We introduce OSVBench, a new benchmark for evaluating Large Language Models (LLMs) on the task of generating complete formal specifications for verifying the functional correctness of operating system kernels. This benchmark is built upon a real-world operating system kernel, Hyperkernel, and consists of 245 complex specification generation tasks in total, each of which is a long-context task of about 20k-30k tokens. The benchmark formulates the specification generation task as a program synthesis problem confined to a domain for specifying states and transitions. This formulation is provided to LLMs through a programming model. The LLMs must be able to understand the programming model and verification assumptions before delineating the correct search space for syntax and semantics and generating formal specifications. Guided by the operating system's high-level functional description, the LLMs are asked to generate a specification that fully describes all correct states and transitions for a potentially buggy code implementation of the operating system. Experimental results with 12 state-of-the-art LLMs indicate limited performance of existing LLMs on the specification generation task for operating system verification. Significant disparities in their performance highlight differences in their ability to handle long-context code generation tasks. The code are available at https://github.com/lishangyu-hkust/OSVBench

Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to train. This work aims to build data-efficient PRMs as verbalized step-wise reward models that verify every step in the solution by generating a verification chain-of-thought (CoT). We propose ThinkPRM, a long CoT verifier fine-tuned on orders of magnitude fewer process labels than those required by discriminative PRMs. Our approach capitalizes on the inherent reasoning abilities of long CoT models, and outperforms LLM-as-a-Judge and discriminative verifiers -- using only 1% of the process labels in PRM800K -- across several challenging benchmarks. Specifically, ThinkPRM beats the baselines on ProcessBench, MATH-500, and AIME '24 under best-of-N selection and reward-guided search. In an out-of-domain evaluation on a subset of GPQA-Diamond and LiveCodeBench, our PRM surpasses discriminative verifiers trained on the full PRM800K by 8% and 4.5%, respectively. Lastly, under the same token budget, ThinkPRM scales up verification compute more effectively compared to LLM-as-a-Judge, outperforming it by 7.2% on a subset of ProcessBench. Our work highlights the value of generative, long CoT PRMs that can scale test-time compute for verification while requiring minimal supervision for training. Our code, data, and models are released at https://github.com/mukhal/thinkprm.

Deep neural networks such as convolutional neural networks (CNNs) and transformers have achieved many successes in image classification in recent years. It has been consistently demonstrated that best practice for image classification is when large deep models can be trained on abundant labelled data. However there are many real world scenarios where the requirement for large amounts of training data to get the best performance cannot be met. In these scenarios transfer learning can help improve performance. To date there have been no surveys that comprehensively review deep transfer learning as it relates to image classification overall. However, several recent general surveys of deep transfer learning and ones that relate to particular specialised target image classification tasks have been published. We believe it is important for the future progress in the field that all current knowledge is collated and the overarching patterns analysed and discussed. In this survey we formally define deep transfer learning and the problem it attempts to solve in relation to image classification. We survey the current state of the field and identify where recent progress has been made. We show where the gaps in current knowledge are and make suggestions for how to progress the field to fill in these knowledge gaps. We present a new taxonomy of the applications of transfer learning for image classification. This taxonomy makes it easier to see overarching patterns of where transfer learning has been effective and, where it has failed to fulfill its potential. This also allows us to suggest where the problems lie and how it could be used more effectively. We show that under this new taxonomy, many of the applications where transfer learning has been shown to be ineffective or even hinder performance are to be expected when taking into account the source and target datasets and the techniques used.

Air pollution is one of the most concerns for urban areas. Many countries have constructed monitoring stations to hourly collect pollution values. Recently, there is a research in Daegu city, Korea for real-time air quality monitoring via sensors installed on taxis running across the whole city. The collected data is huge (1-second interval) and in both Spatial and Temporal format. In this paper, based on this spatiotemporal Big data, we propose a real-time air pollution prediction model based on Convolutional Neural Network (CNN) algorithm for image-like Spatial distribution of air pollution. Regarding to Temporal information in the data, we introduce a combination of a Long Short-Term Memory (LSTM) unit for time series data and a Neural Network model for other air pollution impact factors such as weather conditions to build a hybrid prediction model. This model is simple in architecture but still brings good prediction ability.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in multimodal tasks. Despite their impressive performance, MLLMs suffer from the modality imbalance issue, where visual information is often underutilized compared to textual representations in deeper layers, leading to degraded visual performance or hallucinations. This issue stems from the predominant reliance on next-text-token-prediction during training, which fails to provide direct visual supervisory signals, resulting in progressive homogenization of visual representations throughout the layers. To this end, we propose Latent Visual Reconstruction (LaVer), a novel training framework that facilitates MLLMs in learning more discriminative visual representations via masked image modeling in the joint latent semantic space of LLM. Our method offers direct visual activation to MLLMs, which exhibit increased visual attention allocation, indicating enhanced utilization of visual information. Extensive experiments across diverse benchmarks prove the superiority of our approach in various scenarios, especially those requiring dense visual capabilities. Code of LaVer is available at https://github.com/Fir-lat/LaVer.

Predicting a song's commercial success prior to its release remains an open and critical research challenge for the music industry. Early prediction of music popularity informs strategic decisions, creative planning, and marketing. Existing methods suffer from four limitations:(i) temporal dynamics in audio and lyrics are averaged away; (ii) lyrics are represented as a bag of words, disregarding compositional structure and affective semantics; (iii) artist- and song-level historical performance is ignored; and (iv) multimodal fusion approaches rely on simple feature concatenation, resulting in poorly aligned shared representations. To address these limitations, we introduce GAMENet, an end-to-end multimodal deep learning architecture for music popularity prediction. GAMENet integrates modality-specific experts for audio, lyrics, and social metadata through an adaptive gating mechanism. We use audio features from Music4AllOnion processed via OnionEnsembleAENet, a network of autoencoders designed for robust feature extraction; lyric embeddings derived through a large language model pipeline; and newly introduced Career Trajectory Dynamics (CTD) features that capture multi-year artist career momentum and song-level trajectory statistics. Using the Music4All dataset (113k tracks), previously explored in MIR tasks but not popularity prediction, GAMENet achieves a 12% improvement in R^2 over direct multimodal feature concatenation. Spotify audio descriptors alone yield an R^2 of 0.13. Integrating aggregate CTD features increases this to 0.69, with an additional 7% gain from temporal CTD features. We further validate robustness using the SpotGenTrack Popularity Dataset (100k tracks), achieving a 16% improvement over the previous baseline. Extensive ablations confirm the model's effectiveness and the distinct contribution of each modality.

In this work, we report what happens when two large language models respond to each other for many turns without any outside input in a multi-agent setup. The setup begins with a short seed sentence. After that, each model reads the other's output and generates a response. This continues for a fixed number of steps. We used Mistral Nemo Base 2407 and Llama 2 13B hf. We observed that most conversations start coherently but later fall into repetition. In many runs, a short phrase appears and repeats across turns. Once repetition begins, both models tend to produce similar output rather than introducing a new direction in the conversation. This leads to a loop where the same or similar text is produced repeatedly. We describe this behavior as a form of convergence. It occurs even though the models are large, trained separately, and not given any prompt instructions. To study this behavior, we apply lexical and embedding-based metrics to measure how far the conversation drifts from the initial seed and how similar the outputs of the two models becomes as the conversation progresses.

Backdoor attacks embed input-dependent malicious behavior into neural networks while preserving high clean accuracy, making them a persistent threat for deployed ML systems. At the same time, real-world deployments almost never serve full-precision models: post-training quantization to INT8 or lower precision is now standard practice for reducing memory and latency. This work asks a simple question: how do existing backdoor defenses behave under standard quantization pipelines? We conduct a systematic empirical study of five representative defenses across three precision settings (FP32, INT8 dynamic, INT4 simulated) and two standard vision benchmarks using a canonical BadNet attack. We observe that INT8 quantization reduces the detection rate of all evaluated defenses to 0% while leaving attack success rates above 99%. For INT4, we find a pronounced dataset dependence: Neural Cleanse remains effective on GTSRB but fails on CIFAR-10, even though backdoors continue to survive quantization with attack success rates above 90%. Our results expose a mismatch between how defenses are commonly evaluated (on FP32 models) and how models are actually deployed (in quantized form), and they highlight quantization robustness as a necessary axis in future evaluations and designs of backdoor defenses.

Money laundering and financial fraud remain major threats to global financial stability, costing trillions annually and challenging regulatory oversight. This paper reviews how artificial intelligence (AI) applications can modernize Anti-Money Laundering (AML) workflows by improving detection accuracy, lowering false-positive rates, and reducing the operational burden of manual investigations, thereby supporting more sustainable development. It further highlights future research directions including federated learning for privacy-preserving collaboration, fairness-aware and interpretable AI, reinforcement learning for adaptive defenses, and human-in-the-loop visualization systems to ensure that next-generation AML architectures remain transparent, accountable, and robust. In the final part, the paper proposes an AI-driven KYC application that integrates graph-based retrieval-augmented generation (RAG Graph) with generative models to enhance efficiency, transparency, and decision support in KYC processes related to money-laundering detection. Experimental results show that the RAG-Graph architecture delivers high faithfulness and strong answer relevancy across diverse evaluation settings, thereby enhancing the efficiency and transparency of KYC CDD/EDD workflows and contributing to more sustainable, resource-optimized compliance practices.

We present LOCUS (LOw-cost Customization for Universal Specialization), a pipeline that consumes few-shot data to streamline the construction and training of NLP models through targeted retrieval, synthetic data generation, and parameter-efficient tuning. With only a small number of labeled examples, LOCUS discovers pertinent data in a broad repository, synthesizes additional training samples via in-context data generation, and fine-tunes models using either full or low-rank (LoRA) parameter adaptation. Our approach targets named entity recognition (NER) and text classification (TC) benchmarks, consistently outperforming strong baselines (including GPT-4o) while substantially lowering costs and model sizes. Our resultant memory-optimized models retain 99% of fully fine-tuned accuracy while using barely 5% of the memory footprint, also beating GPT-4o on several benchmarks with less than 1% of its parameters.