Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model to explore \textit{de novo} with each attempt and hindering sample efficiency. While LLMs can uniquely learn from language feedback provided in-context, naively integrating on-line experiences into RL training presents a paradox: feedback from the same problem risks information leakage and memorization, while feedback from different problems often leads to behavior collapse due to irrelevant context. To resolve this tension, we propose \textbf{Language-And-Numerical Policy Optimization (LANPO)}, a framework that cleanly separates the roles of feedback: language guides exploration, while numerical rewards drive optimization. LANPO builds a dynamic experience pool from past trials and introduces two principles to ensure feedback is effective: \emph{Reward-Agnostic Reflection} for safe intra-sample self-correction and \emph{Relevant Abstraction} to distill generalizable lessons from inter-sample experiences. Across mathematical reasoning benchmarks, LANPO enables 7B and 14B models to significantly outperform strong baselines trained with GRPO in test accuracy. Our work provides a robust method for integrating historical experiences into the LLM RL loop, creating more effective and data-efficient learning agents.

Life satisfaction is a crucial facet of human well-being. Hence, research on life satisfaction is incumbent for understanding how individuals experience their lives and influencing interventions targeted at enhancing mental health and well-being. Life satisfaction has traditionally been measured using analog, complicated, and frequently error-prone methods. These methods raise questions concerning validation and propagation. However, this study demonstrates the potential for machine learning algorithms to predict life satisfaction with a high accuracy of 93.80% and a 73.00% macro F1-score. The dataset comes from a government survey of 19000 people aged 16-64 years in Denmark. Using feature learning techniques, 27 significant questions for assessing contentment were extracted, making the study highly reproducible, simple, and easily interpretable. Furthermore, clinical and biomedical large language models (LLMs) were explored for predicting life satisfaction by converting tabular data into natural language sentences through mapping and adding meaningful counterparts, achieving an accuracy of 93.74% and macro F1-score of 73.21%. It was found that life satisfaction prediction is more closely related to the biomedical domain than the clinical domain. Ablation studies were also conducted to understand the impact of data resampling and feature selection techniques on model performance. Moreover, the correlation between primary determinants with different age brackets was analyzed, and it was found that health condition is the most important determinant across all ages. This study demonstrates how machine learning, large language models and XAI can jointly contribute to building trust and understanding in using AI to investigate human behavior, with significant ramifications for academics and professionals working to quantify and comprehend subjective well-being.

Deep learning-based gait recognition has achieved great success in various applications. The key to accurate gait recognition lies in considering the unique and diverse behavior patterns in different motion regions, especially when covariates affect visual appearance. However, existing methods typically use predefined regions for temporal modeling, with fixed or equivalent temporal scales assigned to different types of regions, which makes it difficult to model motion regions that change dynamically over time and adapt to their specific patterns. To tackle this problem, we introduce a Region-aware Dynamic Aggregation and Excitation framework (GaitRDAE) that automatically searches for motion regions, assigns adaptive temporal scales and applies corresponding attention. Specifically, the framework includes two core modules: the Region-aware Dynamic Aggregation (RDA) module, which dynamically searches the optimal temporal receptive field for each region, and the Region-aware Dynamic Excitation (RDE) module, which emphasizes the learning of motion regions containing more stable behavior patterns while suppressing attention to static regions that are more susceptible to covariates. Experimental results show that GaitRDAE achieves state-of-the-art performance on several benchmark datasets.

Despite recent advances, vision-language models trained with standard contrastive objectives still struggle with compositional reasoning -- the ability to understand structured relationships between visual and linguistic elements. This shortcoming is largely due to the tendency of the text encoder to focus on individual words rather than their relations, a limitation reinforced by contrastive training that primarily aligns words with visual objects. In this paper, we introduce REconstruction and Alignment of text Descriptions (READ), a fine-tuning method designed to enhance compositional reasoning by adding two auxiliary objectives to the contrastive learning: (1) a token-level reconstruction objective, where a frozen pre-trained decoder reconstructs alternative captions based on the embedding of the original caption; and (2) a sentence-level alignment objective, which explicitly aligns paraphrased sentences in the embedding space. We show that READ-CLIP, a model derived by applying the READ method to the pre-trained CLIP model, achieves the state-of-the-art performance across five major compositional reasoning benchmarks, outperforming the strongest conventional fine-tuning baseline by up to 4.1%. Furthermore, applying the READ to existing CLIP variants (including NegCLIP and FSC-CLIP) also improves performance on these benchmarks. Quantitative and qualitative analyses reveal that our proposed objectives -- reconstruction and alignment -- offer complementary benefits: the former encourages the encoder to capture relationships between words within a caption, while the latter ensures consistent representations for paraphrases expressed with different wording.

Abstract--Cardiovascular disease (CVD) risk stratification remains a major challenge due to its multifactorial nature and limited availability of high-quality labeled datasets. While genomic and electrophysiological data such as SNP variants and ECG phenotypes are increasingly accessible, effectively integrating these modalities in low-label settings is non-trivial. This challenge arises from the scarcity of well-annotated multimodal datasets and the high dimensionality of biological signals, which limit the effectiveness of conventional supervised models. T o address this, we present a few-label multimodal framework that leverages large language models (LLMs) to combine genetic and electro-physiological information for cardiovascular risk stratification. Our approach incorporates a pseudo-label refinement strategy to adaptively distill high-confidence labels from weakly supervised predictions, enabling robust model fine-tuning with only a small set of ground-truth annotations. T o enhance the interpretability, we frame the task as a Chain of Thought (CoT) reasoning problem, prompting the model to produce clinically relevant rationales alongside predictions. Experimental results demonstrate that the integration of multimodal inputs, few-label supervision, and CoT reasoning improves robustness and generalizability across diverse patient profiles. Experimental results using multimodal SNP variants and ECG-derived features demonstrated comparable performance to models trained on the full dataset, underscoring the promise of LLM-based few-label multimodal modeling for advancing personalized cardiovascular care. Cardiovascular disease remains the leading global killer (about 20.5M deaths in 2023), making early risk stratification essential [1]. Early and accurate stratification of at-risk patients is essential for timely interventions and effective disease management.

We propose a method for image categorization and retrieval that leverages graphs and a graph attention network (GAT)-based autoencoder. Our approach is representative-centric, that is, we execute the categorization and retrieval process via the representative models we construct for the images and image categories. We utilize a graph where nodes represent images (or their representatives) and edges capture similarity relationships. GAT highlights important features and relationships between images, enabling the autoencoder to construct context-aware latent representations that capture the key features of each image relative to its neighbors. We obtain category representatives from these embeddings and categorize a query image by comparing its representative to the category representatives. We then retrieve the most similar image to the query image within its identified category. We demonstrate the effectiveness of our representative-centric approach through experiments with both the GAT autoencoders and standard feature-based techniques.

Abstract-- A major bottleneck in off-road autonomous driving research lies in the scarcity of large-scale, high-quality datasets and benchmarks. T o bridge this gap, we present ORAD-3D, which, to the best of our knowledge, is the largest dataset specifically curated for off-road autonomous driving. ORAD-3D covers a wide spectrum of terrains--including woodlands, farmlands, grasslands, riversides, gravel roads, cement roads, and rural areas--while capturing diverse environmental variations across weather conditions (sunny, rainy, foggy, and snowy) and illumination levels (bright daylight, daytime, twilight, and nighttime). Building upon this dataset, we establish a comprehensive suite of benchmark evaluations spanning five fundamental tasks: 2D free-space detection, 3D occupancy prediction, rough GPS-guided path planning, vision-language model-driven autonomous driving, and world model for off-road environments. T ogether, the dataset and benchmarks provide a unified and robust resource for advancing perception and planning in challenging off-road scenarios. The dataset and code will be made publicly available at https://github.

Abstract--This paper presents a novel framework for speech transcription and synthesis, leveraging edge-cloud parallelism to enhance processing speed and accessibility for Kinyarwanda and Swahili speakers. It addresses the scarcity of powerful language processing tools for these widely spoken languages in East African countries with limited technological infrastructure. The framework utilizes the Whisper and SpeechT5 pre-trained models to enable speech-to-text (STT) and text-to-speech (TTS) translation. The architecture uses a cascading mechanism that distributes the model inference workload between the edge device and the cloud, thereby reducing latency and resource usage, benefiting both ends. On the edge device, our approach achieves a memory usage compression of 9.5% for the SpeechT5 model and 14% for the Whisper model, with a maximum memory usage of 149 MB. Experimental results indicate that on a 1.7 GHz CPU edge device with a 1 MB/s network bandwidth, the system can process a 270-character text in less than a minute for both speech-to-text and text-to-speech transcription. Using real-world survey data from Kenya, it is shown that the cascaded edge-cloud architecture proposed could easily serve as an excellent platform for STT and TTS transcription with good accuracy and response time. I. INTRODUCTION In today's digital age, the need for accurate and efficient speech transcription and synthesis models has been increasing rapidly. These models play an important role in a variety of applications, such as learning new language(s), accessibility tools for people with difficulties in reading and hearing, as well as automated voice assistants [1]. Kinyarwanda and Swahili are two of the local languages spoken in East Africa. While Swahili is the most widely spoken language in Eastern Africa, the speakers range from 60 million to over 150 million [2].

Large Language Models (LLMs) have shown strong reasoning capabilities, with models like OpenAI's O-series and DeepSeek R1 excelling at tasks such as mathematics, coding, logic, and puzzles through Reinforcement Learning with Verifiable Rewards (RLVR). However, their ability to solve more complex optimization problems - particularly NP-hard tasks - remains underexplored. To bridge this gap, we propose NP-ENGINE, the first comprehensive framework for training and evaluating LLMs on NP-hard problems. NP-ENGINE covers 10 tasks across five domains, each equipped with (i) a controllable instance generator, (ii) a rule-based verifier, and (iii) a heuristic solver that provides approximate optimal solutions as ground truth. This generator-verifier-heuristic pipeline enables scalable and verifiable RLVR training under hierarchical difficulties. We also introduce NP-BENCH, a benchmark derived from NP-ENGINE-DATA, specifically designed to evaluate LLMs' ability to tackle NP-hard level reasoning problems, focusing not only on feasibility but also on solution quality. Additionally, we present QWEN2.5-7B-NP, a model trained via zero-RLVR with curriculum learning on Qwen2.5-7B-Instruct, which significantly outperforms GPT-4o on NP-BENCH and achieves SOTA performance with the same model size. Beyond in-domain tasks, we demonstrate that RLVR training on NP-ENGINE-DATA enables strong out-of-domain (OOD) generalization to reasoning tasks (logic, puzzles, math, and knowledge), as well as non-reasoning tasks such as instruction following. We also observe a scaling trend: increasing task diversity improves OOD generalization. These findings suggest that task-rich RLVR training is a promising direction for advancing LLM's reasoning ability, revealing new insights into the scaling laws of RLVR.

In this work we concentrate on the task of goal-oriented Vision-and-Language Navigation (VLN). Existing methods often make decisions based on historical information, overlooking the future implications and long-term outcomes of the actions. In contrast, we aim to develop a foresighted agent. Specifically, we draw upon Q-learning to train a Q-model using large-scale unlabeled trajectory data, in order to learn the general knowledge regarding the layout and object relations within indoor scenes. This model can generate a Q-feature, analogous to the Q-value in traditional Q-network, for each candidate action, which describes the potential future information that may be observed after taking the specific action. Subsequently, a cross-modal future encoder integrates the task-agnostic Q-feature with navigation instructions to produce a set of action scores reflecting future prospects. These scores, when combined with the original scores based on history, facilitate an A*-style searching strategy to effectively explore the regions that are more likely to lead to the destination. Extensive experiments conducted on widely used goal-oriented VLN datasets validate the effectiveness of the proposed method. Our codes are available at https://github.com/woyut/NavQ