MOSS-Audio Technical Report

MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning. MOSS-Audio couples a dedicated audio encoder with a modality adapter and a large language model: the encoder produces 12.5 Hz temporal representations, the adapter projects them into the decoder space, and the decoder generates autoregressive text outputs. Two design choices are central to the system: \textbf{DeepStack cross-layer feature injection}, which exposes the decoder to acoustic information from multiple encoder depths, and \textbf{time markers}, which provide explicit temporal cues by inserting timestamp markers into the audio-token stream. At the data level, we design an event-preserving audio annotation pipeline that segments raw audio at coherent event boundaries, applies branch-specific annotation to speech, music, and general audio, and merges the results into unified captions for pretraining. The intermediate branch-specific captions are further retained to support the construction of task-oriented SFT data. The model is pretrained on large-scale audio-language data, with time-aware objectives incorporated to support temporal grounding, and then undergoes multi-stage post-training to enhance instruction following and audio-grounded reasoning. We release 4B and 8B variants in both Instruct and Thinking configurations. MOSS-Audio achieves strong performance across general audio understanding, speech captioning, ASR, and timestamped ASR, positioning it as a promising understanding foundation for future voice agents.

PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking

Recent vision-language-action and diffusion-based robot policies often use action chunking, where each policy query predicts a sequence of future actions and the robot executes an open-loop prefix before re-querying. While this interface improves local motion continuity, deployment still requires choosing the execution horizon: how much of each predicted chunk should be executed before acquiring a new observation. However, our experiments show that success is strongly task-dependent and non-monotonic with respect to the execution horizon, making a single constant horizon an unreliable deployment rule. We propose PACE (Phase-Aware Chunk Execution), a training-free test-time execution method that selects the execution horizon online from the predicted chunk itself. PACE exploits the phase-dependent kinematic structure of manipulation trajectories by identifying low-speed transition points in the predicted speed profile and using them as candidate replanning boundaries. Because PACE uses only the predicted action chunk, it is plug-and-play and requires no retraining or access to policy internals. We validate PACE through large-scale evaluations in both simulation and real-robot settings. On 50 RoboTwin2.0 tasks, PACE raises the average success rate from 57.8% to 64.2%. In real-robot experiments on bimanual ALOHA and single-arm Franka platforms, PACE improves the average task score from 60.7 to 77.7 and the average success rate from 50.7% to 70.4%. Ablations and rollout-level analyses show that PACE adapts execution horizons across manipulation phases, shortening near transitions while preserving longer execution during coherent motion.

What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies

Vision--language--action (VLA) policies are trained to imitate actions; their loss never asks them to estimate reward, progress, or future success. Their frozen representations nevertheless carry such information, and it can be read out and used to guide action choice without retraining the policy. From mixed successful and failed manipulation trajectories on LIBERO-Goal, we recover Monte-Carlo outcome targets using lightweight linear probes on frozen features. The targets are consistently predictable from OpenVLA, Pi0.5, DINOv2, and CLIP features, and substantially less so from baselines built on progress, time-to-go, task identity, or proprioception. To rule out task and temporal shortcuts, we evaluate the probes under same-task, same-timestep matched comparisons: Pi0.5 probes still reach roughly 92% pairwise ordering accuracy, while label-shuffled controls stay at chance. Used as a test-time selector over sampled Pi0.5 action prefixes, the same probe turns this offline finding into behavior: on push-plate, success rises from 26.7% under greedy decoding to 44.3%, with a second positive case on wine-rack. The gains are not universal and require additional inference compute, but the underlying finding is clean: frozen VLAs already encode information about success that their imitation objective never explicitly demands.

VFEAgent: A Multimodal Agent Framework for End-to-End Automated Finite Element Analysis

Finite Element Analysis (FEA) serves as the cornerstone of modern engineering design. However, its workflow is inherently complex and relies heavily on domain expertise. Although recent efforts have integrated Large Language Models (LLMs) into FEA, existing approaches face limitations in handling multimodal inputs and executing complex tasks. To address these limitations, we propose VFEAgent, an end-to-end multi-agent system designed to automate FEA modeling and simulation directly from input images and problem descriptions. Our methodology integrates two core components: (1) a multimodal vision-language multi-agent pipeline that employs ReAct-driven reasoning to extract structured FEA specifications from heterogeneous inputs and (2) a verification-first code synthesis framework, incorporating robust self-debugging and fallback mechanisms to ensure executability and physical validity. We systematically evaluated the system across various engineering mechanics scenarios. The results demonstrate that VFEAgent achieves a high success rate in generating complete and physically valid simulations, outperforming LLM-based baseline methods in reliability and correctness. These findings validate the feasibility of automating the complete FEA workflow, highlighting the framework's potential to liberate engineers from tedious manual analysis.

TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models

Time series foundation models (TSFMs) are increasingly pretrained on large corpora, raising concerns that evaluation datasets may have been exposed during pretraining and thus yield overly optimistic performance estimates. Auditing such contamination is challenging in time series because signals are continuous and heterogeneous, and often lack corpus documentation. To the best of our knowledge, this is the first work to study pretraining contamination auditing for TSFMs. We formalize the problem of pretraining contamination auditing for TSFMs and propose TSFMAudit, a method based on probe adaptation dynamics. Our key intuition is that contamination manifests as unusually efficient adaptation: after a fine tuning probe, contaminated datasets tend to exhibit faster loss reduction with smaller backbone movement. We evaluate TSFMAudit on 6 TSFMs and 187 datasets using documented training source evidence as supervision, and compare against 10 competitive baselines adapted from the LLM literature.

Toto 2.0: Time Series Forecasting Enters the Scaling Era

We show that time series foundation models scale: a single training recipe produces reliable forecast-quality improvements from 4M to 2.5B parameters. We release Toto 2.0, a family of five open-weights forecasting models trained under this recipe. The Toto 2.0 family sets a new state of the art on three forecasting benchmarks: BOOM, our observability benchmark; GIFT-Eval, the standard general-purpose benchmark; and the recent contamination-resistant TIME benchmark. This report describes our experimental results and details the design decisions behind Toto 2.0: its architecture and training recipe, training data, and the u-muP hyperparameter transfer pipeline. All five base checkpoints are released under Apache 2.0.

ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response

Time series question-answering (TSQA), in which we ask natural language questions to infer and reason about properties of time series, is a promising yet underexplored capability of foundation models. In this work, we present ARFBench, a TSQA benchmark that evaluates the understanding of multimodal foundation models (FMs) on time series anomalies prevalent in software incident data. ARFBench consists of 750 questions across 142 time series and 5.38M data points from 63 production incidents sourced exclusively from internal telemetry at Datadog. We evaluate leading proprietary and open-source LLMs, VLMs, and time series FMs and observe that frontier VLMs perform markedly better than existing baselines; the leading model (GPT-5) achieves a 62.7% accuracy and 51.9% F1. We next demonstrate the promise of specialized multimodal approaches. We develop a novel TSFM + VLM hybrid prototype which we post-train on a small set of synthetic and real data that yields comparable overall F1 and accuracy with frontier models. Lastly, we find models and human domain experts exhibit complementary strengths. We define a model-expert oracle, a best-of-2 oracle selector over model and expert answers, yielding 82.8% F1 and 87.2% accuracy and establishing a new superhuman frontier for future TSQA models. The benchmark is available at https://huggingface.co/datasets/Datadog/ARFBench.

VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection

Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundation models face a fundamental trade-off: 1D temporal models provide fine-grained pointwise localization but lack a global contextual perspective, while 2D vision-based models capture global patterns but suffer from information bottlenecks due to a lack of temporal alignment and coarse-grained pointwise detection. To resolve this dilemma, we propose VETime, the first TSAD framework that unifies temporal and visual modalities through fine-grained visual-temporal alignment and dynamic fusion. VETime introduces a Reversible Image Conversion and a Patch-Level Temporal Alignment module to establish a shared visual-temporal timeline, preserving discriminative details while maintaining temporal sensitivity. Furthermore, we design an Anomaly Window Contrastive Learning mechanism and a Task-Adaptive Multi-Modal Fusion to adaptively integrate the complementary perceptual strengths of both modalities. Extensive experiments demonstrate that VETime significantly outperforms state-of-the-art models in zero-shot scenarios, achieving superior localization precision with lower computational overhead than current vision-based approaches. Code available at: https://github.com/yyyangcoder/VETime.

EIDOS: Latent-Space Predictive Learning for Time Series Foundation Models

Most time series foundation models are pretrained by directly predicting future observations, which often yields weakly structured latent representations that capture surface noise rather than coherent and predictable temporal dynamics. In this work, we introduce EIDOS, a foundation model family that shifts pretraining from future value prediction to latent-space predictive learning. We train a causal Transformer to predict the evolution of latent representations, encouraging the emergence of structured and temporally coherent latent states. To ensure stable targets for latent-space learning, we design a lightweight aggregation branch to construct target representations. EIDOS is optimized via a joint objective that integrates latent-space alignment, observational grounding to anchor representations to the input signal, and direct forecasting supervision. On the GIFT-Eval benchmark, EIDOS mitigates structural fragmentation in the representation space and achieves state-of-the-art performance. These results demonstrate that constraining models to learn predictable latent dynamics is a principled step toward more robust and reliable time series foundation models.

It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks

Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation. However, we contend that existing benchmarks exhibit common limitations in four dimensions: constrained data composition dominated by reused legacy sources, compromised data integrity lacking rigorous quality assurance, misaligned task formulations detached from real-world contexts, and rigid analysis perspectives that obscure generalizable insights. To bridge these gaps, we introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks, tailored for strict zero-shot TSFM evaluation free from data leakage. Integrating large language models and human expertise, we establish a rigorous human-in-the-loop benchmark construction pipeline to ensure high data integrity and redefine task formulation by aligning forecasting configurations with real-world operational requirements and variate predictability. Furthermore, we propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels. By leveraging structural time series features to characterize intrinsic temporal properties, this approach offers generalizable insights into model capabilities across diverse patterns. We evaluate 12 representative TSFMs and establish a multi-granular leaderboard to facilitate in-depth analysis and visualized inspection. The leaderboard is available at https://huggingface.co/spaces/Real-TSF/TIME-leaderboard.