared artifacts such as filings, tables, or extracted values. Real accounting begins earlier: source documents must be reconciled into cited journal entries, aggregated into a balance sheet, and checked for contradictions. We introduce FinBalance, a multi-document accounting reconciliation benchmark built from source-document bundles across eight industries, three period types, and five difficulty levels. Human-authored business scenarios, accounting policies, tax/FX treatments, document schemas, distractors, and inconsistency templates are composed by a deterministic generator whose ledger produces journal entries,balance sheets, and 23 inconsistency-code labels. On a 710-record evaluation split, six contemporary LLMs reach at most 46% exact final-balance-sheet accuracy. Four models show a 26-41 pp gap between BS_exact, the model's reported balance sheet, and BS_recon, the balance sheet obtained by replaying its entries through our ledger. Models often recover numerically plausible entries but fail to bind them to supporting documents and aggregate them consistently. Citation-pressure prompting barely changes document-linking errors, while ledger-feedback ablations substantially improve reported balance sheets and expose inconsistency-detection trade-offs. Expert finance reviewers validate the benchmark design and labels.

10.
arXiv (quant-ph) 2026-06-12

Schrödinger Symmetry in Spherically-symmetric Static Mini-superspaces with Matter Fields

arXiv:2512.13651v3 Announce Type: replace-cross Abstract: Schr\"{o}dinger symmetry has been shown to emerge in a ``fluid limit" from the full superspace to several mini-superspace models. To investigate one aspect of the robustness of this emergent symmetry, we consider two spherically-symmetric static mini-superspace models with matter fields at the classical level: (i) a Maxwell field with a cosmological constant and (ii) $n$ massless scalar fields. By developing a method based on canonical transformations, we demonstrate that for model (i), 3D Schrödinger symmetry emerges, and the solution is the (anti-)de Sitter Reissner-Nordström spacetime, and for model (ii), $(2+n)$D Schrödinger symmetry appears, and the solution is a generalized Janis-Newman-Winicour spacetime and its ``interior", a Kantowski-Sachs type closed universe. Furthermore, for the vacuum model, we find that 2D Schrödinger symmetry holds with different lapse functions and mini-superspace coordinates, suggesting the potential, yet unconfirmed, covariance of the symmetry. Finally, we propose a physical interpretation of the symmetry under the Hamiltonian constraint $H$: symmetry generators commuting with $H$ map a solution to another one, while those non-commuting with $H$ generate a new theory with the Schrödinger symmetry and the transformed configuration is a solution to the new theory. These results reinforce the robustness of the emergent Schrödinger symmetry and open new frontiers for exploring dynamics of matter and gravity.

11.
arXiv (CS.LG) 2026-06-16

The Algebra of Units: From Buckingham's Pi-grec Theorem to Latent-Variable Learning

arXiv:2606.16737v1 Announce Type: cross Abstract: Engineers often measure many quantities-speed, pressure, temperature, length-expressed in different physical units. The Buckingham Pi-grec theorem states that these variables can always be combined into a smaller set of dimensionless numbers whose values fully determine the system's behaviour. Identifying the appropriate dimensionless groups has traditionally required expert knowledge and physical insight. This paper shows that they can instead be discovered automatically from data, without prior knowledge of the governing physics. The key observation is that, after logarithmic transformation, measurements collected under different scalings of the same system lie on a low-dimensional manifold whose geometry is determined by the underlying dimensionless groups. Singular value decomposition (SVD) identifies this manifold directly from data. A subsequent search over integer-exponent combinations recovers candidate dimensionless quantities, while a repeating-variable filter retains only those constructed from the machine's characteristic scales. This procedure recovers familiar engineering groups, including the flow coefficient, head coefficient, and Mach number, while excluding equivalent but less interpretable alternatives. The method is demonstrated on a synthetic compressor dataset containing 16,000 measurements. Starting from raw dimensional variables and no physics input, it recovers the correct dimensionless groups to numerical precision and reproduces the compressor performance map with an error below 0.01%. More broadly, the work reveals a close connection between classical dimensional analysis and modern data-driven learning. Both rely on the same underlying algebraic structure, suggesting new approaches for building physical models that are simultaneously interpretable, scalable, and data-efficient.

12.
arXiv (quant-ph) 2026-06-12

Toward Entanglement Bootstrap for Conformal Field Theory in Any Dimension

arXiv:2606.12540v1 Announce Type: cross Abstract: Given a quantum critical wavefunction in any dimension, we propose a reconstructed Hamiltonian, analogous to the ones previously found for 1+1d CFT and for 2+1d bosonic liquid topologically-ordered states. We test numerically that, for known regularized approximate CFT groundstates (on the icosahedron and the fuzzy sphere), (1) they are close to the groundstate of their reconstructed Hamiltonian, and (2) the spectrum of their reconstructed Hamiltonian on the unit sphere has CFT properties (integer spacing of descendants) and matches known low-lying energies. We show that this provides an automated method to improve the finite-size effects in a fixed Hilbert space.

13.
arXiv (CS.AI) 2026-06-12

When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference

arXiv:2606.08098v2 Announce Type: replace Abstract: Majority voting over sampled answers is the dominant unsupervised aggregator for multi-sample LLM inference. In this paper, we show a delegation-based aggregator (Propagational Proxy Voting, PPV; Sakai et al., 2025) yields an unsupervised consensus rule that beats majority on MMLU-Pro by +1.5 pp overall and +2.24 pp on the non-trivial subset (paired McNemar p ~ 1.0e-14, n = 8,099). Majority discards two signals that every sample carries: within-group letter entropy and between-group reasoning geometry. PPV exposes per-voter levers that consume exactly these two signals: When (how much weight a voter keeps on its own pick) and Whom (how it splits the remainder across peers). We drive When with letter entropy and Whom with per-question-centered embedding cosine. Our method needs no gold labels and no auxiliary training: per-question, we partition 128 sampled generations into 16 groups, compute each group's letter-level semantic entropy and reasoning embedding centroid, and feed both into a stochastic delegation matrix whose stationary distribution selects the consensus answer. We walk through an example in which PPV overturns a clear 10-6 majority for the wrong letter: the 10-voter majority cluster is geometrically incoherent (mean within-cluster cosine -0.02) while the 6-voter minority is tight (+0.26), so propagated delegation mass concentrates on the minority's answer even though entropy alone would keep the majority ahead. We further report delegation strategies with negative results that constrain the design space for unsupervised LLM aggregation. No within-question ensemble of confidence modes closes the oracle gap.

14.
arXiv (CS.AI) 2026-06-16

InvDesMobility: a reliability-gated first-principles feedback framework for closed-loop materials discovery

arXiv:2606.16133v1 Announce Type: cross Abstract: Inverse materials design starts from target functionality and searches for structures that can realize it. Its value in closed-loop discovery depends not only on prediction performance, but also on whether expensive first-principles results are independently validated, provenance-recorded, and admitted as feedback only when evidence is sufficient. This is especially important for composite properties such as carrier mobility, where a final scalar value hides intermediate quantities, fit quality, convergence history, and workflow assumptions. Here we present InvDesMobility, a reliability-gated first-principles feedback framework that integrates multi-agent automated DFT, evidence stratification, generative structure proposal, acquisition ranking, and auditable release. Using 516 2DMatPedia-derived candidates, the workflow produced 280 QC-passed materials and 573 retained carrier-direction seed channels after channel-level reliability gating. These records were split into two feedback objects: relaxed structures updated the generative model, while retained mobility channels trained the acquisition model and set validation priority. Over multiple iterations, InvDesMobility screened 2.4 x 10^6 structures, submitted 102 candidates for DFT validation, and retained 86 reliability-gated generated channels across 41 formulas. Overall, the main contribution is not a fixed list of high-mobility materials, but a transferable feedback contract that makes closed-loop inverse design both useful and auditable when learning from expensive calculated properties. All source data, retained feedback records, and workflows are available at https://github.com/DreamLufei/invDesMobility, with an accompanying evidence website at https://dreamlufei.github.io/invDesMobility/.

15.
arXiv (CS.AI) 2026-06-17

Distributed General-Purpose Agent Networks: Architecture, Key Mechanisms, and Prototypes

arXiv:2606.17368v1 Announce Type: new Abstract: Large language models have accelerated the transition from passive conversational assistants to autonomous agents that can understand goals, plan actions, invoke tools, and execute multi-step tasks. Yet the capability of a single agent remains constrained by its local data, tool permissions, runtime environment, and governance boundary. This paper studies distributed general-purpose agent networks: open peer-to-peer networks in which heterogeneous agents deployed on personal devices, edge nodes, or autonomous computing environments can discover one another, establish trust, negotiate cooperation rules, and execute open-ended tasks. We argue that such networks cannot be obtained by simply combining existing peer-to-peer overlays with conventional multi-agent systems. Unlike traditional P2P networks, agent networks must propagate semantic declarations about intentions, capabilities, states, and cooperation constraints. We therefore propose a layered architecture centered on a protocol adaptation layer that connects upper-level task semantics with lower-level network operations. Based on this architecture, the paper identifies three core mechanism problems: semantic announcement propagation for collaborator discovery, verifiable identity and multi-topic reputation for cooperation governance, and semantic-gradient mechanism design for open task execution. For each problem, we present a technical route, including bodyless gossip with sequential logs, BAID-based identity binding with MG-EigenTrust reputation, and a Stackelberg-style mechanism-generation loop driven by semantic attribution feedback. We further report prototype overhead results for BAID-style tiered verification and mechanism-level simulations of MG-EigenTrust under cross-topic disguise-collusion attacks. The resulting framework provides a system-level foundation for open, trustworthy, and scalable agent collaboration.

16.
arXiv (CS.AI) 2026-06-16

AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems

arXiv:2606.15834v1 Announce Type: new Abstract: The computer systems community has recently seen growing interest in AI-driven system evolution, where AI agents iteratively rewrite systems. Frameworks such as AdaEvolve and Engram report 12-60% score improvements over human-designed algorithms. While these results are promising, there are practical concerns if these AI-evolved programs can perform worse on unseen workloads and exhibit scalability regressions. Given the speed and scale of AI-generated code, we need automated mechanisms to uncover such identify hidden weaknesses in AI-evolved systems programs. To this end, we develop AIChilles that takes as input a baseline program $P$ and an AI-evolved program $P'$, AIChilles searches for valid workloads where $P'$ regresses relative to $P$ in correctness, runtime, memory usage, or output quality. To tackle the diversity in system applications, weakness types and potential bugs, AIChilles combines deterministic workload-parameter extraction, agent-based constraint inference, differential oracles, and code-frequency coverage to discover diverse failures. Across five system applications and 30 AI-evolved programs, AIChilles finds 49 distinct hidden weaknesses. We also show that explicitly including AIChilles in the AI-driven development lifecycle can mitigate several of these weaknesses.

17.
arXiv (CS.CV) 2026-06-16

Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers

Though Vision Transformers (ViTs) have become the dominant backbone in many computer vision tasks, due to permutation equivariance, their attention mechanism lacks explicit spatial inductive biases. This become particularly important in two settings: when model capacity is small or training data is limited. Inspired by the attention masking strategies in Linear Transformers and the scanning patterns of Vision SSMs, we introduce VIOLIN, a lightweight masked attention mechanism that encodes spatial structure within attention via Space Filling Curves (SFCs) with less than 0.0015% extra parameters and negligible computational overhead. VIOLIN scans the image using multiple SFCs to construct curve-specific decay masks, which are then combined and multiplied with the attention matrix. Across a wide range of evaluations, VIOLIN consistently improves performance. In limited data regimes such as fine-tuning on VTAB-1K, it boosts accuracy across all task groups and by up to 8.7% on the tasks where spatial information is essential. It can be combined with parameter-efficient fine-tuning methods such as LoRA to further increase the performance. Beyond fine-tuning, VIOLIN improves various small scale ViT architectures (e.g., DeiT, DINO) during pretraining on ImageNet-1K. Additionally, on pixel-level CIFAR-100 training, a task that is highly dependent on location information, VIOLIN increases accuracy by up to 7.2%. Overall, VIOLIN provides a computationally efficient yet effective way to inject spatial inductive bias into ViTs, especially benefiting small models and limited data settings.

18.
arXiv (quant-ph) 2026-06-16

The Distribution Postulate in Algorithmic Bohmian Mechanics

arXiv:2606.16165v1 Announce Type: new Abstract: In order to make the right empirical predictions Bohmian mechanics requires a special statistical boundary condition – the distribution postulate – but it is unclear how best to understand this condition. We show how one might use the theory of algorithmic randomness to formulate the distribution postulate as an objective constraining law. The framework requires us to say something about admissible quantum-mechanical states and measurements. In return, algorithmic Bohmian mechanics (aBM) guarantees the standard Born statistics for a collection of canonical quantum experiments in the limit, not just with high probability. The algorithmic distribution postulate provides a sharp typicality condition, clarifies the status of quantum probabilities in the deterministic theory, and provides a concrete example of how notions provided by the theory of algorithmic randomness can aid in specifying the content of a physical law.

19.
arXiv (quant-ph) 2026-06-16

Generalized Kerr-Cat Qubit Codes

arXiv:2606.14901v1 Announce Type: new Abstract: We present a systematic study of Schrödinger cat codes constructed from Kerr-type coherent states, including displaced Kerr coherent states and Barut–Girardello Kerr coherent states, each admitting two distinct families determined by the sign of the Kerr nonlinearity. By tuning the Kerr parameter and coherent-state amplitude, these states interpolate between $\mathfrak{su}(2)$, $\mathfrak{su}(1,1)$ coherent states, providing a unified and versatile foundation for this type of bosonic quantum error correction. Unlike standard two-component Schrödinger cat codes, where a single photon-loss event induces an uncorrectable bit-flip, the nonlinear phase-space structure of Kerr cat states enables simultaneous detection and correction of both photon-loss and dephasing errors within a unified recovery framework, with optimal recovery operations determined via convex optimization. We demonstrate that Kerr cat encodings significantly outperform conventional cat codes under combined loss and dephasing noise, and that judicious parameter optimization can suppress both error channels to a level that reduces the overhead of additional error correction layers. We further show that Kerr-deformed coherent-state manifolds under engineered two-photon driving emerge as effective steady states of driven-dissipative dynamics, with single-photon decoherence strongly suppressed and leakage outside the protected manifold appearing only as higher-order corrections in the deformation strength. Our extended formalism identifies generalized Kerr Schrödinger cat codes as promising candidates for fault-tolerant bosonic quantum computation in experimental platforms such as nonlinear photonics.

20.
arXiv (CS.LG) 2026-06-25

Randomized Kriging Believer for Parallel Bayesian Optimization with Regret Bounds

arXiv:2603.01470v3 Announce Type: replace Abstract: We consider the optimization problem of an expensive-to-evaluate black-box function, in which we can obtain noisy function values in parallel. For this problem, parallel Bayesian optimization (PBO) is a promising approach, which aims to optimize with fewer function evaluations by selecting a diverse input set for parallel evaluation. However, existing PBO methods suffer from poor practical performance or lack theoretical guarantees. In this study, we propose a PBO method, called randomized kriging believer (KB), based on a well-known KB heuristic and inheriting the advantages of the original KB: low computational complexity, a simple implementation, versatility across various BO methods, and applicability to asynchronous parallelization. Furthermore, we show that our randomized KB achieves Bayesian expected regret guarantees. We demonstrate the effectiveness of the proposed method through experiments, including those on real-data emulators.

21.
arXiv (CS.LG) 2026-06-11

IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal Agents

arXiv:2606.11652v1 Announce Type: new Abstract: This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents. While existing works have explored various reward designs to improve agentic tool-calling ability, these approaches face inherent limitations for SLM training, especially under multimodal scenarios. First, many existing methods evaluate tool use correctness through exact matching against certain ground-truth or predefined formats. However, this assumption is often unsuitable for multimodal tasks, where multiple tool use paths may be valid and annotated tool trajectories are typically unavailable. Second, such sparse and brittle binary rewards provide little guidance on how to improve the underlying decision process, making them particularly difficult for multimodal SLM to learn from. To address these issues, we propose Input Attribution-Aware Policy Optimization (IAPO), an RL algorithm for improving tool use in multimodal SLM by aligning the model's attribution across input components with that of a stronger teacher. Experiments on Qwen2.5-VL-3B show that the proposed method improves visual question answering accuracy by an average of 3% across six test sets compared with existing visual tool use work, by helping the model attend to the most relevant input evidence.

22.
arXiv (CS.LG) 2026-06-17

Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach

arXiv:2510.19528v2 Announce Type: replace-cross Abstract: We investigate the fundamental problem of leveraging offline data to accelerate online reinforcement learning - a direction with strong potential but limited theoretical grounding. Our study centers on how to learn and apply value envelopes within this context. To this end, we introduce a principled two-stage framework: the first stage uses offline data to derive upper and lower bounds on value functions, while the second incorporates these learned bounds into online algorithms. Our method extends prior work by decoupling the upper and lower bounds, enabling more flexible and tighter approximations. In contrast to approaches that rely on fixed shaping functions, our envelopes are data-driven and explicitly modeled as random variables, with a filtration argument ensuring independence across phases. The analysis establishes high-probability regret bounds determined by two interpretable quantities, thereby providing a formal bridge between offline pre-training and online fine-tuning. Empirical results on tabular MDPs demonstrate substantial regret reductions compared with both UCBVI and prior methods while remaining competitive with related approaches.

23.
arXiv (CS.CL) 2026-06-25

Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution

Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate model outputs through malicious retrieved documents. Existing detection methods typically rely on auxiliary classifiers or additional LLM-based verification, introducing substantial computational overhead. We present TRACE, a lightweight detection framework that identifies poisoning attacks by tracing answer-related tokens through token influence attribution. TRACE first discovers recurrent high-influence keywords across retrieved documents and then performs a secondary verification to confirm their influence on model predictions. Experiments on three QA benchmarks and six LLMs demonstrate strong detection performance while simultaneously uncovering attacker-specified target answers.

24.
arXiv (CS.CV) 2026-06-16

Interpolation between Convolution and Attention via K-Nearest Neighbors

作者:

The shift from Convolutional Neural Networks to Transformers has reshaped computer vision, yet these two architectural families are typically viewed as fundamentally distinct. Convolutional Neural Networks are defined by spatially local convolution operations, while Transformers rely on global self-attention. We argue that convolution and self-attention, despite their apparent differences, can be unified within a single k-nearest neighbor aggregation framework. The critical insight is that both operations are special cases of neighbor selection and weighted aggregation. Convolution selects neighbors by spatial proximity while self-attention selects by feature similarity, revealing that they lie on a continuous spectrum rather than representing categorically different computations. We introduce Convolutional Nearest Neighbors (ConvNN), a unified framework that formalizes this connection. ConvNN exactly recovers standard and depthwise convolution by restricting neighbor selection to normalized spatial coordinates, and exactly recovers self-attention and its sparse variants, including KVT-attention, by replacing spatial proximity with scaled dot-product similarity. Beyond these special cases, ConvNN serves as a drop-in replacement for both convolution and attention layers, enabling systematic exploration of the intermediate spectrum between local and global aggregation through configurable similarity functions, neighbor selection strategies, positional encodings, and aggregation kernels.