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 (CS.CL) 2026-06-15

Decoupled Mixture-of-Experts for Parametric Knowledge Injection

Knowledge injection aims to equip large language models (LLMs) with external, domain-specific, or time-sensitive knowledge. Existing approaches typically face a trade-off between flexibility and integration: retrieval-augmented generation keeps knowledge outside the model but only provides prompt-level augmentation, whereas post-training based methods encode new knowledge into shared parameters but may introduce catastrophic forgetting, knowledge conflict, and costly updates. In this paper, we propose Decoupled Mixture-of-Experts (DMoE), a modular architecture for parametric knowledge injection that decouples both experts and the router from the base model. DMoE converts external knowledge corpora into independently updatable expert modules and uses a lightweight uncertainty-aware router to activate relevant experts only when the base model lacks sufficient knowledge during generation. To support efficient auto-regressive inference, DMoE attaches experts only to the final-layer feed-forward network, preserving KV-cache reuse while enabling parameter-level knowledge augmentation. Experiments on knowledge-intensive benchmarks show that DMoE consistently improves answer quality over retrieval and adapter-based baselines.

02.
arXiv (CS.LG) 2026-06-16

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

arXiv:2602.00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time. Existing infinite-horizon methods, which often rely on discounted contraction, do not naturally account for this fixed-horizon structure. We introduce a modified Q-function: rather than targeting the full-horizon, we learn a K-step lookahead Q-function that truncates planning to the next K steps. To further improve sample efficiency, we introduce a thresholding mechanism: actions are selected only when their estimated K-step lookahead value exceeds a time-varying threshold. We provide an efficient tabular learning algorithm for this novel objective, proving it achieves fast finite-sample convergence: it achieves minimax optimal constant regret for $K=1$ and $\mathcal{O}(\max((K-1),C_{K-1})\sqrt{SAT\log(T)})$ regret for any $K \geq 2$. We numerically evaluate the performance of our algorithm under the objective of maximizing reward. Our implementation adaptively increases K over time, balancing lookahead depth against estimation variance. Empirical results demonstrate superior cumulative rewards over state-of-the-art tabular RL methods across synthetic MDPs and RL environments: JumpRiverswim, FrozenLake and AnyTrading. Code is provided on \href{https://github.com/jamie01713/K-Step-Lookahead}{github}.

04.
arXiv (quant-ph) 2026-06-24

Spectator-transition crosstalk in a spin-3/2 silicon vacancy qudit in silicon carbide revealed by broadband Ramsey interferometry

arXiv:2601.15559v3 Announce Type: replace Abstract: Color center spins in 4H-SiC offer a rare combination of wafer-scale materials maturity with long spin coherence and chip-level photonics, making them promising building blocks for scalable quantum technologies. In particular, the silicon vacancy hosts an S=3/2 ground state, a native qudit that enables compact encodings and subspace-selective control, but also introduces spectator transitions: short, detuned pulses can coherently drive non-addressed level pairs and create crosstalk. Here we use broadband Ramsey interferometry to reveal and quantify such spectator-transition crosstalk. Experimentally, the Ramsey Fourier spectra display multiple lines beyond the addressed single-quantum transition. Analytically, we map each line to a pairwise energy difference between qudit levels of the rotating-frame Hamiltonian and assign its weight via compact amplitudes set by the prepared state and the microwave pulse parameters, predicting a deterministic six-branch structure. Numerical time-domain propagation with the experimental sampling reproduces the detuning map, and the measured peak positions coincide with the analytic branch lines without frequency fitting. Together these results provide a practical, spectator-aware framework for multilevel control in the silicon vacancy qudit. The approach offers clear guidance to suppress crosstalk or, conversely, to exploit spectator lines, for example as additional constraints for in situ pulse calibration and for phase-sensitive quantum state and process estimation.

05.
arXiv (CS.CV) 2026-06-15

Point Cloud Upsampling through Patch-based Frequency Superposition

In recent years, neural networks have become the dominant models in most point cloud upsampling methods. Although these approaches are achieving good results, they do have drawbacks, such as a lack of interpretability and data dependency. Moreover, they have to be trained on a dataset that is similar to the test data in order to perform well. To avoid these disadvantages, we propose Point Cloud Upsampling through Patch-based Frequency Superposition (PUtPFS), an optimization-based approach that selects subsets of points and estimates the surface of this set through superpositioning spatial frequencies. Then, new points are placed on this surface. By successively selecting points in the least dense regions of the point cloud, a uniform upsampling can be reached. With this method, we surpass the current best upsampling results in the commonly considered point-to-surface distance. Furthermore, we achieve the best Chamfer and Hausdorff distance among the optimization-based approaches. As an additional advantage, our method does not need any training data and is mathematically interpretable.

06.
arXiv (CS.CL) 2026-06-11

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment. Chain-of-thought (CoT) reasoning is widely used to improve accuracy and reliability, but its effect on calibration is not fully understood. We show that this picture is incomplete: in some settings, increasing the reasoning budget beyond a task-specific threshold can cause models to become systematically overconfident, assigning high confidence to incorrect answers. We call this phenomenon Calibration Drift Under Reasoning (CDUR) and study it both theoretically and empirically. We define reasoning budget B and analyze conditions under which Expected Calibration Error ECE(B) follows a non-monotonic pattern: it first decreases as reasoning corrects errors, then increases as longer reasoning produces internally consistent but incorrect explanations. We propose a Hypothesis Lock-In model based on autoregressive generation to explain this behavior. We evaluate Llama-3.1-8B and Llama-3.3-70B on 47 reasoning-trap questions across four reasoning budgets and three seeds (1,368 API calls; 574 valid responses). The 8B model shows non-monotonic calibration behavior, while results for the 70B model are limited to baseline evaluation and are inconclusive for budget-dependent effects. We introduce CABStop, a calibration-aware stopping rule that halts reasoning when confidence diverges from an auxiliary accuracy estimate. These results suggest that increasing reasoning depth does not always improve reliability and should be monitored carefully.

07.
arXiv (CS.LG) 2026-06-11

Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies

arXiv:2601.08136v2 Announce Type: replace Abstract: Diffusion and flow policies are gaining prominence in online reinforcement learning (RL) due to their expressive power, yet training them efficiently remains a critical challenge. A fundamental difficulty that distinguishes online RL from standard generative modeling is the lack of direct samples from the target Boltzmann distribution defined by the Q-function. To address this, two seemingly distinct families of methods have been proposed for diffusion policies: a noise-expectation family, which uses a weighted average of noise as the training target, and a gradient-expectation family, which employs a weighted average of Q-function gradients. However, it remains unclear how these objectives are formally related, or whether they can be synthesized into a more general formulation. In this paper, we propose a unified framework, reverse flow matching (RFM), which rigorously addresses the problem of training diffusion and flow models without direct target samples. By adopting a reverse inferential perspective, we formulate the training target as a posterior mean estimation problem given an intermediate noisy sample. Crucially, we introduce Langevin Stein operators to construct zero-mean control variates, deriving a general class of estimators that share the same expectation. We show that existing noise-expectation and gradient-expectation methods are simply two specific instances within this broader class. This unified view yields two key advancements: it extends the capability of targeting Boltzmann distributions from diffusion to flow policies, and it enables the principled combination of Q-value and Q-gradient information to form an effective estimator, thereby improving training efficiency and stability. We instantiate RFM to train a flow policy in online RL and demonstrate improved performance on continuous-control benchmarks compared to diffusion policy baselines.

08.
arXiv (CS.CL) 2026-06-12

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents

Long-horizon tool-use reinforcement learning can learn from outcome verification, but its trajectory-level advantage is broadcast across many reasoning, API, and answer tokens. Self-distillation promises a denser signal by reusing a policy's own rollouts or a privileged teacher. We show, however, that direct token-level self-distillation can silently destroy tool use: it rehearses teacher behavior without knowing which actions the verifier rewards, so useful skills and harmful shortcuts are amplified together. We introduce Sibling-Guided Credit Distillation (SGCD), which uses distillation for credit assignment rather than as a competing actor loss. Dynamic sampling produces mixed successful and failed sibling rollouts; an external LLM summarizes their contrast into a training-only stepwise credit reference; dense teacher/student divergence drives credit reassignment; and bounded detached credit weights reshape GRPO token advantages. The deployed student sees no external LLM, sibling evidence, or oracle. Across AppWorld and $\tau^3$-airline, SGCD improves over matched GRPO comparators: AppWorld TGC $42.9 \to 45.6$ on test_normal and $24.7 \to 27.0$ on test_challenge, and $\tau^3$-airline pass@1 $0.583 \to 0.602$.

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

Rotational Symmetry based Object Pose Estimation from Point Clouds in the Absence of Known 3D Models

Object pose estimation is crucial to many industrial applications, with one example being automated spray painting using a robot. However, confidentiality concerns often limit access to high-quality 3D models, posing a significant challenge for point-cloud-based pose estimation. In such scenarios, rotational symmetry, a readily accessible characteristic of many industrial objects, can provide valuable prior information to facilitate pose estimation.In this paper, we propose a method that leverages the rotational symmetry commonly found in industrial objects to address the challenge caused by the absence of 3D models. The object pose is jointly estimated with point cloud refinement through an iterative optimization process. This optimization relies on a rotational symmetry constraint loss. To construct this loss, each 3D point is rotated according to the currently estimated pose, and multiple correspondences are identified using nearest-neighbor search by exploiting the rotational symmetry property. These correspondences are then used to compute the rotational symmetry constraint loss, which iteratively refines both the pose and the point cloud.By explicitly incorporating rotational symmetry into the optimization process, the proposed method achieves robust pose estimation and generalizes well across diverse object types. The proposed method is evaluated on a dataset specifically created for point clouds without known 3D models, consisting of four categories of synthetic objects and one real wheel hub collected from a production line. Experimental results demonstrate that the proposed method achieves performance comparable to methods that rely on known 3D models.

10.
arXiv (CS.CL) 2026-06-17

Learning from the Self-future: On-policy Self-distillation for dLLMs

On-policy self-distillation (OPSD) has proven effective for post-training large language models (LLMs), yet its application to diffusion LLMs (dLLMs) remains unexplored. Existing OPSD methods are inherently autoregressive-centric. They inject privileged information via left-to-right prefix conditioning with token-level divergence supervision, a design that fundamentally conflicts with the arbitraryorder generation of dLLMs. We introduce d-OPSD, the first OPSD framework tailored for dLLMs. Our approach makes two core contributions. First, we reframe self-teacher construction by using self-generated answers as suffix conditioning, enabling the student model to learn from "self future-experience" rather than privileged prefixes. Second, we shift supervision from token-level to step-level, aligning training with the iterative denoising process of dLLMs. Experiments across four reasoning benchmarks show that d-OPSD consistently outperforms RLVR and SFT baselines with superior sample efficiency, requiring only around 10% of the optimization steps by RLVR and opening a promising pathway for dLLM posttraining. The code is available at https://github.com/xingzhejun/d-OPSD.

11.
arXiv (CS.CL) 2026-06-11

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application

Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies current researches on agentic environments from the perspective of the environment engineering lifecycle, covering their modeling, synthesis, evaluation and application. Specifically, the paper first introduces representative environments from the perspectives of eight attributes and eight domains, providing detailed analyses of their development paths and highlighting their core capabilities. Second, for automated environment synthesis, two paradigms are introduced, such as symbolic synthesis and neural synthesis. This paper also shows different environment evaluation methods in each paradigm. Thirdly, the corresponding environment applications from the perspective of agent-environment co-evolution are discussed. In specific, the paper characterizes the primary pathways for agent evolution in dynamic environments from four complementary perspectives: memory-centric experience evolution, orchestration-centric workflow evolution, trajectory-centric offline evolution, and exploration-centric online evolution. And three paradigms of environment evolution are identified, namely neural-driven, difficulty-driven, and scaling-driven approaches. At last, several promising future directions are discussed, including Environment-as-a-Service, Multi-agent Environments, and Neural-Symbolic Environments.

12.
arXiv (math.PR) 2026-06-24

Conditioning of incoherent sub-dictionaries sampled from a coherent dictionary

arXiv:2606.24323v1 Announce Type: new Abstract: Motivated by the desire to find a realistic and stable random model for $d$-dimensional signals, that are sparse in a transform-based and thus often coherent frame, such as a wavelet or a Gabor frame, we study the conditioning of incoherent sub-dictionaries sampled from a coherent dictionary, such as a unit norm frame. In particular, we show that if the sub-dictionary is selected via a coherence rejective Poisson sampling model, it is well-conditioned with high probability, as long as its expected size scales as $d/\log (K)$, where $K$ is the number of dictionary elements. The result is proved for the more general case of sampling quadratic sub-matrices from a real but not necessarily symmetric $K\times K$ matrix with zero diagonal, where coherence rejective sampling is defined via a symmetric mask, that acts as coherence substitute.

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

Robust State-Conditional Feature-Weighted Jump Models for Temporal Clustering

arXiv:2606.13146v1 Announce Type: cross Abstract: We propose a robust feature-weighted jump model for time-dependent clustering. A penalty is used to encourage smoothness of transitions over time, while robustness is achieved through the use of a Tukey's biweight loss function. An additional parameter controls the variability of feature weights across states, allowing the model to assign state-specific relevance to each feature. We illustrate in simulation how the method accurately recovers the true cluster sequence and reliably identifies relevant features, outperforming competing approaches, particularly in the presence of outliers. We conclude with two empirical applications, one on the number of conflict-related homicides in Kosovo in the period 1998-2000, and another on macroeconomic performance of twelve European countries in the period 1949-2024.

14.
arXiv (CS.CL) 2026-06-18

Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation

Dense retrieval ranks one query vector against one document vector. On long documents, this interface can fail when a short but decisive span is weakened during document encoding before ranking. We study this failure mode as document-side early compression and introduce the Evidence Dilution Index (EDI) to measure how far a document-level representation falls below the strongest chunk-level evidence within the same gold document. Guided by this view, we propose DICE (Document Inference via Chunk Evidence), a training-free document-side strategy that splits documents into chunks, encodes them independently with a frozen model, and aggregates them back into a single vector while preserving the standard one-query-one-document interface. On LongEmbed, DICE improves retrieval across four backbones, with the largest gains on slices beyond 4k tokens: for Dream, Passkey >4k rises from 30.0 to 90.0 and Needle >4k from 23.3 to 74.0. Across 12,779 filtered samples, DICE yields lower EDI than the single-vector baseline in 92.8% of cases. These results establish document-level encoding as a practical and underexplored lever for long-document retrieval.

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

Regional Climate Model Emulation with Diffusion Approaches: What is the Added Value of Generative Machine Learning?

arXiv:2606.14570v1 Announce Type: cross Abstract: Emulators provide a cost-effective alternative to regional climate models (RCMs) by capturing their dynamical downscaling function. They link large-scale predictors simulated by global climate models (GCMs) to RCM-simulated high-resolution fields of the target variable, here precipitation. Machine learning methods, typically deep learning, are cheaper than running RCMs in computation time and energy. Among them, generative models are appealing because they can simulate ensembles of local high-resolution fields consistent with the predictors. This ensemble, which we call the uncertainty envelope, remains to be properly assessed for added value. Here, we make three contributions. First, we introduce ParamDiffusion, a new two-stage diffusion-based framework, and compare it with a state-of-the-art diffusion approach. Second, we expand standard validation through a comprehensive framework aligned with climate-science needs, examining specific precipitation events, including extremes. Third, within this framework, we assess the added value of diffusion approaches relative to deterministic methods. We intercompare four deep-learning models: a deterministic model designed to capture the precipitation tail; a parametric probabilistic model based on it; a recently proposed diffusion approach; and ParamDiffusion, which couples the parametric model with a diffusion model. Our results show that diffusion-based approaches reproduce climatological precipitation statistics with high skill, including distributional tails and spatially compounded extremes, while generating spatially detailed fields. However, none of the assessed models consistently accounts for the most extreme RCM-simulated events within its uncertainty envelope. Diffusion models are therefore promising for probabilistic RCM emulation, but progress is still required before they can reliably represent high-impact precipitation extremes.

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

Anomaly Detection via Mean Shift Density Enhancement

arXiv:2602.03293v2 Announce Type: replace Abstract: Unsupervised anomaly detection stands as an important problem in machine learning. Existing unsupervised anomaly detection algorithms rarely perform well across different anomaly types, often excelling only under specific structural assumptions. This lack of robustness also becomes particularly evident under noisy settings. We propose Mean Shift Density Enhancement (MSDE), a fully unsupervised framework that detects anomalies through their geometric response to density-driven manifold evolution. MSDE is designed as a general purpose anomaly detection framework, based on the principle that normal samples, being well supported by local density, remain stable under iterative density enhancement, whereas anomalous samples undergo large cumulative displacements as they are attracted toward nearby density modes. To operationalize this idea, MSDE employs a weighted mean-shift procedure with adaptive, sample-specific density weights derived from a manifold learning-based fuzzy neighborhood graph. We evaluate MSDE on an anomaly detection benchmark comprising 46 real-world tabular datasets, four realistic anomaly generation mechanisms, and six noise levels. Compared to 13 established unsupervised baselines, MSDE achieves consistently strong, balanced and robust performance for several standard classification metrics, at several noise levels and on average over several types of anomalies. These results demonstrate that displacement-based scoring provides a robust alternative to the existing state-of-the-art for unsupervised anomaly detection.

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

Learning the Geometry of Data: A Mathematical Review of Shape Space Analysis

arXiv:2606.17022v1 Announce Type: cross Abstract: A central objective of machine learning is to identify structure and patterns in data. Advances in data acquisition have increasingly produced datasets whose observations possess rich geometric form, giving rise to shape spaces that encode variability in object geometry. Such datasets arise across a wide range of disciplines, including biology, medicine, anthropology, and computer vision, where subtle geometric differences often carry important scientific information. Traditional machine learning methods, however, are frequently ill-equipped to account for the nonlinear geometric structure underlying these data. This survey synthesizes a rapidly growing body of work on shape space analysis, which provides a mathematical and computational framework for the study of geometric data. Drawing on ideas from differential geometry, statistics, and machine learning, we organize the literature around a common analytical pipeline: shape representation and parameterization, the rigorous construction of robust geodesic metrics, statistical analysis on shape spaces, and geometry-aware learning methods. We discuss how these tools enable the characterization of shape variability, the comparison of geometric objects, and the analysis of structural trajectories across populations and time. To illustrate the breadth of the field, we highlight applications spanning multiple scales of biological organization, including studies of subcellular morphology and primate tooth evolution. Across these and many other domains, researchers face common challenges arising from complex, nonlinear, and often unaligned geometric variation. The review concludes by identifying key theoretical and computational challenges, as well as emerging opportunities driven by increasingly large and diverse geometric datasets.

18.
arXiv (CS.CL) 2026-06-11

Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles

Most fairness research in NLP assumes direct access to protected attributes such as gender, race, or nationality. In practice, however, such information is often unavailable due to privacy constraints, missing metadata, or legal restrictions, even though models may infer it from indirect textual cues. This raises a key question: can debiasing succeed without direct access to sensitive attributes? We propose H-SAL, which performs post-hoc concept and attribute erasure using self-description text as an implicit debiasing signal. To support this setting, we introduce a multi-domain Stack Exchange-based fairness benchmark for helpfulness prediction that includes both explicit and implicit signals, enabling comparison between standard debiasing with protected labels and debiasing without access to sensitive information. Across encoder and decoder-only language models, we find that implicit self-description often matches or outperforms explicit-label-based debiasing. Our results broaden representation-level fairness research and provide a new benchmark for studying debiasing under realistic data constraints.

19.
medRxiv (Medicine) 2026-06-22

National trends and operational drivers of vaccine wastage in Uganda, 2020-2025: a descriptive analysis of four tracer antigens

Background Vaccine wastage reduces immunisation efficiency, increases costs, and complicates supply forecasting. Uganda routinely monitors vaccine use, but national evidence comparing observed wastage with World Health Organization (WHO) and Uganda-specific planning thresholds has been limited. We described national and sub-national trends for four tracer antigens to inform supply-chain planning and forecasting. Methods We conducted a retrospective descriptive analysis of routinely reported immunisation data from Ugandas District Health Information Software 2, 2020-2025. We analysed Bacille Calmette-Guerin (BCG), measles-rubella (MR), oral polio vaccine (OPV), and diphtheria-tetanus-pertussis-containing vaccine (DPT). Vaccine wastage was calculated as the proportion of issued doses not administered. Annual wastage rates were summarised using medians, and temporal trends were assessed using the Mann-Kendall test. Observed wastage was compared with WHO thresholds: BCG[≤]50%, MR[≤]25%, OPV[≤]10%, DPT[≤]15%, and Ugandas planning thresholds: BCG[≤]70%, MR[≤]40%, OPV[≤]15%, DPT[≤]10%. Effective Vaccine Management reports were reviewed to summarise reported reasons for wastage. Results During 2020-2025, median national wastage was 40.6% for BCG, 25.9% for MR, 10.0% for OPV, and 9.2% for DPT. OPV wastage declined from 12.8% in 2020 to 8.0% in 2025, with a significant downward trend ({tau}b=-1.00; p=0.008). OPV and DPT wastage remained largely within their respective Uganda in-country thresholds ([≤]15% and [≤]10%) for most of the study period, while BCG generally remained below the WHO threshold ([≤]50%) and MR frequently exceeded the WHO threshold ([≤]25%) but remained within Uganda's planning threshold ([≤]40%) in most years. The proportion of districts exceeding both WHO and Uganda thresholds declined for OPV from 36.3% to 5.5% (p=0.024) and for DPT from 22.6% to 1.4% (p=0.013). Wastage was consistently higher in lower-level (Health Centre II and III) facilities, compared to hospitals. Among 50 service delivery points, reported reasons included low session attendance (66%), multi-dose vial policy non-compliance (28%), and vaccine expiry (12%). Conclusion Uganda achieved reductions in OPV wastage and district-level improvements in DPT wastage, while BCG and MR remained more variable and frequently had higher wastage. Strengthening adherence to the multi-dose vial policy and improving session planning at lower-level facilities could strengthen vaccine utilisation and forecasting.

20.
arXiv (CS.AI) 2026-06-19

Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models

arXiv:2606.19932v1 Announce Type: cross Abstract: Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a severe performance collapse. We attribute this degradation to the spatially agnostic nature of existing reduction methods, which violate the two-dimensional structural premise required by the selective scanning mechanism. In this work, we propose STORM, a spatial-aware token reduction framework designed to maintain structural integrity throughout the compression process. STORM reformulates reduction into a structured operation on spatial units, enforcing localized constraints to maintain both grid topology and neighborhood coherence. As a plug-and-play module, STORM equips existing reduction pipelines with explicit spatial awareness without any training. Empirical results demonstrate that STORM achieves state-of-the-art pruning accuracy across diverse vision Mamba backbones under training-free settings. Notably, STORM delivers a substantial accuracy recovery on VMamba, outperforming prior methods by up to 63.3\% in top-1 accuracy. Meanwhile, STORM incurs only a 1.0\% accuracy drop on PlainMamba, achieving performance comparable to ViT.

21.
arXiv (CS.AI) 2026-06-18

Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging

arXiv:2606.18521v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a powerful post-training paradigm that surpasses Supervised Fine-Tuning (SFT) in eliciting reasoning intelligence and resisting catastrophic forgetting. Recent studies further reveal that RLVR induces highly sparse and off-principal parameter updates compared to SFT. This naturally raises the question: does such sparsity make RLVR models more amenable to model merging? If so, model merging would offer a scalable, training-free path to aggregate diverse reasoning capabilities from independently trained RLVR models. Surprisingly, we find the opposite, uncovering a sparsity curse: the sparse RLVR updates are spread farther apart in parameter space, forming near-orthogonal shortcuts that make aggregation inherently fragile. This is likely rooted in the stochasticity of RL optimization and the diversity of emergent reasoning patterns. Unlike SFT models that converge to shared, flat basins and merge naturally, RLVR models suffer severe degradation under standard merging methods. Through systematic empirical analysis of the update geometry, we characterize the mechanisms behind this failure and propose Sensitivity-aware Resolving Merging (SAR-Merging), a merging recipe tailored for the unique structure of RLVR parameter spaces. SAR-Merging resolves conflicts in overlapping update regions via Fisher Information-based sensitivity arbitration, followed by magnitude-aware sparsification and rescaling to preserve fragile reasoning pathways. Experiments on mathematical and coding benchmarks demonstrate that SAR-Merging substantially outperforms existing merging methods on RLVR models, enabling both single-task enhancement and multi-capability fusion.

22.
arXiv (quant-ph) 2026-06-12

Accidental Symmetry in the Tavis-Cummings Model via the Schwinger Boson Representation

arXiv:2606.12813v1 Announce Type: new Abstract: The Jaynes-Cummings (JC) Hamiltonian is a paradigmatic model of light-matter interaction and, more generally, qubit-boson interactions, widely used across atomic, optical, and superconducting qubit platforms. In the multi-qubit setting, where n qubits are identically coupled to a single boson mode, this interaction is known as the Tavis-Cummings (TC) Hamiltonian. The structure of the TC model is usually understood in terms of two standard symmetries: permutation invariance of the qubits and a U(1) symmetry associated with conservation of the total excitation number. Here we identify an additional, independent "accidental" symmetry of the TC Hamiltonian and construct the corresponding conserved observable. We show that, for n>2 qubits, this symmetry imposes strong constraints on the realizable unitary transformations. These constraints persist in the presence of the global $J_z$ Hamiltonian, but are removed by adding $J_z^2$, even though $J_z^2$ preserves both permutation invariance and the U(1) symmetry. Finally, we explain the origin of this previously unnoticed symmetry using Schwinger's boson representation of angular momentum. These restrictions have important implications for controllability of the TC system and for its applications to quantum computing, which are investigated further in a companion paper.

23.
arXiv (quant-ph) 2026-06-15

Simultaneous Estimation of Partial-Transpose Moments with Active Memory Independent of the Moment Order

arXiv:2606.14204v1 Announce Type: new Abstract: We study the simultaneous estimation of partial-transpose moments $p_j(\rho_{AB})=\mathrm{Tr}[(\rho_{AB}^{T_B})^j]$, $j=2,\ldots,K$, of an unknown bipartite $n$-qubit state from independent copies under an explicit active-memory constraint. We give a sequential qubit-reuse realization of the partial-transpose permutation that uses at most $2n+1$ active qubits, independent of $K$, and estimates all moments $p_2,\ldots,p_K$ to uniform additive error $\epsilon$ with total copy complexity $O(K\log K/\epsilon^2)$. We also prove two converse bounds. First, any uniformly accurate simultaneous estimator requires $\Omega(K/\epsilon^2)$ copies in the worst case. Second, the same scaling holds on an explicit isospectral two-qubit negative-partial-transpose (NPT) family whose ordinary moments are constant while the partial-transpose moments vary. These results characterize the copy complexity of the partial-transpose moment hierarchy up to a logarithmic factor and extend simultaneous nonlinear-functional estimation from ordinary state powers to partial-transpose spectral data under active quantum memory independent of the target moment order.

24.
arXiv (CS.CV) 2026-06-18

SP-TransientBench: A Real-Captured Single Photon Perception Benchmark

Single-photon LiDAR (SPL) based on single-photon avalanche diode (SPAD) sensing enables time-resolved photon measurements with extreme sensitivity, offering unique potential for active 3D perception in photon-starved scenarios.However, real-world single photon perception remains fundamentally challenging due to unique measurement noise and complex multi-return transient phenomena, which jointly complicate geometric reconstruction and semantic scene understanding. Despite growing interest in SPAD-based sensing, existing studies are largely limited to simulated data or small-scale controlled captures. As a result, systematic evaluation of real-world single photon perception across depth estimation, multi-view reconstruction, and 3D semantic understanding remains underexplored. To bridge this gap, we introduce SP-TransientBench (STB), a real-captured multi-task benchmark for single photon perception. SP-TransientBenc comprises 10 diverse scenes and 10,297 views captured using a solid-state single-photon LiDAR at $256\times192$ resolution. Each view provides full time-of-flight histograms with multi-return behavior,standardized metadata, and calibrated camera poses for multi-view evaluation. We further provide 13-class 3D semantic annotations for selected scenes. By providing dedicated data splits and evaluation protocols for each task, STB enables consistent and reproducible benchmarking of real-world single photon perception across multiple 3D vision problems. The dataset and code will be released upon acceptance.

25.
bioRxiv (Bioinfo) 2026-06-20

RNAStabFormer: Region-Aware Multi-Task Hybrid Learning for RNA Stability Prediction from Pulse-Chase Transcriptomics

作者:

RNA stability is a central layer of post-transcriptional gene regulation, yet large-scale stability labels derived from pulse-chase transcriptomics depend strongly on quantification region, time-window definition, and replicate quality control. We present RNAStabFormer, a controlled learning framework for predicting human RNA stability proxies from transcript sequence. Its core model, RAMHT, combines region-specific nucleotide Transformer encoders for CDS, and sequence, a CDS codon stream, engineered sequence-grammar features, gated fusion, and four task-specific regression heads. We construct four strict consensus labels from ENCODE BrU-seq/BruChase-seq data by crossing gene-sense and exon-sense quantification with late-chase 6 h/2 h and total-chase 6 h/0 h retention ratios, and evaluate all models on fixed repeated-random and chromosome-holdout splits. Across chromosome holdouts, XGBoost remains the strongest standalone model, with median Pearson correlations of 0.504, 0.544, 0.546, and 0.778 on the four labels. RAMHT is competitive with raw-sequence deep models but does not universally exceed engineered-feature baselines. A strict nested RAMHT–XGBoost blend nevertheless improves gene total-chase prediction by 0.017 mean Pearson and exon late-chase prediction by 0.004 mean Pearson over XGBoost. Region and mechanism analyses show that CDS, local k-mer composition, and codon-sensitive signals dominate predictive information. RNAStabFormer therefore provides both a multi-task neural model and a leakage-controlled evaluation protocol for RNA stability prediction from pulse-chase data.