The paper introduces a statistical framework for diffusion transfer in generative modeling across related distributions. It analyzes a shared pooled score and a target‑specific offset, deriving convergence rates that separate the learning costs of these components. The authors prove that under certain regularity assumptions the offset remains bounded and jointly regular as diffusion time approaches zero, enabling polynomially vanishing lower time cutoffs and total‑variation guarantees for diffusion models as density estimators, with synthetic simulations and image benchmarks illustrating the approach.
By Huitao Yang, Oscar Hernan Madrid Padilla
KnowEEG is a feature‑based EEG classification pipeline that extracts 783 per‑electrode statistical features and cross‑brain connectivity metrics, using a balanced sampling strategy to integrate high‑dimensional per‑electrode data with connectivity information. It achieves performance that matches or surpasses state‑of‑the‑art deep learning models on five diverse tasks—including emotion detection, mental workload, eyes open/closed, abnormal EEG, and event detection—without requiring GPU resources. The approach also offers inherent explainability via feature importance rankings, identifying occipital biomarkers in the eyes open/closed task that align with established neuroscience literature.
By Amarpal Sahota, Navid Mohammadi Foumani, Raul Santos-Rodriguez, Zahraa S. Abdallah
DeFlow is a decoupled offline reinforcement learning framework that uses flow matching to accurately model complex behavior manifolds. Instead of backpropagating through ODE solvers, it learns a lightweight refinement module within a data‑derived trust region of the flow manifold, preserving iterative expressivity while avoiding solver differentiation. The approach eliminates the need for balancing loss terms and achieves superior performance on the OGBench benchmark, also enabling efficient offline‑to‑online adaptation.
By Zhancun Mu, Chi Zhang
The paper investigates Graph Transformers (GTs) that use Graph Neural Network (GNN)-based positional encodings. By analyzing GTs through manifold limit models, the authors establish a theoretical link between GTs and Manifold Neural Networks (MNNs), showing that GTs inherit transferability guarantees from their positional encodings. Experiments on standard graph benchmarks confirm that GTs scale comparably to GNNs, and a real‑world shortest‑path estimation task demonstrates their practical efficiency on large terrains.
By Javier Porras-Valenzuela, Zhiyang Wang, Teresa Shang, Yusu Wang, Alejandro Ribeiro
The paper introduces ARMOR, an Adaptive Round-based Multi-task Model designed for robotic failure detection and reasoning. It treats detection and reasoning as a self‑refinement process, iteratively predicting outcomes and natural language explanations conditioned on prior outputs. Training leverages both large sparse binary labels and small rich reasoning annotations through offline and online imitation learning, while inference uses multiple refinement trajectories and a self‑certainty metric to select the best prediction.
By Carl Qi, Xiaojie Wang, Silong Yong, Stephen Sheng, Huitan Mao, Sriram Srinivasan, Manikantan Nambi, Amy Zhang, Yesh Dattatreya
The paper introduces SITAR, a situational distortion metric for evaluating automatic speech recognition (ASR) systems. SITAR aggregates situational severity and cumulative extent into a unified score using a bounded recursive formulation, and is implemented as a lightweight BERT-family regressor that requires minimal runtime cost. The authors validate SITAR through extrinsic and intrinsic protocols, showing it tracks capability scaling and provides diagnostic utility across diverse datasets and models.
By Mingzhe Lu, Jinhao Liu, Yunpeng Li, Hang Su, Lichun Fan, Jian Luan
RoPE-Flow is an end‑to‑end framework that estimates camera‑to‑robot pose from a single monocular image using flow matching. It extracts keypoint‑centered features from predicted 2D heatmaps and employs a graph‑guided condition generator to encode keypoint correlations for flow matching. The method introduces Bone Length Loss and Ray‑Depth Loss to enforce topological consistency and scale stability, and demonstrates superior performance over state‑of‑the‑art approaches on multiple robot types and a new cross‑scene benchmark.
By Liangjing Shao, Wanhao Liu, Zhiwei Fang, Rulin Zhou, Quanlu Zhang, Changjing Liu, Beilei Cui, Yiming Huang, Hongliang Ren
The paper introduces the Dormant Spiking Neuron (DSN), a state-driven mechanism that allows neurons in spiking neural networks to enter a dormant state when their membrane potential falls below a negative threshold. This dynamic gating prunes redundant computations at the instance level and is trained end‑to‑end via backpropagation through time with surrogate gradients. Experiments on static and neuromorphic datasets, including ImageNet, show that DSN reduces computational energy by 40% to over 70% and improves baseline SNN accuracy by 1.34%, outperforming state‑of‑the‑art static pruning methods.
By Ruichen Ma, Yicai Chen, Pujun Zhou, Yue Zuo, Chongyang Li, Shuang Liu, Shaogang Hu, Guanchao Qiao
The NICE Toolbox is a free, open‑source Python framework that automatically measures nonverbal communication signals such as posture, gesture, gaze, facial expression, and speech. It integrates state‑of‑the‑art computer vision and speech‑processing methods into a single package, supporting multi‑camera setups, interchangeable detection algorithms, 2D and 3D visualisation, custom data evaluation, and export to third‑party software. The tool aims to make data exploration of interpersonal communication signals scalable, reproducible, and accessible for psychological research.
By Aleksandr Evgrashin, Carolin Schmitt, Timo L\"ubbing, Ashutosh Jha, Buket Naz Zeren, Sophie K. Bauer, Johannes Kopf-Beck, Anton K. G. Marx, Anamaria Semm, G\"okce Erg\"un, Senya Polikovsky
FPG-Seg is an annotation‑free pipeline for retinal vessel segmentation that combines classical vesselness filtering, Bayesian deep learning, and topology‑aware graph reconstruction. It achieves a clDice score of 0.74–0.78, which is 86–98% of the performance of a fully‑supervised baseline, across four benchmark datasets. The work also presents the first performance benchmark of an annotation‑free vessel segmentation method on the FIVES dataset.
By James Willoughby, Irina Voiculescu
FADRA is a frequency‑aware diffusion framework designed for video face restoration (VFR). It combines a pre‑trained text‑to‑video diffusion model with lightweight LoRA adapters and a Low‑Quality Pixel‑Alignment Feature Fusion module to adapt the generative prior to VFR. The method introduces a Repeated Residual Adaptation Head that refines residuals step‑wise using low‑quality latent cues, and employs a Frequency‑Aware Loss to supervise multiple spectral bands, improving facial detail recovery and temporal consistency.
By Jin Jiang, Jia Wang, Panwen Hu, Weiran Zhao, Shengcai Liao
RoboAtlas is a contextual Active SLAM framework that balances geometric exploration with semantic reasoning through a scalable 3D semantic mapping system called OpenRoboVox. It uses frontier exploration, global semantic‑map reasoning, and egocentric VLM‑based reasoning guided by a contextual multi‑armed bandit to shift from exploration to semantically guided navigation as scene understanding improves. In simulation and on a Unitree Go2 robot, RoboAtlas achieved a 100% task success rate in environments over 1800 m² with ~30k semantic instances, and outperformed prior baselines on the GOAT‑Bench "Val Unseen" benchmark, reaching 90.6% SR with GPT‑4o and 88.8% SR with Qwen2.5‑VL‑7B.
By Alexander Schperberg, Shivam K. Panda, Abraham P. Vinod, Bhagawan Rokaha, M. K. Jawed, Stefano Di Cairano
The paper presents a small coverage‑closure agent that verifies data integrity for LLM‑generated functional tests in hardware design. It reads coverage from simulation reports (cocotb‑coverage YAML) and uses separate scoreboards to check data, rather than relying on the model’s account. Applied to three different RTL designs—a FIFO, a UART transmitter, and an AHB2APB bridge—the agent increased coverage from 91.7%, 88.9%, and 67.4% to 100% within eight iterations, and also uncovered a clock‑domain‑crossing bug in a manual testbench.
By Venkata Krishna Kumar Vedantam
The paper presents a motion- and gravity-aware framework for feed-forward transformer models in multi-view 3D reconstruction. By providing residual optical flow and gravity direction as privileged signals during training, the model learns stronger geometric representations while remaining efficient at inference. Experiments demonstrate consistent accuracy gains, particularly in dynamic scenes and challenging camera motions, with the optimal integration stage depending on the backbone architecture.
By Shiyao Qian, Yuan Ren, Dongfeng Bai
The paper introduces Skill-Decoupled On-Policy Expert Distillation (SCOPED), a method that trains separate experts for each capability and extracts explicit skills via reward-guided reflection. During on‑policy distillation, these skills supervise the experts but are not exposed to the unified student, encouraging the student to learn procedural knowledge internally. Experiments on eight multimodal benchmarks show SCOPED consistently outperforms both the base model and mixed‑capability reinforcement learning, highlighting the benefits of skill decoupling for integrating independently acquired capabilities.
By Yuqi Xiong, Chunyi Peng, Zhipeng Xu, Qing Yang, Zhenghao Liu, Zulong Chen, Yu Gu, Ge Yu
The study investigates whether the language of a user’s instruction affects the safety verdicts of agent guards. By translating 1,220 labeled steps from an English benchmark into German, French, Turkish, Swahili, and Amharic while keeping all other data identical, the authors find that many open, small, and purpose‑built guards alter their verdicts when the instruction is translated, with larger effects for rarer languages. The impact varies with guard size, with smaller models showing greater loss of recall and larger models (e.g., Gemini 3.8 Flash) remaining largely unchanged.
By Hasan Demirkiran, Jens Ernstberger
The paper introduces Atomic Proximal Policy Optimization (Atomic-PPO), a deep reinforcement learning algorithm that reduces the action space via atomic action decomposition to efficiently evaluate electric robo-taxi dispatch and charger allocation. Using a discrete-time Markov decision process and real-world NYC for-hire vehicle data, Atomic-PPO achieves near-optimal fleet dispatching policies and outperforms heuristic approaches. Numerical experiments demonstrate how charger placement, charger quantity, charging speed, and fleet size jointly influence system performance, emphasizing ridership-based charger placement and balanced infrastructure investment.
By Jim Dai, Manxi Wu, Zhanhao Zhang
ChaosBench-Logic is a benchmark that tests large language models on logical and symbolic reasoning within chaotic dynamical systems. It covers 30 diverse systems, each annotated with 11 semantic predicates, and generates 621 questions across seven reasoning categories such as multi-hop implications, cross-system analogies, and counterfactual reasoning. The benchmark defines metrics for logical accuracy, implication consistency, dialogue coherence, and contradiction, and provides an open-source evaluation pipeline.
By Noel Thomas
Harness-Bench is a diagnostic benchmark that evaluates how different harness configurations affect LLM agent performance in realistic workflows. It tests 106 sandboxed offline tasks across multiple model backends, recording artifacts, execution traces, and usage statistics to analyze completion, process quality, efficiency, and failure behavior. The study finds significant variation in outcomes across model-harness pairings, indicating that agent capability should be reported at the configuration level rather than solely by the base model.
By Yilun Yao, Xinyu Tan, Chao-Hsuan Liu, Yaoming Li, Zhengyang Wang, Zongwei Lv, Wenhan Yu, Zhewen Tan, Yuxuan Tian, Lin Sun, Xiangzheng Zhang, Guangxiang Zhao, Tong Yang
TensorDex is a lossless, tensor‑centric storage system designed to reduce the storage footprint of large language models by performing delta compression at the tensor level. It decomposes models into individual tensors, uses compact fingerprints to predict which tensors can be compressed together, and incrementally clusters tensors to select effective reference bases as new models arrive. In experiments on 2,890 Hugging Face models, TensorDex cuts storage usage by 70.5%, outperforms the previous best system by 37%, and achieves compression and decompression speeds of 22.9 GB/s and 28.4 GB/s, respectively.
By Tingfeng Lan, Zirui Wang, Yunjia Zheng, Zhaoyuan Su, Juncheng Yang, Yue Cheng