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) 2026-06-16

A New Definition of Quantum Superposition

arXiv:2606.15607v1 Announce Type: new Abstract: The usual description of the superposition of two (pure quantum) states is ambiguous, since the binary operation of summation in a Hilbert space does not pass down to the quotient projective space. Even though Dirac noted this as early as 1930, it is often asserted that the superposition is a binary operation acting on two states with a value that is a unique state. The goal for this note is to motivate a rigorous, geometrical definition of the superposition of states in the setting of complex projective space, which has been argued elsewhere to be the natural geometric phase space for quantum theory. The upshot is that the new definition of the superposition of two pure states, viewed as two distinct points in the projective space, is the unique (complex) line on which those two points lie. Finally, a comparison is given between superposition and expansion in an orthonormal basis.

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

A Self Consistency Based Reranking for Narrative Question Answering

Narrative question answering (NQA) is a challenging task in natural language processing that requires models to understand long textual contexts, capture relationships across events, and generate coherent responses. Despite recent advances in pretrained language models, most existing approaches rely on a single decoding output during inference, making them sensitive to generation variability and often resulting in incomplete or inconsistent answers .To address this limitation, we propose a self-ensemble Self-Consistency-Based reranking framework for narrative question answering. The proposed method generates multiple candidate answers for each story-question pair and selects the final answer based on semantic agreement among the generated responses. This allows the model to explore diverse answer formulations while improving robustness through consensus-based selection without requiring modifications to the underlying architecture .The framework combines pretrained and fine-tuned language generation with multi-answer inference and similarity-based reranking. We evaluate the proposed approach on the NarrativeQA dataset using multiple models, including FLAN-T5 (Base and Small) and Pegasus-Large, under both baseline and fine-tuned settings .Experimental results demonstrate that the proposed method consistently improves performance across all models. In particular, FLAN-T5-Base achieves the best overall performance, improving from 82.32% to 86.66% (+4.34%) when combined with self-ensemble inference. Additionally, the largest improvement is observed with Pegasus-Large, which increases from 72.50% to 87.07% (+14.57%), highlighting the effectiveness of the proposed strategy.

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

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

Foundation models are transitioning from offline predictors to deployed systems expected to operate over long time horizons. In real deployments, objectives are not fixed: domains drift, user preferences evolve, and new tasks appear after the model has shipped. This elevates continual learning and instant personalization from optional features to core architectural requirements. Yet most adaptation pipelines still follow a static weight paradigm: after training (or after any adaptation step), inference executes a single parameter vector regardless of user intent, domain, or instance-specific constraints. This treats the trained or adapted model as a single point in parameter space. In heterogeneous and continually evolving regimes, distinct objectives can induce separated feasible regions over parameters, forcing any single shared update into compromise, interference, or overspecialization. As a result, continual learning and personalization are often implemented as repeated overwriting of shared weights, risking degradation of previously learned behaviors. We propose HY-WU (Weight Unleashing), a memory-first adaptation framework that shifts adaptation pressure away from overwriting a single shared parameter point. HY-WU implements functional (operator-level) memory as a neural module: a generator that synthesizes weight updates on-the-fly from the instance condition, yielding instance-specific operators without test-time optimization.

04.
medRxiv (Medicine) 2026-06-17

County Year Informatics Model for Annual and Cumulative Unique Lung Cancer Screening Eligibility in Maryland, 2026 to 2045

Purpose: Population-level lung cancer screening programs require denominators that reflect age, smoking history, geography, and changing eligibility over time. We estimated annual prevalent and 20-year cumulative unique low-dose computed tomography screening eligibility for Maryland residents under alternative screening criteria. Methods: We built a deterministic cohort-cell stock-flow simulation using Maryland county-equivalent jurisdiction projections by age, sex, and race/ethnicity, with ACS socioeconomic/nativity covariates and smoking-history priors for ever-smoked status, pack-years, and quit-years. Scenarios included USPSTF 2013 legacy, USPSTF 2021, ACS 2023/2024, a risk-model-expanded sensitivity, and ever-smoked-only capacity stress tests. Cumulative unique eligibility counted people once at first eligibility rather than summing annual prevalent person-years. Results: Under USPSTF 2021, an estimated 238,346 Maryland residents were eligible in 2026 and 245,326 in 2045. The 20-year cumulative unique denominator was 768,668, whereas naively summing annual prevalent counts produced 4,850,735 person-years, a 6.31-fold overcount. ACS 2023/2024 expanded annual eligibility to 314,616 in 2026 and cumulative unique eligibility to 902,796 by adding remote former smokers. Ever-smoked-only adult eligibility was 1,957,699 in 2026 and 3,383,683 cumulative unique over 20 years. Conclusion: A Maryland statewide screening initiative should plan from cumulative unique eligibility and county-equivalent jurisdiction-specific burden rather than annual prevalence alone. Explicit pack-year and quit-year modeling materially changes statewide and county allocation compared with current-smoking proxy models.

05.
arXiv (CS.AI) 2026-06-17

STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training

arXiv:2606.17979v1 Announce Type: new Abstract: Existing RL post-training methods for text-to-image generation usually convert the final-image reward into a single scalar advantage and apply it with the same strength to the entire generative trajectory. However, text-to-image generation naturally has temporal and spatial structure: different denoising steps are responsible for different generation stages, and the content that truly determines text alignment often appears only in part of the image. This granularity mismatch makes it difficult for policy updates to focus on the generative components that actually affect the reward. To address this issue, we propose SpatioTemporal Adaptive Reward (STAR) Allocation for RL post-training of text-to-image diffusion and flow models. STAR uses text-image attention inside the generative model and starts from the core content that the user truly cares about in the prompt. It constructs spatial allocation maps that dynamically vary across denoising steps and rollouts, and allocates the same group-relative advantage to more relevant latent regions with almost no additional computational overhead. STAR then applies stronger policy updates to these regions through a spatially resolved policy objective. We use Stable Diffusion 3.5 Medium as the base model and evaluate on three tasks: GenEval, OCR text rendering, and PickScore. Experimental results show that STAR improves compositional semantic alignment, text rendering, and preference optimization without changing the external reward source, achieving $\mathbf{0.9759}$, $\mathbf{0.9757}$, and $\mathbf{23.60}$ on GenEval, OCR, and PickScore, respectively.

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

Robust Generation of Topological Biphoton Mode via Adiabatic Passage

arXiv:2606.19786v1 Announce Type: new Abstract: Topological waveguide arrays support robust mode propagation in the presence of fabrication imperfections, providing a significant advantage for on-chip quantum information processing. However, this robustness does not fully extend to nonlinear biphoton generation. Structural disorder can enhance the excitation of non-topological biphoton modes during nonlinear interactions, which degrades the quantum properties of the generated state. To overcome this limitation, we propose an adiabatic passage that connects an isolated site to a topological defect array. By initiating the nonlinear process in a strongly isolated regime, nonlinear coupling to unwanted modes is effectively suppressed, thereby preserving the Schmidt number of the generated state. The subsequent adiabatic connection facilitates the high fidelity transfer of the generated biphoton into the topological biphoton mode. Our numerical simulations demonstrate that, unlike conventional topological structures, the adiabatic scheme maintains both high biphoton fidelity and a unit Schmidt number in the presence of waveguide gap disorder. Furthermore, we show that this robustness extends to path entangled NOON states, achieving a near-unity quantum interference visibility. Our approach provides a practical design strategy for disorder-tolerant integrated quantum photonic devices.

09.
arXiv (CS.AI) 2026-06-24

Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles

arXiv:2505.02281v3 Announce Type: replace-cross Abstract: This paper explores the performance of a random Gaussian smoothing zeroth-order (ZO) scheme for minimising quasar-convex (QC) and strongly quasar-convex (SQC) functions in both unconstrained and constrained settings. For the unconstrained problem, we establish the ZO algorithm's convergence to a global minimum along with its complexity when applied to both QC and SQC functions. For the constrained problem, we introduce the new notion of proximal-quasar-convexity and prove analogous results to the unconstrained case. Specifically, we derive complexity bounds and prove convergence of the algorithm to a neighbourhood of a global minimum whose size can be controlled under a variance reduction scheme. Beyond the theoretical guarantees, we demonstrate the practical implications of our results on several machine learning problems where quasar-convexity naturally arises, including linear dynamical system identification and generalised linear models.

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

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents

arXiv:2602.14211v3 Announce Type: replace-cross Abstract: Agent skills extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources, improving reusability but creating a new supply-chain attack surface. A malicious or compromised skill can be repeatedly loaded as trusted guidance and steer downstream tool use. Existing skill-based prompt-injection attacks are often manual and brittle, because explicit malicious instructions are rejected or ignored when they are not aligned with the original workflow. We propose SkillJect, the first automated framework for generating poisoned skills against skill-enabled agent systems. SkillJect uses two coordinated channels. In the artifact channel, it hides the payload inside an auxiliary helper script. In the instruction channel, it rewrites SKILL.md with a front-loaded inducement strategy, placing injected content at the beginning and framing the helper script as a mandatory prerequisite or initialization step. The rewritten instruction explicitly references the helper-script path and provides an executable example command, making the helper appear to be a legitimate setup step before normal skill operations. SkillJect further adopts a closed-loop multi-agent process to improve attack effectiveness. An Attack Agent generates poisoned skills, a Victim Agent executes downstream tasks with the poisoned skill, and an Evaluate Agent inspects execution traces to determine whether the hidden payload was executed. The Attack Agent then uses this feedback to diagnose failure causes and rewrite SKILL.md, while keeping the payload fixed. Experiments across skill-enabled platforms, backend LLMs, and attack categories show that SkillJect substantially outperforms naive direct injection and prior manual skill-injection attacks, highlighting poisoned skills as a persistent threat in reusable skill ecosystems.

11.
arXiv (CS.CV) 2026-06-24

From Open Waters to Enclosed Cabins: ProteusVPR for Cross-Scene Visual Place Recognition in Maritime Perception and Cabin Inspection

Autonomous robotic inspection in maritime environments presents unique challenges for Visual Place Recognition (VPR) due to cross-scene perceptual shifts. Robots navigating ship-borne environments must transition between visually distinct domains: open decks with sparse textures and severe illumination changes, and enclosed cabins with repetitive structures and high visual ambiguity. Existing VPR methods, designed primarily for urban or indoor scenes, fail to generalize reliably across these starkly different scenarios. To address this, we propose ProteusVPR, a two-stage retrieval-refinement framework. The first stage employs any standard VPR model for initial image retrieval. The second stage introduces a geometric-visual estimation network that fuses the retrieved image with two temporally preceding frames, incorporating geometric descriptors, a local affine coordinate system, and camera azimuth encoding to achieve precise localization. To support this task, we introduce the XHZ dataset, an 8K-panoramic ship-borne dataset collected from an operational vessel, featuring multi-floor cabin structures, deck transition zones, and strict query-database separation for rigorous evaluation. Extensive experiments on the XHZ dataset demonstrate that ProteusVPR consistently improves the localization accuracy across multiple VPR backbones, reducing mean localization error by over 60\% on average and that ProteusVPR offers an effective and robust solution for precise visual localization in challenging, cross-scene maritime environments.

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

Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents

arXiv:2606.12674v1 Announce Type: new Abstract: Compact language models (LMs) reduce cost, latency, and deployment risk for tool agents. Yet MCP-style tool use requires more than isolated function calling: an agent must discover tools from live catalogs, satisfy schemas, preserve dependencies across intermediate outputs, and ground final responses in executed evidence. Small planners often generate plausible workflow graphs that fail under tool resolution, parameter validation, dependency tracking, or execution. We argue that this failure mode is poorly handled by small-corpus distillation. A few hundred teacher traces can teach workflow format, but rarely cover the recovery behavior needed to repair failed plans over changing tool catalogs. We introduce Evoflux, an inference-time evolutionary search method that treats compact tool use as the repair of executable tool workflows. It evolves typed workflow graphs through structured edits, execution feedback, adaptive intensity, meta-guided redesign, and diversity pruning. On held-out MCP-Bench tasks spanning live MCP servers and 250 tools, Evoflux raises execution feasibility from roughly 3% to 17-24% across small planners. In contrast, SFT and SFT+DPO on the same search-mined data match, underperform, or collapse below zero-shot performance; ReAct reaches higher peaks, but with higher variance and token cost. These results show that execution-grounded search is more reliable under scarce teacher-trace budgets.

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

Foundations of Practical Quantum Advantage in Quantum-Informed Machine Learning for Predicting Chaos

arXiv:2606.13422v1 Announce Type: cross Abstract: We develop theoretical foundations for a practical quantum-advantage mechanism in quantum-informed machine learning for chaotic dynamical systems. A family of k-indexed higher-order quantum statistical priors (Q-Priors) hosts the k-point marginal of the invariant measure on n_q = kq qubits, extending the single-site construction of prior work. We prove a two-stage advantage. In the representation stage, superposition and entanglement compactly store non-factorisable spatial correlations of the invariant measure on n_q qubits. In the extraction stage, joint Bell measurements on two copies estimate any post hoc Pauli functional with a copy-pair count independent of n_q, whereas any adaptive single-copy protocol for the corresponding full-Pauli read-out requires Omega(2^(n_q)) copies; this is a provable quantum-classical separation in copy-measurement complexity. The two-copy read-out is realised in simulation and on IQM superconducting processors. Two case studies instantiate the mechanism in workflows of independent scientific value: a turbulent channel-flow study in which the two-copy read-out yields a named non-diagonal correlator of the invariant measure (the velocity-direction coherence), and a medium-range weather forecasting workflow on the European Centre for Medium-Range Weather Forecasts ERA5 reanalysis in which the diagonal k

14.
arXiv (CS.CV) 2026-06-12

Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning

Unsupervised video object-centric learning aims to decompose dynamic scenes into persistent, object-level representations without supervision. However, existing slot-based methods struggle to maintain stable object identity in challenging settings such as rapid motion and partial occlusion. First, they typically encode both the per-frame appearance of an object and its identity across frames in a single slot vector, creating an objective conflict that leads to slot swapping: reconstruction requires sensitivity to transient visual changes, whereas temporal consistency requires invariance to them. Second, the token renormalization used in Slot Attention can amplify weakly attending slots, allowing them to absorb tokens from other objects and destabilize slot-to-object correspondence. We propose Dual-State Slot Attention (DSSA), a fully self-supervised framework that addresses these limitations by separating appearance from identity and by reducing spurious updates from weakly matching slots. DSSA decomposes each slot into a local state for per-frame appearance and an identity state for temporally stable object information, thereby aligning reconstruction and temporal consistency with separate representations. The identity state is updated through a learned recurrent transition that acts as a temporal filter on the local state, while competition-modulated aggregation (CMA) down-weights updates from weakly matching slots and prevents them from absorbing tokens from other objects. Experiments on MOVi-C, MOVi-D, and YouTube-VIS demonstrate that DSSA consistently improves segmentation quality and temporal consistency over prior methods, while also yielding stronger downstream object recognition and video dynamics prediction. Code and models will be made publicly available upon acceptance.

15.
arXiv (CS.CV) 2026-06-18

Hierarchical Multi-Modal Retrieval for Knowledge-Grounded News Image Captioning

Traditional image captioning methods often struggle to generate comprehensive, context-rich descriptions, especially for details not directly observable from visual cues. To overcome this, we propose a novel retrieval-augmented image captioning framework that generates captions with deeper insights, such as object attributes, event context, and underlying significance, by leveraging external knowledge. Our approach features a hierarchical multi-modal article retrieval mechanism that moves beyond monolithic text entities. This retrieval considers article structure-aware features, including weighted textual components (e.g., headlines, body sections) and visual placement patterns, alongside multi-faceted similarity computations (content–visual, visual–visual, and discourse positioning). A subsequent contextual relevance refinement stage further enhances the retrieved information. The retrieved articles then serve as the knowledge base for caption generation: first, a VLM generates a concise image description; second, we segment relevant information from the retrieved articles based on this description; and finally, an LLM utilizes both the description and extracted knowledge to generate a comprehensive, contextually detailed caption. We participated in the ACM Multimedia EVENTA 2025 Challenge and achieved 5th place with an overall score of 0.2824 on the private test set of the OpenEvent-V1 dataset. Source code is publicly released at https://github.com/mf0212/EVENTA-Challange.

16.
arXiv (math.PR) 2026-06-16

Experimentation for Different Scheduling Policies on Queues: Mixed Differences-in-Q Estimators Based on Little's Law

arXiv:2605.29641v2 Announce Type: replace-cross Abstract: In data centers, tasks are dispatched to various servers to evenly distribute the workload. When a data center considers implementing a new scheduling algorithm, it typically conducts an A/B test prior to deployment to assess the real-world impact of this new method. However, a straightforward A/B test might be interfered with so-called ``Markovian'' interference. We utilized the Differences-in-Q estimator, as developed by Farias et al. (2022), and introduced mixed Differences-in-Q estimators grounded in Little's Law. We show that our A/B testing methods significantly reduce bias and variance when testing various scheduling policies. Extensive simulations were conducted under scenarios like non-stationary arrival rates, heterogeneous service rates, and communication delays. These simulations highlight the robustness and efficacy of our A/B testing approach.

17.
arXiv (CS.LG) 2026-06-18

Quantum Annealing Enhanced Reinforcement Learning for Accurate Remaining Useful Lifetime Prediction

arXiv:2606.18503v1 Announce Type: new Abstract: Remaining useful life (RUL) estimation is central to predictive maintenance, where an unplanned failure can cost far more than the asset itself. Statistical degradation models miss the strong nonlinearity of real systems, and data-driven models often converge to suboptimal solutions in high-dimensional, non-convex search spaces. We propose a Quantum Annealing enhanced Q-Learning (QAQL) framework that couples the sampling behaviour of quantum annealing with the sequential decision making of Q-learning. Each Q-value update is encoded as a small quadratic unconstrained binary optimization (QUBO) whose ground state is the greedy action; rather than acting as a deterministic optimizer, the annealer returns a distribution over near-optimal actions across many reads, and this stochastic action selection supplies the exploration that curbs premature convergence on nonlinear degradation trajectories. The QUBO is solved on the D-Wave Advantage system using minor embedding, with the annealer woven into the reinforcement-learning loop rather than bolted on after training. We validate QAQL on two public benchmarks: the NASA C-MAPSS turbofan engine datasets and a device-fleet predictive maintenance dataset. Averaged over many independent runs and across six error metrics, QAQL outperforms the classical and quantum baselines considered in this study, with statistically significant improvements. The results indicate that quantum annealing is a usable, not merely theoretical, optimizer inside a reinforcement-learning loop for industrial predictive-maintenance applications.

18.
arXiv (CS.CL) 2026-06-16

AmchiBias: Measuring Stereotypical Bias in Goan Identity Groups with a Minimal Pair Dataset in English and Konkani

Socio-cultural stereotypical bias is an important consideration in the development and deployment of NLP systems. It is however often considered only at the national level, despite rich subnational socio-cultural structures. We present AmchiBias, the first benchmark for measuring socio-cultural stereotypical bias for the Indian state of Goa with its unique historically multicultural setting. It covers various Goan identity groups and comprises 313 minimal pairs across eight sociodemographic dimensions in both English and Devanagari Konkani. We then evaluate stereotypical bias in five multilingual encoder models on this benchmark. We find near-chance scores in Konkani, reflecting language incompetence for general multilingual models and a lack of Goan cultural competence for Indian language models. Queried in English, models with a stronger Indian language coverage show higher bias for pan-Indian groups than hyperlocal Goan groups. This suggests the English signal reflects pan-Indian pretraining associations rather than genuine Goan cultural knowledge. Our findings highlight a critical gap in low-resource multilingual NLP evaluation for hyperlocal community identities.

19.
arXiv (CS.LG) 2026-06-16

CREST: Deployment-Realistic Hardware-in-the-Loop NAS for Embedded Sensing Systems

arXiv:2606.15004v1 Announce Type: cross Abstract: Deploying neural networks on low-power microcontrollers (MCUs) requires selecting model architectures under tight memory, latency, and energy constraints. Existing workflows often simplify this process along one or more axes: static proxy costs such as FLOPs or parameters, treating one MCU as representative, and continuous-inference tests instead of deployed sensing schedules. These assumptions can mis-rank Pareto-front candidates, miss infeasible deployments, and obscure schedule-dependent energy. We present CREST (Cross-platform Runtime Evaluation and Search Tool), a deployment-realistic hardware-in-the-loop (HIL) neural architecture search (NAS) framework for MCU sensing systems. CREST keeps the optimizer, HIL measurement boundary, logging, and replay workflow fixed while exposing workload, model family, target backend, schedule, quantization, and scoring policy as configurable axes. This makes deployment effects experimentally separable within one reusable workflow. We evaluate CREST on inertial odometry and audio classification across three Arm Cortex-M targets. For inertial odometry, measured-energy HIL search reduces median per-inference energy by 41.7% versus FLOPs-based selection and 40.8% versus memory-traffic-based selection at similar error. FLOPs-based selection also chooses infeasible deployments on memory-constrained targets. On the STM32 N657 target, continuous-inference and duty-cycled searches produce different Pareto frontiers. For audio classification, the same application-level policy selects different DS-CNN architectures on different boards, and cross-board replay changes deployment cost substantially. Overall, CREST shows that deployment-realistic MCU NAS must jointly optimize model architecture, target platform, runtime schedule, and deployment policy rather than relying only on static proxy costs or continuous-inference measurements.

20.
arXiv (CS.AI) 2026-06-15

DIFF-ERO: A Conformance-Aware Loss for Deep Learning in Process Mining

arXiv:2606.14283v1 Announce Type: cross Abstract: Deep learning has driven many recent advances in process analytics, especially for predictive and prescriptive monitoring. However, standard objectives such as cross-entropy optimize local next-step likelihoods and only implicitly capture control-flow structure. As a result, models can achieve high token-level accuracy while permitting imprecise global behaviour. We introduce DIFF-ERO, a conformance-aware loss function for deep learning models on process data. DIFF-ERO is a differentiable formulation of entropy-based stochastic conformance that incorporates control-flow information during training. Our approach constructs batch-level stochastic transition matrices with soft edge memberships, allowing structural precision and recall signals to directly inform backpropagation. The loss is model-agnostic and can be applied whenever the final representation parametrizes stochastic transitions. We instantiate DIFF-ERO in transformer encoder-decoder pipelines for next-activity prediction and use it jointly with cross-entropy to analyse its theoretical components with respect to convergence. Across benchmarks comparing other loss functions and targets, DIFF-ERO shows improved predictive performance where structure matters most while maintaining parity elsewhere. At the same time, the learned stochastic automaton converges towards the structural ground truth, indicating that the network internalizes process model structure.

21.
arXiv (CS.LG) 2026-06-12

EPM-JEPA: Operator-Side Experience Modulation in JEPA-Family World Models

arXiv:2606.12979v1 Announce Type: new Abstract: JEPA-family world models use a static predictor whose weights do not adapt when test-time dynamics diverge from training. We compare two mechanisms for incorporating accumulated experience into a JEPA predictor under distribution shift: operand-side injection, where a compressed experience representation is added as a residual to the predictor's hidden state (EI-JEPA), and operator-side modulation, where the same representation generates low-rank weight deltas via LoRA applied to the predictor's weights (EPM-JEPA). On a pre-registered comparison (Moving MNIST, gravity shift), EPM-JEPA (D_shift^{n=50} = 0.7848 +/- 0.0078, three seeds) differs from EI-JEPA (0.8238) by delta = 4.74% - Outcome C: a null result - by our stated criterion, a valid outcome. As a secondary, non-pre-registered observation, EPM-JEPA improves 1.90% over a no-memory baseline (0.8000), consistently across seeds, while EI-JEPA underperforms the baseline, indicating the benefit is specific to weight-level modulation. Our primary contribution is a mechanism analysis: the D_shift^{n=50} trajectory reflects three independent dynamical processes - buffer cycling, EMA target drift, and an intrinsic LoRA settling transient of +0.021 - rather than convergence to equilibrium. These findings motivate PEM-JEPA, a physics-grounded successor addressing this dynamical-peak limitation.

22.
arXiv (CS.LG) 2026-06-16

Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning

arXiv:2606.16236v1 Announce Type: new Abstract: Reinforcement learning (RL) often suffers from performance degradation when deployed in environments that differ from those encountered during training. Existing techniques such as domain randomization (DR) mitigate this, but require access to diverse training environments and full trajectory observability, assumptions that fail in privacy-preserving or restricted scenarios where only scalar performance metrics are available. We propose Generalization via Evolutionary Reward Shaping (GERS), a bilevel optimization approach to improve generalization on unseen test environments using only scalar feedback from validation environments. At the lower level, an RL agent guided via a reward function shaped by the upper level learns a policy on a limited set of training environments with accessible trajectory data; at the upper level, CMA-ES optimizes the reward shaping parameters to maximize the cumulative unshaped reward on separate validation environments for which trajectory access is unavailable. Results on continuous control tasks indicate that GERS outperforms the standard RL baseline on unseen test environments. GERS performance is comparable to DR, despite DR treating the combined set of training and validation environments of GERS as a single training set that requires trajectory access, whereas GERS cannot access validation trajectories. These results confirm that GERS effectively enhances generalization under restricted data access constraints.

23.
bioRxiv (Bioinfo) 2026-06-22

When Less Is Not More: DICEPro Mitigates the Impact of Incomplete Reference Matrices on Cellular Frequency Deconvolution.

Cellular deconvolution aims to estimate the frequencies of different cell populations from gene expression measurements in a biological sample. Supervised approaches, such as CIBERSORTx and DISSECT, critically depend on the reference signature matrix, which encodes the gene expression profiles of cell-types based on prior knowledge. Despite numerous deconvolution methods, the impact of missing cell populations in the reference matrix remains understudied. Here, we evaluate the robustness of state-of-the-art deconvolution approaches using simulations based on real dataset examples combined with statistical modeling, validated against published data, and multiple real benchmark datasets. Results show that deconvolution performance remains stable when the reference matrix includes most cell-types, but declines sharply as the matrix becomes incomplete, especially for abundant cell populations. To address the limitations of incomplete reference matrices, we introduce DICEPro, an optimization-based framework designed to enhance existing deconvolution methods. By systematically adjusting the reference signatures, DICEPro better accounts for missing or underrepresented cell populations, leading to improved precision and robustness. We show that DICEPro consistently boosts deconvolution performance across both simulated datasets, derived from real data examples, and multiple real biological datasets, offering a practical solution when standard methods are hindered by incomplete references.

24.
arXiv (CS.CL) 2026-06-15

Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2

作者:

Structured width pruning of GLU-MLP layers in Llama-3.2 models, guided by the Peak-to-Peak Magnitude (PPM) criterion, reveals a systematic dichotomy in how reducing the expansion ratio affects different model capabilities. While performance on tasks relying on parametric knowledge (e.g., MMLU, GSM8K) and perplexity metrics degrades predictably with decreasing expansion ratios, instruction-following capabilities improve at the 2.4x equilibrium ratio (IFEval: +4.8 points / +46% in Llama-3.2-1B and +3.7 points / +39% in Llama-3.2-3B), and multi-step reasoning remains robust (MUSR). This pattern, observed consistently across both evaluated model sizes, challenges the prevailing assumption in compression research that pruning induces uniform degradation. To investigate this, we evaluated seven expansion ratio configurations using comprehensive benchmark suites that assess factual knowledge, mathematical reasoning, language comprehension, instruction-following, and truthfulness. Our analysis identifies the expansion ratio as a critical architectural parameter that selectively reshapes the model's task performance profile, rather than merely serving as a compression metric.

25.
arXiv (CS.CL) 2026-06-18

LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents

RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity parameters accumulate monotonically across stages, while regularization parameters predominantly oscillate in response to shifting training dynamics. This distinction matters because fixed schedules commit all parameters to fixed trajectories and therefore cannot express the non-stationary exploration-exploitation tradeoffs that regularization must track; the principle provides actionable design rules for multi-stage training. We discover this through LLMZero, a system where LLM agents search over training trajectories via tree search, diagnosing pathologies at each checkpoint and proposing coordinated multi-parameter transitions. Across 4 diverse GRPO tasks, LLMZero discovers strategies that improve over the base model by 9% to 140% relative and over grid search by 6% to 15% relative, consistently outperforming random search and the skill-based agent. The structural principle transfers across tasks, providing an explanation for why discovered strategies take qualitatively different forms yet share similar parameter dynamics.