Embodied Internet of Things (IoT) systems are promoting the adoption of task-oriented semantic communication (SemCom), in which the trustworthy task decisions require both semantic information reliability and source legitimacy. However, existing trustworthy designs in SemCom mainly focus on semantic content recovery and protection, with limited attention to source legitimacy. Motivated by this limitation, this paper establishes a new information exploitation paradigm for integrated SemCom-identity protection to address active source impersonation and passive identity inference by treating each SemCom signal as an inherent carrier of both task-relevant semantic information and transmitter physical identity information. We first examine these two information resources and then analyze their integration feasibility at the observation, processing, and decision levels. To exploit these resources for trustworthy decision making, we further develop a dual-branch identity protection mechanism under different operating modes. In the authentication mode, semantic recovery and physical-layer source verification are performed in parallel using the same received observation. In the concealment mode, identity exposure is suppressed while semantic recovery quality is maintained to support anonymous sensing reports. The resulting outputs are jointly interpreted to support task decisions under mode-specific identity protection requirements. Finally, two representative case studies on active source impersonation and passive identity inference are presented to evaluate the proposed framework.
Time-series forecasting is foundational to a wide spectrum of web-scale services, spanning personalized recommendations, energy scheduling, and infrastructure capacity planning. Accurate long-term time series forecasting (LTSF) requires models to capture long-range temporal dependencies while adapting to periodic patterns that vary across variables. Although frequency-aware methods offer a global view of temporal dynamics, they typically rely on inflexible heuristic designs, such as predefined period lengths, manually selected or randomly sampled top-k frequency components, and separate spectral transformations. Consequently, they fail to account for time-frequency heterogeneity, where variables that appear synchronized in the time domain can differ substantially in the frequency domain. Meanwhile, Mamba-based forecasters, despite their efficiency in long-range modeling, introduce frequency information only as auxiliary signals, leaving spectral evidence disconnected from state transitions. In this work, we propose AdaMamba, a novel approach that explicitly internalizes input-dependent frequency information into the modeling of temporal dependencies. AdaMamba comprises an interaction learning module and an adaptive frequency-gated state space module: the former captures cross-variable dependencies and multi-scale temporal context, while the latter generates context-dependent frequency bases and unifies temporal forgetting into a single time-frequency gate that directly modulates state evolution. Extensive experiments on seven public LTSF benchmarks and four domain-specific datasets demonstrate that AdaMamba consistently outperforms state-of-the-art baselines while maintaining competitive computational efficiency.
Rui Zhang, Yujia Su, Ruixuan Li, Yuhua Li, Yixin Su
Open-source LLMs provide a flexible alternative to closed-source models for Text-to-SQL but still struggle with complex queries. Finetuning with chain-of-thought (CoT) data improves reasoning, yet standard datasets lack CoT annotations, requiring synthetic generation. Existing synthesis methods only verify the final answer, allowing flawed reasoning steps to corrupt the training data. We propose VCoT-SQL, a framework that improves Text-to-SQL generation through intermediate-step validated CoT supervision and a dedicated SQL validator, which enables small open-source models to outperform frontier closed-source models. VCoT-SQL trains two complementary models on curated reasoning traces: an SQL generator using clause-level CoT templates where reasoning steps are verified via execution and schema alignment checks, and an SQL validator using diagnostic CoT templates to detect syntactic, semantic, and type level errors. We further design a hierarchical schema filtering pipeline that integrates and refines complementary retrieval strategies to distill relevant database elements. VCoT-SQL achieves 66.82% execution accuracy on challenging dataset BIRD dev and 86.8% on Spider test, improving the base 7B model by 7% on BIRD. Notably, our CoT synthesis relies on 7B models yet outperforms methods that use 72B-scale or even proprietary closed source teachers for data generation, demonstrating that rigorous step-level validation can be more effective than scaling up teacher model size. Our dataset and code are available at https://github.com/INTREBID/VCoT-SQL.
Chunxiao Wu, Huixin Huang, Jialei Pan, Qiang Liang, Tao Wu, Cheng Wu, Long Huang, Yuanji Li 等 12 位作者
Self-supervised pre-training on synthetic aperture radar (SAR) imagery enables transferable representations, but the optical-SAR domain gap and speckle perturbations limit representation stability. Most SAR foundation models use masked image modeling (MIM) through pixel reconstruction or structural feature prediction, which is sensitive to speckle or relies on predefined operators. Joint modeling of cross-view semantics and perturbation stability at corresponding spatial locations remains underexplored. We propose XuanJian-DINOSAR, a SAR foundation model based on global and local semantic consistency. We curate over 360K publicly available SAR target chips, detection images, and scene images spanning diverse targets, scenes, and sensors, and adapt an optically pre-trained DINOv2 model to SAR through self-supervised learning. The framework combines DINO global semantic self-distillation, iBOT local masked modeling, and KoLeo feature-distribution regularization to learn globally discriminative and locally structure-aware representations. We introduce a local semantic consistency branch tailored to SAR intensity statistics and coherent imaging characteristics. Shared geometric transformations produce spatially aligned teacher weak views and student strong views. Intensity transformations and Gamma multiplicative speckle perturbations are applied to student views, while a cosine consistency loss aligns patch tokens at corresponding locations, promoting stability under radiometric perturbations. This objective complements the cross-region and cross-scale semantic consistency of DINOv2 multi-crop training, jointly enforcing global and local semantic consistency. Experiments on multiple downstream classification and detection datasets demonstrate state-of-the-art performance on most evaluation metrics, validating the generality and transferability of the learned representations.
In transactional databases, achieving active-active replication among geo-distributed replicas is challenging due to the high coordination cost in ensuring the serializability of concurrent cross-node transactions. Deterministic concurrency control (DCC) has emerged as a promising alternative: it establishes a global order for a batch of transactions before execution and thereby amortizes this coordination cost across the batch. To better understand the performance characteristics of DCC, we conduct a theoretical analysis of traditional two-phase locking and optimistic concurrency control to account for geo-replication and introduce a model for DCC. We compare the three paradigms and identify the conditions under which DCC is advantageous. Guided by the insights from this analysis, we then present Quirinus, a DCC-based geo-replicated database that optimizes transaction execution through speculative execution, transaction reordering, integration of conflict-free replicated data types (CRDTs), and fast-path commit. Even without these optimizations, Quirinus achieves up to 6.2x the TPC-C throughput of Tiga under our configuration.
Gengyu Rao, Ghadeer Ahmed H Alabandi, Su Ann Chong, Thomas Huber, Kailash Gogineni, Subhajit Dutta Chowdhury, Saleel Kudchadker, Suchita Pati 等 31 位作者
Large language models (LLM) have been the key focus of recent machine learning breakthroughs. As the model size grows exponentially, the computation needed for training is astronomical. A GPU can do a huge amount of arithmetic. However, the data its compute units need is not always available when they are ready. This data may still be in slow memory or on another GPU. While the chip waits, expensive compute sits idle, and at scale even a small drop in utilization translates into substantial cost. In this paper, we treat this waiting time as the primary bottleneck. We focus on hardware features designed for explicit data movement. These features load data from off-chip memory onto the chip, rearrange it into the layout the computation requires as it is loaded, and transfer it between GPUs. By orchestrating them, we keep a steady pipeline of data flowing to the compute units so that they remain busy. We present kernel and framework implementations that address this bottleneck using three key data-movement instructions and hardware features. The Tensor Data Mover (TDM) moves tensor data from high-bandwidth memory (HBM) into on-chip memory. Transpose-load instructions transpose tensor data into the layout that LLM computations require as it is loaded on-chip. Finally, System DMA (SDMA) and Remote DMA (RDMA) move data between GPUs over the scale-up and scale-out networks, respectively. Our results show that TDM and transpose-load provide on average 1.88x and 1.19x speedup at the kernel level, respectively. The SDMA and RDMA lead to on average 1.16x and 1.33x speedup for computation overlapped with communication. This is the first AMD LLM training system to utilize all the GPU data pipelining features. Our implementation has been integrated into open source framework and library for AMD GPUs. https://github.com/AMD-AGI/Primus-Turbo https://github.com/AMD-AGI/Primus
AI 速览：作者提出让编码智能体在仿真中重建任务并生成带动作标签的逼真多视角数据，以替代人工遥操作采集机器人示范。
Teleoperation remains the default way to collect robot demonstrations, but every episode costs robot and operator time, and every new task starts from scratch. We ask whether a coding agent can take over the teleoperator's job. In our DataFarm, the agent receives a data request and one calibration episode of the robot in the target scene and rebuilds the task in simulation: it writes the scene, an expert controller, and a success judge. The simulator supplies exact actions, and a video model conditioned on real images renders each rollout as photographic video, generating all camera views together consistently. The output is real-ready data: synchronized camera views labelled with the robot's actions, on which a policy can be trained directly and deployed on the real robot. Independent judges certify the expert and every rendered episode before admission. On five real-robot tasks, policies trained only on farm data match policies trained on as many teleoperated episodes (93 vs. 84 successes in 100 trials), and under an unseen tablecloth and coloured light they keep 87 successes where the teleoperation-trained policies fall to 46. Adapting a task is fully automatic and costs \$21 of API usage on average, paid once per task, plus \$5 for a render contract; every further episode costs \$0.80 on average for simulation, rendering, and review, with no robot or operator. One hour of three-view data for a task costs \$107 on average, these costs included, slightly below a quote of \$117 for teleoperation in China and below \$290 in labour alone in North America.
Andrey Ignatov, Georgy Perevozchikov, Radu Timofte, Yuhong He, Yuxuan Qiu, Tianyu Hao, Ruoqi Li, Yueqi Yang 等 22 位作者
With the increasing importance of mobile camera quality in modern smartphones, growing attention has been directed toward computational photography and advanced image signal processing (ISP) algorithms aimed at enhancing various perceptual attributes of captured images. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose the participants to design fast solutions that can reconstruct RGB photos from RAW Bayer camera data while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale Fujifilm UltraISP dataset consisting of RAW-RGB image pairs captured with the Sony IMX586 Quad Bayer mobile sensor and a professional 102MP medium format FujiFilm GFX100 camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to reconstruct high-quality 5MP RGB image from raw data on both platforms under 100 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.
Qwen3-8B reviewing Llama-3.1-8B in math adds 33.2 points, yet Qwen3-8B alone is 6.4 points more accurate than the result. Reviewing another model's answer is usually judged by its gain over the generator. We show that this confuses verification, which adds accuracy beyond either model alone, with capability transfer, where a stronger reviewer supplies answers it could have given on its own. Measured against the stronger model alone, across 48 pairs of 12 open-weight models (3B to 72B) in math, knowledge, code and reasoning, review beats it in only 9 of 96 review directions, and does worse the larger the capability gap. The reason is anchoring: the reviewer mostly follows the generator, discarding its own correct answers. Review costs 2.6 to 2.8 times as much as the stronger model alone, while a selector using the same two calls is 2.7 to 4.2 points more accurate than review and cheaper. Studies of verification should report the stronger model alone, not only the gain over the generator.
Recent 3D large multimodal models (3D-LMMs) rely on a visual bottleneck to compress complex 3D scene evidence into a limited number of visual tokens compatible with large language models (LLMs). Current visual bottlenecks, however, often passively compress heterogeneous 3D evidence into a homogeneous object-centric token sequence, leaving the spatial organization of the scene under-represented. This under-representation forces the LLM to recover spatial relations from a flattened token sequence, leading to unstable reasoning in relation-intensive and spatially ambiguous scenes. To address this issue, we propose SceneScaffold, an active scene-state construction framework for unified 3D scene understanding. SceneScaffold reformulates the visual bottleneck from a passive feature compressor into an active scene organizer, constructing a role-aware spatial scaffold before language reasoning. Specifically, SceneScaffold organizes superpoint-level visual evidence into scene-state components with distinct structural roles: entity states preserve core object semantics, scene-frame states maintain spatial references via boundary and region anchors, relation states encode object-environment interaction cues, and a global summary provides compact context. Through this role-aware construction, SceneScaffold provides the LLM with a spatially organized scene representation before language reasoning. Experiments on unified 3D scene understanding tasks, including 3D visual grounding, question answering, and dense captioning, demonstrate the effectiveness of SceneScaffold, while diagnostic results further show its applicability to relation-intensive and spatially ambiguous cases. Code is available at https://github.com/lixiangqi707/SceneScaffold.
Man Liu, Xingchen Liu, Hairui Zhao, Guangming Tan, Dingwen Tao
The rapid scaling of large language models (LLMs) has made communication overhead a critical bottleneck in distributed model-parallel training. Although existing low-precision compression methods can effectively reduce communication costs, further reducing the communication footprint to ultra-low-bit formats such as FP4 introduces new challenges, including limited numerical range, sub-byte storage overhead, and increased computational cost from fine-grained quantization. In this paper, we present \textbf{FP4Quant}, a micro-grouped FP4 compression framework for efficient model-parallel LLM training. FP4Quant integrates a micro-grouped dual-scale FP4 quantization mechanism to preserve local tensor distribution characteristics, a warp-cooperative FP4 packing scheme to enable efficient sub-byte data representation, and a hybrid two-level FWHT pipeline to mitigate quantization errors with GPU-aware execution optimization. Experiments on NVIDIA H100 GPUs with Qwen-7B demonstrate up to 1.56$\times$ end-to-end throughput improvement over BF16, revealing a trade-off between throughput and model quality.
LLM-powered semantic queries increasingly combine relational processing with multiple LLM-based operators over unstructured data. Efficiently serving such queries is challenging due to runtime dynamism at two coupled levels. Across queries, dynamic arrivals and heterogeneous resource demands continuously change scheduling priorities. Within a query, heterogeneous characteristics across fine-grained input batches cause operator costs and selectivities to vary throughout execution, making a statically optimized plan unreliable. These two forms of dynamism create a circular dependency: inter-query scheduling requires estimates of remaining LLM work, while the remaining work depends on runtime plan choices whose costs become observable only during execution. We present SeqoFlow, a runtime framework that jointly adapts query plans and schedules concurrent semantic queries. SeqoFlow enumerates equivalence-preserving plan alternatives under operator dependencies and decomposes queries into fine-grained units, enabling safe plan adaptation and query preemption at batch boundaries. To support both decisions without exhaustively profiling candidate plans on the target LLM, SeqoFlow uses lightweight speculative estimation to capture runtime costs. These estimates jointly guide plan adaptation and inter-query scheduling, closing the loop between query optimization and LLM inference. Experiments across diverse query structures, data distributions, and arrival rates show that SeqoFlow substantially reduces end-to-end latency compared to existing semantic query systems, adaptive query processing techniques, and conventional scheduling policies.
Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a promising approach for enhancing the reasoning capabilities of large language models. However, it still remains unclear whether RLVR can extend reasoning capabilities beyond what is already encoded in the base model. In this paper, we study this question through the lens of primacy bias: the tendency of models to over-rely on already-learned representations, disproportionately improving performance on problems they already handle well while underexploring harder ones that require departing from those representations. Through our controlled experiments and large-scale analysis, we show that RLVR training on mixed data tends to further sharpen performance on easier problems while yielding only marginal gains on harder ones. We find that although hard problems lead to modest gains overall, they are actually the ones that help most in expanding the model's reasoning capabilities and pushing the representations. However, prolonged training on these hard problems may also hurt and lead to forgetting on easy problems. These findings help to better understand some of the prior conflicting observations about RLVR, specifically, why on (OOD) domains where the base model performs poorly, improvements on hard problems can expand reasoning; while on well-trained domains, forgetting can reduce performance and mask genuine gains obtained from hard problems.
Graph-based network intrusion detection systems (GIDS) report strong benchmark detection metrics, but those metrics establish little about deployability. We approach the problem from first principles: rather than inheriting the preprocessing, windowing, and thresholding conventions of each published system, we ask what a controlled comparison requires and impose it uniformly. The result is GIDS-Eval, an evaluation framework that decomposes a GIDS into six interchangeable stages and turns those conventions into explicit experimental variables, so reported performance can be attributed to individual stages instead of whole pipelines. We survey nine representative GIDS, reimplement five of them within GIDS-Eval, and evaluate them on four datasets under one matched protocol. We identify nine recurring evaluation gaps and quantify the impact of each: two crafted edges achieve full evasion against three of the eight detector-dataset pairs with anything to hide; the snapshot window alone accounts for a mean 38.3% relative swing in average precision (AP); aligning preprocessing across systems moves AP by up to 61.8 percentage points for a single detector; and none of the 18 detector-dataset pairs we replay can alert as events arrive. We introduce GIDS-Lite, an encoder-free control built in the same framework, which ranks first by AP on two of the four datasets at up to 575$\times$ lower runtime. Architectural complexity is therefore not a consistent driver of detection quality under our matched protocol on current benchmarks, but it does enlarge the runtime, calibration, and attack surfaces operators must defend.
JSON-LD is getting increasing attention for publishing Linked Data, especially within cultural heritage. We present LODox Data Viewer, a reusable web component library for data presentation and visualization in semantic portals. It renders JSON-LD as human-readable, themeable cards, embeddable in any semantic portal page with a single script tag. Package URL: https://www.npmjs.com/package/lodox-data-viewer
Recent advances in Large Language Models have transformed how data can be linked, discovered, and enhanced. LODox, Linked Open Data at Oxford, is an evolving web-based platform that embraces this transformation for cultural heritage Linked Open Data. LODox features a novel interface with intuitive card-based data presentation and visualization in a semantic portal. It represents an evolving approach to explore heterogeneous cultural heritage data across multiple sources through a unified interface. In this paper, we will briefly describe the LODox architecture, its implementation, and future development plan, particularly its alignment and integration with Solid.
Safe autonomous navigation requires not only geometric obstacle avoidance but also semantic awareness. Different object categories demand different safety clearances, and the set of relevant categories may expand as the robot explores novel environments. Vision-language models (VLMs) offer rich semantic representations for building maps of unknown scenes, yet their confidence scores are poorly calibrated, making raw predictions unreliable for safety-critical planning. Conformal prediction (CP) can provide coverage guarantees, but existing methods assume a fixed label set and stationary data, limiting their use in open-world settings. We propose Conformal Semantic Mapping for Open-World Safe Robot Navigation (CoSMO), a semantic safety mapping framework that transforms VLM embeddings into online-calibrated coverage sets and safety-aware obstacle dilations under distribution shift. By calibrating directly in the embedding space, CoSMO avoids the score rescaling that arises in confidence calibration as the vocabulary expands. Experiments on the Matterport3D (MP3D) dataset show that CoSMO reduces semantic collisions by 61.6% relative to a geometry-only baseline, while maintaining formal coverage guarantees even under delayed expert feedback. Real-world experiments on a quadruped robot further demonstrate generalization by achieving long-run empirical coverage of 90.73% against the 90% target. Project website: https://yangming911.github.io/cosmo-page/.
Many benchmarks now prefer open-ended questions for testing LLM and NLP methods. We find that the choice of a calibration rule can flip when only the correctness labels change: on 141 pilot answers, rules chosen with exact-match labels look 0.239 Brier points better than raw confidence but are 0.103 worse under human labels. How such flips arise remains unclear. We look deeply into their mechanism: reference matching rejects many correct answers (exact match misses 42%), and an exact Brier identity shows these errors favour rules giving such answers lower confidence, which abstain on them at common thresholds. Guided by this, we propose FactForm, a grader that trusts reference matches and otherwise consults evidence retrieved from the question alone. One LLM call per answer fills a fixed-order closed form that a program scores. On 998 fresh EVOUNA answers with 400 fact-based human labels, FactForm reaches a balanced error of 0.077 and an AUROC of 0.985, against 0.112 and 0.930 for the best of eight traditional graders. Its same-model stability is no worse than that of LLM judges (mean absolute run-to-run difference 0.0136 against 0.0159 to 0.0206). We hope this helps benchmarks grade open-ended answers more accurately, with repeatable and discriminative scores.
Theo Rode, Rui Zhang, Ryan Aubrey, Olivia Li, Jessica Huang, Liv Chu, Healani Dowd, Calden Wloka
Monocular depth estimation aims to predict depth maps from single RGB images (forgoing the need for stereo camera pairs) and has seen impressive leaps in performance in recent work due to the introduction of affine-invariant losses and the use of foundation model features. These monocular depth models predict affine-invariant depth, which describes the relative positions of objects in the scene instead of absolute depth. While these models demonstrate strong performance on single image benchmarks and qualitatively consistent predictions in video, their effectiveness at preserving consistent spatial structure has been less thoroughly explored. Many potential real-world applications, such as handling video streams as input, rely on coherent three dimensional consistency in scenes. Further, anchoring relative depth predictions to a metric reference for a given scene is a key challenge for applying monocular depth models to real-world situations. We develop a novel evaluation protocol for monocular depth models using video sequences with moving camera positions to test the consistency of prediction across variation in viewpoint. We demonstrate this methodology over diverse, real-world video sequences where we are able to anchor depth model output to metric depth values using structure from motion. Our work demonstrates open challenges in the development of broadly applicable monocular depth foundation models, particularly with their ability to provide temporal consistency over long time frames. We also identify challenges in the straightforward adoption of structure-from-motion as a metric grounding tool for monocular depth estimation models.
Haomiao Chen, Keith W Jamison, Daniel Chong, Yunrui Zhang, Mert R. Sabuncu, Amy Kuceyeski
A central question in neuroscience is what visual features drive brain responses across regions. Classic approaches rely on handcrafted stimuli to test specific hypotheses, limiting discovery to features defined before experiments. Here we introduce NeuroVolve, a data-driven generative framework for synthesizing images that achieve flexible, user-defined patterns of brain activation in individuals. NeuroVolve recovers established selectivity across visual cortical regions and, paired with subject-specific brain encoding models, generates personalized stimuli reflecting individual differences in neural preference. Beyond single-region selectivity, NeuroVolve uncovers multi-region response selectivity, characterizing how regions jointly represent visual content during naturalistic perception. We further demonstrate generalization beyond visual cortex: in a prospective fMRI experiment, NeuroVolve-generated stimuli targeting the amygdala, a classically non-sensory region, drove measured activation consistent with predictions in novel participants. Together, these results establish NeuroVolve as a less constrained, data-driven tool for probing individual-level neural selectivity across the brain.
AI 速览：RFW-A 将智能体程序合成与程序化生成结合，先由智能体构建并验证类别级可复用生成器，再以程序化执行低成本批量产出铰接资产，并构建了 RFW-A-400K 数据集。
High-quality articulated assets are essential for embodied perception, simulation, and manipulation, yet constructing them at scale remains difficult. Manual annotation and procedural modeling require substantial human effort. Recent agentic systems automate asset construction through program synthesis, but repeat costly reasoning and refinement for every new asset. Our key observation is that assets within a category can share construction logic despite variations in structure and appearance. Agentic synthesis and procedural generation are therefore complementary: agents can construct reusable programs, while procedural execution reuses the resulting logic across many samples. We therefore present RFW-A, which combines the two in a new articulated-asset generation paradigm. Starting from existing articulated programs, RFW-A organizes reusable components and their dependencies into category-level generators. Agents test and refine these generators across sampled configurations and motion states. Once constructed and validated, the generators produce diverse assets through procedural execution with no further model calls or token charges. The estimated API cost of generator authoring averages $10.62, amortizing to $0.05 per asset over 200 assets, versus $1.24 for the sampled per-asset agentic synthesis baseline. Using RFW-A, we built RFW-A-400K, containing over 400K sim-ready articulated assets across more than 500 categories. Experiments show high structural and kinematic validity and stable execution across physics simulators. Beyond asset validity, training with RFW-A-400K improves part-level articulation estimation on seen and unseen categories, while policies trained in simulation with retrieved and program-edited assets transfer zero-shot to real articulated objects.
Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback enable coherent, controllable multi-shot videos. In parallel, video world models provide action-conditioned observations and predicted futures, serving as interactive environments for agents. We study their intersection through the agent harness: an executable runtime that constructs context, exposes tools, maintains state, routes feedback, and manages budgets around video models. This report examines three directions. First, agentic video generation, where harnesses coordinate scripting, shot planning, asset management, production, and editing, alongside the evaluation challenges of these systems. Second, agentic world modeling, where harnesses mediate observation, control, execution, and state. We discuss hybrid designs in which game engines or agent-written programs maintain world state while video models render observations, and how agents and world models can mutually evaluate and improve one another. Third, recursive self-improvement (RSI) in video model development, distinguishing output revisions, updates to harness state, generator parameters, and evaluators, and changes to the improvement procedure itself. We identify how these improvements feed back into subsequent development. Across these directions, we analyze essential agent capabilities, including audiovisual perception, long-horizon planning, memory, code-based interaction, feedback-guided control, skill reuse, and multi-agent coordination. We conclude with challenges in autonomous video production, lifelong memory, programmable hybrid control, autonomous model development, provenance, cost accounting, and evaluation linking video quality and task performance to sustained improvements in models and harnesses.
AI Cosmos Team, Jinfeng Zhou, Yuxuan Chen, Fangming Chang, Mingyu Su, Yifan Zhu, Yuan Wang, Bo Zhang 等 35 位作者
Large language models (LLMs) can improve task performance during learning, yet these gains do not necessarily reflect learners' ability to thereafter apply the knowledge and skills independently. We present AI Cosmos, an agentic infrastructure for situated learning that organizes learning around two complementary principles: scenario-based participation and cumulative assets of practice. AI Cosmos organizes learners and role-specialized agents within learning scenarios that integrate task-relevant knowledge and, when needed, executable workbenches. An asset-memory loop preserves the processes and outcomes of practice as reusable assets with explicit provenance and dependencies. We evaluate scenario-based interaction through two preregistered randomized controlled studies examining the acquisition of legal reasoning and programming competence, holding the same underlying LLM across conditions. AI Cosmos achieves greater learning gains than a conventional LLM in legal reasoning and higher mastery of unseen programming problems than an LLM-as-Teacher baseline.
Hailong Yan, Yongrui Zhang, Xiangtao Zhang, Le Zhang
We propose MorphSIG, a training-free framework that reformulates subject-driven image generation (SIG) as pseudo-video feature transport. MorphSIG contains two core modules: Progressive Decoupled Anchoring, which uses frequency-domain decoupling and structural scrambling during early denoising to break structural locking and enable a gradual transition from free composition to identity alignment; and Pseudo-flow Guided Feature Transport, which constructs a latent-space pseudo-flow field to mimic Image-to-Video temporal coherence and transport subject semantics precisely. To address stylistic homogeneity and the lack of ground truth in existing benchmarks, we further introduce a benchmark with diverse stylized subjects. Extensive experiments show that MorphSIG significantly improves pose diversity and subject fidelity over baselines without additional training. Overall, MorphSIG bridges static generation and dynamic propagation, providing a cost-effective paradigm for high-fidelity subject consistency.
Zhefan Rao, Meng Chu, Xuan Billy Zhang, Jingfan Chen, Guohao Cai, Runyi Li, Shiyi Du, Xu Huang 等 92 位作者
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction requires separate evidence about action selection and state evolution. We introduce Dual Exam, which tests Agents under fixed environment response mechanisms and World Models under fixed action interventions across physical, digital, social, and scientific domains. The Agent track compares 10 configurations on 1,088 items in 15 reporting categories. The World Model track contains 400 cases across eight scenarios; 15 configurations have full coverage and one covers six scenarios. GPT 6 Astra leads the case-weighted Agent Index at 31.3, and GPT-Image-2 leads the full-coverage WM Overall at 21.7. These scores use different tasks and metrics and are not directly comparable. A 150-case pilot of one coupled pairing records zero task successes and motivates component-level diagnosis. Results reveal uneven task performance and failures to preserve task-relevant state. Their value for predicting coupled success or sustained reciprocal learning remains to be established.
Sihan Yang, Weichen Bai, Ruichuan An, Yiming Cheng, Zhiyuan Feng, Tianyi Jiang, Renye Yan, Ning Ding 等 12 位作者
As executable environments for language agents scale, generating and verifying their rollouts becomes increasingly expensive. Under finite rollout budgets, this raises an important question: can data management at the environment level make agentic reinforcement learning (RL) more efficient by organizing, evaluating, and scheduling task instances together with the environments that determine their tools, states, transitions, and verification? To address this question, we introduce EnvSched (Environment-aware Scheduling), an online scheduler that learns from rollout history. EnvSched assigns scheduling value through two complementary modeling choices: exploitation prioritizes tasks likely to provide informative reward differences, while coverage spreads each batch across underobserved environments and interaction patterns. EnvSched organizes environment--task pairs as nodes in a dual-relation graph, with within-environment edges capturing task semantics and shared tool, state, and verifier structure, and cross-environment edges capturing abstract execution and reward topology. By propagating historical rollout statistics along both edge types, it predicts within-task reward variance. These predictions guide a scheduler that allocates each batch to tasks with high predicted reward variance and underobserved environments and tasks. Environment quotas and a similarity penalty further limit concentration and redundancy, yielding informative and diverse batches without additional pilot rollouts. In RL on Qwen3-8B, EnvSched achieves an average score of 48.81 across BFCL-v3, tau-Bench, and ACEBench-Agent after 40 training steps, exceeding the highest score attained by random task selection after 120 steps. It also improves downstream performance across model sizes at the same training budget.
Mixture-of-Experts (MoE) inference on memory-constrained edge platforms is often dominated by expert-weight movement rather than computation. Although each token activates only a small subset of experts, routing is input-dependent, so all experts must remain accessible and memory movement dominates latency. Existing approaches such as uniform pruning and expert dropping overlook two properties of MoE execution: expert combinations are highly skewed in frequency, and experts contribute asymmetrically within each combination. We present CRISP, a combination-aware framework that co-designs pruning and runtime scheduling for efficient MoE serving on memory-constrained edge platforms. CRISP reorders neurons by importance so one stored expert can support multiple execution widths, assigns differentiated execution to hot, warm, and cold combinations based on frequency and expert role, and exploits heterogeneous widths to overlap expert loading with computation. Across Mixtral-8x7B and DeepSeek-MoE-16B, CRISP improves throughput by up to $2.1\times$ at the same memory budget while limiting accuracy loss to 3.6\% relative to full-width inference. Our results highlight that efficient edge MoE serving requires jointly optimizing which expert capacity is preserved and how expert execution is scheduled.
Qiaoling Chen, Jiaxiang Cheng, Xueqing Deng, Tiankai Hang, Ji Hou, Jiaqi Li, Yifan Liu, Tao Lu 等 38 位作者
Interactive world generation requires models to follow successive commands while preserving relevant history and action consequences. We present Hy-Nomas, a video world model with an 8B diffusion backbone that supports free-form text instructions and continuous camera control across multiple interaction turns. It generates variable-length segments conditioned on current inputs and cached history. Our central design aligns structured video captions with action-aware causal attention: descriptive context remains accessible across segments, while action instructions are restricted to their intended temporal windows. A vision-language Prompt Enhancer (PE) translates user requests and multimodal interaction histories into structured conditions for the next segment. A multi-stage curriculum progressively introduces causal generation, text interaction, camera control, and training on model-generated histories, followed by diffusion distillation. In human evaluation, Hy-Nomas shows superior performance over existing world models. We release model weights, code and benchmarks, together with a lightweight adaptation workflow, to support reproducible research on interactive world generation.
Self-disclosures on the Web support diverse psychological analyses, from recognizing expressed experiences to identifying symptom-relevant information. We study a shared, question-conditioned decision interface for this heterogeneous problem in content analysis. We organize PsyJudgeBench, comprising 13 annotated datasets and 82 questions across six psychological areas, while preserving source-specific criteria and masks for unobserved labels. We introduce PsyJev, a System-1 model that directly produces distributions over answers specified in each request. Joint supervised training establishes the shared judgment function, followed by Judgment-Anchored RLCD (JA-RLCD), which adapts logit-space reward optimization to heterogeneous psychological judgments through balanced supervision, selective retention of correct SFT predictions, and question-group reward optimization. The Qwen3.5-based 2B, 4B, and 9B models achieve 64.33, 66.21, and 67.56 average test F1, respectively. The 9B model exceeds the strongest external comparison by 2.54 points. Controlled 2B comparisons examine the training stages and anchored refinement. Further analyses examine question-conditioned judgment, inference cost, and probability quality, complemented by qualitative comparisons across models.
Erle Zhu, Genrui Zhang, Keyang Hu, Mingyu Su, Hongning Wang
Coding agents are moving from handling one request at a time to serving as persistent assistants to which users hand a stream of work: a build, a data-processing job and a bug fix may all be pending on the same machine at once. Such an agent must decide when to take on new tasks, how to delegate and overlap them, and how to stay within the machine's CPU and memory. Existing benchmarks cannot measure this, because they evaluate each task in isolation. We introduce AOS-Bench, which evaluates an agent system as a workload manager: verified tasks arrive over time and must be delivered under shared CPU and memory limits, and the same tasks run one at a time serve as a per-system reference. Across five model--harness pairs, isolated task success does not carry over evenly. On heavy workloads every system loses 13 to 23 points. On medium workloads, systems span 11 points in isolated success but 26 points in stream success, and two systems 0.6 points apart in isolation deliver 54\% and 68\% of the same tasks. Execution-policy interventions trace much of this gap to task intake: serial dispatch leaves 73\% of heavy-workload tasks unclaimed. Yet more elaborate management does not necessarily help. A fixed concurrency of two comes within four points of the best agent-managed policy on both medium and heavy workloads, and under every policy median CPU use stays below 30\% of the provisioned cores while tasks wait. These results identify workload management as a distinct capability for agents, and AOS-Bench as a way to measure it.