Designing protein sequences that fold into a target 3D structure--known as protein inverse folding--is a fundamental challenge in protein engineering. While recent deep learning methods have achieved impressive performance by recovering native sequences, they often overlook the one-to-many nature of the problem: multiple diverse sequences can fold into the same structure.

USER: Please segment .

Learning a compact representation of history is critical for planning and generalization in partially observable environments. While meta-reinforcement learning (RL) agents can attain near Bayes-optimal policies, they often fail to learn the compact, interpretable Bayes-optimal belief states. This representational inefficiency potentially limits the agent's adaptability and generalization capacity. Inspired by predictive coding in neuroscience--which suggests that the brain predicts sensory inputs as a neural implementation of Bayesian inference--and by auxiliary predictive objectives in deep RL, we investigate whether integrating self-supervised predictive coding modules into meta-RL can facilitate learning of Bayes-optimal representations. Through state machine simulation, we show that meta-RL with predictive modules consistently generates more interpretable representations that better approximate Bayes-optimal belief states compared to conventional meta-RL across a wide variety of tasks, even when both achieve optimal policies. In challenging tasks requiring active information seeking, only meta-RL with predictive modules successfully learns optimal representations and policies, whereas conventional meta-RL struggles with inadequate representation learning. Finally, we demonstrate that better representation learning leads to improved generalization. Our results strongly suggest the role of predictive learning as a guiding principle for effective representation learning in agents navigating partial observability.

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.

By integrating the lighting, appearance, and geometry cues within a unified diffusion architecture, IllumiCraft generates temporally coherent videos aligned with user-defined prompts. It supports background-conditioned and text-conditioned video relighting and provides better fidelity than existing controllable video generation methods.

Time series forecasting holds significant value in various domains such as economics, traffic, energy, and AIOps, as accurate predictions facilitate informed decision-making. However, the existing Mean Squared Error (MSE) loss function sometimes fails to accurately capture the seasonality or trend within the forecasting horizon, even when decomposition modules are used in the forward propagation to model the trend and seasonality separately. To address these challenges, we propose a simple yet effective Decomposition-Based Loss function called DBLoss. This method uses exponential moving averages to decompose the time series into seasonal and trend components within the forecasting horizon, and then calculates the loss for each of these components separately, followed by weighting them. As a general loss function, DBLoss can be combined with any deep learning forecasting model. Extensive experiments demonstrate that DBLoss significantly improves the performance of state-of-the-art models across diverse real-world datasets and provides a new perspective on the design of time series loss functions.

Recent advancements in speech synthesis technology have enriched our daily lives, with high-quality and human-like audio widely adopted across real-world applications. However, malicious exploitation like voice-cloning fraud poses severe security risks. Existing defense techniques struggle to address the production large language model (LLM)-based speech synthesis. While previous studies have considered the protection for fine-tuning synthesizers, they assume manually annotated transcripts. Given the labor intensity of manual annotation, end-to-end (E2E) systems leveraging automatic speech recognition (ASR) to generate transcripts are becoming increasingly prevalent, e.g., voice cloning via commercial APIs.