However, deploying these models can be unreliable when significant distribution gaps exist between training and test data, while fine-tuning for diverse scenarios is often costly. This creates a need for methods that can efficiently adapt to new data at test time without expensive retraining. Cache-based test-time adapters serve this purpose by storing representative test samples to guide subsequent classifications. Yet, these methods typically employ naive cache management with limited capacity, leading to severe catastrophic forgetting when samples are inevitably dropped during updates. In this paper, we propose Dota(DistributiOnal Test-time Adaptation), a simple yet effective method addressing this limitation. Crucially, instead of merely memorizing individual test samples, Dotacontinuously estimates the underlying distribution of the test data stream. Test-time posterior probabilities are then computed using these dynamically estimated distributions via Bayes' theorem for adaptation. This distribution-centric approach enables the model to continually learn and adapt to the deployment environment. Extensive experiments validate that Dota significantly mitigates forgetting and achieves state-of-the-art performance compared to existing methods.

Symmetry is pervasive in robotics and has been widely exploited to improve sample efficiency in deep reinforcement learning (DRL). However, existing approaches primarily focus on spatial symmetries--such as reflection, rotation, and translation--while largely neglecting temporal symmetries. To address this gap, we explore time reversal symmetry, a form of temporal symmetry commonly found in robotics tasks such as door opening and closing. We propose Time Reversal symmetry enhanced Deep Reinforcement Learning (TR-DRL), a framework that combines trajectory reversal augmentation and time reversal guided reward shaping to efficiently solve temporally symmetric tasks. Our method generates reversed transitions from fully reversible transitions, identified by a proposed dynamicsconsistent filter, to augment the training data. For partially reversible transitions, we apply reward shaping to guide learning, according to successful trajectories from the reversed task. Extensive experiments on the Robosuite and MetaWorld benchmarks demonstrate that TR-DRL is effective in both single-task and multitask settings, achieving higher sample efficiency and stronger final performance compared to baseline methods. Our project website and source code can be found in 1 and 2.

Mask-based pretraining has become a cornerstone of modern large-scale models across language, vision, and recently biology. Despite its empirical success, its role and limits in learning data representations have been unclear. In this work, we show that the behavior of mask-based pretraining can be directly characterized by test risk in high-dimensional minimum-norm ("ridge-less") linear regression, without relying on further model specifications.

Recent research on representation learning has proved the merits of multi-modal clues for robust semantic segmentation. Nevertheless, a flexible pretrain-andfinetune pipeline for multiple visual modalities remains unexplored. In this paper, we propose a novel multi-modal learning framework, termed OmniSegmentor.

Large Language Models (LLMs) are increasingly being explored across a range of reasoning tasks. However, LLMs sometimes struggle with reasoning tasks under uncertainty that are relatively easy for humans, such as planning actions in stochastic environments. The adoption of LLMs for reasoning is impeded by uncertainty challenges, such as LLM uncertainty and environmental uncertainty. LLM uncertainty arises from the stochastic sampling process inherent to LLMs. Most LLM-based Decision-Making (LDM) approaches address LLM uncertainty through multiple reasoning chains or search trees. However, these approaches overlook environmental uncertainty, which leads to poor performance in environments with stochastic state transitions.

Frontier large language models (LLMs) have shown great success in text modeling and generation tasks across domains. However, natural language exhibits inherent semantic hierarchies and nuanced geometric structure, which current LLMs do not capture completely owing to their reliance on Euclidean operations such as dotproducts and norms. Furthermore, recent studies have shown that not respecting the underlying geometry of token embeddings leads to training instabilities and degradation of generative capabilities. These findings suggest that shifting to non-Euclidean geometries can better align language models with the underlying geometry of text. We thus propose to operate fully in Hyperbolic space, known for its expansive, scale-free, and low-distortion properties.

We study Online Convex Optimization with adversarial constraints (COCO). At each round a learner selects an action from a convex decision set and then an adversary reveals a convex cost and a convex constraint function. The goal of the learner is to select a sequence of actions to minimize both regret and the cumulative constraint violation (CCV) over a horizon of length T. The best-known policy for this problem achieves O( T)regret and O( T)CCV. In this paper, we improve this by trading off regret to achieve substantially smaller CCV. This trade-off is especially important in safety-critical applications, where satisfying the safety constraints is non-negotiable. Specifically, for any bounded convex cost and constraint functions, we propose an online policy that achieves O( dT+Tβ)regret and O(dT1 β)CCV, where dis the dimension of the decision set and β [0,1]is a tunable parameter. We begin with a special case, called the CONSTRAINEDEXPERT problem, where the decision set is a probability simplex and the cost and constraint functions are linear. Leveraging a new adaptive small-loss regret bound, we propose a computationally efficient policy for the CONSTRAINEDEXPERT problem, that attains O( T lnN+Tβ)regret and O(T1 β lnN)CCV for N number of experts.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Newsom, California Legislature reach $351.7-billion Two locations will return to Southern California. This is read by an automated voice. Please report any issues or inconsistencies here .

The coordinated activity of neural populations underlies myriad brain functions. Manipulating this activity using brain stimulation techniques has great potential for scientific and clinical applications, as they causally influence the nervous system. To improve the accuracy by which one can manipulate neural activity, it is important to (1) take into account the pre-stimulation brain state, which can influence the brain's response to stimulation, and (2) adaptively update stimulation parameters over time to compensate for changes in the brain's response to stimulation. In this work, we propose Online MicroStimulation Optimization (OMiSO), a brain stimulation framework that leverages brain state information to find stimulation parameters that can drive neural population activity toward specified states. OMiSO includes two key advances: i) training a stimulation-response model that leverages the pre-stimulation brain state, and inverting this model to choose the stimulation parameters, and ii) updating this inverse model online using newly-observed responses to stimulation. We tested OMiSO using intracortical microstimulation with a "Utah" array and found that it outperformed competing methods that do not incorporate these advances. Taken together, OMiSO provides greater accuracy in achieving specified activity states, thereby advancing neuromodulation technologies for understanding the brain and for treating brain disorders.

Lifelong knowledge editing enables continuous, precise updates to outdated knowledge in large language models (LLMs) without computationally expensive full retraining. However, existing methods often accumulate errors throughout the editing process, causing a gradual decline in both editing accuracy and generalization. To tackle this problem, we propose Neuron-Specific Masked Knowledge Editing (NMKE), a novel fine-grained editing framework that combines neuron-level attribution with dynamic sparse masking. Leveraging neuron functional attribution, we identify two key types of knowledge neurons, with knowledge-general neurons activating consistently across prompts and knowledge-specific neurons activating to specific prompts. NMKE further introduces an entropy-guided dynamic sparse mask, locating relevant neurons to the target knowledge. This strategy enables precise neuron-level knowledge editing with fewer parameter modifications. Experimental results from thousands of sequential edits demonstrate that NMKE outperforms existing methods in maintaining high editing success rates and preserving model general capabilities in lifelong editing.