W paradigm e introduce that enhances Autoregressi image ve Retrie generation val Augmentation by autoregressi ( v A ely R-R incorporating AG), a novel knearest neighbor retrievals at the patch level. Unlike prior methods that perform a fix single, ed reference static retrie images, val before AR-RA generation G performs and conte condition xt-aware the retrie entire vals generation at each genon eration step, using prior-generated patches as queries to retrieve and incorporate the evolving most rele generation vant patch-le needs vel while visual avoiding references, limitations enabling (e.g., the o model ver-cop to ying, respond stylisto tic bias, etc.) prevalent in existing methods. To realize AR-RAG, we propose two parallel frameworks: (1) Distribution-Augmentation in Decoding (DAiD), a tion training-free of model-predicted plug-and-use patches decoding with the strate distrib gy that ution directly of retrie mer v ges ed patches, the distrib and u(2) Feature-Augmentation in Decoding (FAiD), a parameter-efficient fine-tuning method convolution that progressi operations vely and smooths leverages the them features to augment of retriev the ed patches image generation via multi-scale process.

Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objectives in openended text generation: fostering diversity and creativity while preserving logical coherence. Existing truncated sampling techniques, including temperature scaling, top-p (nucleus) sampling, and min-p sampling, aim to manage this trade-off.

USER: Please segment .

Continual learning is often motivated by the idea, known as the big world hypothesis, that "the world is bigger" than the agent. Recent problem formulations capture this idea by explicitly constraining an agent relative to the environment. These constraints lead to solutions in which the agent continually adapts to best use its limited capacity, rather than converging to a fixed solution. However, explicit constraints can be ad hoc, difficult to incorporate, and may limit the effectiveness of scaling up the agent's capacity. In this paper, we characterize a problem setting in which an agent, regardless of its capacity, is constrained by being embedded in the environment.

We present a Directional Consistency (DC)-driven Adaptive Density Control (ADC) for 3DGaussian Splatting (DC4GS). Whereas the conventional ADC bases its primiti the DC ve of splitting the gradients on the magnitudes into ADC, and of positional realize it gradients, through the we angular further incorporate coherence of the gradients.

The rapid growth of data-driven technologies and the emergence of various datasharing paradigms have underscored the need for efficient and stable data exchange protocols. In any such exchange, agents must carefully balance the benefit of acquiring valuable data against the cost of sharing their own. Ensuring stability in these exchanges is essential to prevent agents--or groups of agents--from departing and conducting local (and potentially more favorable) exchanges among themselves. To address this, we study a model where n agents participate in a data exchange. Each agent has an associated payoff for the data acquired from other agents and a cost incurred during sharing its own data.

Watermarking is widely regarded as a promising defense against the misuse of large language models (LLMs); however, existing methods are fundamentally constrained by their vulnerability to scrubbing and spoofing attacks. This vulnerability stems from an inherent trade-off governed by watermark window size: smaller windows resist scrubbing better but are easier to reverse-engineer, enabling lowcost statistics-based spoofing attacks. This work expands the trade-off boundary by introducing a novel mechanism, equivalent texture keys, where multiple tokens within a watermark window can independently support the detection. Based on the redundancy, we propose a watermark scheme with Sub-vocabulary decomposed Equivalent tExture Key (SEEK). SEEK achieves a Pareto improvement, enhancing robustness to scrubbing attacks without sacrificing resistance to spoofing.

Recent advancements in Vision-Language-Action (VLA) models have shown promise for end-to-end autonomous driving by leveraging world knowledge and reasoning capabilities.

While energy-based models have recently proven to be a powerful framework for learning to reason with neural networks, their practical application is still limited by computational cost. That is, existing methods for energy-based iterative reasoning suffer from computational bottlenecks by relying on expensive optimization routines during training and especially during inference.

Visual reinforcement learning has shown promise in various real-world applications. However, deploying policies in complex real-world environments with visual perturbations remains a significant challenge. We notice that humans tend to filter information at the object level prior to decision-making, facilitating efficient skill transfer across different contexts. Inspired by this, we introduce Focus-ThenReuse (FTR), a method utilizing a novel object selection mechanism to focus on task-relevant objects, and directly reuse the simulation-trained policy on them.