arXiv:2608. 07420v1 Announce Type: new Abstract: World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursively rolling out their own predictions.
arXiv:2610.27000v1 Announce Type: new Abstract: Deep generative models provide an effective modern solution to alleviating the problem of data scarcity by synthesizing realistic time series. However,...
Timer‑M1 is a pretrained multivariate time‑series foundation model that learns with primitives for zero‑shot forecasting. It uses a primitive‑based data synthesis and pretraining pipeline to generate series with shared temporal and relational patterns, assembling them into multivariate samples with distinct channel roles. The model employs gated two‑dimensional Transformer blocks that dynamically allocate cross‑variate attention, achieving top performance on several large‑scale forecasting benchmarks.
AdaMamba introduces an adaptive frequency-gated Mamba architecture for long‑term time series forecasting. The model integrates an interaction learning module that captures cross‑variable dependencies and multi‑scale context, and an adaptive frequency‑gated state space module that generates context‑dependent frequency bases and unifies temporal forgetting into a single time‑frequency gate. Experiments on seven public benchmarks and four domain‑specific datasets show that AdaMamba consistently outperforms state‑of‑the‑art baselines while remaining computationally efficient.
The paper introduces HART, a Hybrid Attention-RWKV Time-series Foundation Model that alternates attention and RWKV blocks to improve long-horizon forecasting. It identifies a problem in RWKV-7 called Placeholder Idling Decay, where repeated state transitions degrade historical information during non-autoregressive multi-step forecasting. Experiments on GIFT-Eval and TIME-Benchmark show that HART outperforms pure RWKV on medium and long horizons while matching short-horizon performance, and achieves comparable long-horizon MASE to a much larger Transformer with only 36 M parameters.
arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.
arXiv:2505. 23863v3 Announce Type: replace-cross Abstract: Understanding chaotic dynamics is a fundamental problem across scientific disciplines, including climate science, neuroscience, and fluid dynamics, yet direct experimentation and intervention in such systems are often infeasible.
WorldAgen is a unified framework that jointly learns world modeling and action prediction using a shared Transformer backbone with two specialized heads. It introduces a Mixed Unidirectional Attention Mask to separate the world model and agent model, and enables Test-Time Training (TTT) by sampling exploratory actions and updating the world model with real state transitions. Experiments on CALVIN and LIBERO show that WorldAgen matches or surpasses state‑of‑the‑art methods, especially when TTT is applied to a few samples.
The paper introduces recirculation, an inference‑time architectural enhancement for foundation models that reduces perplexity and improves accuracy on generation and reasoning tasks without adding significant latency. Recirculation adds a specific form of recurrence, enabling the model to function as a dynamical system that tracks belief states, and is distinct from chain‑of‑thought or depth‑recurrence methods. An adaptive variant requires minimal hyperparameter tuning and achieves notable gains on the Gemma3 family, including a 23% perplexity drop and a 21% accuracy increase on GSM8k.
arXiv:2605. 27406v2 Announce Type: replace Abstract: Structured state space models (SSMs) have recently emerged as a promising foundation for sequence modeling, with Mamba-based architectures demonstrating strong performance through input-dependent state transitions, albeit at considerable complexity.
arXiv:2606. 24969v1 Announce Type: new Abstract: While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requires architectures that balance efficient training with highly expressive latent states.
arXiv:2610.26903v1 Announce Type: new Abstract: Action-conditioned world models support planning and policy evaluation by predicting future states. However, learning an accurate one-step predictor ca...