We propose Llama-Mimi, a speech language model that uses a unified tokenizer and a single Transformer decoder to jointly model sequences of interleaved semantic and acoustic tokens. Comprehensive evaluation shows that Llama-Mimi achieves state-of-the-art performance in acoustic consistency and possesses the ability to preserve speaker identity. Our analysis further demonstrates that increasing the number of quantizers improves acoustic fidelity but degrades linguistic performance, highlighting the inherent challenge of maintaining long-term coherence. We additionally introduce an LLM-as-a-Judge-based evaluation to assess the spoken content quality of generated outputs. Our models, code, and speech samples are publicly available.

Characterizing the geometry of an object orbiting around a star from its transit light curve is a powerful tool to uncover various complex phenomena. This problem is inherently ill-posed, since similar or identical light curves can be produced by multiple different shapes. In this study, we investigate the extent to which the features of a shape can be embedded in a transit light curve. We generate a library of two-dimensional random shapes and simulate their transit light curves with light curve simulator, Yuti. Each shape is decomposed into a series of elliptical components expressed in the form of Fourier coefficients that adds increasingly diminishing perturbations to an ideal ellipse. We train deep neural networks to predict these Fourier coefficients directly from simulated light curves. Our results demonstrate that the neural network can successfully reconstruct the low-order ellipses, which describe overall shape, orientation and large-scale perturbations. For higher order ellipses the scale is successfully determined but the inference of eccentricity and orientation is limited, demonstrating the extent of shape information in the light curve. We explore the impact of non-convex shape features in reconstruction, and show its dependence on shape orientation. The level of reconstruction achieved by the neural network underscores the utility of using light curves as a means to extract geometric information from transiting systems.

Image classification has traditionally relied on parameter-intensive model training, requiring large-scale annotated datasets and extensive fine tuning to achieve competitive performance. While recent vision language models (VLMs) alleviate some of these constraints, they remain limited by their reliance on single pass representations, often failing to capture complementary aspects of visual content. In this paper, we introduce Multi Agent based Reasoning for Image Classification (MARIC), a multi agent framework that reformulates image classification as a collaborative reasoning process. MARIC first utilizes an Outliner Agent to analyze the global theme of the image and generate targeted prompts. Based on these prompts, three Aspect Agents extract fine grained descriptions along distinct visual dimensions. Finally, a Reasoning Agent synthesizes these complementary outputs through integrated reflection step, producing a unified representation for classification. By explicitly decomposing the task into multiple perspectives and encouraging reflective synthesis, MARIC mitigates the shortcomings of both parameter-heavy training and monolithic VLM reasoning. Experiments on 4 diverse image classification benchmark datasets demonstrate that MARIC significantly outperforms baselines, highlighting the effectiveness of multi-agent visual reasoning for robust and interpretable image classification.

Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations. To achieve this goal, the models are expected to focus only on image content-related features instead of overfitting degradations. Recently, numerous approaches such as Dropout and Feature Alignment have been proposed to suppress models' natural tendency to overfit degradations and yield promising results. Nevertheless, these works have assumed that models overfit to all degradation types (e.g., blur, noise, JPEG), while through careful investigations in this paper, we discover that models predominantly overfit to noise, largely attributable to its distinct degradation pattern compared to other degradation types. In this paper, we propose a targeted feature denoising framework, comprising noise detection and denoising modules. Our approach presents a general solution that can be seamlessly integrated with existing super-resolution models without requiring architectural modifications. Our framework demonstrates superior performance compared to previous regularization-based methods across five traditional benchmarks and datasets, encompassing both synthetic and real-world scenarios.

Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventions. While textual interventions often target semantics, visual interventions typically rely on coarse pixel-level perturbations, limiting semantic insights on multimodal integration. In this study, we introduce V-SEAM, a novel framework that combines Visual Semantic Editing and Attention Modulating for causal interpretation of VLMs. V-SEAM enables concept-level visual manipulations and identifies attention heads with positive or negative contributions to predictions across three semantic levels: objects, attributes, and relationships. We observe that positive heads are often shared within the same semantic level but vary across levels, while negative heads tend to generalize broadly. Finally, we introduce an automatic method to modulate key head embeddings, demonstrating enhanced performance for both LLaVA and InstructBLIP across three diverse VQA benchmarks. Our data and code are released at: https://github.com/petergit1/V-SEAM.

This paper describes the participation of the SINAI team in the eRisk@CLEF lab. Specifically, two of the proposed tasks have been addressed: i) Task 1 on the early detection of signs of pathological gambling, and ii) Task 3 on measuring the severity of the signs of eating disorders. The approach presented in Task 1 is based on the use of sentence embeddings from Transformers with features related to volumetry, lexical diversity, complexity metrics, and emotion-related scores, while the approach for Task 3 is based on text similarity estimation using contextualized word embeddings from Transformers. In Task 1, our team has been ranked in second position, with an F1 score of 0.808, out of 41 participant submissions. In Task 3, our team also placed second out of a total of 3 participating teams.

This paper describes the participation of the SINAI team in the eRisk@CLEF lab. Specifically, one of the proposed tasks has been addressed: Task 2 on the early detection of signs of pathological gambling. The approach presented in Task 2 is based on pre-trained models from Transformers architecture with comprehensive preprocessing data and data balancing techniques. Moreover, we integrate Long-short Term Memory (LSTM) architecture with automodels from Transformers. In this Task, our team has been ranked in seventh position, with an F1 score of 0.126, out of 49 participant submissions and achieves the highest values in recall metrics and metrics related to early detection.

Since compute grows much faster than web text available for language model pre-training, we ask how one should approach pre-training under fixed data and no compute constraints. We first show that existing data-constrained approaches of increasing epoch count and parameter count eventually overfit, and we significantly improve upon such recipes by properly tuning regularization, finding that the optimal weight decay is $30\times$ larger than standard practice. Since our regularized recipe monotonically decreases loss following a simple power law in parameter count, we estimate its best possible performance via the asymptote of its scaling law rather than the performance at a fixed compute budget. We then identify that ensembling independently trained models achieves a significantly lower loss asymptote than the regularized recipe. Our best intervention combining epoching, regularization, parameter scaling, and ensemble scaling achieves an asymptote at 200M tokens using $5.17\times$ less data than our baseline, and our data scaling laws predict that this improvement persists at higher token budgets. We find that our data efficiency gains can be realized at much smaller parameter counts as we can distill an ensemble into a student model that is 8$\times$ smaller and retains $83\%$ of the ensembling benefit. Finally, our interventions designed for validation loss generalize to downstream benchmarks, achieving a $9\%$ improvement for pre-training evals and a $17.5\times$ data efficiency improvement over continued pre-training on math mid-training data. Our results show that simple algorithmic improvements can enable significantly more data-efficient pre-training in a compute-rich future.

With the advancement of mid/post-training techniques, LLMs are pushing their boundaries at an accelerated pace. Legacy benchmarks saturate quickly (e.g., broad suites like MMLU over the years, newer ones like GPQA-D even faster), which makes frontier progress hard to track. The problem is especially acute in Korean: widely used benchmarks are fewer, often translated or narrow in scope, and updated more slowly, so saturation and contamination arrive sooner. Accordingly, at this moment, there is no Korean benchmark capable of evaluating and ranking frontier models. To bridge this gap, we introduce KAIO, a Korean, math-centric benchmark that stresses long-chain reasoning. Unlike recent Korean suites that are at or near saturation, KAIO remains far from saturated: the best-performing model, GPT-5, attains 62.8, followed by Gemini-2.5-Pro (52.3). Open models such as Qwen3-235B and DeepSeek-R1 cluster falls below 30, demonstrating substantial headroom, enabling robust tracking of frontier progress in Korean. To reduce contamination, KAIO will remain private and be served via a held-out evaluator until the best publicly known model reaches at least 80% accuracy, after which we will release the set and iterate to a harder version.

Multi-stage information retrieval (IR) has become a widely-adopted paradigm in search. While Large Language Models (LLMs) have been extensively evaluated as second-stage reranking models for monolingual IR, a systematic large-scale comparison is still lacking for cross-lingual IR (CLIR). Moreover, while prior work shows that LLM-based rerankers improve CLIR performance, their evaluation setup relies on lexical retrieval with machine translation (MT) for the first stage. This is not only prohibitively expensive but also prone to error propagation across stages. Our evaluation on passage-level and document-level CLIR reveals that further gains can be achieved with multilingual bi-encoders as first-stage retrievers and that the benefits of translation diminishes with stronger reranking models. We further show that pairwise rerankers based on instruction-tuned LLMs perform competitively with listwise rerankers. To the best of our knowledge, we are the first to study the interaction between retrievers and rerankers in two-stage CLIR with LLMs. Our findings reveal that, without MT, current state-of-the-art rerankers fall severely short when directly applied in CLIR.