HAMON: Passive diffractive optical system for long-horizon time-series forecasting
HAMON is a proposed forecasting architecture that replaces learned digital sequence-mixing layers with a passive diffractive optical core: historical values are encoded onto an optical aperture and cascaded trainable phase masks with free-space diffraction produce forecasts in the output field. At inference, prediction requires only a single passive optical propagation pass with no digital temporal mixing. The system outperforms strong digital baselines on ETTm2 and ETTh2 benchmarks by up to 14% MSE improvement, though it trails on high-channel-count datasets like Traffic and Electricity. The work raises a substrate-level question about whether forecasting operators need to be implemented digitally at all, and defines a concrete target for optical computing hardware.
Related guides (2)
Related events (8)
AHA-WAM: Asynchronous world-action modeling with temporal decoupling for robot manipulation
AHA-WAM introduces a dual Diffusion Transformer architecture that decouples world prediction (low-frequency) from action execution (high-frequency) in robot manipulation policies, addressing the inefficiency of existing world-action models that force both branches to operate at the same temporal resolution. The system uses a rolling key-value memory video DiT as a long-horizon scene planner and a fast action DiT that queries layerwise latent context via joint attention, with Observation-Guided Video-Context Routing enabling asynchronous execution. On RoboTwin benchmarks, AHA-WAM achieves 92.80% average success and 78.3% on real-world tasks at 24.17 Hz, a 4.59x speedup over Fast-WAM, without robot-data pretraining.
Zero Touch Predictive Orchestration: Automated Time-Series Forecasting for Cloud-Edge Continuum Cold Start
A preprint proposes a fully automated time-series prediction architecture for Cloud-Edge Continuum (CEC) orchestration, addressing the cold-start problem where newly discovered edge nodes lack historical data for localized model training. The system combines a lightweight Resource Exposer for telemetry collection with a novel data-mixing methodology that merges sparse local samples with TimeTrack, a publicly released high-resolution dataset, then feeds the result through a Neural Architecture Search engine to auto-generate baseline models. Experiments show the approach improves MSE, MAE, and MAPE and accelerates convergence versus training on local data alone or generic datasets.
COGENT: Continuous graph emulator with Neural ODEs for long-term physical forecasting on irregular meshes
COGENT is a new architecture combining graph neural networks with Neural Ordinary Differential Equations for continuous-time physical forecasting on irregular geospatial meshes. The model encodes historical system states and forcings into latent dynamics that can be queried at arbitrary future times, avoiding the error accumulation of autoregressive rollout. Evaluated on ice-sheet simulations from the Ice-sheet and Sea-level System Model, COGENT shows improved long-range stability over autoregressive graph baselines. The work introduces training stabilization strategies including rollout-horizon sampling and progressive scheduling.
TunerDiT: Training-free Progressive Steering of Diffusion Transformers for Multi-Event Video Generation
TunerDiT is a training-free method for steering video diffusion transformers (DiTs) to generate long-horizon videos containing multiple sequential events. The approach identifies intrinsic turning points in the DiT denoising trajectory where text conditioning shifts from global layout to fine-grained detail, then applies two steering mechanisms: Event-Partitioned Masking and Cross-Event Prompt Fusion. The authors also introduce Meve, a benchmark prompt suite for multi-event video generation, and report state-of-the-art results across 8 metrics with improved text alignment scaling with event count.
LLM Agent Framework for Last-Mile Time Series Forecasting Revision
This paper introduces a 'last-mile forecasting' framework where an LLM agent sits atop a statistical forecasting backbone to incorporate weakly structured business context—holidays, campaigns, expert feedback, external events—into decision-ready forecasts. The system uses tool-invocation for contextual retrieval, converts reasoning into explicit revision actions under safety constraints, and supports long-horizon forecasting via map-reduce decomposition with a memory bank for post-hoc reflection. The authors validate the approach through real-world case studies, positioning it as a bridge between statistical prediction and operationally usable forecasts.
Benchmark of deep learning architectures for multi-horizon behavioural forecasting in mobile health
A new arXiv preprint benchmarks six deep learning architectures, two zero-shot foundation models, and statistical baselines on multi-horizon behavioural forecasting from wearable and smartphone data across 800+ participants. Key findings include: no single architecture dominates (PatchTST leads among trained models), TimesFM matches or exceeds trained models zero-shot especially in low-data regimes, and participant-level fine-tuning reduces per-feature RMSE by 16–60%. The study is the first to jointly evaluate modern deep learning, foundation models, and personalisation for this domain.
ADAS: Attention-Discounted Adaptive Sampler improves parallel decoding for masked diffusion language models
Researchers propose ADAS, a training-free reranking rule for masked diffusion language model decoding that addresses token interaction failures in parallel token commitment. The method greedily penalizes candidates that attend strongly to already-selected uncertain positions, using attention weights as soft marginal penalties rather than hard constraints. Evaluated on LLaDA-8B-Base and Dream-7B-Base across GSM8K, MATH500, HumanEval, and MBPP, ADAS improves low-NFE performance by 9–10 percentage points on average when plugged into existing samplers with only 3.1% runtime overhead.
Probabilistic Time Series Forecasting with Transformers
This Hugging Face blog post introduces probabilistic time series forecasting using Transformer-based models available in the Hugging Face ecosystem. It covers the application of attention-based architectures to sequential prediction tasks with uncertainty quantification. The post serves as a tutorial and capability demonstration for time series modeling within the Transformers library.