In this paper, we point out that there exist scaling and initialization problems in most existing multiple kernel learning (MKL) approaches, which employ the large margin principle to jointly learn both a kernel and an SVM classifier. The reason is that the margin itself can not well describe how good a kernel is due to the negligence of the scaling. We use the ratio between the margin and the radius of the minimum enclosing ball to measure the goodness of a kernel, and present a new minimization formulation for kernel learning. This formulation is invariant to scalings of learned kernels, and when learning linear combination of basis kernels it is also invariant to scalings of basis kernels and to the types (e.g., L

Robotic manipulation systems operating in diverse, dynamic environments must exhibit three critical abilities: multitask interaction, generalization to unseen scenarios, and spatial memory. While significant progress has been made in robotic manipulation, existing approaches often fall short in generalization to complex environmental variations and addressing memory-dependent tasks. To bridge this gap, we introduce SAM2Act, a multi-view robotic transformer-based policy that leverages multi-resolution upsampling with visual representations from large-scale foundation model. SAM2Act achieves a state-of-the-art average success rate of 86.8% across 18 tasks in the RLBench benchmark, and demonstrates robust generalization on The Colosseum benchmark, with only a 4.3% performance gap under diverse environmental perturbations. Building on this foundation, we propose SAM2Act+, a memory-based architecture inspired by SAM2, which incorporates a memory bank, an encoder, and an attention mechanism to enhance spatial memory. To address the need for evaluating memory-dependent tasks, we introduce MemoryBench, a novel benchmark designed to assess spatial memory and action recall in robotic manipulation. SAM2Act+ achieves competitive performance on MemoryBench, significantly outperforming existing approaches and pushing the boundaries of memory-enabled robotic systems. Project page: https://sam2act.github.io/

Non-autoregressive (NAR) generative models are valuable because they can handle diverse conditional generation tasks in a more principled way than their autoregressive (AR) counterparts, which are constrained by sequential dependency requirements. Recent advancements in NAR models, such as diffusion language models, have demonstrated superior performance in unconditional generation compared to AR models (e.g., GPTs) of similar sizes. However, such improvements do not always lead to improved conditional generation performance. We show that a key reason for this gap is the difficulty in generalizing to conditional probability queries unseen during training. As a result, strong unconditional generation performance does not guarantee high-quality conditional generation. This paper proposes Tractable Transformers (Tracformer), a Transformer-based generative model that is more robust to different conditional generation tasks. Unlike existing models that rely solely on global contextual features derived from full inputs, Tracformers incorporate a sparse Transformer encoder to capture both local and global contextual information. This information is routed through a decoder for conditional generation. Empirical results demonstrate that Tracformers achieve state-of-the-art conditional generation performance on text modeling compared to recent diffusion and AR model baselines.

Personal space, also known as peripersonal space, is crucial in human social interaction, influencing comfort, communication, and social stress. Estimating and respecting personal space is essential for enhancing human-computer interaction (HCI) and smart environments. Personal space preferences vary due to individual traits, cultural background, and contextual factors. Advanced multimodal sensing technologies, including eye-tracking and wristband sensors, offer opportunities to develop adaptive systems that dynamically adjust to user comfort levels. Integrating physiological and behavioral data enables a deeper understanding of spatial interactions. This study develops a sensor-based model to estimate comfortable personal space and identifies key features influencing spatial preferences. Our findings show that multimodal sensors, particularly eye-tracking and physiological wristband data, can effectively predict personal space preferences, with eye-tracking data playing a more significant role. An experimental study involving controlled human interactions demonstrates that a Transformer-based model achieves the highest predictive accuracy (F1 score: 0.87) for estimating personal space. Eye-tracking features, such as gaze point and pupil diameter, emerge as the most significant predictors, while physiological signals from wristband sensors contribute marginally. These results highlight the potential for AI-driven personalization of social space in adaptive environments, suggesting that multimodal sensing can be leveraged to develop intelligent systems that optimize spatial arrangements in workplaces, educational institutions, and public settings. Future work should explore larger datasets, real-world applications, and additional physiological markers to enhance model robustness.

Initializing with pre-trained models when learning on downstream tasks is becoming standard practice in machine learning. Several recent works explore the benefits of pre-trained initialization in a federated learning (FL) setting, where the downstream training is performed at the edge clients with heterogeneous data distribution. These works show that starting from a pre-trained model can substantially reduce the adverse impact of data heterogeneity on the test performance of a model trained in a federated setting, with no changes to the standard FedAvg training algorithm. In this work, we provide a deeper theoretical understanding of this phenomenon. To do so, we study the class of two-layer convolutional neural networks (CNNs) and provide bounds on the training error convergence and test error of such a network trained with FedAvg. We introduce the notion of aligned and misaligned filters at initialization and show that the data heterogeneity only affects learning on misaligned filters. Starting with a pre-trained model typically results in fewer misaligned filters at initialization, thus producing a lower test error even when the model is trained in a federated setting with data heterogeneity. Experiments in synthetic settings and practical FL training on CNNs verify our theoretical findings.

Classification is a ubiquitous and fundamental problem in artificial intelligence and machine learning, with extensive efforts dedicated to developing more powerful classifiers and larger datasets. However, the classification task is ultimately constrained by the intrinsic properties of datasets, independently of computational power or model complexity. In this work, we introduce a formal entropy-based measure of classificability, which quantifies the inherent difficulty of a classification problem by assessing the uncertainty in class assignments given feature representations. This measure captures the degree of class overlap and aligns with human intuition, serving as an upper bound on classification performance for classification problems. Our results establish a theoretical limit beyond which no classifier can improve the classification accuracy, regardless of the architecture or amount of data, in a given problem. Our approach provides a principled framework for understanding when classification is inherently fallible and fundamentally ambiguous.

Recent advances in large language models (LLMs) have shown promising improvements, often surpassing existing methods across a wide range of downstream tasks in natural language processing. However, these models still face challenges, which may hinder their practical applicability. For example, the phenomenon of hallucination is known to compromise the reliability of LLMs, especially in fields that demand high factual precision. Current benchmarks primarily focus on hallucination detection and factuality evaluation but do not extend beyond identification. This paper proposes an explanation enhanced hallucination-detection model, coined as HuDEx, aimed at enhancing the reliability of LLM-generated responses by both detecting hallucinations and providing detailed explanations. The proposed model provides a novel approach to integrate detection with explanations, and enable both users and the LLM itself to understand and reduce errors. Our measurement results demonstrate that the proposed model surpasses larger LLMs, such as Llama3 70B and GPT-4, in hallucination detection accuracy, while maintaining reliable explanations. Furthermore, the proposed model performs well in both zero-shot and other test environments, showcasing its adaptability across diverse benchmark datasets. The proposed approach further enhances the hallucination detection research by introducing a novel approach to integrating interpretability with hallucination detection, which further enhances the performance and reliability of evaluating hallucinations in language models.

Text-to-image generation models have gained popularity among users around the world. However, many of these models exhibit a strong bias toward English-speaking cultures, ignoring or misrepresenting the unique characteristics of other language groups, countries, and nationalities. The lack of cultural awareness can reduce the generation quality and lead to undesirable consequences such as unintentional insult, and the spread of prejudice. In contrast to the field of natural language processing, cultural awareness in computer vision has not been explored as extensively. In this paper, we strive to reduce this gap. We propose a RusCode benchmark for evaluating the quality of text-to-image generation containing elements of the Russian cultural code. To do this, we form a list of 19 categories that best represent the features of Russian visual culture. Our final dataset consists of 1250 text prompts in Russian and their translations into English. The prompts cover a wide range of topics, including complex concepts from art, popular culture, folk traditions, famous people's names, natural objects, scientific achievements, etc. We present the results of a human evaluation of the side-by-side comparison of Russian visual concepts representations using popular generative models.

Sarcasm is a linguistic phenomenon that intends to ridicule a target (e.g., entity, event, or person) in an inherent way. Multimodal Sarcasm Explanation (MuSE) aims at revealing the intended irony in a sarcastic post using a natural language explanation. Though important, existing systems overlooked the significance of the target of sarcasm in generating explanations. In this paper, we propose a Target-aUgmented shaRed fusion-Based sarcasm explanatiOn model, aka. TURBO. We design a novel shared-fusion mechanism to leverage the inter-modality relationships between an image and its caption. TURBO assumes the target of the sarcasm and guides the multimodal shared fusion mechanism in learning intricacies of the intended irony for explanations. We evaluate our proposed TURBO model on the MORE+ dataset. Comparison against multiple baselines and state-of-the-art models signifies the performance improvement of TURBO by an average margin of $+3.3\%$. Moreover, we explore LLMs in zero and one-shot settings for our task and observe that LLM-generated explanation, though remarkable, often fails to capture the critical nuances of the sarcasm. Furthermore, we supplement our study with extensive human evaluation on TURBO's generated explanations and find them out to be comparatively better than other systems.

The technique of "testing by betting" frames nonparametric sequential hypothesis testing as a multiple-round game, where a player bets on future observations that arrive in a streaming fashion, accumulates wealth that quantifies evidence against the null hypothesis, and rejects the null once the wealth exceeds a specified threshold while controlling the false positive error. Designing an online learning algorithm that achieves a small regret in the game can help rapidly accumulate the bettor's wealth, which in turn can shorten the time to reject the null hypothesis under the alternative $H_1$. However, many of the existing works employ the Online Newton Step (ONS) to update within a halved decision space to avoid a gradient explosion issue, which is potentially conservative for rapid wealth accumulation. In this paper, we introduce a novel strategy utilizing interior-point methods in optimization that allows updates across the entire interior of the decision space without the risk of gradient explosion. Our approach not only maintains strong statistical guarantees but also facilitates faster null hypothesis rejection in critical scenarios, overcoming the limitations of existing approaches.