Scalable and reproducible policy evaluation has been a long-standing challenge in robot learning. Evaluations are critical to assess progress and build better policies, but evaluation in the real world, especially at a scale that would provide statistically reliable results, is costly in terms of human time and hard to obtain. Evaluation of increasingly generalist robot policies requires an increasingly diverse repertoire of evaluation environments, making the evaluation bottleneck even more pronounced. To make real-world evaluation of robotic policies more practical, we propose AutoEval, a system to autonomously evaluate generalist robot policies around the clock with minimal human intervention. Users interact with AutoEval by submitting evaluation jobs to the AutoEval queue, much like how software jobs are submitted with a cluster scheduling system, and AutoEval will schedule the policies for evaluation within a framework supplying automatic success detection and automatic scene resets. We show that AutoEval can nearly fully eliminate human involvement in the evaluation process, permitting around the clock evaluations, and the evaluation results correspond closely to ground truth evaluations conducted by hand. To facilitate the evaluation of generalist policies in the robotics community, we provide public access to multiple AutoEval scenes in the popular BridgeData robot setup with WidowX robot arms. In the future, we hope that AutoEval scenes can be set up across institutions to form a diverse and distributed evaluation network.

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning large language models with human preferences. While recent research has focused on algorithmic improvements, the importance of prompt-data construction has been overlooked. This paper addresses this gap by exploring data-driven bottlenecks in RLHF performance scaling, particularly reward hacking and decreasing response diversity. We introduce a hybrid reward system combining reasoning task verifiers (RTV) and a generative reward model (GenRM) to mitigate reward hacking. We also propose a novel prompt-selection method, Pre-PPO, to maintain response diversity and enhance learning effectiveness. Additionally, we find that prioritizing mathematical and coding tasks early in RLHF training significantly improves performance. Experiments across two model sizes validate our methods' effectiveness and scalability. Results show that RTV is most resistant to reward hacking, followed by GenRM with ground truth, and then GenRM with SFT Best-of-N responses. Our strategies enable rapid capture of subtle task-specific distinctions, leading to substantial improvements in overall RLHF performance. This work highlights the importance of careful data construction and provides practical methods to overcome performance barriers in RLHF.

The detection of telecom fraud faces significant challenges due to the lack of high-quality multimodal training data that integrates audio signals with reasoning-oriented textual analysis. To address this gap, we present TeleAntiFraud-28k, the first open-source audio-text slow-thinking dataset specifically designed for automated telecom fraud analysis. Our dataset is constructed through three strategies: (1) Privacy-preserved text-truth sample generation using automatically speech recognition (ASR)-transcribed call recordings (with anonymized original audio), ensuring real-world consistency through text-to-speech (TTS) model regeneration; (2) Semantic enhancement via large language model (LLM)-based self-instruction sampling on authentic ASR outputs to expand scenario coverage; (3) Multi-agent adversarial synthesis that simulates emerging fraud tactics through predefined communication scenarios and fraud typologies. The generated dataset contains 28,511 rigorously processed speech-text pairs, complete with detailed annotations for fraud reasoning. The dataset is divided into three tasks: scenario classification, fraud detection, fraud type classification. Furthermore, we construct TeleAntiFraud-Bench, a standardized evaluation benchmark comprising proportionally sampled instances from the dataset, to facilitate systematic testing of model performance on telecom fraud detection tasks. We also contribute a production-optimized supervised fine-tuning (SFT) model trained on hybrid real/synthetic data, while open-sourcing the data processing framework to enable community-driven dataset expansion. This work establishes a foundational framework for multimodal anti-fraud research while addressing critical challenges in data privacy and scenario diversity. The project will be released at https://github.com/JimmyMa99/TeleAntiFraud.

In this paper, we propose a novel factored agent architecture designed to overcome the limitations of traditional single-agent systems in agentic AI. Our approach decomposes the agent into two specialized components: (1) a large language model (LLM) that serves as a high level planner and in-context learner, which may use dynamically available information in user prompts, (2) a smaller language model which acts as a memorizer of tool format and output. This decoupling addresses prevalent issues in monolithic designs, including malformed, missing, and hallucinated API fields, as well as suboptimal planning in dynamic environments. Empirical evaluations demonstrate that our factored architecture significantly improves planning accuracy and error resilience, while elucidating the inherent trade-off between in-context learning and static memorization. These findings suggest that a factored approach is a promising pathway for developing more robust and adaptable agentic AI systems.

In this paper, we introduce NeuRaLaTeX, which we believe to be the first deep learning library written entirely in LaTeX. As part of your LaTeX document you can specify the architecture of a neural network and its loss functions, define how to generate or load training data, and specify training hyperparameters and experiments. When the document is compiled, the LaTeX compiler will generate or load training data, train the network, run experiments, and generate figures. This paper generates a random 100 point spiral dataset, trains a two layer MLP on it, evaluates on a different random spiral dataset, produces plots and tables of results. The paper took 48 hours to compile and the entire source code for NeuRaLaTeX is contained within the source code of the paper. We propose two new metrics: the Written In Latex (WIL) metric measures the proportion of a machine learning library that is written in pure LaTeX, while the Source Code Of Method in Source Code of Paper (SCOMISCOP) metric measures the proportion of a paper's implementation that is contained within the paper source. We are state-of-the-art for both metrics, outperforming the ResNet and Transformer papers, as well as the PyTorch and Tensorflow libraries. Source code, documentation, videos, crypto scams and an invitation to invest in the commercialisation of NeuRaLaTeX are available at https://www.neuralatex.com

Large real-world robot datasets hold great potential to train generalist robot models, but scaling real-world human data collection is time-consuming and resource-intensive. Simulation has great potential in supplementing large-scale data, especially with recent advances in generative AI and automated data generation tools that enable scalable creation of robot behavior datasets. However, training a policy solely in simulation and transferring it to the real world often demands substantial human effort to bridge the reality gap. A compelling alternative is to co-train the policy on a mixture of simulation and real-world datasets. Preliminary studies have recently shown this strategy to substantially improve the performance of a policy over one trained on a limited amount of real-world data. Nonetheless, the community lacks a systematic understanding of sim-and-real co-training and what it takes to reap the benefits of simulation data for real-robot learning. This work presents a simple yet effective recipe for utilizing simulation data to solve vision-based robotic manipulation tasks. We derive this recipe from comprehensive experiments that validate the co-training strategy on various simulation and real-world datasets. Using two domains--a robot arm and a humanoid--across diverse tasks, we demonstrate that simulation data can enhance real-world task performance by an average of 38%, even with notable differences between the simulation and real-world data. Videos and additional results can be found at https://co-training.github.io/

Bayesian optimization (BO) has recently become more prevalent in protein engineering applications and hence has become a fruitful target of benchmarks. However, current BO comparisons often overlook real-world considerations like risk and cost constraints. In this work, we compare 72 model combinations of encodings, surrogate models, and acquisition functions on 11 protein binder fitness landscapes, specifically from this perspective. Drawing from the portfolio optimization literature, we adopt metrics to quantify the cold-start performance relative to a random baseline, to assess the risk of an optimization campaign, and to calculate the overall budget required to reach a fitness threshold. Our results suggest the existence of Pareto-optimal models on the risk-performance axis, the shift of this preference depending on the landscape explored, and the robust correlation between landscape properties such as epistasis with the average and worst-case model performance. They also highlight that rigorous model selection requires substantial computational and statistical efforts.

--Audio-Visual Question Answering (A VQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing A VQA approaches often suffer from overfitting to dataset biases, leading to poor robustness. T o address these challenges, we first introduce a novel dataset, FortisA VQA, constructed in two stages: (1) rephrasing questions in the test split of the public MUSIC-A VQA dataset and (2) introducing distribution shifts across questions. The first stage expands the test space with greater diversity, while the second enables a refined robustness evaluation across rare, frequent, and overall question distributions. Second, we introduce a robust Multimodal Audio-Visual Epistemic Network (MA VEN) that leverages a multifaceted cycle collaborative debiasing strategy to mitigate bias learning. Experimental results demonstrate that our architecture achieves state-of-the-art performance on FortisA VQA, with a notable improvement of 7.81%. Additionally, our evaluation reveals the limited robustness of existing multimodal QA methods. We also verify the plug-and-play capability of our strategy by integrating it with various baseline models across both datasets. UMANS possess the extraordinary capacity to seam-lessly integrate auditory and visual cues, effectively establishing a cohesive relationship between visual and auditory stimuli [1-3]. Jie Ma, Pinghui Wang, Jing Tao and Zhou Su are with the Ministry of Education of Key Laboratory for Intelligent Networks and Network Security, School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China. Zhitao Gao and Jun Liu are with the Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering, School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China. Qi Chai is with the Information Hub, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, 510000, China. The question in current A VQA datasets is generated by a limited set of predefined templates, which may not be in line with the real-world scenario. Our findings indicate that existing methods such as STG [6] are not robust, which may be attributed to excessive bias learning, such as memorizing statistical regularities between critical question words and answers. It requires the system to learn high-order interaction representations of the concepts encompassed with audio, video, and language modalities. As is known to us [8-10], the high-level reasoning ability of the system mainly relies on large-scale data that does not contain harmful biases or statistical regularities. However, completely avoiding the negative bias in datasets seems challenging [11] due to the inherent skewness in real-world data distributions.

--We introduce DD3G, a formulation that Distills a multi-view Diffusion model (MV-DM) into a 3D Generator using gaussian splatting. DD3G compresses and integrates extensive visual and spatial geometric knowledge from the MV-DM by simulating its ordinary differential equation (ODE) trajectory, ensuring the distilled generator generalizes better than those trained solely on 3D data. Unlike previous amortized optimization approaches, we align the MV-DM and 3D generator representation spaces to transfer the teacher's probabilistic flow to the student, thus avoiding inconsistencies in optimization objectives caused by probabilistic sampling. The introduction of probabilistic flow and the coupling of various attributes in 3D Gaussians introduce challenges in the generation process. T o tackle this, we propose PEPD, a generator consisting of Pattern Extraction and Progressive Decoding phases, which enables efficient fusion of probabilistic flow and converts a single image into 3D Gaussians within 0.06 seconds. Furthermore, to reduce knowledge loss and overcome sparse-view supervision, we design a joint optimization objective that ensures the quality of generated samples through explicit supervision and implicit verification. Leveraging existing 2D generation models, we compile 120k high-quality RGBA images for distillation. Experiments on synthetic and public datasets demonstrate the effectiveness of our method. Our project is available at: https://qinbaigao.github.io/DD3G I NTRODUCTION W ITH the rapid development of 2D-AIGC [1] and 3D Gaussian Splatting [2] technologies, there is a significant opportunity for the automated generation of 3D assets from a single image. However, a key challenge that has * Corresponding author. Hao Qin, Ming Kong, Mengxu Lu, and Qiang Zhu are with School of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China (e-mail: haoqin@zju.edu.cn;

--Epilepsy is a common neurological disorder that affects around 65 million people worldwide. Detecting seizures quickly and accurately is vital, given the prevalence and severity of the associated complications. Recently, deep learning-based automated seizure detection methods have emerged as solutions; however, most existing methods require extensive post-processing and do not effectively handle the crucial long-range patterns in EEG data. In this work, we propose SeizureTransformer, a simple model comprised of (i) a deep encoder comprising 1D convolutions (ii) a residual CNN stack and a transformer encoder to embed previous output into high-level representation with contextual information, and (iii) streamlined decoder which converts these features into a sequence of probabilities, directly indicating the presence or absence of seizures at every time step. Extensive experiments on public and private EEG seizure detection datasets demonstrate that our model significantly outperforms existing approaches (ranked in the first place in the 2025 "seizure detection challenge" organized in the International Conference on Artificial Intelligence in Epilepsy and Other Neurological Disorders), underscoring its potential for real-time, precise seizure detection. Epilepsy is a prevalent neurological disorder distinguished by recurring seizures. Worldwide, there are approximately 65 million people with epilepsy, more than Parkinson's disease, Alzheimer's disease, and Multiple Sclerosis combined.