Research

• General in-context learning for embodied agents1 paper raises it · 0 address it

  Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Cost and latency in embodied control loops1 paper raises it · 0 address it

  High computational and time costs limit real-time applicability of agentic systems in dynamic environments.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Physical-state verification and failure recovery1 paper raises it · 0 address it

  Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Long-horizon task preservation in embodied agents1 paper raises it · 0 address it

  Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it

  Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.

  • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

• Federated learning51+37.8%
• Agents554+8.0%
• Sensing communication150.0%
• Frontier LLMs474−0.2%
• Character recognition OCR17−5.6%
• Quantum machine learning24−7.7%
• Inference & serving283−7.8%
• Voice AI105−9.5%

• arXiv cs.CVOct 19

  PDNet: Exploring Pruning and Distillation for Real-Time Worker Activity Recognition in Industrial Assembly

  Malek Baba, Thinesh Thiyakesan Ponbagavathi, Alina Roitberg

  In this work, we address real-time fine-grained human activity recognition (HAR) in industrial assembly and introduce PDNet, a new framework that jointly exploits structured pruning and knowledge distillation for 3D convolutional networks. We start by training a 3D-CNN backbone in a supervised manner. Then, PDNet applies channel-wise structured pruning to obtain a more compact network. In the third step, our method is optimized using knowledge distillation from the large unpruned teacher to recover accuracy lost due to pruning. On the challenging MECCANO dataset with an X3D-M backbone, the pruned model without distillation reaches a Top-1 accuracy of 25.54 %, while PDNet raises this to 39.46 %, with only 6.90 MB model size and 3.78 GFLOPs. These results show that distillation within PDNet is highly effective in restoring pruned model performance and highlight its high potential for resource-constrained HAR in industrial assembly.

  PDF
• arXiv cs.LGOct 19

  Strength Controls Change How Interventions Compare Across Sparse Autoencoder Codes

  Jinchen Zhang, Zheyuan Liu, Yihan Zhu, Meng Jiang

  Changing sparse autoencoder (SAE) codes can alter both intervention direction and magnitude, so comparing intervention effects requires a strength control specifying what is held equal. Norm matching and output calibration provide different controls, but whether interventions yield different effects across codes after strength matching remains unclear. We compare intervention effects under these controls for fixed feature groups in Gemma and Llama and observe: (1) Whole-patch scaling. With one coefficient per input, full-output Kullback-Leibler (KL) calibration leaves smaller mean effect gaps from the encoder-based reference intervention than total-norm matching for nonnegative least-squares (NNLS) refits. On new Llama inputs, total-norm matching loses 11 reference transfers, whereas full-output calibration preserves every transfer decision. (2) Positionwise scaling. On a small matched gender-agreement subset, positionwise norm matching leaves smaller observed mean gaps than full-output calibration. (3) Answer exclusion. Compared with unscaled NNLS, answer-excluded calibration reduces gaps in the measured subject-verb agreement comparisons but increases them for gender refits.…

  PDF
• arXiv cs.ROOct 19

  SPAR: Structural Pruning and Action Recovery for Vision-Language-Action Models

  Shenli Zheng, Zhou Fang, Yuan Du, Yijiang Liu, Li Du

  The limited onboard computing resources of robots make the inference demands of vision-language-action (VLA) models costly to accommodate. Reducing these demands through aggressive compression, however, can degrade manipulation performance beyond what supervised fine-tuning alone recovers. We present SPAR (Structural Pruning and Action Recovery), which simultaneously prunes the hidden and feed-forward intermediate dimensions of the large language model (LLM) backbone through pruning-aware tuning, then applies reinforcement learning (RL) to recover policy performance. Applied to $π_{0.5}$, SPAR reduces the language backbone from 2.34B to 0.09B parameters and the full model from 3.37B to 1.12B, removing approximately 96% and 67% of their parameters, respectively. At this compression level, RL raises average success across the four LIBERO suites from 84.55% to 93.45%, an 8.90-percentage-point gain. The compressed policy achieves a $1.98\times$ full-policy inference speedup over the unpruned model. These results identify substantial intermediate-dimension redundancy and show that post-pruning RL can recover manipulation performance in compact policies.

  PDF
• arXiv cs.LGOct 19

  Wet-Biased Data Pipelines Mislead the Training and Evaluation of Generative Precipitation Nowcasting

  Christoph Metzl, Stefan Kapsreiter, Kianusch Vahid Yousefnia, Virginia Poli, Richard Müller +2

  Generative models for precipitation nowcasting are trained and evaluated predominantly on wet-biased datasets, which over-represent precipitation events to emphasize rare extremes. Selecting test cases based on target observations is known to favor forecasts that match the selected distribution rather than the intended deployment distribution. We show analytically how this target-dependent sampling also shifts the conditional distribution learned by generative models. When training and test sampling match, even an ideal model learns precisely the distribution favored by evaluation, allowing the evaluation bias to conceal the training bias. Using a fixed satellite-to-radar diffusion model, we demonstrate that target-dependent test sampling can reverse the calibration assessment. The model appears under-predictive on a wet-biased test set but over-predictive on a deployment-representative test set. This result is replicated outside the model's training domain after a seven-year gap. Utilizing classifier-free guidance as an example, we demonstrate how the contradictory calibration assessment can misdirect downstream model development.

  PDF
• arXiv stat.MLOct 19

  Gaussian Approximation of Besov Functions for Logistic Classification on Manifolds

  Guanhang Lei, Lei Shi, Xiaoming Yuan

  We study Gaussian kernel approximation and regularized logistic classification on a connected compact smooth embedded manifold $X\subset\mathbb R^d$ without boundary and of intrinsic dimension $\varrho$. Two main challenges are to derive a fast oracle inequality without assuming a bounded Bayes function and to construct Gaussian approximants that exploit both the intrinsic dimension and the target's regularity without saturation. We address the first challenge through a Bernstein-type inequality whose constant depends linearly on the supremum norm of the predictor. Combined with localized complexity estimates, this yields an oracle inequality over separable normed function spaces. To address the second challenge, we establish a uniform Sobolev operator expansion and cancel its lower-order bias terms using a signed combination of Gaussian kernel integral operators at different bandwidths. Real interpolation then gives an $L_2(X)$ approximation error of order $γ^α$ for functions in $B^α_{2,\infty}(X)$, where $γ$ is the bandwidth. By constructing the approximants directly on the manifold without ambient extension, we obtain a squared Gaussian RKHS norm bound of order $γ^{-\varrho}$.…

  PDF
• arXiv cs.CVOct 19

  3D Diffusion Models for Medical Imaging

  Frank-Peter Schilling, Daniel Barco, Philipp Denzel, Marc Stadelmann

  Generative deep learning methods such as Variational Autoencoders, Generative Adversarial Networks or Diffusion Models have achieved remarkable results in image synthesis. In particular, Diffusion Models have demonstrated superior image fidelity and sample diversity compared to other approaches on standard benchmarks, while also offering more flexible training dynamics as evidenced both in natural image domains and in medical applications. In medical imaging including Computed Tomography, Magnetic Resonance Imaging or Positron Emission Tomography, such models have various important use-cases including data augmentation, domain transfer, image reconstruction, inpainting, image augmentation and artifact correction. Further, generated images can be conditioned on patient characteristics, medical reports, segmentation masks or other images. Specific challenges arise due to the 3D volumetric nature of medical images, which translate to substantial demands in terms of memory, compute, and training data. This article provides a comparative overview of 3D Diffusion Models which have been developed for medical images, with a focus on current performance, limitations, and an outlook for…

  PDF
• arXiv cs.CLOct 19

  AfriGuard: Safety and Robust Refusal For African Languages

  Israel Abebe Azime, Jesujoba O. Alabi, Iffat Maab, Alexander D. Cai, Tadesse Destaw Belay +17

  Large language models (LLMs) designed to interact with users are typically trained to respond appropriately to harmful or toxic content. However, ensuring appropriate responses becomes more challenging in diverse linguistic and cultural contexts, where safety risks may be expressed or interpreted differently. Building safe AI systems therefore requires detecting safety risks, understanding their nature, and responding appropriately, while accounting for linguistic and cultural variations that add complexity to each stage. In this work, we introduce AfriGuard, a culturally grounded multilingual dataset for studying harmful intent, safety-category understanding, and refusal behavior across 10 African languages and English. Our findings reveal that guardrail models underperform both open- and closed-source LLMs on safety-intent and safety-category classification, while models show limited understanding of appropriate safety behavior, scoring below 60% F1. We further find that models often fail to respond appropriately to unsafe prompts not because they explicitly refuse, but because they produce linguistically inadequate responses that result in incidental non-assistance rather than…

  PDF
• arXiv cs.LGOct 19

  A Simple and Unified Method for Gradient-Variation Regret

  Hang Yu, Peng Zhao

  Gradient-variation online learning has attracted increasing attention for its connections to game theory and optimization. It has been studied in both non-stationary online learning, which aims to minimize dynamic regret against time-varying comparator sequences, and universal online learning, which seeks to adapt to unknown loss curvature. Prior work obtained gradient-variation bounds using different techniques tailored to each setting. We propose a simple and unified method based on surrogate losses with a quadratic penalty on decision movement, yielding gradient-variation bounds in both settings. For non-stationary online learning, the method induces an optimistic-to-gradient-variation reduction, enabling a broad class of algorithms to match the rate established by Zhao et al. (2024). For universal online learning, it yields a simple algorithm that matches the optimal universal regret bounds of Yan et al. (2024) while relaxing the extended smoothness assumption. Finally, we apply our method to online games and improve on existing guarantees.

  PDF
• arXiv cs.LGOct 19

  On Learning Expand-and-Sparsify Representations

  Alireza Asghari, Parikshit Ram, Kaushik Sinha

  Expand-and-sparsify ($\texttt{EaS}$) representations lift an input to a much higher dimension through a linear map and keep only the $k$ largest coordinates. Existing theory builds that map at random and needs the expanded dimension to grow exponentially in the input dimension, which puts the construction out of practical reach. We ask what is gained by learning the map by gradient descent instead, and how that gain depends on how wide the expansion is. We sweep $73$ OpenML classification tasks and $48$ regression tasks under a protocol that holds the datasets, expanded dimensions, sparsity levels and splits fixed across every method, and we summarise each comparison by a median over datasets and a Wilcoxon signed rank test. We report four findings. First, learning the expansion helps most when the expansion is narrowest, and its advantage over a random map decays to nothing by the widest expansions we run, so a learned $\texttt{EaS}$ layer can be made small. Second, with the map learned, a top-$k$ representation that keeps at most a tenth of its coordinates is indistinguishable from a dense $\texttt{ReLU}$ layer of the same expanded dimension at every expansion factor we test,…

  PDF
• arXiv cs.AIOct 19

  VeriCUA: Learning Proactive Verification for Reliable GUI Agent Rewards

  Zhizhou Wang, Yaxi Lu, Zhong Zhang, Zikun Hu, Xin Cong +2

  Reinforcement learning for computer-use agents increasingly relies on proactive reward agents that interact with the post-execution GUI environment to verify what recorded screenshots cannot reveal. The reliability of such verification hinges on two coupled decisions: what to check and when to stop. Existing methods leave these decisions to prompted foundation models. However, neither scaling up the model nor providing few-shot examples reliably improves verification: prompted Judges ranging from 4B to GPT-5.4 all plateau at 68%-70% macro-average agreement. This is because the value of a check depends on the environment rather than the task alone, and becomes apparent only through execution. Learning from execution is itself constrained, as the Actor's terminal state cannot be faithfully replicated during training, allowing only one verification attempt per state. We introduce VeriCUA, a proactive reward agent that learns its verification strategy from these single attempts. A trainable Judge decides what to check and when to stop, while a frozen Probe executes the checks in the live environment. Online reinforcement learning optimizes the Judge for both verdict correctness and…

  PDF
• arXiv cs.CVOct 19

  YUTELA: A Scalable Edge Cloud AIoT System for Multi-Site Video Anomaly Detection with Scene Specific Adaptation

  Shanle Yao, Babak Rahimi Ardabili, Amir Kimiyaie, Hamed Tabkhi

  Building upon our previous Ancilia framework, this work presents \emph{YUTELA}, an edge--server--cloud AIoT system for long-term, multi-site video anomaly detection. YUTELA replaces workstation-based on-site processing with NVIDIA Jetson Thor edge devices and redesigns the multi-camera pipeline through camera batching and redistribution, shared memory, reduced inter-stage data transfer, task integration, and TensorRT-accelerated inference. It maintains a separate anomaly model per camera, retrained on a centralized GPU server once enough recent pseudo-normal data are collected, with updated weights returned to the edge. With eight cameras, TensorRT increases throughput from 14.17 to 29.94 FPS under normal density, and the optimized edge node exceeds the throughput of the workstation-based Ancilia system in seven of nine workload settings, reaching up to 2.03 times its throughput at extreme density. This gain comes at the cost of higher latency under lighter loads with four or eight streams. YUTELA was then operated continuously for 170 hours at four public sites using 31 existing CCTV cameras. The deployment shows that runtime load is driven by scene activity and input frame rate…

  PDF
• arXiv cs.SEOct 19

  VerusEval: Evaluating LLM-Generated Verus Specifications Beyond Verifier Acceptance

  Ding Wang, Chao Jiang, Dugang Liu, Zhiwu Xu, Cheng Wen +4

  Large language models (LLMs) are increasingly used to generate Verus contracts for Rust programs together with the proofs that establish them. Yet verifier acceptance, the common measure of success, shows only that the implementation satisfies the generated contract, so it leaves open whether the contract captures the intended behavior. Assessing specification generation therefore requires an evaluation methodology, not a single metric. We present VerusEval, a framework that evaluates generated contracts along six dimensions, including Verus-native checks for semantic triviality, validated input-output (I/O) suites, and contract equivalence, and that relates them so that the strength and blind spots of each become measurable. Evaluating 13,716 artifacts from four workflows, five LLMs, and two prompting settings on 762 tasks, we find that acceptance overstates quality: only 42.3\% of the accepted artifacts complete all three semantic checks without a flag, and across workflows and models, higher acceptance does not consistently come with more correct contracts. I/O evaluation rejects 23.6\% of the accepted artifacts, yet only 63.2\% of those that pass it are proved equivalent. Of…

  PDF
• arXiv cs.CLOct 19

  Training Negatives Still Matter After Calibrating Answerability Readouts

  Jinchen Zhang, Zheyuan Liu, Yihan Zhu, Meng Jiang

  Answerability readouts predict whether a passage supplies an answer, but whether calibration can compensate for removing negative passages during training remains unclear. We present a controlled study of how training-negative construction affects calibrated prediction, ranking, and downstream answer retention. We compare native training, which retains negative passages, with empty training, which removes them, holding questions, labels, positive examples, and model weights fixed. Both are calibrated on the same labeled native examples. On SQuAD 2.0 and RepLiQA, native-trained logistic readouts at selected depths achieve lower Brier loss for Qwen2.5-7B-Instruct and Gemma-2-9B-it, with or without output scores. Native fusion also outperforms calibrated output alone. Post-hoc AUROC analysis shows better ranking under native training, beyond what threshold adjustment alone can explain. On the official SQuAD 2.0 development set, native readout policies improve F1 over empty policies but retain more answers to unanswerable questions. The advantage varies by estimator and depth, while RepLiQA's text shortcuts limit claims about contextual understanding. Unfinished generations prevent…

  PDF
• arXiv math.NAOct 19

  Residual-Based Adaptive Refinement in Hybrid Variational-Collocation PINNs for Singular Elliptic PDEs with Mixed Dirichlet-Neumann Boundary Conditions

  Somnath Giri, Muslim Malik, Rishikesh Yadav

  Solutions of second-order elliptic PDE problems on nonconvex or cracked domains with mixed Dirichlet-Neumann conditions typically lie outside $H^2(Ω)$. Near re-entrant corners, crack tips and points where the boundary condition changes type, the gradient grows like $r^{λ-1}$ with $λ<1$. We study residual-based adaptive refinement in hybrid variational-collocation PINNs. A multiscale Fourier-feature network is trained on a composite loss. The loss combines a variational residual tested against Legendre bubble functions, a strong-form collocation term and penalties for the Dirichlet and Neumann data. The variational term needs only first derivatives of the network, whereas the collocation term requires second derivatives and provides a residual that can be evaluated at any point. After each training stage, candidate points selected by this residual are added to the collocation set. The method is tested on five two dimensional benchmarks, namely a Mode~III crack, a cross-shaped domain with four re-entrant corners with unequal amplitude, a reaction-diffusion problem with four localized peaks, a monotone semilinear problem with a boundary layer and the Motz problem. Compared with…

  PDF
• arXiv eess.IVOct 19

  Progressive multi-scale tumor-state memory for incomplete multimodal brain tumor segmentation

  Milad Rostamian, Mohammadreza Mohammadi, Mohsen Soryani

  Brain tumor segmentation uses complementary magnetic resonance imaging (MRI) sequences, but some sequences may be unavailable in practice. Their absence changes the information available for segmenting different tumor regions. Fusion methods can support different input subsets. However, fusion at several scales does not by itself specify how tumor evidence is retained and updated to guide fusion at later stages. We propose a progressive multi-scale tumor-state memory network (PMTM) for segmentation from any non-empty subset of T1ce, T1, FLAIR, and T2. PMTM maintains a compact state for the current subject across the encoder stages. At each stage, we use assignment maps to pool spatial features into ordered evidence vectors for each available modality. We average these vectors across the available modalities, and a learned gate combines this evidence with the previous state. The up- dated state guides residual fusion at that stage and is used in the state update at the next stage. A modality-token mixer also models interactions among the available modalities at each stage. We apply semantic supervision to the assignment maps at all four stages. We evaluate PMTM on BraTS2018,…

  PDF
• arXiv q-fin.PMOct 19

  Regime-Aware Interpretable Ranking for Sector Rotation

  Kelvin J. L. Koa, Ziling Liu, Xinyang Li, Shuowei Feng, Ruoyu Liang +5

  Sector rotation is a common decision in benchmark-relative portfolio management, where portfolio managers rank sectors for overweight and underweight positions. We formulate this task as ranking sector actions by expected future risk-adjusted active performance, measured with forward sector-benchmark Sharpe ratios. Such rankings should preserve temporal information, express model outputs through economically familiar signal characteristics, account for changes in signal relevance across macroeconomic environments, and capture dependencies among sectors. We propose RegimeRank, an interpretable sector-ranking model that represents fundamental and technical signals through expert-defined temporal characteristics, conditions them on learned macro factors via cross-attention, and models cross-sector dependencies through self-attention. Expected-gradient attributions identify the contributions of individual signal-transformation pairs, while macroeconomic and cross-sector attention maps provide diagnostics of the learned conditioning and relational structure. We evaluate RegimeRank on weekly S&P 500 data from 2002 to 2024 under combinatorial purged cross-validation, where it…

  PDF
• arXiv cs.ROOct 19

  ALIGN: Aligning Condition Estimation and Expression in Advantage-Conditioned Behavior Cloning

  Zechen Wang, Zhenqi Qiu, Houlong Xiong, Suohang Zhang, Yiyu Ren +6

  Human-collected robot manipulation data often mix successful behavior with retries, pauses, recoveries, and failures. Advantage-Conditioned Behavior Cloning (AC-BC) can exploit such mixed-quality data, but only if the conditioning signal is both accurately constructed from offline trajectories and effectively incorporated into the policy's action-vector-field prediction. Existing pipelines can weaken this signal by thresholding estimator-derived advantage scores into noisy conditions, and by routing conditions through prompts that weakly affect the action vector field. We introduce ALIGN, a condition-aligned AC-BC framework for vision-language-action policies. ALIGN directly predicts categorical pairwise conditions in the policy-facing label space and injects them into a DiT action expert through AdaRMS modulation fused with flow time. We evaluate ALIGN on deliberately mixed real-robot datasets for ARX X5 bowl stacking and Franka key hanging, each combining standard demonstrations with retry-heavy trajectories. ALIGN improves condition fidelity, strengthens conditional vector-field separability, and achieves 90.0% and 56.7% closed-loop success, compared with 56.7% and 33.3% for…

  PDF
• arXiv cs.AIOct 19▲ 10

  Remembering Has a Price: Learning Memory Worth under Resource Constraints

  Guannan Lai, Zi-Yang Bai, Jun-Peng Jiang, Han-Jia Ye

  Lifelong agents continually accumulate and reuse experience to improve after deployment, yet in practice they often operate under tight generation, interaction, and memory budgets. Under such stringent joint constraints, we find that existing lifelong-memory methods can become ineffective, with several sophisticated approaches offering little advantage over simple retrieval or even no-memory agents. This reveals a more fundamental problem: resource scarcity makes each memory decision more consequential. When only a small amount of past experience can be retained or reused and opportunities for reasoning and recovery are limited, retrieving a relevant but ineffective memory can consume scarce context and hinder downstream execution. The key challenge is therefore not simply to retrieve relevant experience, but to determine which experiences are actually worth retaining and reusing. To address this challenge, we propose TokenWorth, a lightweight online memory framework that learns query-dependent memory worth from sparse execution feedback and applies it consistently to memory retrieval and bounded memory management. Across three LifelongAgentBench environments and both local and…

  Code
• arXiv cs.CVOct 19

  When Guidance Becomes a Guard: Early Interception of Unsafe Inputs in Text-to-Image Generation

  Yanchun Li, Yujin Wu, Gangkai Shen, Ming Yang, Li Zeng +3

  Text-to-image diffusion models can produce unsafe content, while output filtering intervenes only after synthesis. We investigate whether native generation signals enable early detection of unsafe and adversarial inputs. We find that classifier-free guidance exposes strong safety signals in conditional responses, accessible through compact statistics and linear readouts. Based on this finding, we propose Conditional Semantic Trajectory Interception (CSTI), which aggregates activation contrasts between conditional and unconditional responses at early checkpoints for calibrated risk detection. CSTI fits concept-specific detectors using canonical concept and safe examples, without attack samples, intermediate image decoding, or generator modification. Across five generators, four adversarial attack collections, and two general NSFW datasets, CSTI achieves the strongest overall performance among six baselines at a matched 5% FPR. Early interception reduces generation latency by over 60% on intercepted paths. These results demonstrate the effectiveness of native conditional responses for early safety interception.

  PDF
• arXiv cs.CLOct 19

  TeleASR-Amharic: A Benchmark for Robust Amharic ASR in Realistic Telecommunication Conditions

  Dagnachew Mekonnen Marilign, Enrique Molero, Abrham Haile, Louis Powell, Israel Abebe Azime

  The real-world usability of ASR models remains challenging, particularly for low-resource languages, where existing speech resources are often collected in clean studio environments. In this work, we introduce TeleASR-Amharic, a benchmark for evaluating Amharic ASR under various acoustic and telecommunication conditions. We analyze the major degradations observed in real telecommunications recordings and develop a benchmark that covers multiple channel conditions, environmental disturbances, and telecom-domain variations. Our results show that telecommunication degradation can substantially reduce recognition performance, making even high-performing ASR models impractical under severe conditions. For example, the WER of the best-performing model increases from 0.23 to 0.79 under severe telecommunication degradation, corresponding to a relative increase of 243% in recognition errors. We further investigate the effects of different noise and channel distortions and show that scaling training data and applying carefully designed telecommunication-aware augmentation substantially improve robustness. In particular, our best training configuration achieves a 23.6% relative WER…

  PDF