Test-time scaling has emerged as a transformative paradigm for enhancing the performance of large reasoning models, enabling dynamic allocation of computational resources during inference. However, as the landscape of reasoning models rapidly expands, a critical question remains: how can we systematically compare and evaluate the test-time scaling capabilities across different models? In this paper, we introduce ARISE (Adaptive Resolution-aware Scaling Evaluation), a novel metric specifically designed to assess the test-time scaling effectiveness of large reasoning models. Unlike existing evaluation approaches, ARISE incorporates two key innovations: (1) sample-level awareness that effectively penalizes negative scaling behaviors where increased computation leads to performance degradation, and (2) a dynamic sampling mechanism that mitigates the impact of accuracy fluctuations and token count instability on the final assessment. We conduct comprehensive experiments evaluating state-of-the-art reasoning models across diverse domains including mathematical reasoning, code generation, and agentic tasks. Our results demonstrate that ARISE provides a reliable and fine-grained measurement of test-time scaling capabilities, revealing significant variations in scaling efficiency across models. Notably, our evaluation identifies Claude Opus as exhibiting superior scaling characteristics compared to other contemporary reasoning models.

This study examines the use of social media and news images to detect and measure hailstones, utilizing pre-trained multimodal large language models. The dataset for this study comprises 474 crowdsourced images of hailstones from documented hail events in Austria, which occurred between January 2022 and September 2024. These hailstones have maximum diameters ranging from 2 to 11cm. We estimate the hail diameters and compare four different models utilizing one-stage and two-stage prompting strategies. The latter utilizes additional size cues from reference objects, such as human hands, within the image. Our results show that pretrained models already have the potential to measure hailstone diameters from images with an average mean absolute error of 1.12cm for the best model. In comparison to a single-stage prompt, two-stage prompting improves the reliability of most models. Our study suggests that these off-the-shelf models, even without fine-tuning, can complement traditional hail sensors by extracting meaningful and spatially dense information from social media imagery, enabling faster and more detailed assessments of severe weather events. The automated real-time image harvesting from social media and other sources remains an open task, but it will make our approach directly applicable to future hail events.

Low-Rank Adaptation (LoRA) has emerged as a dominant method in Parameter-Efficient Fine-Tuning (PEFT) for large language models, which augments the transformer layer with one down-projection $A$ and one up-projection $B$. However, LoRA's reliance on a single down-projection matrix ($A$) creates a representational bottleneck, as this solitary feature extractor is inherently insufficient for capturing the diverse signals required by complex tasks. This motivates our architectural shift to focus on enriching the feature adaptation to improve the downstream task adaptation ability. We propose MASA (Multi-$A$ Shared Adaptation), an architecture that implements a multi-$A$, single-$B$ structure where the multi-$A$ expert ensemble is asymmetrically shared across layers to ensure parameter efficiency. In MASA, these specialized experts capture diverse features, which are then integrated by a single, layer-specific $B$-matrix. The effectiveness and versatility of our method are validated through a comprehensive suite of experiments spanning multi-domain generalization, single-domain specialization, and multi-task reasoning. For example, on the MMLU benchmark, MASA achieves an average accuracy of 59.62%, outperforming the standard LoRA by 1.08 points (a relative improvement of 1.84%) with comparable learnable parameters of 0.52%.

Recent studies probing the Argument from the Poverty of the Stimulus (APS) have applied Large Language Models (LLMs) to test the learnability of complex syntax through surprisal-based metrics. However, divergent conclusions raise questions concerning the insights these metrics offer. While Wilcox et al. (2024) used direct minimal pair comparisons (the "wh-effect") to demonstrate that models successfully generalise knowledge of filler-gap dependencies, Lan et al. (2024) used a Difference-in-Differences (DiD) metric and found that models largely fail on parasitic gaps (PGs). This paper argues that the direct minimal pair approach offers greater diagnostic transparency. We demonstrate this by generating a full 8-permutation paradigm of refined PG stimuli and evaluating the GPT-2 model used in previous studies with a systematic Wilcox-style wh-effect analysis. Our results show that GPT-2 succeeds across all four tested conditions, indicating robust knowledge of filler-gap licensing principles even in complex PG environments. This finding, which contrasts with the more ambiguous results from DiD-style metrics, suggests that the choice of evaluation metric is critical for assessing an LLM's syntactic competence.

Large Language Models (LLMs) are increasingly applied to complex tasks that require extended reasoning. In such settings, models often benefit from diverse chains-of-thought to arrive at multiple candidate solutions. This requires two competing objectives: to inject enough stochasticity to explore multiple reasoning chains, and to ensure sufficient accuracy and quality in each path. Existing works pursue the first objective by increasing exploration at highly uncertain steps with higher temperature or larger candidate token sets, while others improve reliability by rejecting samples with low confidence post-generation, implying that low confidence correlates with low answer quality. These two lines of thought are in conflict, as they conflate different sources of uncertainty. To resolve this, we argue that the decoding rule should be calibrated by correctness, not confidence alone. We should sample from tokens with higher estimated correctness, and reduce sampling where expected correctness is low. We propose simple strategies that achieve this goal: Greedy-Threshold makes sampling greedy at very low confidence steps. Calibrated-T opK and Calibrated-ε set truncation threshold based on estimated rank-wise correctness. Large Language Models (LLMs) are used for a wide range of generation tasks, ranging from open-ended text to structured problem-solving. In many cases, producing more than one candidate output improves not only fluency, but also reliability, since different samples may capture alternative valid continuations (Wang et al., 2023; Lin et al., 2024). This practice highlights a fundamental trade-off: introducing enough randomness to explore multiple options while still ensuring the accuracy and quality of each individual output (Tan et al., 2024; Meister et al., 2024; Shi et al., 2024). Existing works optimize exploration by raising temperatures or enlarging candidate token sets step-by-step (Nguyen et al., 2025; Zhang et al., 2024; Hewitt et al., 2022). These methods assume that higher entropy is a signal of uncertainty between multiple valid next steps, warranting broader exploration.

Low-light image enhancement (LLIE) is vital for safety-critical applications such as surveillance, autonomous navigation, and medical imaging, where visibility degradation can impair downstream task performance. Recently, diffusion models have emerged as a promising generative paradigm for LLIE due to their capacity to model complex image distributions via iterative denoising. This survey provides an up-to-date critical analysis of diffusion models for LLIE, distinctively featuring an in-depth comparative performance evaluation against Generative Adversarial Network and Transformer-based state-of-the-art methods, a thorough examination of practical deployment challenges, and a forward-looking perspective on the role of emerging paradigms like foundation models. We propose a multi-perspective taxonomy encompassing six categories: Intrinsic Decomposition, Spectral & Latent, Accelerated, Guided, Multimodal, and Autonomous; that map enhancement methods across physical priors, conditioning schemes, and computational efficiency. Our taxonomy is grounded in a hybrid view of both the model mechanism and the conditioning signals. We evaluate qualitative failure modes, benchmark inconsistencies, and trade-offs between interpretability, generalization, and inference efficiency. We also discuss real-world deployment constraints (e.g., memory, energy use) and ethical considerations. This survey aims to guide the next generation of diffusion-based LLIE research by highlighting trends and surfacing open research questions, including novel conditioning, real-time adaptation, and the potential of foundation models.

Time series classification (TSC) spans diverse application scenarios, yet labeled data are often scarce, making task-specific training costly and inflexible. Recent reasoning-oriented large language models (LLMs) show promise in understanding temporal patterns, but purely zero-shot usage remains suboptimal. We propose FETA, a multi-agent framework for training-free TSC via exemplar-based in-context reasoning. FETA decomposes a multivariate series into channel-wise subproblems, retrieves a few structurally similar labeled examples for each channel, and leverages a reasoning LLM to compare the query against these exemplars, producing channel-level labels with self-assessed confidences; a confidence-weighted aggregator then fuses all channel decisions. This design eliminates the need for pretraining or fine-tuning, improves efficiency by pruning irrelevant channels and controlling input length, and enhances interpretability through exemplar grounding and confidence estimation. On nine challenging UEA datasets, FETA achieves strong accuracy under a fully training-free setting, surpassing multiple trained baselines. These results demonstrate that a multi-agent in-context reasoning framework can transform LLMs into competitive, plug-and-play TSC solvers without any parameter training. The code is available at https://github.com/SongyuanSui/FETATSC.

A sum-product network (SPN) is a graphical model that allows several types of probabilistic inference to be performed efficiently. In this paper, we propose a privacy-preserving protocol which tackles structure generation and parameter learning of SPNs. Additionally, we provide a protocol for private inference on SPNs, subsequent to training. To preserve the privacy of the participants, we derive our protocol based on secret sharing, which guarantees privacy in the honest-but-curious setting even when at most half of the parties cooperate to disclose the data. The protocol makes use of a forest of randomly generated SPNs, which is trained and weighted privately and can then be used for private inference on data points. Our experiments indicate that preserving the privacy of all participants does not decrease log-likelihood performance on both homogeneously and heterogeneously partitioned data. We furthermore show that our protocol's performance is comparable to current state-of-the-art SPN learners in homogeneously partitioned data settings. In terms of runtime and memory usage, we demonstrate that our implementation scales well when increasing the number of parties, comparing favorably to protocols for neural networks, when they are trained to reproduce the input-output behavior of SPNs.

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two practical bottlenecks: (1) context length grows rapidly during training, inflating memory usage and latency, and triggering out-of-memory (OOM) failures; and (2) intermediate tensors accumulate with context length, making cross-device data movement a major system bottleneck. We present EARL, a scalable system for efficient agentic RL. EARL designs a parallelism selector that dynamically adapts model and training parallelism across RL stages based on sequence length and system load, and a data dispatcher that performs layout-aware, decentralized exchange of intermediate data batches. Together, these components increase throughput, reduce long-context failures, and enable stable large-scale training of agentic LLMs without relying on hard limits or penalties of context length.

Deep generative models often face a fundamental tradeoff: high sample quality can come at the cost of memorisation, where the model reproduces training data rather than generalising across the underlying data geometry. We introduce Carré du champ flow matching (CDC-FM), a generalisation of flow matching (FM), that improves the quality-generalisation tradeoff by regularising the probability path with a geometry-aware noise. Our method replaces the homogeneous, isotropic noise in FM with a spatially varying, anisotropic Gaussian noise whose covariance captures the local geometry of the latent data manifold. We prove that this geometric noise can be optimally estimated from the data and is scalable to large data. Further, we provide an extensive experimental evaluation on diverse datasets (synthetic manifolds, point clouds, single-cell genomics, animal motion capture, and images) as well as various neural network architectures (MLPs, CNNs, and transformers). We demonstrate that CDC-FM consistently offers a better quality-generalisation tradeoff. We observe significant improvements over standard FM in data-scarce regimes and in highly non-uniformly sampled datasets, which are often encountered in AI for science applications. Our work provides a mathematical framework for studying the interplay between data geometry, generalisation and memorisation in generative models, as well as a robust and scalable algorithm that can be readily integrated into existing flow matching pipelines.