arXiv:2508.12265v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have demonstrated remarkable progress in reasoning across diverse domains. However, effective reasoning in real-world tasks requires adapting the reasoning strategy to the demands of the problem, ranging from fast, intuitive responses to deliberate, step-by-step reasoning and tool-augmented thinking. Drawing inspiration from cognitive psychology, we propose a novel taxonomy of LLM reasoning strategies along two knowledge boundaries: a fast/slow boundary separating intuitive from deliberative processes, and an internal/external boundary distinguishing reasoning grounded in the model's parameters from reasoning augmented by external tools. We systematically survey recent work on adaptive reasoning in LLMs and categorize methods based on key decision factors. We conclude by highlighting open challenges and future directions toward more adaptive, efficient, and reliable LLMs.
Science Journals
arXiv:2510.25370v2 Announce Type: replace
Abstract: Forecasting transformative technologies remains a critical but challenging task, particularly in fast-evolving domains such as Information and Communication Technologies (ICTs). Traditional expert-based methods struggle to keep pace with short innovation cycles and ambiguous early-stage terminology. In this work, we propose a novel, data-driven pipeline to monitor the emergence of transformative technologies by identifying patterns of technological convergence.
Our approach leverages advances in Large Language Models (LLMs) to extract semantic triples from unstructured text and construct a large-scale graph of technology-related entities and relations. We introduce a new method for grouping semantically similar technology terms (noun stapling) and develop graph-based metrics to detect convergence signals. The pipeline includes multi-stage filtering, domain-specific keyword clustering, and a temporal trend analysis of topic co-occurence.
We validate our methodology on two complementary datasets: 278,625 arXiv preprints (2017--2024) to capture early scientific signals, and 9,793 USPTO patent applications (2018-2024) to track downstream commercial developments. Our results demonstrate that the proposed pipeline can identify both established and emerging convergence patterns, offering a scalable and generalizable framework for technology forecasting grounded in full-text analysis.
arXiv:2607.06705v1 Announce Type: new
Abstract: Surface characterization is essential for revealing the structural, chemical, and physical properties of materials. Yet high-resolution methods such as atomic force microscopy (AFM) require complex equipment and delicate skillsets, making them particularly challenging for applications involving soft and biological materials in liquids. Here, we propose and validate an innovative motion-enabled sensing scheme that uses untethered micromotors as robotic probes to interact with surfaces or objects, with their motion responses serving as sensing signals for characterization. This sensing concept is validated by employing 3D electrokinetic tweezers, which control micro/nanoparticles with up to 20 nm positioning precision in solution, to drive Au microsphere motors along designed scanning paths. When the motors encounter local chemical or structural variations, their locomotion changes, allowing motion itself to serve for the detection. This effort enables untethered motors, for the first time, to detect biomolecular patterns and lithographically defined microridge arrays in liquid environments. The work establishes robotic locomotion as a new sensing modality, opening a wireless, solution-compatible, and low-cost technical pathway to standard surface sensing.
arXiv:2607.06750v1 Announce Type: new
Abstract: This paper provides the first near-optimal lower bounds for one-bit compressed sensing of approximately sparse signals lying in a scaled $\ell_1$ ball, which is a commonly adopted relaxation of the exactly $k$-sparse assumption. In prior works, the best known upper bounds on uniform Euclidean error are of order $\widetilde{O}((k/m)^{1/3})$, where $m$ is the number of measurements. Under sub-Gaussian matrices, we establish nearly matching lower bounds for both the canonical one-bit compressed sensing model and the uniformly dithered model. Our argument is to first embed a small Euclidean ball into the signal set, which is straightforward for the dithered model but relies on a lifting map for the canonical model, and then construct two signals in this small ball that are separated in Euclidean distance by at least $(k/m)^{1/3}$ (up to logarithmic factor) but are indistinguishable from the binary measurements. Moreover, our argument extends to approximately sparse signals that live in a properly scaled $\ell_q$ ball $(q\in [0,1])$, yielding a lower bound $\widetilde{\Omega}((k/m)^{\frac{2-q}{2+q}})$ that smoothly bridges the cases of exact sparsity ($q=0$) and $\ell_1$ sparsity ($q=1$). Finally, we discuss the extensions of our lower bounds to sub-Weibull matrices, adversarial bit flipping, matrix recovery, and characterize the transition to the non-sparse case.
arXiv:2607.06820v1 Announce Type: new
Abstract: Recent advances in AI for Mathematics have focused largely on autoformalization and theorem proving, leaving the role of Computer Algebra Systems (CAS) in agentic LLM workflows underexplored. We propose a ReAct-style agentic setup that combines LLM reasoning with verifiable feedback from SageMath, together with Context7 for the up-to-date documentation. We evaluate this agentic setup across frontier models for solving research-level mathematical problems from the RealMath benchmark in a setting that emulates a computational-mathematics research loop. We also propose a refinement to the RealMath benchmark by introducing a multi-step post-processing procedure and a multi-stage validation pipeline, both of which improve the quality and reliability of the extracted problem set. Our experiments reveal substantial performance gains from SageMath access across all evaluated models on +9.7~pp on average, the gains range from 1.5~pp to 27.8~pp and narrow the gap between open-weight and closed models. Qwen~3.7-Max benefits from SageMath the most, while GPT-5.5 achieves the highest solve rate of $75.2\%$ and the lowest token usage among tool-enabled configurations. Our findings suggest that CAS-augmented agents represent a promising direction for assisting mathematicians in computational exploration, and we believe that this work is a step towards automated conjecture discovery. The project repository is available online.
arXiv:2607.06922v1 Announce Type: new
Abstract: Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers. Deciding the number of neurons during the design of a deep neural network to maximize performance is not intuitive. Particularly, many application scenarios are real-time and have a strict latency constraint, while conventional neural network optimization methods do not directly change the temporal cost of model inference for latency-critical edge systems. In this work, we propose a latency-oriented neural network learning method to optimize models for high accuracy while fulfilling the latency constraint. For efficiency, we also introduce a universal hardware-customized latency predictor to optimize this procedure to learn a model that satisfies the latency constraint by only a one-shot training process. The experiment results reveal that, compared to state-of-the-art methods, our approach can well-fit the 'hard' latency constraint and achieve high accuracy. Under the same training settings as the original model and satisfying a 34 ms latency constraint on the ImageNet-100 dataset, we reduce GoogLeNet's latency from 40.32 ms to 34 ms with a 0.14% accuracy reduction on the NVIDIA Jetson Nano. When coupled with quantization, our method can be further improved to only 0.04% drop for GoogLeNet. On the NVIDIA Jetson TX2, we compress VGG-19 from 119.98 ms to 34 ms and even improve its accuracy by 0.5%, and we scale GoogLeNet up from 20.27 ms to 34 ms and achieve higher accuracy by 0.78%. We also open source this framework at https://github.com/ntuliuteam/ZeroBN
arXiv:2508.21556v3 Announce Type: replace
Abstract: Modeling human-object interactions (HOI) from an egocentric perspective is a critical yet challenging task, particularly when relying on sparse signals from wearable devices like smart glasses and watches. We present ECHO, the first unified framework to jointly recover human pose, object motion, and contact dynamics solely from head and wrist tracking. To tackle the underconstrained nature of this problem, we introduce a novel tri-variate diffusion process with independent noise schedules that models the mutual dependencies between the human, object, and interaction modalities. This formulation allows ECHO to operate with flexible input configurations, making it robust to intermittent tracking and capable of leveraging partial observations. Crucially, it enables training on a combination of large-scale human motion datasets and smaller HOI collections, learning strong priors while capturing interaction nuances. Furthermore, we employ a smooth inpainting inference mechanism that enables the generation of temporally consistent interactions for arbitrarily long sequences. Extensive evaluations demonstrate that ECHO achieves state-of-the-art performance, significantly outperforming existing methods lacking such flexibility. The project page is available at https://ptrvilya.github.io/echo/.
arXiv:2509.05450v2 Announce Type: replace
Abstract: Silicon Photomultipliers (SiPMs) have been widely adopted for photon detection in next-generation dark matter and neutrino detection experiments. Internal crosstalk, resulting from secondary photons produced during charge avalanches, is a significant noise mechanism in SiPMs and is likely to impact the performance of physics detectors. This work presents experimental data for trends in crosstalk probability with temperature and overvoltage for two different SiPM devices, and demonstrates a novel method for identifying the source mechanisms of crosstalk avalanches. This is done by using measurements of avalanche triggering probabilities for different charge carrier types to identify the device regions in which crosstalk avalanches are produced. This is possible because crosstalk photons absorbed in n-doped regions will produce hole-triggered avalanches, and those absorbed in p-doped regions will produce electron-triggered avalanches. Thus crosstalk probability can be related to device structure to assess the effectiveness of existing crosstalk mitigation methods. We identify optical reflections from the device surface as a significant source of crosstalk, likely to dominate in devices with effective crosstalk mitigation in bulk. Lastly, a diagnostic technique is presented to identify and reduce crosstalk in novel SiPM structures.
arXiv:2607.06986v1 Announce Type: new
Abstract: Singing voice synthesis (SVS) has progressed rapidly, yet its ability to generalize across diverse musical genres remains underexplored. Existing benchmarks are heavily biased toward pop music, limiting systematic analysis of genre-dependent behavior. We introduce MMGenre, a benchmark for multi-genre SVS diagnosis, supported by an automatic pipeline for constructing genre-aligned music scores. MMGenre spans 10 major genres and 26 subgenres, enabling comprehensive analysis of genre-aware synthesis. Extensive evaluation of representative SVS models reveals limited genre discrimination: synthesized vocals across genres exhibit highly similar acoustic characteristics and weak separability. While zero-shot genre adaptation yields only marginal improvements, lightweight genre-specific continued training leads to substantial gains. MMGenre provides a standardized framework for multi-genre SVS evaluation and exposes critical challenges in achieving genre-aware singing voice synthesis.
arXiv:2607.07125v1 Announce Type: new
Abstract: Exotic helium atoms act as unique atomic traps for heavy, negatively charged particles, protecting them from nuclear annihilation and nuclear capture on timescales long enough to enable high-precision laser spectroscopy. Such measurements serve as stringent tests of three-body quantum electrodynamics and offer a direct route to determining fundamental particle masses. Motivated by upcoming spectroscopic efforts targeting pionic ($\pi^{-\,4}\mathrm{He}^+$) and kaonic ($K^{-\,4}\mathrm{He}^+$) helium, we present a rigorous theoretical evaluation of the collisional and density effects governing these systems. Using an ab initio potential energy surface and coupled-channel quantum scattering calculations, we study the collisional stability of the candidate metastable states against inelastic quenching in a cryogenic helium buffer gas. Furthermore, we provide theoretical reference values for the pressure broadening and pressure shift coefficients of the targeted transitions. These results establish an essential benchmark for future experiments, paving the way for refined determinations of the pion and kaon masses.
arXiv:2607.07612v1 Announce Type: new
Abstract: Artificial intelligence is rapidly evolving from generative systems to agentic AI capable of autonomously planning and executing tasks. Widely characterized as the Year of Agentic AI, 2025 marked accelerated development and deployment, introducing new ethical and governance challenges. This paper presents a systematic review of the emerging literature on agentic AI governance. Our analysis identifies features that distinguish agentic AI from traditional systems and why it warrants targeted governance attention. We synthesize prevailing governance priorities, proposed mechanisms, and stakeholder roles shaping this evolving domain. As an initial scholarly effort, this review lays the preliminary groundwork for developing a structured roadmap to guide responsible and adaptive agentic AI governance.
arXiv:2601.20226v2 Announce Type: replace
Abstract: We propose two methodologies for modelling aggregated supply and demand curves in the EPEX SPOT Day\char45 Ahead market, emphasizing generative models as a way to recover distributional variability. The first is a low\char45 dimensional parametric representation that yields deterministic point forecasts; the second is a high\char45 dimensional order\char45 level representation that samples from a conditional distribution of plausible curves. Both model the full curve structure, enabling the analysis of price sensitivity, volume sensitivity, and price impact.
The parametric representation uses plateau levels, elastic\char45 region boundaries, and polynomial coefficients, forecast with eXtreme Gradient Boosting. The main contribution is the generative representation, which uses price arrivals and volume\char45 increment marks and is implemented with conditional Denoising Diffusion Probabilistic Models.
Using French EPEX data from 2021 to 2024, we evaluate both approaches through curve reconstruction and a price\char45 maker storage optimization problem. The parametric implementation provides a deterministic reference, while the diffusion\char45 based implementation produces distributions of plausible curves and achieves higher realized profits and smaller gaps to an oracle benchmark in the storage application.
arXiv:2602.04521v2 Announce Type: replace
Abstract: Modern deployments require LLMs to enforce safety policies at scale, yet many controls rely on inference-time interventions that add recurring compute cost and serving complexity. Activation steering is widely used, but it requires runtime hooks and scales cost with the number of generations; conditional variants improve selectivity by gating when steering is applied but still retain an inference-time control path. We ask whether selective refusal can be moved entirely offline: can a mechanistic understanding of category-specific refusal be distilled into a circuit-restricted weight update that deploys as a standard checkpoint? We propose C-{\Delta}{\theta} Circuit Restricted Weight Arithmetic}, which (i) localizes refusal-causal computation as a sparse circuit using EAP-IG and (ii) computes a constrained weight update {\Delta}{\theta}C supported only on that circuit (typically <5% of parameters). Applying {\Delta}{\theta}C yields a drop-in edited checkpoint with no inference-time hooks, shifting cost from per request intervention to a one-time offline update. We evaluate category-targeted selectivity and capability retention on refusal and utility benchmarks.
arXiv:2602.08923v3 Announce Type: replace
Abstract: Multi-hop all-reduce is the de facto backbone of large model training. As the training scale increases, the network often becomes a bottleneck, motivating the reduction of the volume of transmitted data. Accordingly, recent systems have demonstrated significant acceleration of the training process using gradient quantization. However, these systems are not optimized for multi-hop aggregation, where entries are partially summed multiple times along their aggregation topology.
We present DynamiQ, a quantization framework that bridges the gap between quantization best practices and multi-hop aggregation. DynamiQ introduces novel techniques to better represent partial sums, codesigned with a decompress accumulate recompress fused kernel to facilitate fast execution.
We extend PyTorch DDP to support DynamiQ over NCCL P2P, and across different LLMs, tasks, and scales, we demonstrate consistent improvement of up to 34.2% over the best among state-of-the-art methods such as Omni-Reduce, THC, and emerging standards such as MXFP4, MXFP6, and MXFP8. Further, DynamiQ is the only evaluated method that consistently reaches near-baseline accuracy (e.g., 99.9\% of the BF16 baseline) and does so while significantly accelerating the training.
arXiv:2607.07396v1 Announce Type: new
Abstract: We prove an information-theoretically optimal \emph{gap-majority lemma} in the two-player randomized communication model. For a base function $f: \mathcal{X} \to \{\pm 1\}$, its $n$-fold \emph{gap-majority composition}, denoted $\mathsf{GapMAJ} \circ f^n$, takes $n$ inputs $(X_1, \ldots, X_n)$ and distinguishes whether $f^{+n}(X_1,\ldots,X_n) := f(X_1) + \ldots + f(X_n)$ is at least $0.01\sqrt{n}$ or at most $-0.01\sqrt{n}$. We show that if computing $f$ with success probability $0.501$ requires $I$ bits of information, then computing $\mathsf{GapMAJ} \circ f^n$ with success probability $0.99$ requires $n \cdot (I - O(1))$ bits of information. This result is asymptotically optimal in two aspects: it achieves the correct linear scaling of information cost and the correct constant-constant tradeoff between error rates. This makes $\mathsf{GapMAJ}$, to our knowledge, only the third explicit outer gadget that admits a strong composition theorem in the two-player communication setting, following the identity and XOR gadgets.
From an application side, our gap-majority lemma can be viewed as a generic amplification tool that lifts the hardness of deciding $f$ into the hardness of approximating $f^{+n}$. Using this framework, we give a new proof to the communication lower bound of Gap-Hamming and derive a tight streaming lower bound of triangle counting, demonstrating the versatility of the gap-majority lemma.
arXiv:2402.01811v2 Announce Type: replace
Abstract: Credit scoring has been catalogued by the European Commission and the Executive Office of the US President as a high-risk classification task, in light of the potential harms of making loan approval decisions based on models that would be biased against certain groups. To address this concern, recent credit scoring research has considered a range of fairness-enhancing techniques put forward by the machine learning community to reduce bias and unfair treatment in classification systems. While the definition of fairness or the approach they follow to impose it may vary, most of these techniques, however, disregard the robustness of the results. This can create situations where unfair treatment is effectively corrected in the training set, but when producing out-of-distribution classifications, unfair treatment is incurred again. Instead, in this paper, we will investigate how to apply Distributionally Robust Optimisation (DRO) methods to credit scoring, thereby empirically evaluating how they perform in terms of fairness, ability to classify correctly, and the robustness of the solution against changes in the marginal proportions. In so doing, we find DRO methods to provide a substantial improvement in terms of fairness, with almost no loss in predictive performance. These results thus indicate that DRO can improve fairness in credit scoring, provided that further advances are made in efficiently implementing these systems. In addition, our analysis suggests that many of the commonly used fairness metrics are not ideally suited to the credit scoring setting, as they evaluate performance at a single classification threshold.
arXiv:2602.05088v4 Announce Type: replace
Abstract: Millions of people now use generative AI chatbots for psychological support. Despite their promise, the most pressing question in AI for mental health is whether these tools are safe. The field currently lacks a validated, automated benchmark for evaluating AI chatbot safety, particularly for users at risk of suicide. The Validation of Ethical and Responsible AI in Mental Health (VERA-MH) evaluation was recently proposed to address this need. This human validation study examined the alignment of VERA-MH safety ratings with expert clinician judgments. We simulated conversations between large language model (LLM)-based users spanning a range of suicide risk levels and disclosure styles and general-purpose AI chatbots. Licensed mental health clinicians from Spring Health independently rated chatbot safety using the VERA-MH scoring rubric. An LLM-based evaluator ("judge") applied the same rubric to the same conversations. We examined agreement among clinicians, between clinician consensus and the LLM judge, and across different judge LLMs. Clinicians also rated user-agent realism, suicide risk, and disclosure. Clinicians showed strong agreement in safety ratings (chance-corrected inter-rater reliability [IRR] = 0.77), establishing a reliable clinical consensus reference. The LLM judge was strongly aligned with this consensus (IRR = 0.81), and ratings were stable across judge models and repeated evaluations. Ratings of user-agent realism and fidelity to intended suicide risk and disclosure styles were mixed. These findings support the reliability of VERA-MH as an open-source, fully automated benchmark for evaluating AI chatbot suicide risk detection and response. Because these results reflect an earlier version of the benchmark, future work should validate updated versions, assess generalizability and robustness, and expand VERA-MH to additional domains of AI safety in mental health.
arXiv:2602.06838v3 Announce Type: replace
Abstract: Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity and non-independent and identically distributed (Non-IID) data often lead to unstable and biased gradient. When differential privacy is enforced, conventional fixed gradient clipping and Gaussian noise injection may further amplify gradient perturbations, resulting in training oscillation and degraded model performance. To address these challenges, we propose an adaptive differentially private federated learning framework that explicitly targets model efficiency under heterogeneous and privacy-constrained settings. On the client side, a lightweight local dimensionality reduction module is introduced to learn reduced-dimensional intermediate representations and produce more structured gradients during backpropagation, thereby mitigating noise amplification during local optimization. On the server side, an adaptive gradient clipping strategy dynamically adjusts clipping thresholds based on historical update statistics to avoid over-clipping and noise domination. Furthermore, a constraint-aware robust aggregation mechanism is designed to suppress unreliable or noise-dominated client updates and stabilize global optimization. Extensive experiments on CIFAR-10, SVHN, and STL-10 demonstrate that the proposed method consistently improves convergence stability and classification performance under differential privacy.
arXiv:2602.10751v3 Announce Type: replace
Abstract: We study the problem of predicting numeric labels that are constrained to the integers or to a subrange of the integers. For example, the number of up-votes on social media posts, or the number of bicycles available at a public rental station. While it is possible to model these as continuous values, and to apply traditional regression, this approach changes the underlying distribution on the labels from discrete to continuous. Discrete distributions have certain benefits, which leads us to the question whether such integer labels can be modeled directly by a discrete distribution, whose parameters are predicted from the features of a given instance. Moreover, we focus on the use case of output distributions of neural networks, which adds the requirement that the parameters of the distribution be continuous so that backpropagation and gradient descent may be used to learn the weights of the network. We investigate several options for such distributions, some existing and some novel, and test them on a range of tasks, including tabular learning, sequential prediction and image generation. We find that overall the best performance comes from two distributions: Bitwise, which represents the target integer in bits and places a Bernoulli distribution on each, and a discrete analogue of the Laplace distribution, which uses a distribution with exponentially decaying tails around a continuous mean.
arXiv:2602.11399v2 Announce Type: replace
Abstract: As unsupervised pretraining becomes increasingly ubiquitous in reinforcement learning, a more thorough theoretical understanding of these methods becomes of equal importance to their empirical success. We focus on the setting of unsupervised learning via interaction, where the forward-backward (FB) representation learning serves as a prototypical and popular example. In this paper, we shed light on FB by formally contextualizing the method within a broader class of recent methods that use regression to obtain a low-rank approximation of a successor measure ratio. Our analysis clarifies when FB representations can exist and how the low-rank approximation converges in practice. Building upon the theory, we propose a variant of FB that is both more amenable to theoretical understanding and simpler to optimize in practice. Experiments in didactic settings, as well as in $10$ state-based and image-based continuous control domains, demonstrate that our method converges to desired representations with $10^5 \times$ smaller errors than FB, achieving $+24\%$ improved zero-shot performance on average. We also demonstrate that zero-shot policies inferred by our algorithm provide an efficient initialization if the user prefers further fine-tuning on downstream tasks. Our project website is available at https://chongyi-zheng.github.io/onestep-fb.
arXiv:2602.12323v2 Announce Type: replace
Abstract: The widespread availability of fine-tuned LoRA modules for open pre-trained models has led to an interest in methods that can adaptively merge LoRAs to improve performance. These methods typically include some way of selecting LoRAs from a pool and tune merging coefficients based on a task-specific dataset. While adaptive merging methods have demonstrated improvements in some settings, no past work has attempted to recycle LoRAs found "in the wild" on model repositories like the Hugging Face Hub. To address this gap, we consider recycling from a pool of nearly 1,000 user-contributed LoRAs trained from the Llama 3.1 8B-Instruct language model. Our empirical study includes a range of adaptive and non-adaptive merging methods in addition to a new method designed via a wide search over the methodological design space. We demonstrate that adaptive merging methods can improve performance over the base model but provide limited benefit over training a new LoRA on the same data used to set merging coefficients. We additionally find not only that the specific choice of LoRAs to merge has little importance, but that using LoRAs with randomly initialized parameter values yields similar performance. This raises the possibility that adaptive merging from recycled LoRAs primarily works via some kind of regularization effect, rather than by enabling positive cross-task transfer. To better understand why past work has proven successful, we confirm that positive transfer is indeed possible when there are highly relevant LoRAs in the pool. We release the model checkpoints and code online.
arXiv:2602.17588v4 Announce Type: replace
Abstract: Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene, often proceeding autonomously past critical decision points or requesting unnecessary confirmation. In this work, we introduce the task of modeling human intervention to support collaborative web task execution. We collect CowCorpus, a dataset of 400 real-user web navigation trajectories containing over 4,200 interleaved human and agent actions. We identify four distinct patterns of user interaction with agents -- hands-off supervision, hands-on oversight, collaborative task-solving, and full user takeover. Leveraging these insights, we train language models (LMs) to anticipate when users are likely to intervene based on their interaction styles, yielding a 61.4-63.4% improvement in intervention prediction accuracy over base LMs. Finally, we deploy these intervention-aware models in live web navigation agents and evaluate them in a user study, finding a 36.8% increase in user-rated agent usefulness. Together, our results show structured modeling of human intervention leads to more adaptive, collaborative agents.
arXiv:2602.23615v3 Announce Type: replace
Abstract: Current Large Multimodal Models (LMMs) struggle with high-resolution visual inputs during the reasoning process, as the number of image tokens increases quadratically with resolution, introducing substantial redundancy and irrelevant information. A common practice is to identify key image regions and refer to their high-resolution counterparts during reasoning, typically trained with external visual supervision. However, such visual supervision cues require costly grounding labels from human annotators. Meanwhile, it remains an open question how to enhance a model's grounding abilities to support reasoning without relying on additional annotations. In this paper, we propose High-resolution Annotation-free Reasoning Technique (HART), a closed-loop framework that enables LMMs to focus on and self-verify key regions of high-resolution visual inputs. HART incorporates a post-training paradigm in which we design Advantage Preference Group Relative Policy Optimization (AP-GRPO) to encourage accurate localization of key regions without external visual annotations. Notably, HART provides explainable reasoning pathways and enables efficient optimization of localization. Extensive experiments on MME-RealWorld-Lite, TreeBench, V* Bench, HR-Bench-4K/8K, and MMStar demonstrate that HART improves performance across a wide range of high-resolution visual tasks, consistently outperforming strong baselines.
arXiv:2603.01730v3 Announce Type: replace
Abstract: Decentralized federated learning (DFL) has emerged as a transformative server-free paradigm that enables collaborative learning over large-scale heterogeneous networks. However, it continues to face fundamental challenges, including data heterogeneity, restrictive assumptions for theoretical analysis, and degraded convergence when standard communication- or privacyenhancing techniques are applied. To overcome these drawbacks, this paper develops a novel algorithm, PaME (DFL by Partial Message Exchange). The central principle is to allow only randomly selected sparse coordinates to be exchanged between two neighbor nodes. Consequently, PaME achieves substantial reductions in communication costs while still preserving a high level of privacy, without sacrificing accuracy. Moreover, grounded in rigorous analysis, the algorithm is shown to converge at a linear rate under the gradient to be locally Lipschitz continuous and the communication matrix to be doubly stochastic. These two mild assumptions not only dispense with many restrictive conditions commonly imposed by existing DFL methods but also enables PaME to effectively address data heterogeneity. Furthermore, comprehensive numerical experiments demonstrate its superior performance compared with several representative decentralized learning algorithms.
arXiv:2603.03532v2 Announce Type: replace
Abstract: Voting Advice Applications (VAA) are tools designed to help voters compare political candidates on policy preferences prior to elections. VAAs are popular tools in European countries and in other countries with multi-party democratic systems. Through a freedom of information request we got access to the inner workings of a popular Danish VAA called the 'textit{Kandidattest' which is implemented by a major Danish news outlet and has been used for general, municipal, and European elections. Users and politicians from every political party answer the same online questionnaire and get matched based on the agreement percentage stemming from their answers. VAAs play a significant role in elections with 45\% of surveyed voters reporting they followed their recommendations in the past Danish general election. However, the inner workings of VAAs have not been thoroughly evaluated until now. We find that the algorithm is not robust enough for users to trust the agreement percentages in the output, as small changes to the algorithm can lead to different results, potentially affecting election outcomes. We conduct an algorithmic audit of the Kandidattest's robustness, using simulated responses to investigate the tool's brittleness, with respect to minor adjustments of the algorithm's weight, and changes in the number of questions in the questionnaire.