arXiv:2503.00163v2 Announce Type: replace
Abstract: The study of collisionless shocks and their role in cosmic ray acceleration has gained importance through observations and simulations, driving interest in reproducing these conditions in laboratory experiments using high-power lasers. In this work, we examine the role of three-dimensional (3D) effects in ion acceleration in quasi-perpendicular shocks under laboratory-relevant conditions. Using hybrid particle-in-cell simulations (kinetic ions and fluid electrons), we explore how the Alfv\'enic and sonic Mach numbers, along with plasma beta, influence ion energization, unlocked only in 3D, and establish scaling criteria for when conducting 3D simulations is necessary. Our results show that efficient ion acceleration requires Alfv\'enic Mach numbers $\geq 25$ and sonic Mach numbers $\geq 13$, with plasma-$\beta \leq 5$. We theoretically found that, while 2D simulations suffice for current laboratory-accessible shock conditions, 3D effects become crucial for shock velocities exceeding 1000 km/s and experiments sustaining the shock for at least 10 ns. We surveyed previous laboratory experiments on collisionless shocks and found that 3D effects are unimportant under those conditions, implying that 1D and 2D simulations should be enough to model the accelerated ion spectra. However, we do find that the same experiments are realistically close to accessing the regime relevant to 3D effects, an exciting prospect for future laboratory efforts. We propose modifications to past experimental configurations to optimize and control 3D effects on ion acceleration. These proposed experiments could be used to benchmark plasma astrophysics kinetic codes and/or employed as controllable sources of energetic particles.
Science Journals
arXiv:2607.16773v1 Announce Type: new
Abstract: The classical Ingleton inequality is known to hold for entropic points under specific exact conditional independence constraints. Recently, Matveev and Romashchenko (2026) investigated the stability of these implications, quantifying the extent to which the Ingleton inequality can be violated when a group of conditional mutual information terms is small but non-zero. While their proofs relied fundamentally on the complex framework of tropical probability spaces, we revisit these stability results using a completely tropicalization-free approach. By developing an alternative framework, we significantly streamline the underlying concepts and proofs, derive explicit error terms, and improve some estimates. Furthermore, we resolve an open problem posed in prior work by exhibiting a new infinite family of entropy inequalities that establishes the stability of the sum of two Ingleton expressions.
arXiv:2503.01701v2 Announce Type: replace
Abstract: Most microeconomic models of interest involve optimizing a piecewise linear function. These include contract design in hidden-action principal-agent problems, selling an item in posted-price auctions, and bidding in first-price auctions. When the relevant model parameters are unknown and determined by some (unknown) probability distributions, the problem becomes learning how to optimize an unknown and stochastic piecewise linear reward function. Such a problem is usually framed within an online learning framework, where the decision-maker (learner) seeks to minimize the regret of not knowing an optimal decision in hindsight. This paper introduces a general online learning framework that offers a unified approach to tackle regret minimization for piecewise linear rewards, under a suitable monotonicity assumption commonly satisfied by microeconomic models. We design a learning algorithm that attains a regret of $\widetilde{O}(\sqrt{nT})$, where $n$ is the number of ``pieces'' of the reward function and $T$ is the number of rounds. This result is tight when $n$ is \emph{small} relative to $T$, specifically when $n \leq T^{1/3}$. Our algorithm solves two open problems in the literature on learning in microeconomic settings. First, it shows that the $\widetilde{O}(T^{2/3})$ regret bound obtained by Zhu et al. [Zhu+23] for learning optimal linear contracts in hidden-action principal-agent problems is not tight when the number of agent's actions is small relative to $T$. Second, our algorithm demonstrates that, in the problem of learning to set prices in posted-price auctions, it is possible to attain suitable (and desirable) instance-independent regret bounds, addressing an open problem posed by Cesa-Bianchi et al. [CBCP19].
arXiv:2503.10677v3 Announce Type: replace
Abstract: Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG leverages external knowledge sources, such as documents, databases, or structured data, to improve model performance and generate more accurate and contextually relevant outputs. This survey aims to provide a comprehensive overview of RAG by examining its fundamental components, including retrieval mechanisms, generation processes, and the integration between the two. We discuss the key characteristics of RAG, such as its ability to augment generative models with dynamic external knowledge, and the challenges associated with aligning retrieved information with generative objectives. We also present a taxonomy that categorizes RAG methods, ranging from basic retrieval-augmented approaches to more advanced models incorporating multimodal data and reasoning capabilities. Additionally, we review the evaluation benchmarks and datasets commonly used to assess RAG systems, along with a detailed exploration of its applications in fields such as question answering, summarization, and information retrieval. Finally, we highlight emerging research directions and opportunities for improving RAG systems, such as enhanced retrieval efficiency, model interpretability, and domain-specific adaptations. This paper concludes by outlining the prospects for RAG in addressing real-world challenges and its potential to drive further advancements in natural language processing.
arXiv:2503.18931v3 Announce Type: replace
Abstract: Vision Foundation Models (VFMs) provide strong visual representations for a wide range of applications. In this work, we enhance prevailing VFMs through multimodal training, allowing them to effectively process visual inputs at varying resolutions while producing visual representations that are better aligned with language representations, regardless of their original pre-training objectives. To this end, we introduce M-CPT, a Multimodal Continual Pre-Training framework designed to improve the understanding capability of pre-trained VFMs while preserving their strong visual representation quality. M-CPT introduces a Continual Position Embedding (CPE) for handling flexible visual resolutions, along with a feature alignment objective that improves the consistency between visual and textual representations during multimodal training. Extensive experiments on leading VFMs, including DINOv2, SigLIP, and AIMv2, demonstrate that M-CPT consistently improves multimodal understanding performance while preserving strong performance on standard vision benchmarks such as classification and segmentation.
arXiv:2607.18069v1 Announce Type: new
Abstract: As more capable AI models are increasingly integrated into critical computer systems, the lack of control over AI intent motivates safety mechanisms. Existing software safeguards impose only behavioral constraints that can potentially be bypassed by sufficiently intelligent models. While hardware-level safety enforcement has been recognized as an essential last line of defense, few mechanisms have been proposed beyond policy regulations on unauthorized accesses or coarse full-chip shutdown. What is missing is a fine-grained, dynamic intervention mechanism at the architecture level.
In this paper, we introduce a set of microarchitecture knobs which dynamically control the available hardware resources to limit AI performance at runtime. We evaluate candidate knobs spanning the GPU memory subsystem, across capacity, bandwidth, latency and frequency dimensions, and narrow down to four strong candidates: L2 size, L2 latency, L2 bandwidth, and shared memory port access rate. To minimize new logic and extra design cost, we build all four mechanisms from well-established microarchitectural primitives: cache way masking, credit-based rate limiting, latency insertion, and bank arbitration. We show that these knobs achieve high performance sensitivity (up to 80% performance cut at 1/8 resource availability), negligible implementation cost (<~10K flip flops), fast stabilization after dynamic throttling (5-80K cycles), and minimal collateral impact on the rest of the chip. Further, multi-knob analysis reveals combinations of knobs that amplify the performance degradation beyond the effect of each knob individually, which enables a broader range of performance targets.
arXiv:2607.18074v1 Announce Type: new
Abstract: Equivariant graph neural networks repeatedly apply edge-conditioned tensor-product convolutions over graph edges. Conventional implementations materialize edge-specific weights, messages, and adjoints, causing tensor-product workspace and memory traffic to grow rapidly with graph size and operator width. This limits feasible workloads and can prevent larger problems from fully utilizing the GPU.
We show that these edge-sized intermediates are artifacts of the execution schedule, not requirements of the equivariant operator. By reassociating radial projection, spherical-harmonic coupling, and graph aggregation, edge-local products can be consumed directly into bounded receiver-side state. The resulting streaming formulation preserves fully connected multiplicity mixing and extends through forward, backward, and double backward.
We implement this formulation in Sobek, a generated-CUDA backend, and evaluate it across edge-scaling regimes and varied feature structures. Across two operator families and all three differentiation orders, Sobek is faster in all 75 capacity-matched comparisons, with speedups ranging from $1.2\times$ to $49.7\times$, and reduces peak allocated memory by up to 99\%. It also executes workloads up to two orders of magnitude beyond OpenEquivariance's capacity while retaining near-peak throughput. These results show that edge-scaled tensor-product workspace is a property of the conventional schedule, not of equivariant convolution itself.
arXiv:2607.16789v1 Announce Type: new
Abstract: Real-world perception and decision making are inherently multimodal, integrating complementary signals across modalities. However, training multimodal models faces two main obstacles. First, collecting large-scale, well-aligned paired multimodal datasets is often impractical, making end-to-end multimodal training difficult. Second, existing multimodal representations frequently entangle information shared across modalities with modality-specific information, hindering interpretability and control. We introduce MultiLoReFT, an efficient and scalable low-rank representation fine-tuning framework for multimodal learning with pretrained unimodal models. MultiLoReFT extends low-rank adaptation to the multimodal setting and learns interpretable projection subspaces that decouple shared and modality-specific information. Across simulated and real-world benchmarks, it produces representations that support multimodal prediction while explicitly revealing how shared and modality-specific information is distributed across modalities.
arXiv:2607.16918v1 Announce Type: new
Abstract: We develop new adaptive numerical schemes for one- and two-dimensional hyperbolic systems of conservation laws. The methodology relies on the use of a smoothness indicator to automatically partition the computational domain into smooth and nonsmooth (``rough``) regions. We then follow the scheme adaption strategy recently introduced in [S. Chu, P. Feng, V. A. Kolotilov, A. Kurganov, and V. V. Ostapenko, Commun. Comput. Phys., accepted], but instead of the quasi-linear (QL) fifth-order finite-difference scheme used there, we employ the new QL seventh- and ninth-order schemes in the smooth regions. A series of numerical experiments for the Euler equations of gas dynamics demonstrates that the new adaptive schemes contain a smaller amount of numerical dissipation and achieve higher resolution compared with their counterpart that uses the QL fifth-order scheme in the smooth areas.
arXiv:2504.00617v5 Announce Type: replace
Abstract: Exceptional points (EPs) are central to non-Hermitian physics because of their unique properties and broad application prospects. While extensively studied in parity-time ($\mathcal{P}\mathcal{T}$)-symmetric systems and under Markovian dynamics, their exploration in broader pseudo-Hermitian settings, particularly in those involving non-Markovian environments, remains largely unexplored. In this study, we investigate a pseudo-Hermitian system consisting of three coupled optical cavities interacting with non-Markovian environments. Compared to the Markovian baseline, we demonstrate that the emergence of non-Markovian memory effects enlarges the dimensionality of the parameter space of the system, thereby giving rise to higher-order EPs. Furthermore, we show that these non-Markovianity-induced higher-order EPs admit a topological characterization as defects in the relevant pseudo-Hermitian parameter space, with quantized charges described by resultant winding numbers. Moreover, we observe that the pseudo-Hermitian system with an effective gain induced by coherent perfect absorption enables the higher-order EPs to be directly read out from the output spectrum. We also note that the non-Markovian mechanism for generating higher-order EPs is not restricted to pseudo-Hermitian systems, but can be extended to generic non-Hermitian quantum systems. Additionally, possible experimental implementations based on superconducting circuits are also discussed.
arXiv:2607.18110v1 Announce Type: new
Abstract: Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with distinct quality profiles. We propose Experiential Learning (EL), which repurposes the feedback model from an LLM-as-a-Judge into an LLM-as-a-Coach. The coach distills its assessment of each on-policy response into transferable experiential knowledge, which conditions a teacher model and is internalized by the policy through on-policy context distillation. Compared with scalar rewards, this higher-bandwidth feedback channel provides dense supervision and preserves fine-grained preferences among high-quality responses. Across two policy families, with feedback from the policy itself or a proprietary model, EL consistently outperforms rubric-based RL on held-out and unseen open-ended tasks. Notably, EL generalizes better beyond the training distribution, and mitigates reward hacking. These findings establish experiential knowledge as a richer and more generalizable learning signal for post-training on non-verifiable tasks.
arXiv:2607.16997v1 Announce Type: new
Abstract: Mathematicians distinguish proofs that explain, simplify, or introduce a nonstandard route, but these judgments are difficult to operationalize. We study a deliberately narrower construct: time-relative proof-route nonstandardness in formal mathematics. For a Lean theorem, PriorProof extracts the dependency footprint of its elaborated proof term and scores the weighted surprisal of that footprint under a retrieval-conditioned, hierarchically smoothed prior built only from an earlier quarterly snapshot of Mathlib. The method requires no hand-built technique ontology and no human labels: statement retrieval is learned from proof-derived contrastive pairs, while the scored object is read mechanically from proof terms. In a blinded topology study, 100 presentations collapse to 76 distinct underlying pairs: 12 canonical contrasts shown three times for consistency screening and 64 distinct stratified pairs. Against the majority of three retained domain raters, PriorProof agrees on 53/76 pairs (69.7%, Wilson 95% CI 58.7-78.9%), including 11/12 canonical pairs (91.7%, 64.6-98.5%) and 42/64 stratified pairs (65.6%, 53.4-76.1%). Score-gap quartiles are nonmonotone after repeat collapse; the endpoints are 12/19 (63.2%, 41.0-80.9%) in the smallest-gap bin and 16/19 (84.2%, 62.4-94.5%) in the largest, supporting an endpoint-calibration tendency rather than a resolved staircase. The best language-model condition agrees on 60/76 pairs (78.9%, 68.5-86.6%); on paired outcomes, PriorProof alone is correct on 8 pairs and the model alone on 15 (exact two-sided McNemar p = 0.210), so the difference is not established at this sample size. We therefore present PriorProof not as a replacement for expert or model judgment, but as a decomposable, time-anchored signal whose score gap provides an interpretable reliability indicator.
arXiv:2607.17745v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly considered for environmental enforcement, but their ability to produce traceable enforcement decisions remains unclear. We introduce WuYu-EnvLE-Bench, a benchmark built from real enforcement cases, regulatory standards, and expert review. It contains 2,521 benchmark instances, 14 tasks, and 12 pollution-medium subdomains across pre-enforcement, in-enforcement, and post-enforcement workflows. Using Absolute Environmental Enforcement Score (AES) and Intelligent Enforcement Index (IEI), we evaluate open-source and closed-source LLMs across capability, response quality, and resource efficiency. Results show that LLMs perform well on rule-bounded tasks but remain unreliable in evidence-chain construction, contradiction detection, multi-source integration, and procedural judgment. Model scaling also shows diminishing returns: medium-sized models approach leading models in structured tasks, while larger models do not reliably overcome evidence-reasoning bottlenecks. WuYu-EnvLE-Bench highlights the need for evidence-grounded, rule-aware, and task-adaptive enforcement reasoning.
arXiv:2607.16936v1 Announce Type: new
Abstract: Pediatric bone age prediction is a crucial task in clinical practice that can help diagnose endocrine disorders and provide insight into a child's growth and development. However, conventional bone age prediction methods are often labor-intensive and require specialized radiological expertise. This paper presents a Deep Learning (DL)-based approach to pediatric bone age prediction using EfficientNet with Additive Attention, a state-of-the-art neural network architecture for image classification and regression tasks. The method utilizes over 12,000 X-ray images from the RSNA bone age dataset. It involves image preprocessing, transforming them into three-channel images, and training a Convolutional Neural Network (CNN) to automatically learn the features of hand bone images. This approach provides a more effective and accurate solution for predicting bone age, which is critical in diagnosing pediatric endocrine diseases. This work uses two variations of the EfficientNet model (B0 and B4), where EfficientNetB4 is also finetuned with the Additive Attention mechanism. These three models predict the age for the original age, and their comparison is shown in curves. The predicted ages depict that in most cases, EfficientNetB4 and EfficientNetB4 with Additive Attention (EN-AA) successfully predicted the bone ages more accurately regarding the original age, and their performance was better than the EfficientNetB0. Specific performance metrics are provided to underscore this improvement. Learning curves for training and validation loss confirm effective learning without overfitting or underfitting, further validating our approach's efficacy in pediatric endocrine disease diagnosis.
arXiv:2607.16517v1 Announce Type: cross
Abstract: Neural activity is widely held to organize on low-dimensional structure embedded in a high-dimensional state space. Persistent homology reads such structure directly from the pattern of pairwise correlations, without assuming in advance which variables are relevant. We apply persistent homology to microelectrode-array (MEA) recordings of spontaneous activity from human (Lancaster) and mouse (Pa\c{s}ca) cortical organoids, spanning $26$--$234$ simultaneously sorted units, and ask whether topological data analysis resolves structure at the node counts that neural recordings actually deliver. Building weighted networks in correlation space and characterizing them by Vietoris--Rips filtration, we find that the first homology ($H_1$, loops) rises significantly above a rate- and population-preserving null in $14$ of $18$ datasets. This loop structure occupies a non-redundant core: it is robust to random removal of units yet disrupted by targeted removal of the units that carry it. Topological richness grows with network size, and second homology ($H_2$) emerges significantly above the null only in the larger networks. These results show that persistent homology resolves structured topology in neural recordings at the scale experiments actually deliver.
arXiv:2607.16828v1 Announce Type: new
Abstract: Despite the impressive generative capabilities of text-to-image diffusion models, they remain vulnerable to implicit sexual prompts, where subtle cues disguised as benign terms or adversarial tokens unexpectedly generate the inappropriate content due to model biases or latent correlations in training data. Existing safety mechanisms face fundamental limitations: detection methods primarily identify explicit content and fail to capture implicit malicious intent, while mitigation approaches rely on static negative prompts inadequate for diverse implicit scenarios. To address these challenges, we propose UniNDM, a unified noise-driven framework that rethinks safety mechanisms through the lens of noise dynamics in diffusion processes. Our key insight is that early-stage predicted noise exhibits inherent separability between normal and sexually explicit content, which we theoretically demonstrates quadratically increasing semantic concentration with timestep. Leveraging this property, we develop a lightweight noise-based detector achieving superior accuracy with virtually no computational overhead. For mitigation, we introduce noise-enhanced adaptive negative guidance: dynamically generating context-specific negative prompts via large language models to handle diverse implicit content, while optimizing initial noise by suppressing attention concentration on explicit tokens to provide comprehensive protection. Besides the U-Net-based diffusion models, we further extend our framework to emerging Diffusion Transformer architectures through region-constrained semantic guidance tailored for their unified multimodal attention. Comprehensive experiments across U-Net models and DiT models on both natural and adversarial datasets demonstrate substantial improvements over state-of-the-art methods, including SLD, UCE, Safree, etc. Our code is publicly available at https://github.com/Aries-iai/UniNDM.
arXiv:2504.17356v3 Announce Type: replace
Abstract: Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning (RL)-based subspace exploration strategy provides a novel objective optimization-directed perspective and promising performance. Nevertheless, even with improved performance, current reinforcement learning approaches face challenges similar to conventional methods when dealing with complex datasets. These challenges stem from the inefficient paradigm of using one agent per feature and the inherent complexities present in the datasets. This observation motivates us to investigate and address the above issue and propose a novel approach, namely HRLFS. Our methodology initially employs a Large Language Model (LLM)-based hybrid state extractor to capture each feature's mathematical and semantic characteristics. Based on this information, features are clustered, facilitating the construction of hierarchical agents for each cluster and sub-cluster. Extensive experiments demonstrate the efficiency, scalability, and robustness of our approach. Compared to contemporary or the one-feature-one-agent RL-based approaches, HRLFS improves the downstream ML performance with iterative feature subspace exploration while accelerating total run time by reducing the number of agents involved.
arXiv:2607.17051v1 Announce Type: new
Abstract: The convergence of a finite element discretization for the two-dimensional Ricci flow is proved. In this method, the Ricci flow on a two-dimensional surface is formulated into solution-driven metric evolution, with the metric evolution driven by the Gauss curvature. The Gauss curvature satisfies a parabolic equation that in turn depends on the metric, thereby enhancing the parabolic structure of the problem. The solution-driven metric evolution formulation is discretized by the finite element method, and the convergence of finite element approximations is proved by adapting the matrix-vector formulation developed in the literature initially for studying solution-driven surface evolution in extrinsic curvature flow. In addition to its convergence, the proposed method also preserves important geometric structures of the Ricci flow at the discrete level, such as area conservation and the Gauss-Bonnet theorem. Extensive numerical experiments are presented to demonstrate the convergence of the proposed method as well as the simulation of Ricci flow.
arXiv:2607.17417v1 Announce Type: new
Abstract: Large language models confabulate chemical objects (molecular formulas, space groups, formation energies) in fluent reasoning traces, concentrated on long-tail entities where confidence is least trustworthy. Deterministic, database-grounded verification can catch and repair such errors without the coverage cost of blanket retrieval; the binding constraint, we find, is detection, not repair. Our tiered verifier extracts each checkable claim, checks it against authoritative databases and physics, and feeds the reference into a gated correction loop. Across four models and 528 condition-pinned prompts, gated correction cuts committed-formula error from 22% to 4% at $3.2\times$ fewer retrievals than blanket augmentation, beating a conversational oracle. Repair succeeds wherever a flag fires (80--97%); the bottleneck is in-loop detection recall. Grounding improves the final answer only when the verifier's scope reaches the deliverable (83% to 90%), and the lift appears only where extractable long-tail error exists: absent on near-ceiling physical constants, large on isotope half-lives (11% to 0%).
arXiv:2607.17901v1 Announce Type: cross
Abstract: In an incomplete round robin tournament, teams play against different sets of opponents. Given varying strengths of the teams, this raises a fairness issue. We establish the complexity of determining whether a fair draw exists under various scenarios involving the presence of pots (i.e., strength based groups of teams), teams coming from the same association, connectivity requirements, and others. We also show experimentally how fair incomplete round robin tournaments can be generated.
arXiv:2412.11475v3 Announce Type: replace
Abstract: We present OmniVLM, a sub-billion-parameter vision-language model for efficient on-device inference. OmniVLM introduces a token compression mechanism that reduces visual token sequence length from 729 to 81 tokens, significantly reducing computational overhead while preserving visual-semantic fidelity. Through a multi-stage training pipeline of pretraining, supervised fine-tuning, and minimal-edit Direct Preference Optimization (DPO), OmniVLM matches the performance of larger models. On multiple benchmarks including ScienceQA, POPE, and MMMU, OmniVLM outperforms existing baselines like nanoLLAVA within a 968M-parameter footprint. Empirical results on the same laptop demonstrate 9.1x faster time-to-first-token (0.75s vs 6.82s) and 1.5x higher decoding speed (29.41 vs 19.20 tokens/s) compared to nanoLLAVA, enabling efficient deployment on edge devices. The model weights can be accessed on huggingface: https://huggingface.co/NexaAIDev/OmniVLM-968M, and the inference examples can be find in Appendix B.
arXiv:2506.00625v2 Announce Type: replace
Abstract: The imbalanced distribution of long-tailed data presents a significant challenge for deep learning models, causing them to prioritize head classes while neglecting tail classes. Two key factors contributing to low recognition accuracy are the deformed representation space and a biased classifier, stemming from insufficient semantic information in tail classes. To address these issues, we propose permutation-invariant and head-to-tail feature fusion (PI-H2T), a highly adaptable method. PI-H2T enhances the representation space through permutation-invariant representation fusion (PIF), yielding more clustered features and automatic class margins. Additionally, it adjusts the biased classifier by transferring semantic information from head to tail classes via head-to-tail fusion (H2TF), improving tail class diversity. Theoretical analysis and experiments show that PI-H2T optimizes both the representation space and decision boundaries. Its plug-and-play design ensures seamless integration into existing methods, providing a straightforward path to further performance improvements. Extensive experiments on long-tailed benchmarks confirm the effectiveness of PI-H2T.
arXiv:2502.04411v3 Announce Type: replace
Abstract: Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation in averaging. While model routing addresses this issue by selecting individual models during inference, it imposes excessive storage and compute costs, and fails to leverage the common knowledge from different models. In this work, we observe that different layers exhibit varying levels of parameter conflicts. Building on this insight, we average layers with minimal parameter conflicts and use a novel task-level expert routing for layers with significant conflicts. To further reduce storage costs, inspired by task arithmetic sparsity, we decouple multiple fine-tuned experts into a dense expert and several sparse experts. Considering the out-of-distribution samples, we select and merge appropriate experts based on the task uncertainty of the input data. We conduct extensive experiments on both LLaMA and Qwen with varying parameter scales, and evaluate on real-world reasoning tasks. Results demonstrate that our method consistently achieves significant performance improvements while requiring less system cost.
arXiv:2607.17946v1 Announce Type: new
Abstract: Large Language Models (LLMs) often struggle to navigate value conflicts when trained with the compressed scalar rewards of Reinforcement Learning from Human Feedback (RLHF). To address this challenge, we investigate how chain-of-thought (CoT) reasoning can help improve performance in this domain. Geometrically, we show that CoT correlates with further smoothing the model's loss landscape in its sharpest direction, helping resolve the optimization instability of traditional scalar rewards. We also demonstrate via relevant downstream benchmarks that value conflict-focused CoT may generalize to different kinds of moral reasoning, demonstrating that this CoT has the potential to be an effective mechanism for better moral reasoning. To capitalize on this potential, we create a new value conflict-focused CoT design that further smooths the sharpest direction of the loss landscape and increases moral reasoning performance. This finding shows that explicitly modifying and improving the design of reasoning dynamics offers a promising avenue for improving model performance on user requests with complex value conflicts, advancing pluralistic alignment in LLMs.
arXiv:2607.17458v1 Announce Type: new
Abstract: In conventional optical microscopy, accessing subwavelength information is classically constrained by the Abbe diffraction limit which remains a significant challenge in nanophotonics. To overcome this limitation, we introduce a scheme that generates a tightly confined near-field focal spot under non-diffracting Bessel beam illumination, employing a series of high refractive-index nanoscale structures. Furthermore, the utilization of higher-order Bessel beams enables additional resolution enhancement beyond the diffraction limit. Our results demonstrate a subwavelength resolution of (lambda/53) with a pyramidal nanostructure. To elucidate the factors governing the focusing behavior, we systematically investigate the influence of different geometrical parameters related to the incident Bessel beam on the focusing performance and shows that these factors critically determine the stability and spatial profile of the focal spot. These findings highlight the potential of the proposed approach for various applications in super-resolution imaging and quantum technology.