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.

• Training & fine-tuning42+90.9%
• AI safety29+61.1%
• Computer vision31+55.0%
• Evals62+34.8%
• Federated learning48+29.7%
• Code models13+18.2%
• Quantum machine learning24+14.3%
• Image & video generation20+5.3%

• arXiv cs.CLOct 16

  ConvexLLM: Scaling Convex-Hull Speech Interfaces to General-Purpose Audio Intelligence

  Ming-Hao Hsu, Shujie Liu, Yuxuan Hu, Yuxiang Wang, Yingda Shen +2

  Speech and audio language models connect continuous acoustic representations to decoders pretrained primarily on text data. Most such models use MLP or Q-Former interfaces to map acoustic features into the decoder's input space, requiring the decoder to learn how to interpret the resulting representations. We investigate whether grounding these representations in the decoder's existing text embeddings can help it use acoustic information while better preserving its pretrained text capabilities. We present ConvexLLM, a general-purpose speech and audio language model whose C-Gate interface represents audio as continuous convex combinations of frozen text embeddings. ConvexLLM achieves an eleven-task VoiceBench aggregate of 75.36, the highest among the open-weight models we compare, and an MMAU Test-mini accuracy of 62.50%. Its largest margins over the baselines are on spoken knowledge and reasoning tasks, while the strongest baselines are more accurate on audio understanding and transcription. In a comparison with a 2B-parameter decoder, C-Gate achieves higher aggregate spoken-language performance than MLP and Q-Former interfaces, with text-task performance close to MLP and…

  PDF
• arXiv cs.CVOct 16

  PanoBench: A Panoptic Occupancy Prediction Benchmark for Autonomous Driving

  Yi Feng, Zizhan Guo, Junwu E, Yu Ma, Mengtan Zhang +6

  Panoptic occupancy unifies 3D geometry, semantics, and instance identities, but its development is limited by scarce instance-aware annotations. Existing benchmarks mainly provide semantic labels reconstructed from incomplete sensor observations, while panoptic datasets have limited domain coverage or annotation completeness. We introduce PanoBench, a camera-centric panoptic occupancy prediction benchmark spanning synthetic and real-world driving scenes. It combines PanoBench-CarlaOcc, PanoBench-nuScenes, and PanoBench-KITTI360 through canonical data interfaces and unified evaluation protocols, providing multi-resolution annotations with persistent instance identities. The synthetic branch derives complete panoptic geometry from simulated meshes. For real-world data, a new pipeline reconstructs backgrounds using geometric priors and topology constraints, generates foreground mesh assets from multi-frame multi-view images, and fuses them into sparse panoptic voxels. A unified valid-mask protocol evaluates complete thing instances supported by temporal observations while scoring stuff regions at the voxel level. Analyses of observation fidelity, geometric completeness, spatial…

  PDF
• arXiv cs.CVOct 16

  PreciseEdit: Strong Yet Stable Semantic Transport for One-Step Image Editing

  Jingyi Wang, Xiao Lu

  Recent one-step text-to-image (T2I) models enable efficient image synthesis, opening up new possibilities for interactive Web-based image editing. However, existing one-step editing methods often construct a global transport field through simple vector operations between conditional predictions. While such strong transport can effectively drive the image toward the target semantics, it may be released along unreliable directions or over non-edited regions, leading to structural distortions within the editing region and background drift elsewhere. More importantly, stabilizing the editing process through global smoothing or uniformly weakening the transport field often makes large semantic changes overly conservative. In this work, we revisit one-step image editing from the perspective of the tension between semantic strength and transport stability, and identify a key insight: strong semantic transport is not inherently unstable. What matters is whether it is applied along reliable directions and at reliable spatial locations. Motivated by this insight, we introduce PreciseEdit, a model-agnostic, training-free and inversion-free one-step editing framework that strengthens…

  PDF
• arXiv cs.CROct 16

  From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation

  Gabriel Hortea, Simon Pietro Romano, Juan Tapiador, Mario Varlese

  Small Language Models (SLMs) are increasingly attractive for resource-constrained environments due to their low computational footprint. These characteristics also make them candidates for future autonomous malware, where connectivity, latency, privacy, or operational constraints may preclude cloud-based inference. Yet the ability of ultra-compact models to support malware during post-exploitation remains poorly understood. We systematically evaluate seven open-source SLMs (20M-1.5B parameters) on two post-exploitation code-generation tasks: Directory Enumeration and Backdoor Generation. We compare Python (high-resource) and Lua (low-resource) across prompting strategies, task formulations, iterative reasoning, grammar-constrained decoding, and execution-feedback loops. Results show that offensive code-generation capabilities do not increase linearly with model size. Successful execution depends on the interaction of model capacity, task formulation, and prompting strategy, with task formulation exerting a greater influence than prompt engineering alone. Algorithmic formulation combined with few-shot prompting enables Qwen2.5-Coder 1.5B to reach Pass@5 of 100% in both Python and…

  PDF
• arXiv cs.CVOct 16

  ReVision: Reprogramming Image Generators for Dense Visual Perception

  Yitong Yang, Yinglin Wang, Xuexin Liu, Wei Chen, Zhaoyang Xu +4

  Recent image generators exhibit rich visual priors that can support dense visual perception. However, existing approaches typically encode multiple perception tasks into a shared parameterization, making joint training sensitive to the mixture and weighting of heterogeneous data and prone to cross-task interference. To address this issue, we introduce ReVision, an instruction-conditioned parameter generation framework built on a frozen multimodal understanding model and a frozen image generator. Given an image and a free-form instruction, the understanding model jointly encodes them into a multimodal image--instruction representation, which a trainable parameter generator maps to transient low-rank updates for the generator. Each image--instruction pair induces a distinct set of transient prediction parameters, enabling instance-specific adaptation while both pretrained backbones remain unchanged. ReVision requires no task-specific heads, explicit task identifiers, or stored adapters. A shared RGB output interface unifies segmentation, depth estimation, and surface-normal prediction. Across diverse dense prediction benchmarks, ReVision achieves competitive performance with…

  PDF
• arXiv cs.CVOct 16

  PONDER: Learning to Generate in the Right Order

  Julius Erbach, Dominik Narnhofer, Bernt Schiele, Jan Eric Lenssen, Konrad Schindler

  We introduce PONDER, a method that learns in which order an image generator should fill in content and which of its earlier predictions to revise. Masked generative models construct a sample by repeatedly filling in subsets of missing variables. The order of these partial predictions determines the context available in subsequent steps and therefore affects the quality of the final sample. Common strategies are to choose the order randomly or based on local confidence estimates. Conditioned on the partially generated sample and the generator's features, our policy chooses which positions to fill next and/or which previously filled positions to mask for later regeneration, a mechanism we call rethinking. In this way, the generation process is able to adapt to the evolving context and also to revise earlier predictions. We optimize the policy using group-relative policy gradients, with rewards that measure constraint satisfaction, human preference, or distribution quality. For the latter, we introduce FIDgrad, an image-level reward derived from the (first-order) change in Fréchet Inception Distance caused by adding a generated sample to the current feature distribution. With the…

  PDF
• arXiv cs.CLOct 16

  EduWild: How Teacher-Configured Chatbots Fail in Real-World Use and How to Fix Them

  Ziqi Liu, Ruiwei Xiao, Yuxuan Li, John Stamper

  Teachers increasingly configure educational chatbots through natural-language instructions, but how these bots fail in real-world use remains poorly understood. We introduce EduWild, a dataset of 1,726 conversations with 217 teacher-configured chatbots, each paired with the instructions and configuration behind it, including 900 conversations from the intended end users of 35 deployed chatbots. We develop a 29-code taxonomy covering factual, workflow, diagnostic, and pedagogical failures and apply it using a human-calibrated LLM judge. The most frequent failures are lapses in following teacher intent --- bots skip required workflow steps (53.8% of end-user conversations), omit expectation setup (33.4%), and overload learners with information or questions (37.1%). Guided by these findings, we design a prompt-based harness targeting the six most frequent failure modes. In a study with 200 college students across ten bots, the harness reduces the mean number of target failure codes per conversation from 1.406 to 0.489, a 65.2% relative reduction with bots weighted equally. These findings show how real-world failure analysis can guide practical improvements to educational chatbots.

  PDF
• arXiv cs.LGOct 16

  Out of Support, Not Out of Reach: In-Context Learning with Unsupported Instructions and Composed Tasks

  Xuhan Tong, Yuchen Zeng, Jiawei Zhang

  In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks from a small set of input-output demonstrations, without parameter updates. Yet existing theory primarily explains ICL as identifying a latent task already represented in pretraining, leaving unclear whether ICL can succeed when either the instruction or the target task falls outside the pretraining support. We develop a theoretical framework under mild assumptions that separates these two forms of distribution shift. For target tasks represented in pretraining, we show that demonstrations can identify the task and reduce sensitivity to pretrain-supported prompt templates as their number increases. For an unsupported instruction, we show that under a fixed model-induced reference extension, demonstration evidence can dominate an $N$-independent instruction shift while preserving the exponential identification rate. We then use the same ICL framework as an interpretive lens for long-horizon target tasks that are not represented in pretraining but admit a plan that decomposes them into pretraining-supported subtasks. Applying the supported-task analysis step by step yields a standard accumulated-error…

  PDF
• arXiv cs.CLOct 16

  Truth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods

  Ponhvoan Srey, Jason Lucas, Pittawat Taveekitworachai, Junyoung Lee, Anh Tuan Luu

  Large Language Models (LLMs) encode substantial factual knowledge. Yet, estimating confidence in factual claims reliably remains challenging. We study likelihood-based factual confidence from the complementary perspectives of discrimination and calibration across multilingual factual statements. Specifically, we instantiate contrastive generative likelihoods as Contrastive Factual Evidence (CFE), which compares the likelihood of the same claim under competing factual and non-factual conditions, and derive its probabilistic counterpart, the Contrastive Factual Posterior (CFP). We show analytically that CFP calibration depends on the differential error between the two surrogate conditionals, allowing errors shared across them to cancel and yield tighter calibration bounds. Empirically, CFP substantially improves calibration while maintaining factual discrimination comparable to its strongest competitor. Nonetheless, discrimination is uniformly weak across methods in lower-resource languages, which simultaneously undermines the utility of the measured calibration. To this end, we interpret a likelihood geometry, within which an evidence-bearing direction is induced, along with an…

  PDF
• arXiv cs.SDOct 16

  Interpreting SSL Representations for Spoof Detection: a WavLM Study

  Mohamed Mallat, Michele Panariello, Massimiliano Todisco, Nicholas Evans, Anthony Larcher

  Self-supervised speech models such as WavLM achieve strong spoofing detection performance, yet which layers encode the most spoof-relevant information and what acoustic properties they capture remain opaque. We present a layer-wise interpretability study of WavLM using the ASVspoof 5 database, combining three complementary analyses: (i) per-layer linear probing with attack-level evaluation across speech synthesis, voice conversion, and adversarial attacks; (ii) a canonical correlation analysis (CCA) linking layer representations to spoofing-relevant acoustic features; (iii) an exhaustive grid search over layer subsets showing that use of five layers outperforms full thirteen-layer pooling. CCA analysis reveals that, while most acoustic features peak in alignment with mid-layers and then decay, voice quality measures jitter, shimmer, and the harmonics-to-noise ratio show the opposite trend, with correlation increasing toward later layers. Embedding visualisations reveal that deeper layers capture a continuous acoustic similarity among attacks rather than discrete categories, suggesting these layers encode fundamental synthesis artifacts rather than attack-specific signatures.

  PDF
• arXiv cs.AIOct 16

  Trapped in Your Story: Evaluating Narrative-Induced Sycophancy in Large Language Models

  Runtai Yang, Dandan Zhu, Kaiwei Zhang, Guangtao Zhai

  Large language models (LLMs) are known to exhibit sycophancy by adjusting their responses toward users' expressed views. However, real users often justify their opinions through reasons, personal experiences, causal explanations, and broader narratives, raising the question of whether such narratives can further steer model judgments. We construct a controlled benchmark of 500 debatable questions across ten domains, where the user stance is held fixed while its justification is systematically varied without introducing new task-relevant evidence. Each question is instantiated under 11 matched conditions: one neutral baseline and five mirrored narrative levels for each of two opposing positions, yielding 5,500 evaluation instances. We evaluate seven LLMs and observe substantial differences in narrative-induced agreement. The effect is not monotonic with narrative elaboration: personal experience can reduce agreement, whereas causal framing and worldview-based synthesis increase it. Controlled GPT-5.1 ablations further show that causal framing produces the strongest positive effect, while claim-preserving bullet presentation also increases agreement over paragraph form. These…

  PDF
• arXiv cs.CLOct 16

  Perceive, Solve, Reason: Progressive Capability Formation in Time Series-LLMs

  Xin Qiu, Junlong Tong, Wei Zhang, Xiaoyu Shen

  Large language models (LLMs) can now perceive, describe, and reason about images and audio, yet time series understanding remains underestimated: most work uses LLMs as forecasters and classifiers, reasoning studies are few and narrow, and no suite trains and evaluates the full range of capabilities. In this paper, we build the first such suite, with 337K training and 44K evaluation samples across three progressive capabilities, Perceive, Solve, and Reason, and use it to ask how time series should enter an LLM that must master all three, and in what order. We find that a dedicated encoder is essential: with one, a 4B model surpasses GPT-4o on every perception attribute we test, whereas textualizing the series costs 8--10 points in reasoning accuracy. The capabilities then build on one another: learning them in order beats mixing the same data and rivals reasoning-only training with over three times the reasoning data, but only when an encoder is used. Analyses further reveal that capabilities are transferred through distinct network depths rather than simply stacked, and that a stage converged on its own benchmark is not necessarily ready for the next. Distilled into a simple…

  PDF
• arXiv cs.LGOct 16

  Uncertainty-aware AI-enabled framework for predicting hydrogen dispersion in confined spaces to enhance operator situational awareness

  Niclas Flehmig, Mary Ann Lundteigen, Shen Yin

  We present a two-stage AI-enabled framework for enhancing operator situational awareness during compressed hydrogen bunkering in maritime confined spaces. In the event of a leak, the framework first estimates the unknown leakage rate from early sensor readings and then forecasts how the hydrogen cloud will disperse over the next time steps, providing operators with a predicted concentration map together with confidence bounds. The framework is based on two independent AI models building one AI system. The AI system is designed as a decision-support tool. It augments sensor readings, and thus enhances operator situational awareness and supports decision-making. This enables preventive safety barriers to be deployed before hazardous concentrations are reached, while an independent emergency shutdown system remains the ultimate safety layer. The system design incorporates safeguards to ensure the AI system operates within its competence envelope. Trained and tested on an open dataset of confined-space hydrogen releases, the framework achieves a mean absolute error of $0.052$~g/s in leakage-rate estimation and $\approx0.018$ in hydrogen-concentration prediction, approaching the…

  PDF
• arXiv cs.AIOct 16

  LocalIntent: Outcome-Specific Structured Generation for Backend-Compatible Smart Building Automation with Local LLMs

  Tianyang Liu, Jiayue Wang, Zhanhao Cheng, Changyang Wang, Shaoshu Zhu +2

  Locally deployed large language models (LLMs) can reduce reliance on remote cloud services for natural language smart building automation, but backend-facing processing requires correct outcome selection, alignment with local capabilities, and valid structured outputs. We investigate whether a complete outcome-specific prompting design improves compact-model outputs beyond generic route-then-generate prompting. The proposed LocalIntent approach routes requests to ordinary or persistent-rule branches: the former produces commands, clarifications, or rejections, while the latter generates trigger-action rules, followed by deterministic validation. We evaluate four locally executed Gemma and Qwen models spanning 2B-9B parameters on 101 non-persistent and 54 persistent-rule records, comparing Monolithic prompting, generic two-stage prompting, LocalIntent, and validation-guided repair. Across the evaluated datasets, LocalIntent achieves higher intent understanding, device identification, and action/parameter correctness than generic two-stage prompting, while clarification/mode correctness remains model-dependent. The largest gains occur for rules, where LocalIntent improves intent…

  PDF
• arXiv stat.MLOct 16

  Adaptive conformal prediction on the Grassmannian

  Dimitrios Loukrezis, Zachary J. Grey, Dimitris G. Giovanis

  We introduce a conformal prediction framework for regression with Grassmann-valued responses. The proposed method constructs prediction regions in the form of metric balls directly on the Grassmann manifold, using basis-invariant geometric distances as non-conformity measures and scaling the corresponding non-conformity scores through a learned prediction difficulty estimator. This yields locally adaptive, input-dependent prediction regions that respect the underlying manifold geometry, while retaining the finite-sample marginal coverage guarantee of split conformal prediction under exchangeability. We evaluate several Grassmannian distance metrics and compare their prediction-region efficiency on synthetic benchmarks and an airfoil inverse shape-design problem. The results highlight the advantages of geometry-aware non-conformity scores, while local adaptation improves empirical coverage uniformity across prediction difficulty levels and, in strongly heteroscedastic settings, can substantially reduce prediction-region size while maintaining the target coverage.

  PDF
• arXiv cs.SEOct 16

  MLOps-Bench: Benchmarking AI Agents on Production ML Engineering in Real Repositories

  Quoc Co Tran, Hitesh Laxmichand Patel, Diwakar Mahajan, Kshitij Bakliwal, Avi Sil +1

  AI agents are increasingly expected to modify and maintain machine-learning systems in production, yet existing benchmarks primarily evaluate either competition-style ML experimentation or generic repository issue resolution. We introduce MLOps-Bench, a repository-grounded benchmark for production ML engineering. Unlike prior ML-agent benchmarks, MLOps-Bench evaluates executable lifecycle changes inside real ML repositories, spanning data pipelines, feature engineering, model training, model serving, monitoring, CI/CD and governance, and end-to-end integration. Each task is grounded in repository evidence and includes a natural-language requirement, oracle patch, plausible buggy baseline, fail-to-pass tests, pass-to-pass tests, and provenance metadata. The benchmark contains 212 validated tasks from 31 public ML repositories, with 636 fail-to-pass tests and 856 pass-to-pass tests. We evaluate six agents and find that the best system solves 31.2% of tasks while passing 68.7% of tests, showing that current agents often make partial progress but still fail production-relevant behavioral requirements. MLOps-Bench shifts agent evaluation beyond model building and issue fixing toward…

  PDF
• arXiv cs.LGOct 16

  A Topological Signature of Learning under Noisy Labels

  Zhongtian Sun, Fan Mo, Prayag Tiwari, Kelin Xia

  How does noisy supervision change the representations learned by a neural network? Training accuracy measures agreement with training labels but provides little information about representation geometry. We use persistent homology to track loop structure across distance thresholds in neural activations. Experiments span image classification, text classification, and modular arithmetic. On a fixed CIFAR-10/ResNet-18 training probe, equally sized clean-label and corrupted-label subsets show no detectable persistence difference at epoch 10, whereas corrupted-label subsets have higher persistence at epoch 50. The contrast survives uniform-scale controls, even though predictions match the assigned noisy labels for only 7-11% of corrupted probe examples at that checkpoint. Normalisation preserves the crossover between clean and noisy training trajectories on CIFAR-10/ResNet-18, whereas CIFAR-100/ResNet-18 shows no crossover under any of the five evaluated constructions. In a separate noise-rate calibration comparison across five pipelines, mean activation norm achieves a higher mean in-sample R2 than raw persistence (0.936 versus 0.908). These findings show that noisy supervision…

  PDF
• arXiv cs.CLOct 16

  MuninAI: A Self-Hosted Agentic Framework for Independent Research Groups

  Markus Fischer, Jens Meiler, Matthias Elgeti

  Research groups that want a language model grounded in their own literature face a choice between hosted services that receive their unpublished work and self-hosted deployments that keep the data local but give the model no access to the corpus. Munin is an open-source framework for a self-hosted scientific assistant that indexes a group's corpus and its citation graph, and wraps whichever open-weight model the group can serve in an agent harness with specialised reading, search, and computation tools. We claim that the harness, rather than the specific model, is what makes the system useful on domain literature, and we ship the evaluation suite that tests this claim with the software. On 199 paired literature questions, the harness more than doubles the accuracy of the base model, from 0.387 to 0.874 (+0.487, 95% CI [0.407, 0.568]), while naive retrieve-then-answer scores below the unaided model on every backbone tested. Under the harness, roughly twice as many answer claims trace to a passage the model read itself as with fixed top-5 retrieval. When the source paper for a question is removed from the corpus, the system abstains on about nine in ten of the questions it had…

  PDF
• arXiv stat.MLOct 16

  Towards optimal selection schedules for online active learning

  Hugo Cui, Francesca Mignacco, Francesco Mori

  We consider the problem of online linear classification, where a stream of unlabeled samples is available, and annotation is costly. We investigate the optimal query policy, that prescribes whether and when a sample should be labeled and used for a training step, or instead discarded, so as to minimize a given objective. We focus on the realizable case, under Gaussian design, in the high-dimensional regime where data dimension and number of unlabeled samples grow proportionally. We consider two objectives: 1) the generalization error under a labeling budget, and 2) a cumulative cost function where mistakes have unit cost and queries cost $Δ$. We first show that the myopic policies that greedily minimize at all times the increment in the objective correspond to either small or intermediate-margin policies, that prescribe the selection of samples whose margins fall within certain intervals that shrink with time. Within this class, we numerically ascertain the optimal schedules for the selection thresholds that minimize the final values of the objectives. Taking inspiration from the myopic policy for the cumulative cost, we design a very simple query policy schedule that we compare…

  PDF
• arXiv cs.CVOct 16

  TAN: A Size- and Form-Adaptive Masked-Convolution Encoder for Tissue Graphs

  Jan Herschel, Anselm von Gladiss

  Tissue graphs represent histology images as graphs over tissue-conforming superpixels, which keeps homogeneous tissue regions intact instead of cutting them into rectangular patches. To embed superpixels, current encoders crop them to bounding boxes and then pad, resize, or mask them, so background or fill values can leak into the node features. This matters in practice, and especially in medical imaging, where a prediction should depend on the tissue and not on an arbitrary preprocessing choice: on BACH, changing only the fill of the masked region shifts the accuracy of frozen encoders by up to 6 percentage points, larger than the differences among the four best encoders under mean fill, and the preferred fill differs between datasets, so it cannot be fixed once and for all. We present TAN (Tissue-Aware Network), a compact convolutional encoder (0.41M parameters) that processes each superpixel at its native shape and extent and excludes background from every operation, which makes its embeddings exactly invariant to the fill by construction. Under identical masks and an identical graph classifier, TAN's accuracy on BACH is not significantly different from that of the…

  PDF