This paper focuses on explaining the timbre conveyed by speech signals and introduces a task termed voice timbre attribute detection (vTAD). In this task, voice timbre is explained with a set of sensory attributes describing its human perception. A pair of speech utterances is processed, and their intensity is compared in a designated timbre descriptor. Moreover, a framework is proposed, which is built upon the speaker embeddings extracted from the speech utterances. The investigation is conducted on the VCTK-RVA dataset. Experimental examinations on the ECAPA-TDNN and FACodec speaker encoders demonstrated that: 1) the ECAPA-TDNN speaker encoder was more capable in the seen scenario, where the testing speakers were included in the training set; 2) the FACodec speaker encoder was superior in the unseen scenario, where the testing speakers were not part of the training, indicating enhanced generalization capability. The VCTK-RVA dataset and open-source code are available on the website https://github.com/vTAD2025-Challenge/vTAD.
Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present. The entropy model plays a key role in learned image compression, which estimates the probability distribution of the latent representation for further entropy coding. Most existing methods employed hyper-prior and auto-regressive architectures to form their entropy models. However, they only aimed to explore the internal dependencies of latent representation while neglecting the importance of extracting prior from training data. In this work, we propose a novel entropy model named Dictionary-based Cross Attention Entropy model, which introduces a learnable dictionary to summarize the typical structures occurring in the training dataset to enhance the entropy model. Extensive experimental results have demonstrated that the proposed model strikes a better balance between performance and latency, achieving state-of-the-art results on various benchmark datasets.
Endoscopic video-based tasks, such as visual navigation and surgical phase recognition, play a crucial role in minimally invasive surgeries by providing real-time assistance. While recent video foundation models have shown promise, their applications are hindered by (1) computational inefficiencies and (2) suboptimal performance caused by limited data for pre-training in endoscopy. To address these issues, we present EndoMamba, a foundation model designed for real-time inference while learning generalized spatiotemporal representations. First, to mitigate computational inefficiencies, we propose the EndoMamba backbone, optimized for real-time inference. Inspired by recent advancements in state space models, EndoMamba integrates Bidirectional Mamba blocks for spatial modeling within individual frames and vanilla Mamba blocks for past-to-present reasoning across the temporal domain. This design enables both strong spatiotemporal modeling and efficient inference in online video streams. Second, we propose a self-supervised hierarchical pre-training diagram to enhance EndoMamba's representation learning using endoscopic videos and incorporating general video domain knowledge. Specifically, our approach combines masked reconstruction with auxiliary supervision, leveraging low-level reconstruction to capture spatial-temporal structures and high-level alignment to transfer broader knowledge from a pretrained general-video domain foundation model. Extensive experiments on four downstream tasks--classification, segmentation, surgical phase recognition, and localization--demonstrate that EndoMamba outperforms existing foundation models and task-specific methods while maintaining real-time inference speed. The source code is available at https://github.com/TianCuteQY/EndoMamba.
Natural language image-caption datasets, widely used for training Large Multimodal Models, mainly focus on natural scenarios and overlook the intricate details of mathematical figures that are critical for problem-solving, hindering the advancement of current LMMs in multimodal mathematical reasoning. To this end, we propose leveraging code as supervision for cross-modal alignment, since code inherently encodes all information needed to generate corresponding figures, establishing a precise connection between the two modalities. Specifically, we co-develop our image-to-code model and dataset with model-in-the-loop approach, resulting in an image-to-code model, FigCodifier and ImgCode-8.6M dataset, the largest image-code dataset to date. Furthermore, we utilize FigCodifier to synthesize novel mathematical figures and then construct MM-MathInstruct-3M, a high-quality multimodal math instruction fine-tuning dataset. Finally, we present MathCoder-VL, trained with ImgCode-8.6M for cross-modal alignment and subsequently fine-tuned on MM-MathInstruct-3M for multimodal math problem solving. Our model achieves a new open-source SOTA across all six metrics. Notably, it surpasses GPT-4o and Claude 3.5 Sonnet in the geometry problem-solving subset of MathVista, achieving improvements of 8.9% and 9.2%. The dataset and models will be released at https://github.com/mathllm/MathCoder.
With the development of photorealistic diffusion models, models trained in part or fully on synthetic data achieve progressively better results. However, diffusion models still routinely generate images that would not exist in reality, such as a dog floating above the ground or with unrealistic texture artifacts. We define the concept of feasibility as whether attributes in a synthetic image could realistically exist in the real-world domain; synthetic images containing attributes that violate this criterion are considered infeasible. Intuitively, infeasible images are typically considered out-of-distribution; thus, training on such images is expected to hinder a model's ability to generalize to real-world data, and they should therefore be excluded from the training set whenever possible. However, does feasibility really matter? In this paper, we investigate whether enforcing feasibility is necessary when generating synthetic training data for CLIP-based classifiers, focusing on three target attributes: background, color, and texture. We introduce VariReal, a pipeline that minimally edits a given source image to include feasible or infeasible attributes given by the textual prompt generated by a large language model. Our experiments show that feasibility minimally affects LoRA-fine-tuned CLIP performance, with mostly less than 0.3% difference in top-1 accuracy across three fine-grained datasets. Also, the attribute matters on whether the feasible/infeasible images adversarially influence the classification performance. Finally, mixing feasible and infeasible images in training datasets does not significantly impact performance compared to using purely feasible or infeasible datasets.
While large language models demonstrate impressive performance on static benchmarks, the true potential of large language models as self-learning and reasoning agents in dynamic environments remains unclear. This study systematically evaluates the efficacy of self-reflection, heuristic mutation, and planning as prompting techniques to test the adaptive capabilities of agents. We conduct experiments with various open-source language models in dynamic environments and find that larger models generally outperform smaller ones, but that strategic prompting can close this performance gap. Second, a too-long prompt can negatively impact smaller models on basic reactive tasks, while larger models show more robust behaviour. Third, advanced prompting techniques primarily benefit smaller models on complex games, but offer less improvement for already high-performing large language models. Yet, we find that advanced reasoning methods yield highly variable outcomes: while capable of significantly improving performance when reasoning and decision-making align, they also introduce instability and can lead to big performance drops. Compared to human performance, our findings reveal little evidence of true emergent reasoning. Instead, large language model performance exhibits persistent limitations in crucial areas such as planning, reasoning, and spatial coordination, suggesting that current-generation large language models still suffer fundamental shortcomings that may not be fully overcome through self-reflective prompting alone. Reasoning is a multi-faceted task, and while reasoning methods like Chain of thought improves multi-step reasoning on math word problems, our findings using dynamic benchmarks highlight important shortcomings in general reasoning capabilities, indicating a need to move beyond static benchmarks to capture the complexity of reasoning.
The O-RAN architecture is transforming cellular networks by adopting RAN softwarization and disaggregation concepts to enable data-driven monitoring and control of the network. Such management is enabled by RICs, which facilitate near-real-time and non-real-time network control through xApps and rApps. However, they face limitations, including latency overhead in data exchange between the RAN and RIC, restricting real-time monitoring, and the inability to access user plain data due to privacy and security constraints, hindering use cases like beamforming and spectrum classification. In this paper, we leverage the dApps concept to enable real-time RF spectrum classification with LibIQ, a novel library for RF signals that facilitates efficient spectrum monitoring and signal classification by providing functionalities to read I/Q samples as time-series, create datasets and visualize time-series data through plots and spectrograms. Thanks to LibIQ, I/Q samples can be efficiently processed to detect external RF signals, which are subsequently classified using a CNN inside the library. To achieve accurate spectrum analysis, we created an extensive dataset of time-series-based I/Q samples, representing distinct signal types captured using a custom dApp running on a 5G deployment over the Colosseum network emulator and an OTA testbed. We evaluate our model by deploying LibIQ in heterogeneous scenarios with varying center frequencies, time windows, and external RF signals. In real-time analysis, the model classifies the processed I/Q samples, achieving an average accuracy of approximately 97.8% in identifying signal types across all scenarios. We pledge to release both LibIQ and the dataset created as a publicly available framework upon acceptance.
Multi-token prediction has emerged as a promising objective for improving language model pretraining, but its benefits have not consistently generalized to other settings such as fine-tuning. In this paper, we propose MuToR, a simple and effective approach to multi-token prediction that interleaves learnable register tokens into the input sequence, each tasked with predicting future targets. Compared to existing methods, MuToR offers several key advantages: it introduces only a negligible number of additional parameters, requires no architectural changes--ensuring compatibility with off-the-shelf pretrained language models--and remains aligned with the next-token pretraining objective, making it especially well-suited for supervised fine-tuning. Moreover, it naturally supports scalable prediction horizons. We demonstrate the effectiveness and versatility of MuToR across a range of use cases, including supervised fine-tuning, parameter-efficient fine-tuning (PEFT), and pretraining, on challenging generative tasks in both language and vision domains. Our code will be available at: https://github.com/nasosger/MuToR.
Recently, post hoc explanation methods have emerged to enhance model transparency by attributing model outputs to input features. However, these methods face challenges due to their specificity to certain neural network architectures and data modalities. Existing explainable artificial intelligence (XAI) frameworks have attempted to address these challenges but suffer from several limitations. These include limited flexibility to diverse model architectures and data modalities due to hard-coded implementations, a restricted number of supported XAI methods because of the requirements for layer-specific operations of attribution methods, and sub-optimal recommendations of explanations due to the lack of evaluation and optimization phases. Consequently, these limitations impede the adoption of XAI technology in real-world applications, making it difficult for practitioners to select the optimal explanation method for their domain. To address these limitations, we introduce \textbf{PnPXAI}, a universal XAI framework that supports diverse data modalities and neural network models in a Plug-and-Play (PnP) manner. PnPXAI automatically detects model architectures, recommends applicable explanation methods, and optimizes hyperparameters for optimal explanations. We validate the framework's effectiveness through user surveys and showcase its versatility across various domains, including medicine and finance.
The success of today's large language models (LLMs) depends on the observation that larger models perform better. However, the origin of this neural scaling law -- the finding that loss decreases as a power law with model size -- remains unclear. Starting from two empirical principles -- that LLMs represent more things than the model dimensions (widths) they have (i.e., representations are superposed), and that words or concepts in language occur with varying frequencies -- we constructed a toy model to study the loss scaling with model size. We found that when superposition is weak, meaning only the most frequent features are represented without interference, the scaling of loss with model size depends on the underlying feature frequency; if feature frequencies follow a power law, so does the loss. In contrast, under strong superposition, where all features are represented but overlap with each other, the loss becomes inversely proportional to the model dimension across a wide range of feature frequency distributions. This robust scaling behavior is explained geometrically: when many more vectors are packed into a lower dimensional space, the interference (squared overlaps) between vectors scales inversely with that dimension. We then analyzed four families of open-sourced LLMs and found that they exhibit strong superposition and quantitatively match the predictions of our toy model. The Chinchilla scaling law turned out to also agree with our results. We conclude that representation superposition is an important mechanism underlying the observed neural scaling laws. We anticipate that these insights will inspire new training strategies and model architectures to achieve better performance with less computation and fewer parameters.
The Image Signal Processor (ISP) is a fundamental component in modern smartphone cameras responsible for conversion of RAW sensor image data to RGB images with a strong focus on perceptual quality. Recent work highlights the potential of deep learning approaches and their ability to capture details with a quality increasingly close to that of professional cameras. A difficult and costly step when developing a learned ISP is the acquisition of pixel-wise aligned paired data that maps the raw captured by a smartphone camera sensor to high-quality reference images. In this work, we address this challenge by proposing a novel training method for a learnable ISP that eliminates the need for direct correspondences between raw images and ground-truth data with matching content. Our unpaired approach employs a multi-term loss function guided by adversarial training with multiple discriminators processing feature maps from pre-trained networks to maintain content structure while learning color and texture characteristics from the target RGB dataset. Using lightweight neural network architectures suitable for mobile devices as backbones, we evaluated our method on the Zurich RAW to RGB and Fujifilm UltraISP datasets. Compared to paired training methods, our unpaired learning strategy shows strong potential and achieves high fidelity across multiple evaluation metrics. The code and pre-trained models are available at https://github.com/AndreiiArhire/Learned-Lightweight-Smartphone-ISP-with-Unpaired-Data .
With the advent of neural language models, the performance of code generation has been significantly boosted. However, the problem of repetitions during the generation process continues to linger. Previous work has primarily focused on content repetition, which is merely a fraction of the broader repetition problem in code generation. A more prevalent and challenging problem is structural repetition. In structural repetition, the repeated code appears in various patterns but possesses a fixed structure, which can be inherently reflected in grammar. In this paper, we formally define structural repetition and propose an efficient decoding approach called RPG, which stands for Repetition Penalization based on Grammar, to alleviate the repetition problems in code generation for LLMs. Specifically, RPG first leverages grammar rules to identify repetition problems during code generation, and then strategically decays the likelihood of critical tokens that contribute to repetitions, thereby mitigating them in code generation. To facilitate this study, we construct a new dataset CodeRepetEval to comprehensively evaluate approaches for mitigating the repetition problems in code generation. Extensive experimental results demonstrate that RPG substantially outperforms the best-performing baselines on CodeRepetEval dataset as well as HumanEval and MBPP benchmarks, effectively reducing repetitions and enhancing the quality of generated code.
There can be many competing and contradictory explanations for a single model prediction, making it difficult to select which one to use. Current explanation evaluation frameworks measure quality by comparing against ideal "ground-truth" explanations, or by verifying model sensitivity to important inputs. We outline the limitations of these approaches, and propose three desirable principles to ground the future development of explanation evaluation strategies for local feature importance explanations. We propose a ground-truth Agnostic eXplanation Evaluation framework (AXE) for evaluating and comparing model explanations that satisfies these principles. Unlike prior approaches, AXE does not require access to ideal ground-truth explanations for comparison, or rely on model sensitivity - providing an independent measure of explanation quality. We verify AXE by comparing with baselines, and show how it can be used to detect explanation fairwashing. Our code is available at https://github.com/KaiRawal/Evaluating-Model-Explanations-without-Ground-Truth.
Software vulnerabilities such as buffer overflows and SQL injections are a major source of security breaches. Traditional methods for vulnerability detection remain essential but are limited by high false positive rates, scalability issues, and reliance on manual effort. These constraints have driven interest in AI-based approaches to automated vulnerability detection and secure code generation. While Large Language Models (LLMs) have opened new avenues for classification tasks, their complexity and opacity pose challenges for interpretability and deployment. Sparse Autoencoder offer a promising solution to this problem. We explore whether SAEs can serve as a lightweight, interpretable alternative for bug detection in Java functions. We evaluate the effectiveness of SAEs when applied to representations from GPT-2 Small and Gemma 2B, examining their capacity to highlight buggy behaviour without fine-tuning the underlying LLMs. We found that SAE-derived features enable bug detection with an F1 score of up to 89%, consistently outperforming fine-tuned transformer encoder baselines. Our work provides the first empirical evidence that SAEs can be used to detect software bugs directly from the internal representations of pretrained LLMs, without any fine-tuning or task-specific supervision.
The Spiking Neural Network (SNN) has drawn increasing attention for its energy-efficient, event-driven processing and biological plausibility. To train SNNs via backpropagation, surrogate gradients are used to approximate the non-differentiable spike function, but they only maintain nonzero derivatives within a narrow range of membrane potentials near the firing threshold, referred to as the surrogate gradient support width gamma. We identify a major challenge, termed the dilemma of gamma: a relatively large gamma leads to overactivation, characterized by excessive neuron firing, which in turn increases energy consumption, whereas a small gamma causes vanishing gradients and weakens temporal dependencies. To address this, we propose a temporal Inhibitory Leaky Integrate-and-Fire (ILIF) neuron model, inspired by biological inhibitory mechanisms. This model incorporates interconnected inhibitory units for membrane potential and current, effectively mitigating overactivation while preserving gradient propagation. Theoretical analysis demonstrates ILIF effectiveness in overcoming the gamma dilemma, and extensive experiments on multiple datasets show that ILIF improves energy efficiency by reducing firing rates, stabilizes training, and enhances accuracy. The code is available at github.com/kaisun1/ILIF.
Spiking Neural Networks (SNNs) have shown competitive performance to Artificial Neural Networks (ANNs) in various vision tasks, while offering superior energy efficiency. However, existing SNN-based Transformers primarily focus on single-image tasks, emphasizing spatial features while not effectively leveraging SNNs' efficiency in video-based vision tasks. In this paper, we introduce SpikeVideoFormer, an efficient spike-driven video Transformer, featuring linear temporal complexity $\mathcal{O}(T)$. Specifically, we design a spike-driven Hamming attention (SDHA) which provides a theoretically guided adaptation from traditional real-valued attention to spike-driven attention. Building on SDHA, we further analyze various spike-driven space-time attention designs and identify an optimal scheme that delivers appealing performance for video tasks, while maintaining only linear temporal complexity. The generalization ability and efficiency of our model are demonstrated across diverse downstream video tasks, including classification, human pose tracking, and semantic segmentation. Empirical results show our method achieves state-of-the-art (SOTA) performance compared to existing SNN approaches, with over 15\% improvement on the latter two tasks. Additionally, it matches the performance of recent ANN-based methods while offering significant efficiency gains, achieving $\times 16$, $\times 10$ and $\times 5$ improvements on the three tasks. https://github.com/JimmyZou/SpikeVideoFormer
The effects of personnel scheduling on the quality of care and working conditions for healthcare personnel have been thoroughly documented. However, the ever-present demand and large variation of constraints make healthcare scheduling particularly challenging. This problem has been studied for decades, with limited research aimed at applying Satisfiability Modulo Theories (SMT). SMT has gained momentum within the formal verification community in the last decades, leading to the advancement of SMT solvers that have been shown to outperform standard mathematical programming techniques. In this work, we propose generic constraint formulations that can model a wide range of real-world scheduling constraints. Then, the generic constraints are formulated as SMT and MILP problems and used to compare the respective state-of-the-art solvers, Z3 and Gurobi, on academic and real-world inspired rostering problems. Experimental results show how each solver excels for certain types of problems; the MILP solver generally performs better when the problem is highly constrained or infeasible, while the SMT solver performs better otherwise. On real-world inspired problems containing a more varied set of shifts and personnel, the SMT solver excels. Additionally, it was noted during experimentation that the SMT solver was more sensitive to the way the generic constraints were formulated, requiring careful consideration and experimentation to achieve better performance. We conclude that SMT-based methods present a promising avenue for future research within the domain of personnel scheduling.
A recent area of increasing research is the use of Large Language Models (LLMs) in penetration testing, which promises to reduce costs and thus allow for higher frequency. We conduct a review of related work, identifying best practices and common evaluation issues. We then present AutoPentest, an application for performing black-box penetration tests with a high degree of autonomy. AutoPentest is based on the LLM GPT-4o from OpenAI and the LLM agent framework LangChain. It can perform complex multi-step tasks, augmented by external tools and knowledge bases. We conduct a study on three capture-the-flag style Hack The Box (HTB) machines, comparing our implementation AutoPentest with the baseline approach of manually using the ChatGPT-4o user interface. Both approaches are able to complete 15-25 % of the subtasks on the HTB machines, with AutoPentest slightly outperforming ChatGPT. We measure a total cost of \$96.20 US when using AutoPentest across all experiments, while a one-month subscription to ChatGPT Plus costs \$20. The results show that further implementation efforts and the use of more powerful LLMs released in the future are likely to make this a viable part of vulnerability management.
LLM-based multi-agent has gained significant attention for their potential in simulation and enhancing performance. However, existing works are limited to pure simulations or are constrained by predefined workflows, restricting their applicability and effectiveness. In this paper, we introduce the Multi-Agent Scaling Simulation (MASS) for portfolio construction. MASS achieves stable and continuous excess returns by progressively increasing the number of agents for large-scale simulations to gain a superior understanding of the market and optimizing agent distribution end-to-end through a reverse optimization process, rather than relying on a fixed workflow. We demonstrate its superiority through performance experiments, ablation studies, backtesting experiments, experiments on updated data and stock pools, scaling experiments, parameter sensitivity experiments, and visualization experiments, conducted in comparison with 6 state-of-the-art baselines on 3 challenging A-share stock pools. We expect the paradigm established by MASS to expand to other tasks with similar characteristics. The implementation of MASS has been open-sourced at https://github.com/gta0804/MASS.
In the era of increasingly sophisticated natural language processing (NLP) systems, large language models (LLMs) have demonstrated remarkable potential for diverse applications, including tasks requiring nuanced textual understanding and contextual reasoning. This study investigates the capabilities of multiple state-of-the-art LLMs - GPT-3.5, GPT-4, LLAMA3, Mistral 7B, and Claude-2 - for zero-shot and few-shot annotation of a complex textual dataset comprising social media posts in Russian and Ukrainian. Specifically, the focus is on the binary classification task of identifying references to human rights violations within the dataset. To evaluate the effectiveness of these models, their annotations are compared against a gold standard set of human double-annotated labels across 1000 samples. The analysis includes assessing annotation performance under different prompting conditions, with prompts provided in both English and Russian. Additionally, the study explores the unique patterns of errors and disagreements exhibited by each model, offering insights into their strengths, limitations, and cross-linguistic adaptability. By juxtaposing LLM outputs with human annotations, this research contributes to understanding the reliability and applicability of LLMs for sensitive, domain-specific tasks in multilingual contexts. It also sheds light on how language models handle inherently subjective and context-dependent judgments, a critical consideration for their deployment in real-world scenarios.