Lu Shi

Linli Shi, Ruijun Zhang, Ziyun Wang

Event cameras offer microsecond temporal resolution, low latency, and high dynamic range, making them attractive for robotics. However, labeled event-camera data for a specific robot and scene is scarce and expensive to collect, which slows the development of event-based perception and control. We present EVIS: a physics-grounded event camera plugin for NVIDIA Isaac Sim that generates high-rate, fully labeled event streams directly inside a physics simulator. The plugin implements a faithful log-intensity contrast event model with per-pixel asynchronous reference updates; it migrates from a normal RGB camera with few changes and integrates into any Isaac Sim / Isaac Lab scene, inheriting the simulator's physics and frame-perfect ground truth. It is fully configurable, and offers an interpolation option that renders only sparse keyframes and synthesizes the in-between frames through bidirectional motion-vector warping, making real-time generation on a single GPU possible. Optional sensor noise and motion blur further narrow the gap to real cameras. The generated streams are directly usable by pretrained event networks for downstream tasks. Code repository: https://github.com/spikelab-jhu/isaac-sim-event-camera-plugin

Ke Cheng, Hanqiao Ye, Lei Shi et al.

Driving-world generation has emerged as a core capability for scalable autonomous-driving simulation, yet existing methods remain limited in object-level controllability and long-horizon stability. We present M$^\text{4}$World, a Multi-view and Multimodal generative driving world model that synthesizes future surround-view video streams and synchronized LiDAR scans while supporting interactive object Manipulation and stable Minute-long streaming. Fine-grained object manipulation is realized through a flexible conditioning interface that supports explicit control over both the spatial layout and visual appearance of individual objects. Stable minute-long streaming, on the other hand, is achieved through a multi-stage training framework that enables online causal generation in only four denoising steps while maintaining coherent world dynamics throughout extended rollouts. Building on these components, we introduce an efficient few-clip post-training as well as a suite of visual reference-conditioned generation models, preserving general generation ability while allowing rare-case customization for long-tail controllability. To assess controllability beyond realism, we further introduce an automated VLM-based judging pipeline that evaluates scene-level condition adherence, view-wise object controllability, and cross-view object consistency. Comprehensive experiments show that M$^\text{4}$World consistently delivers high generation quality, precise controllability, and stable minute-long streaming. Together with downstream long-tail augmentation and scene editing, these results demonstrate the potential of M$^\text{4}$World for controllable, scalable driving simulation.

Lei Shi, Anlan Zhang, Rita Lyu et al.

AI judges offer a scalable, low-cost alternative to human evaluation, but their outputs can be biased relative to human preferences and highly item-dependent, varying across judges, tasks, and domains. When uncalibrated AI evaluations are used for model ranking, item scoring, or population-level quality reporting, these biases can directly distort downstream decisions. We propose BACON, a four-stage pipeline that combines budgeted human calibration with multiple AI-judge outputs to produce more accurate annotations. BACON constructs full-coverage auxiliary features for every item, including multi-judge scores, token-level uncertainty statistics, and contextual embeddings. It then collects human labels for a small sampled subset and trains a cross-fitted outcome model to generate calibrated item-level surrogate predictions. These predictions support two use cases: population-level estimation of summary metrics, such as means or quantiles, using an augmented estimating-equation estimator with valid confidence intervals; and individual-level surrogate scoring for item ranking and annotation. BACON treats AI judges as auxiliary measurements rather than ground truth: human labels provide the calibration anchor, while AI-derived signals improve efficiency. Across diverse tasks, domains, and labeling budgets, BACON improves predictive accuracy and ranking consistency, and reduces bias and variance relative to raw AI outputs and purely human-label-based methods. These results show that BACON offers a practical, statistically grounded framework for scalable evaluation with limited human annotation.

Ang Li, Ben Liu, Bin Han et al.

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

Shide Zhou, Kailong Wang, Ling Shi et al.

Defining the reasoning boundaries and ensuring the reliability of Large Reasoning Models (LRMs) remains a critical challenge. Current benchmarks primarily rely on static datasets susceptible to data contamination or synthetic tasks lacking fine-grained difficulty control. Furthermore, standard outcome-based evaluations often conceal reasoning flaws by neglecting the reasoning process. To address these limitations, we introduce TRACE, a testing framework that models temporal reasoning as constraint satisfaction problems via Allen's Interval Algebra. This approach enables precise regulation of logical complexity and incorporates a Trace-Based Verification Oracle to validate reasoning faithfulness. Using this framework, we construct TRACEBench, an extensive benchmark comprising 1,200 synthesized test instances across graded difficulty levels. We employ TRACE to evaluate eight widely used LRMs on TRACEBench. The results confirm a strong negative correlation between model performance and our difficulty metric (Pearson's r approximately -0.96), validating the effectiveness of our difficulty control mechanism. Moreover, our trace-based analysis exposes significant discrepancies between reasoning validity and final answers, revealing a high spurious guessing rate of approximately 28% in mid-sized models. In addition, we diagnose scale-dependent failure modes, ranging from Degenerative Loops in small models to Reasoning Explosion in advanced architectures. TRACE thus provides a robust, automated platform for benchmarking the true temporal reasoning capabilities of LRMs.

Liyao Wang, Ruipu Wu, Haojun Xu et al.

Cross-view object geo-localization (CVOGL) aims to locate a target object from a query view (e.g., ground or drone) within a geo-tagged reference image (e.g., satellite). Existing approaches heavily rely on 2D appearance matching and are constrained by limited datasets lacking geometric metadata, diverse prompts, and standard field-of-view imagery. To address these intertwined challenges, we first introduce \dataset, a large-scale, high-fidelity building dataset comprising over 220,000 ground-satellite and drone-satellite pairs. It provides multi-modal prompts (points, boxes, masks) and camera poses to enable flexible target referring and explicit spatial modeling. Furthermore, we propose a novel single-stage Geometry-Aware Geo-localization framework (GAGeo), built upon the permutation-equivariant 3D foundation model $π^3$. By seamlessly integrating visual features, referring prompts, and learnable task tokens, our model adapts the inherited 3D prior to jointly predict bounding boxes, segmentation masks, and camera poses in a single forward pass. Additionally, we introduce a contrastive loss that utilizes the satellite view as a universal anchor, implicitly aligning ground and drone representations to enable zero-shot ground-to-drone localization without requiring triplet training data. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art methods, exhibiting exceptional generalization ability in unseen scenes and novel cross-view setups.

Negin Raoof, Richard Zhuang, Marianna Nezhurina et al.

Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts such as SWE-Smith, SERA, and Nemotron-Terminal typically target a single benchmark, leaving open the question of how to train models that generalize across diverse agentic tasks. The OpenThoughts-Agent (OT-Agent) project addresses this gap with a fully open data curation pipeline for training agentic models. We conduct more than 100 controlled ablation experiments to systematically investigate each stage of the pipeline, yielding insights on the importance of task sources and diversity. We then assemble a training set of 100K examples from our pipeline and fine-tune Qwen3-32B on this dataset, which yields an average accuracy of 44.8% across seven agentic benchmarks and a 3.9 percentage point improvement over the strongest existing open data agentic model (Nemotron-Terminal-32B, 40.9%). Moreover, our training data exhibits strong scaling properties, outperforming alternative open datasets at every training set size in compute-controlled comparisons. We publicly release our training sets, data pipeline, experimental data, and models at openthoughts.ai to support future open research on agentic model training.

Wei-Cheng Tseng, Gashon Hussein, Yuzhu Dong et al.

Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating policy rollouts. Autoregressive rollouts accumulate compounding errors, observations across multiple camera views must remain mutually consistent, and the evaluator must generalize to policies whose behaviors lie outside the training distribution. We address these challenges with SC3-Eval, a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator by enforcing three complementary forms of consistency. First, forward-inverse dynamics consistency jointly trains the model to predict frames from actions and to recover actions from frames, anchoring generated rollouts to a physically plausible action manifold and counteracting the drift a forward-only model cannot penalize. Second, cross-view consistency trains the model to inpaint each camera view from the other, keeping the multi-camera observation coherent over long rollouts without any explicit memory mechanism. Third, test-time consistency reuses the inverse dynamics mode at inference as a per-action-chunk uncertainty signal that terminates rollouts whose generated frames drift away from the requested actions. We also demonstrate SC3-Eval rollouts reproduce the failure modes that policies exhibit in real-world rollouts, supporting fine-grained diagnostic comparison rather than aggregate ranking alone. Across seven real-world vision-language-action policies, SC3-Eval attains a closed-loop Pearson correlation of $0.929$ and MMRV of $0.119$, outperforming three strong prior video-model-based baselines, and generalizes to new tasks.

Xinyi Zheng, Ling Shi, Tianlong Yu et al.

Large Language Models (LLMs) have made significant progress in reasoning, particularly in deductive reasoning, which is crucial for high-stakes decision-making. As models improve, evaluation benchmarks should evolve to keep pace. However, existing benchmarks lack fine-grained control over logical complexity and struggle to balance semantic diversity with logical consistency. To address these issues, we propose QMFOL, an automated framework for generating monadic first-order logic reasoning tasks with quantifiable and controllable complexity. It constructs formal logical structures using conjunction and disjunction patterns, enabling precise control over reasoning depth, width, label types, and distractors. These structures are then translated into natural language via LLMs, with logical consistency ensured through round-trip verification using an external prover. Based on our framework, we build QMFOLBench, a benchmark comprising 2880 instances with 960 configurations across diverse logical and semantic dimensions. Evaluations on six large reasoning models (LRMs) and two LLMs show that performance degrades and computational overhead increases with rising logical complexity. Models perform better on True-labeled tasks than on False or Unknown ones, and exhibit sensitivity to semantic variation. Overall, QMFOL offers a scalable and reliable approach for constructing deductive reasoning benchmarks with controllable complexity, enabling more precise evaluation of reasoning capabilities in modern language models.

Weibin Gu, Chen Yang, Lu Shi et al.

Offline models for autonomous robots often fail under time-varying dynamics outside their training distribution. Koopman operator theory offers a linear representation of nonlinear dynamics via lifting, but its transition to real-time recursive estimation may suffer numerical vulnerabilities: covariance windup under low excitation when using exponential forgetting, and vanishing gain without forgetting. This paper introduces a Covariance-Regulated Recursive Koopman Learning (CR-RKL) framework with two complementary strategies--error dead-zone gating and constant-trace normalization--each independently capable of preventing covariance explosion and parameter freezing, with the latter additionally preserving the geometric structure of uncertainty. Validated on a non-holonomic differential-drive robot with wheel slip and Stribeck friction and on a 26-gram butterfly-inspired flapping-wing micro aerial vehicle, CR-RKL achieves numerically stable and accurate online modeling, and when embedded in model predictive control, it maintains reliable tracking performance under uncertain, time-varying dynamics.

Guangji Chen, Long Shi, Qingqing Wu et al.

Providing reliable communication for unmanned aerial vehicles (UAVs) via existing cellular networks is crucial for enabling the rapid growth of the low-altitude economy. However, UAV jittering significantly degrades communication quality due to induced beam misalignment. Inspired by recent advances in integrated sensing and communication, we propose a novel two-stage active sensing-assisted communication framework tailored for ground-to-UAV links with jittering. Specifically, two schemes are conceived to leverage sensing for enhancing communication performance, namely the communication-oriented scheme and the sensing-oriented scheme. For the sensing-oriented scheme, deterministic signals are employed in the first stage to facilitate angle-of-arrival (AoA) acquisition at the UAV side, followed by pure communication service in the second stage by using the estimated AoA. In contrast, the communication-oriented scheme employs Gaussian information-bearing signals throughout both stages, with AoA estimation relying on Gaussian random signals. For both schemes, we provide maximum likelihood estimators for AoA, along with analytical results characterizing the Cramér-Rao bound. To capture the performance limit, closed-form expressions for the achievable rates of the two schemes are derived, unveiling a fundamental tradeoff between sensing and communication quality across the two stages by tuning the time allocated to the first stage. The optimal time allocation that maximizes the overall rate is obtained in semi-closed-form. Based on these results, we unveil a sufficient condition under which the communication-oriented scheme outperforms the sensing-oriented scheme, which admits an interesting threshold-based structure. Asymptotic analysis demonstrates that the performance loss of the proposed schemes relative to the jitter-free upper bound approaches zero in the high transmit power regime.