# Research Papers — 2026-10 · bundle page 65 of 156 > Full-text markdown of papers #3201–3250 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/65 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/64.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/66.md) ### ASSET: Adaptive Speech Segmentation via Reinforcement Learning Authors: Cihan Xiao, Yuan Tseng, Matthew Wiesner, Desh Raj, Leibny Paola Garcia Perera, Sanjeev Khudanpur, David Harwath Published: 2026-10-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.14309v1 Speech large language models (LLMs) are often built using pretrained acoustic encoders as an audio interface to an LLM decoder. However, LLMs scale poorly with input sequence length, while acoustic encoders tend to produce substantially longer sequences than typical textual inputs. This motivates learning to compress encoder outputs while preserving task-oriented information. To this end, we introduce ASSET, a reinforcement learning (RL)-based framework that learns to adaptively compress encoder outputs by first partitioning them into variable-duration segments and then pooling each segment into a continuous audio token. We use group-relative policy optimization (GRPO) to train a segmenter with task performance feedback and a token-rate penalty. In automatic speech recognition (ASR) experiments, ASSET achieves performance comparable to a transcript-assisted character-boundary oracle with approximately 25% fewer audio tokens on English LibriSpeech, while improving on a phone-boundary oracle at a similar token rate on Mandarin AISHELL. Exploratory experiments on non-ASR tasks further illustrate how learned segmentation changes when the framework is adapted to tasks beyond transcription. --- ### ConicFlow: constrained Inference-time optimal control for flow matching models Authors: Shervin Khalafi, Kasra Fallah, Sung Cho, Dongsheng Ding, James Anderson, Alejandro Ribeiro Published: 2026-10-09 Categories: cs.AI, cs.CV, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2610.14307v1 We propose ConicFlow, which frames constrained sampling from a flow matching model at inference time as an optimal control problem that balances deviation from the pretrained trajectory against reward, subject to hard terminal constraints. We discretize this problem and adapt receding-horizon control, optimizing only a short window of the trajectory at each step for computational tractability. We address the resulting sequence of receding-horizon subproblems with a receding-horizon primal-dual algorithm. Its dual multipliers capture the difficulty of satisfying each constraint and are refined throughout sampling, steering generation toward feasible final samples. We further propose a terminal-estimate variant that avoids accumulating local truncation errors by evaluating the reward and constraints at the predicted terminal point rather than at the end of the current horizon. Under standard regularity assumptions, we establish finite-horizon guarantees on suboptimality. Under convex-affine structure, we derive a sharper bound that scales linearly with omitted horizon length, and we show that the terminal-estimate variant is provably tighter when the flow dynamics change slowly. Experiments in both low- and high-dimensional settings with a recent large-scale flow matching model show that ConicFlow achieves high reward and strong constraint satisfaction while deviating less from the pretrained flow than recent baselines. --- ### Learning to See through Action: Predictive Curiosity for Robots Authors: Stelios Zarifis, Panagiotis Filntisis, George Retsinas, Petros Maragos Published: 2026-10-09 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2610.14302v1 Humans and animals do not learn vision from a fixed set of data: they move, interact, and learn from the visual consequences of their actions. Motivated by this developmental view, we study whether robots can improve visual learning by actively collecting experience through curiosity-driven interaction. We introduce DySCOVER, a self-supervised framework for active robot visual learning. A robot observes RGB frames, learns a visual autoencoder that encodes and reconstructs them, and trains a recurrent world model to predict the next visual latent state conditioned on the current state and action. The agent's policy is trained only with intrinsic rewards: reconstruction error encourages visually novel observations, while the world model's error encourages transitions whose consequences are not yet predictable. This prediction error biases the policy toward more intricate trajectories that enrich the agent's set of experiences with observations beyond those encouraged by visual novelty alone. Our experiments conducted with robotic arms as the embodied agents show that adding predictive curiosity improves the vision model over using visual curiosity alone. Across variations in initial conditions, experience capacity, embodiment, and scene content, adding predictive curiosity consistently improved visual learning. These results show that predictive curiosity can improve active visual learning beyond reconstruction-based curiosity alone. --- ### RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can Authors: Yi-Jen Shih, Puyuan Peng, Haohe Liu, David Harwath, Abdelrahman Mohamed Published: 2026-10-09 Categories: eess.AS, cs.AI, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2610.14299v1 Recent Speech Full-Duplex (FDX) models are capable of engaging in naturalistic conversation by listening and speaking at the same time. Building on this foundation, recent architectures introduce internal thinking streams to enhance their intelligence. To guarantee these streams process successfully in real time, existing methods enforce a fixed decoding rate, which assumes a hardware profile capable of a specific latency. We argue this static approach is severely suboptimal. Because internal thinking is intrinsically asynchronous, an ideal FDX model should sustain real-time conversational flow while allowing each stream to decode at its own hardware-adaptive rate. Thinking streams must process as fast as the hardware allows to deliver accurate answers faster. To solve this, we propose RUBATO, a novel multistream positional encoding that assigns independent clocks to entirely decouple the streams. This structural isolation empowers the model to zero-shot interpolate across any inference decoding speed. It drastically simplifies dataset construction by requiring training on only two extreme decoding speeds while smoothly adapting to any intermediate rate during deployment. RUBATO demonstrates consistent robustness across five spoken reasoning tasks. On Spoken GSM8K, a baseline model collapses to 1.7% accuracy at interpolated speeds. Conversely, RUBATO-Full sustains 48.7% to 51.1% accuracy across all rates, leveraging faster hardware to achieve a 6.5x shorter time-to-answer with a constant time-to-first-response. This advantage holds on BIG-Bench Audio and amplifies significantly during complex full-duplex interruptions. Specifically, when a user interjects while the model is actively speaking and reasoning, RUBATO-Full achieves 40.0% to 45.1% accuracy, whereas the baseline fails completely. --- ### Diagnosing Generalization Boundaries in AI-Based Vulnerability Detection via Calibrated Embedding Distances Authors: Konstantin Ievtushenko, Ralf Lämmel, Jan Jürjens Published: 2026-10-09 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2610.14296v1 High benchmark scores in learning-based vulnerability detection mask severe degradation under distribution shifts. This paper demonstrates that calibrated embedding geometry exposes these hidden generalization boundaries on syntactically similar vulnerable and patched code pairs. An evaluation of CodeBERT and Qwen2.5-Coder across pattern, project, and temporal shifts on a strictly paired dataset reveals three main findings. First, whitened intermediate-layer embeddings with local nearest-neighbour scoring separate unfamiliar samples with a mean out-of-distribution AUROC of 0.739 (RQ1). Second, distance scores reveal a shift-specific reliability gradient where accuracy drops by over 35 percentage points and cross-project shifts cause the sharpest degradation, even though temporal shifts drift geometrically farthest (RQ2). Third, false positives on patched code systematically correlate with geometric proximity to vulnerable training neighbourhoods, increasing from 9.4% in the lowest-risk decile to 58.8% in the highest (RQ3). These calibrated distances establish a diagnostic signal that maps representation geometry directly to model degradation without requiring auxiliary models. --- ### Controllable Diverse Sampling through Pullback Directions Authors: Sylvain Dehayem Kenfouo, Aaron Zweig, Mingxuan Zhang, Elham Azizi Published: 2026-10-09 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.14294v1 Conditional diffusion models can generate high-quality images that align closely with a given prompt. However, samples generated from different random seeds may remain visually similar, limiting creative exploration. Existing approaches can increase variation, but often require additional optimization or sampling overhead, while stronger perturbations may introduce distortions that degrade image quality or prompt alignment. We propose a training-free method that leverages the local pullback geometry induced by the mapping from the conditioning-embedding space to the image space to identify directions of maximal output sensitivity. By steering different sampling trajectories along these directions, we encourage distinct generations while maintaining consistency with the conditioning signal. Experiments on MS-COCO and BrushNet show the efficacy of the method in improving diversity on prompt-conditioned image generation and inpainting. --- ### GeoFix: Geometry Fixing for 4D Consistent Generation Authors: Yeobin Hong, Hyojun Go, Dohun Lee, Jeongjae Lee, Sunghwan Hong, Federico Tombari, Zhaochong An, Jong Chul Ye, Konrad Schindler, Dominik Narnhofer Published: 2026-10-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.14293v1 Video diffusion models increasingly serve as priors for 4D generation, but the generated videos often lack geometric consistency. Recent approaches address this through post-training by designing geometric rewards, yet this can degrade texture and fine detail, requiring auxiliary appearance rewards and careful reward balancing. To address this challenge, we propose GeoFix, a unified framework that improves geometric consistency and visual quality with a single geometric reward, applicable to both training and inference-time reward alignment. Our reward measures cross-view depth consistency in static scene regions, targeting structural inconsistencies without directly constraining appearance or penalizing valid object motion. Crucially, depth agreement increases with camera field-of-view overlap even in real videos and 4D datasets, allowing a smaller camera movement to be mistaken for better geometry. We account for this effect by calibrating the reward against the overlap-dependent trend. GeoFix achieves a 39% improvement in WorldScore 3D consistency and a 4% increase in VBench Quality Score. --- ### Layer-wise Input Recoverability in Deep Neural Networks Authors: Maxwell Spiridonov, Alireza Rahmansetayesh, Pierre Baldi Published: 2026-10-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.14290v1 The inner workings of deep neural networks are still not well understood. The information bottleneck framework, which characterizes deep networks by the mutual information between their hidden representations and the network's input, has been used to identify compression of input information with respect to an input image and output labels. We instead study how much of a layer's own input is recoverable from the layer's output in convolutional neural networks (CNNs). A convolutional layer applies its filters to one input patch at a time, so we evaluate recoverability on sampled input patches with a reconstruction-based probe and not on the entire feature map. The probe's size thus depends on channels and kernel size and not on feature map size, which lets our method scale to deep CNNs with wide feature maps. For each layer, we compare pretrained, random, and reconstruction-optimized encoders, using linear and linear-plus-residual-MLP decoders. We measure recoverability as $R^2$ between input patches and their reconstructions on a held-out set. Across nine ImageNet CNNs, recoverability generally decreases with depth but is more consistently predicted by the compression of the layer. Learning-attributed recoverability, the difference between pretrained and random encoders, is not uniform across architectures. We introduce single-property random controls, which transfer one pretrained property onto a random encoder, and find that each control changes recoverability with a consistent sign across models: copying pretrained singular vectors tends to raise recoverability, while copying the pretrained singular-value spectrum or activation sparsity lowers it. --- ### TGSR: Text-Grounded Diffusion for Faithful Image Super-Resolution Authors: Zhiming Hu, Ran Zhang, Angela Ye, Raghav Goyal, Faraz Ali, Tristan Ty Aumentado-Armstrong, Samrudhdhi B. Rangrej, Konstantinos G. Derpanis, Iqbal Mohomed, Alex Levinshtein Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.14281v1 Diffusion models have achieved remarkable success in image super-resolution (SR) by leveraging strong generative priors to enhance perceptual quality. However, for textual content, these priors often produce text hallucinations: non-existent or distorted text, which alter scene semantics and compromise model reliability. While recent methods focus on enhancing text generation, they do so indiscriminately, leaving hallucinations fundamentally unresolved. We argue the core problem is a lack of selective control. Therefore, we reformulate text SR as a selective generation problem: text is resolved only when reliable generation is expected, while other scene content is fully super-resolved. We introduce TGSR (Text-Grounded Super-Resolution), a test-time framework that progressively identifies and suppresses likely hallucinated text regions during generation. To enable this, we train dedicated detectors on a large-scale dataset curated from diverse diffusion-based SR outputs. TGSR consistently improves text fidelity across multiple backbones, increasing recognition precision by up to 17.68 points without degrading perceptual quality, underscoring the value of selective control in generative SR. --- ### The RNN Homunculus: Learning to Gate Long-Term Memory Authors: Zeyu Fan, Alexandru-Dragos Manolache, Jan van Gemert Published: 2026-10-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.14279v1 Learning long-range dependencies with recurrent neural networks (RNNs) is difficult because of the vanishing gradient problem. Gated recurrent neural networks like GRUs and LSTMs address this problem and are commonly explained by their ability to create additive copy paths through time. This explanation is correct, but incomplete: useful RNN gate values must themselves be learned, which is typically done with another RNN. We study this gate-learning problem through carefully controlled sequence classification tasks. Our analysis shows that gated architectures struggle when all training samples require long-range memory and thus equally suffer from the vanishing gradient problem. We intervene by adding short-dependency samples which let gated models learn solutions that capture long-dependency samples, but also generalize across different class labels. When properly learned, gated RNNs match or even exceed the test accuracy of modern architectures like Mamba and xLSTM. Overall, our results highlight gate learning as a central part of learning long-range memory and show how training data can support this process by exposing the same task over shorter dependencies. --- ### Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference Authors: Xingyu Xie, Xiaoyong Xie, Zhouchen Lin, Kim-Chuan Toh Published: 2026-10-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.14277v1 Tensor parallelism ends every layer with an all-reduce that sits between two dependent matrix multiplications, so its cost cannot be hidden and grows as compute outpaces interconnect bandwidth. Sending 4-bit instead of 16-bit values would cut this cost by nearly 4x, but the all-reduce must add the values it carries, and rounding the sum injects an error at every call. Model quality depends on how these errors accumulate over layers, yet existing methods treat each call on its own. We present Echo, a 4-bit all-reduce for training and inference that controls the accumulated error. Echo moves data in 4 bits and sums in high precision, so each value is quantized at most twice per call for any number of GPUs. The summation reveals each injected error, and Echo feeds it back into later calls, so old errors cancel instead of accumulating. We prove that the accumulated error stays bounded independently of depth. On A100 GPUs, Echo is 2.09x faster than the 16-bit NCCL all-reduce on 1 GB messages. It speeds up the time to first token by up to 1.16x and the training step by up to 1.09x on an idle interconnect, and by up to 1.44x and 1.38x as background traffic grows. It keeps the average accuracy over seven benchmarks within 0.4 points of 16-bit inference on Qwen3-8B. In 10B-token pretraining, its final loss is less than 0.9% above that of 16-bit training. Echo needs no FP8 or FP4 hardware. --- ### The Thinking Leakage in Reinforcement Learning for LLMs Authors: Wenxuan Zhu, Shuming Liu, Bang An, Aznaur Aliev, Bing Li, Yibo Yang, Bernard Ghanem Published: 2026-10-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.14270v1 Hybrid reasoning models such as the Qwen3 series switch between a THINK mode and a NO-THINK mode through a few chat-template tokens. A popular recipe trains such models with reinforcement learning in NO-THINK mode and reports improved reasoning performance. We provide evidence that much of this gain can be explained by thinking leakage: the gain comes largely from partially reactivating the reasoning abilities of the original model's THINK mode instead of learning enhanced reasoning behavior. We train Qwen3-1.7B, 4B, and 8B with GRPO in NO-THINK mode. As accuracy improves, responses become longer and more reflective, are increasingly judged by the original model to resemble its own thinking, and the model's internal activations shift toward its THINK mode. We then investigate at the level of weights, activations, and attention heads: scaling the RL update further elicits THINK-mode behavior and approaches THINK-mode accuracy but does not exceed it; in Qwen3-8B, replacing a low-dimensional THINK-related activation subspace of the RL-trained model with its original-model value removes most of the RL gain, and the reverse exchange transfers a considerable fraction of the gain to the original model; and the RL-induced shift passes through the attention heads that read the empty think block. We further identify a possible mechanism in the GRPO training signal: responses favored by the advantage-weighted update are more THINK-like, and a gradient step computed from this signal moves the model toward its THINK state. Thus, gains in NO-THINK mode can largely reflect reactivation of reasoning abilities already present in the original model. --- ### RoboFake: Are Deepfake Detectors Ready for Humanoid Face Robots? Authors: Hao Chen, Junnan Xu Published: 2026-10-09 Categories: cs.CV, cs.CR, cs.RO arXiv: https://arxiv.org/abs/2610.14269v1 Humanoid face robots can now move their lips in sync with speech and show detailed facial expressions. Give such a robot the face of a real person and drive it with generated speech, and you get a face forgery that happens in front of the camera: the camera records a real object, and no pixel is edited. We call this a RoboFake. In this paper we ask what current deepfake detectors do when they see a robot face. We test six public detectors trained on FaceForensics++ on video of a physical lip-syncing face robot, on a synthesized video of the same robot, and on rendered robot faces. All thresholds are fixed on FaceForensics++, and every result is compared with real human faces that went through the same processing as the robot videos. At a threshold that flags 5% of real faces, three detectors flag almost every physical robot frame, while two flag fewer than 7%. A matched human control and masking show that the response comes from the face, not from the processing or the background. However, it does not track synthesis: with only the face visible, three of the six detectors give the physical robot a higher fake score than its synthesized video. The response is also fragile, and light JPEG compression is enough to push most robot frames below the threshold for some detectors. Our results suggest that current detectors flag today's robots because their faces do not look human, not because they recognize a forgery. We release our evaluation protocol and code, and state three testable hypotheses about realistic, interactive RoboFakes. --- ### Learning to Sync at the Edge: Client-Side Adaptive Synchronization for Federated Learning Authors: Ebasa Temesgen, Ammar Ahmed, Nathan Lechamo, Ali Anwar, Maria Gini Published: 2026-10-09 Categories: cs.DC, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2610.14268v1 The scalability and performance of edge federated learning are fundamentally constrained by synchronization bottlenecks. Clients operate under heterogeneous compute, time-varying communication conditions, and, in some settings, privacy constraints, yet synchronization is often still handled with fixed schedules. However, synchronization decisions are often made outside the client, even though the client directly observes local progress, resource state, and communication conditions. We present a client-side reinforcement learning synchronization framework in which each client decides during training whether to upload, download, synchronize bidirectionally, or defer communication. The framework places a lightweight scheduler alongside the local model and formulates synchronization as a resource-aware control problem driven by local learning and system state. We study this framework on two representative edge workloads, spatiotemporal traffic forecasting and image classification. Across both settings, adaptive client-side synchronization improves the accuracy-cost trade-off, reducing system cost in traffic forecasting while maintaining competitive cost and improving final accuracy in image classification. We also consider privacy-constrained settings, where synchronization must account for not only latency and energy but also privacy expenditure. Overall, our results show that synchronization in edge federated learning is better treated as an adaptive client-side control problem than only as a server-side coordination mechanism. --- ### Thinking with Images without Coordinates Authors: Meng Cao, Haoze Zhao, Yi Wang, Ian Reid, Xiaodan Liang Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.14265v1 Recent advances in multi-modal large language models have shifted toward the "thinking with images" paradigm to improve reasoning faithfulness, yet existing methods rely heavily on explicit coordinate- based grounding. We identify two fundamental limitations in this approach, i.e., a semantic gap where sparse regressions miss high-dimensional latent structures, and a resolution gap due to the granularity mismatch between patch-level tokens and pixel-level coordinates. To address these, we propose TiCO (Thinking with images without COordinates). It reformulates visual reasoning as a semantic evidence discovery process within the latent space, and evidence is injected as token-level regions without pixel coordinates. Specifically, TiCO utilizes a dedicated probe token to estimate similarity distributions and performs importance sampling over spatially connected components to generate diverse, semantically dominant evidence rollouts. Extensive experiments across multiple high-resolution and general visual reasoning benchmarks demonstrate that our TiCO consistently outperforms state-of-the-art coordinate-based methods with significantly improved inference efficiency. --- ### BigCell: Generating Gigapixel Whole-Slide Images Authors: Srikar Yellapragada, Alexandros Graikos, Zilinghan Li, Kostas Triaridis, Tarak Nath Nandi, Ji Dong K Bai, Beatrice Knudsen, Tahsin Kurc, Prateek Prasanna, Rajarsi R. Gupta, Ravi K Madduri, Joel Saltz et al. Published: 2026-10-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.14261v1 Whole-slide images (WSIs) are gigapixel-scale digital scans of histopathology tissue and serve as the primary basis for cancer diagnosis. Existing histopathology generative models operate at the patch scale, producing fixed-size tiles of at most 1024$\times$1024 pixels which encompass only a small fraction of the WSI. In contrast, text reports for clinical diagnoses and slide-level diagnostic labels -- the supervision that exists at scale -- operate at the whole-slide level. We present BigCell, the first approach to generate coherent whole-slide histopathology images at native gigapixel resolution. BigCell trains a flow-matching transformer at 2048$\times$2048 pixels on over 120,000 publicly available WSIs spanning multiple organ types. Conditioning on embeddings from pathology foundation models and using an inference-time sliding-window pipeline, BigCell generates coherent images of up to 32,768$\times$32,768 pixels, outperforming prior tile generators on both tile-level and slide-level fidelity metrics. To make gigapixel synthesis practical, we introduce an adaptive scheduling strategy that prioritizes important slide regions, speeding up image generation by over 3\ttimes with minimal quality degradation. Furthermore, we propose the first text-to-image synthesis at 8k resolution by training a separate model that produces dense conditioning grids directly from pathology text reports. We demonstrate that augmenting with synthetic samples improves slide-level few-shot classification performance by up to $18 \%$ over baselines trained on real data. --- ### Variance Fingerprints: Component-Wise Identification of Content Factors by Augmentation Design Authors: D. Hudson Smith Published: 2026-10-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.14260v1 Augmentation-based self-supervised learning can recover the content shared across views without separating its underlying factors into individual coordinates. We ask whether augmentations can be designed to make those factors identifiable. Our approach allows content factors to fluctuate across augmented views while preserving their mean for each source instance. Each instance receives a fixed, recorded set of augmentation strengths that controls how much its factors fluctuate. When factors respond differently to changes in these strengths, their patterns of variation provide information that distinguishes them. Under suitable decoder and support assumptions, we prove that these differences identify individual factors in a conditional Gaussian model, up to permutation, scaling, and translation. We then develop a learner that uses the recorded strengths to estimate these patterns jointly across instances, enabling learning from few views per instance. Synthetic experiments demonstrate near-perfect factor recovery through nonlinear mixing. Controlled dSprites experiments show improved coordinate alignment using augmentations that target known factors, even without telling the learner which augmentation corresponds to which representation coordinate. These results suggest a route to component identification in self-supervised learning: augmentation design can supply identifying information beyond shared content alone. --- ### Do Artificial Neural Networks Need Dendritic Nanotubes? Two Reasons for Shrinking Importance Estimates in Continual Learning Authors: Saurav K. Aryal Published: 2026-10-09 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2610.14258v1 Regularization-based continual learning protects each parameter in proportion to an estimate of its importance, yet these estimates come from finite samples and heuristics and are used as if they were exact. We report four studies that start from a biologically inspired mechanism and end with a statistical explanation of it. Motivated by dendritic nanotubes, we let transient lateral links diffuse importance tags between hidden units. Links between co-active units gave no significant gain, but random links with lifetimes of 25 or 200 steps raised final accuracy on 20-task Permuted MNIST by 1.5 to 2.6 points. We show that random diffusion implements linear shrinkage of importance toward the layer mean in expectation. A simulation of the link process alone predicts shrinkage weights of 0.23 and 0.52 for these lifetimes, and graph-free shrinkage at 0.25 and 0.5 reproduces both the accuracy and the dispersion of the consolidated importance, while every activity-dependent rule did worse than random links. A five-seed screen across EWC, SI, and MAS found nominal gains for SI and MAS on Permuted MNIST and losses on task-incremental Split CIFAR-100, where forgetting was small and shrinkage cost plasticity. Varying the number of importance samples then separates two mechanisms on Permuted MNIST. For EWC, the gain fell by about ten points per tenfold increase in samples, from 19.6 points with 10 samples to -0.4 with 1000, a variance effect. For MAS, a gain of about one point persisted at 1000 samples, consistent with a bias in the importance measure rather than noise. Shrinkage had no detectable effect for MAS on a domain-incremental CIFAR-100 benchmark. Finally, we show that a standard heteroscedastic empirical Bayes rule shrinks the largest Fisher-type estimates most, which may explain its poor results, and point to a log-scale alternative. --- ### Image Diffusion Models Are Good 3D Human Motion Generators Authors: Siyuan Yang, Chong Wang, Hao Cheng, Jun Liu, Bihan Wen, Alex Kot, Hedvig Kjellstrom Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.14254v1 Text-to-motion generation typically relies on dataset-specific skeletal representations, with models trained separately for benchmarks with different joint layouts. We investigate whether image diffusion architectures can model 3D human motion through a common image-compatible representation that accommodates heterogeneous skeletal layouts while preserving motion-specific kinematic structure. To this end, we organize root-centered joint trajectories into topology-informed joint--time images and model global root dynamics through a complementary latent stream. A motion autoencoder conditions local-motion decoding on the root latent, while a text-conditioned Scalable Interpolant Transformer (SiT) jointly generates both latent streams, with supervision on decoded 3D joint positions further constraining generation in motion space. In addition to dataset-specific models, we train a single motion autoencoder on HumanML3D and KIT-ML, followed by a single text-conditioned SiT shared across both datasets, preserving their respective skeletal definitions without skeleton retargeting to a common joint layout. Experiments on HumanML3D and KIT-ML show that our dataset-specific models achieve state-of-the-art performance, while shared training yields further gains on both benchmarks, demonstrating the benefits of shared modeling across heterogeneous skeletal layouts. --- ### SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing Authors: Arman Zarei, Sayan Nag, Bryan Wang, Franck Dernoncourt, Varun Manjunatha, Nedim Lipka, Soheil Feizi, Samyadeep Basu Published: 2026-10-09 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2610.14253v2 Slider-based control aims to give users continuous, fine-grained control over the intensity of individual edits in instruction-based image editing. However, existing approaches fail to deliver reliable continuous controllability: traversing a slider can produce abrupt visual jumps and non-monotonic changes, while jointly controlled sliders can interfere with one another. To systematically study these limitations, we introduce SlideBench, a comprehensive benchmark for continuous image editing spanning diverse editing categories and equipped with a unified suite of metrics quantifying monotonic progression, perceptual continuity, and inter-slider disentanglement. Building on these observations, we propose SliderEdit++, which explicitly regularizes the intermediate editing trajectory rather than supervising only its endpoints. Our method combines velocity- and semantic-space trajectory regularization with spectral control to encourage smooth, predictable slider traversal, together with a disentanglement objective that reduces interference between independently controlled edits. On SlideBench, SliderEdit++ achieves state-of-the-art performance, improving the overall score by 18.5% relative to the strongest baseline. At the same time, using a few-step editing backbone makes our method approximately 3x to 20x faster than existing slider-based approaches, enabling substantially more responsive interactive editing. --- ### Adaptive-Depth Is a Finishing Stage Authors: Andrei Piterbarg, Sean McLeish, Dhruv Pai, Benjamin Keigwin Published: 2026-10-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.14252v1 Looped transformers reuse the same layer multiple times, allowing inference compute to be adjusted without changing the model. Recent adaptive-depth methods train the model across multiple loop depths from the beginning of training. We introduce fixed-first training, which varies model depth only during a short final phase of training. At 200M parameters, training a model of fixed-depth 2 for the first 67% of the run reduces modeled training compute by 45% while keeping mean negative log-likelihood (NLL) across inference depths within 0.5% of training across depths throughout. At 1B parameters, training initially at depth 4 reduces modeled compute by 31% to 37% and wall-clock time by 32% to 39%, while keeping final NLL within 0.8% and downstream differences within the observed seed variation. These results show that training over the full range of depths can be reserved for a short finishing phase with only small changes in performance. --- ### Akule: Fast and Scalable Multi-Robot Motion Planning via Sparse Interaction Diffusion Authors: Manav Vora, Gokul Puthumanaillam, Aditya Penumarti, Jane Shin, Melkior Ornik Published: 2026-10-09 Categories: cs.RO, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.14248v1 Diffusion models provide expressive trajectory priors for multi-robot motion planning (MRMP), but scaling them to large teams requires coordinating individual motions without expensive joint computation. We introduce Akule, a sparse interaction diffusion framework that augments a frozen single-robot prior with three learned modules: a reusable pairwise correction model $R_φ$, a contextual selector $U_ψ$ that determines which corrections to evaluate, and a composer $G_ω$ that combines their effects through context-dependent signed weights. This decomposition separates which interactions merit computation from how their effects should be combined into coordinated denoising updates. We train $R_φ$ using matched pairwise trajectory optimizations, then learn $G_ω$ and $U_ψ$ from physically optimized joint trajectories without requiring a prescribed ground-truth interaction graph. The resulting joint proposals are passed to a downstream search-based planner for validation and repair. Across diverse MRMP benchmarks, Akule achieves competitive planning success, complete-planner speedups of up to $25\times$, zero-shot population transfer, and successful planning with up to $256$ robots. Ablations further demonstrate that learned selection and composition reduce pre-repair conflicts and downstream repair effort relative to heuristic selection and uniform summation. --- ### Learning Non-Gaussian SEMs with Conditional Risk, and Why the Direction of Recursion Matters Authors: Ujas Shah, Panagiota Birmpa, Rebecca Morrison Published: 2026-10-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.14246v1 Variance-based methods recover a Gaussian linear structural equation model (SEM) with equal or suitably constrained error variances, either by recursively identifying the source nodes with smallest conditional variance (top-down method) or sink nodes with highest conditional variance (bottom-up method). We show that the use of conditional variance is incidental: replacing it with the conditional risk, i.e., the minimal expected loss of linear prediction under the negative log-likelihood of the noise distribution, extends both methods to non-Gaussian noise. Existing methods are the least-squares special case. This yields two main results. First, exploiting the noise distribution improves structure recovery: the matched-loss procedures recover the SEM more accurately than their least-squares counterparts and the LiNGAM methods, which are designed for non-Gaussianity. Second, the two methods, interchangeable in the Gaussian setting, separate under non-Gaussian noise: the top-down method is correct for every noise density with finite differential entropy, whereas the bottom-up method requires a regularity condition and can fail without it, for instance under mean-zero exponential or Cauchy noise. Simulations confirm both results. --- ### Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study Authors: Ruomeng Ding, Qianli Shen, Zhaoyang Han, Meixin Chen, Daoyuan Chen, Yaliang Li Published: 2026-10-09 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.14238v1 LLM data engineering requires iterative experimentation to determine how data selection, rewards, and curricula affect model learning, making it a natural setting for AI-for-AI (AI4AI) research. Can agents use experimental feedback to progressively improve strategies, and do the resulting strategies improve target-model performance on held-out data? We study how agents use experimental feedback to develop data-engineering strategies under fixed training and evaluation protocols. Our Agentic Data Engineering (ADE) framework lets agents pursue, revise, or combine research directions using cumulative findings. Strategies are selected by in-loop scores and evaluated on held-out benchmarks. Across four tasks-math and code data selection, math reward design, and math curriculum learning-selected strategies achieve absolute gains over generic baselines of up to 13.34% on AIME25 Pass@32 and 5.85% averaged across four held-out benchmarks under fixed training conditions. In-loop scores improve over successive experiments, while held-out trajectories show that later in-loop gains do not always improve generalization. Comparisons of research organization and feedback access favor combining evidence analysis with cumulative findings. Research trajectories show how earlier findings inform strategy revisions and combinations across research directions. --- ### Latent World Action Model for GUI Agents Authors: Seungjun Yu, Hojun Choi, Seojeong Park, Jaeyo Shin, Hyunjung Shim Published: 2026-10-09 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2610.14228v1 Pixel-space world models have recently emerged as a promising approach for GUI agents, predicting future screens prior to execution and subsequently re-perceiving them for action selection. However, this two-stage paradigm faces two key challenges in GUI environments: (L1) the high computational cost of pixel reconstruction and (L2) the need to reconstruct large and diverse appearance-level details beyond what is required for action selection. In practice, this screen-generation objective can induce an identity shortcut problem, where future-state prediction largely preserves the current state rather than capturing action-induced changes. In this work, we reformulate GUI world modeling by shifting the prediction target from full-screen reconstruction to action-induced future information in latent space. Concretely, we leverage a large multimodal model as the latent world model, whose shared representations support two dedicated heads for both action selection and predictive transition modeling. The action head directly translates these latent representations into action selection, while the transition head captures action-conditioned future information. To mitigate the identity shortcut, we further introduce an action-aware contrastive objective that encourages the transition representations to capture discriminative action-induced changes. Extensive experiments across offline and online GUI settings show that our method achieves up to 31.9% and 40.6% relative gains in success rate over pixel-space world models, respectively, while substantially reducing inference latency by up to 98.9%. Our code is available at https://github.com/sjyu001/latent2world. --- ### CAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT Authors: Séléna Jean-Mactoux, Sophie Loizillon, Ghina Jardali, Amandine Crombé, Nathalie Lassau, Alexandre Bône Published: 2026-10-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.14226v1 Purpose : To develop and evaluate CAPTOR, a deep-learning vision-language foundation model for oncologic chest-abdomen-pelvis (CAP) CT interpretation. Materials & Methods : CAPTOR (Chest-Abdomen-Pelvis foundaTion model for Oncologic Radiology) is a contrastive vision-language model, trained using a pretraining strategy for oncologic CAP CT (in single- or multiple-series acquisitions), on a multicenter retrospective dataset from North America, Europe and Asia, predominantly from tumor lesion examinations. CAPTOR was compared with state-of-the-art CT foundation models on three downstream tasks: disease detection, survival prediction using TumorImagingBench and image retrieval. Classification and retrieval were both evaluated on held-out internal and public test sets, stratified by anatomical coverage and indication. Bootstrap resampling was used to estimate confidence intervals, and pairwise comparisons were performed using permutation tests. Results : CAPTOR was trained and tested on 25,512 and 10,794 CT-report pairs respectively. TumorImagingBench datasets comprised between 134 and 421 studies each. CAPTOR outperformed all baseline models, on the classification task, on the CAP subset (AUC 0.767, 95%CI: 0.734-0.793, vs. 0.695, 95%CI: 0.645-0.736 for the next-best, p<0.001) and oncologic subset (AUC 0.784, 95%CI: 0.759-0.805, vs. 0.734, 95%CI: 0.703-0.767 p<0.001), ranked first on three of the four oncologic prognostic benchmarks, and achieved superior retrieval performance on CAP and oncologic subsets. Conclusion : A foundation model trained on oncology-enriched CAP CT data outperformed relevant state-of-the-art models in its target clinical context, underscoring the importance of clinically aligned pretraining. We release our preprocessing, training and inference code : https://github.com/Guerbet-AI/CAPTOR and model weights : https://huggingface.co/Guerbet-AI/CAPTOR --- ### Harness^2: Recursive Agent Harnessing for an Open World Authors: Ruiyao Xu, Yanfei Chen, Zhongying CuiZhu, Bhavana Dalvi Mishra, Yifei Ming, Han Yu, Rujun Han, Chen-Yu Lee, Tomas Pfister Published: 2026-10-09 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.14224v1 LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatically evolve these harnesses. However, deploying RSI in open-world settings still faces two critical challenges. First, open-world tasks are typically unseen during the harness design phase and novel at test time, leaving no ground-truth verifiers to reliably guide online harness edits. Second, the RSI process remains highly task-specific and fails to generalize to novel scenarios. We introduce Harness^2, a plug-and-play, recursive agent harnessing framework that addresses these challenges through two connected levels of recursion. Task-level recursion refines the current task's harness using a contrastive Propose-Probe-Compose step that reliably guides edits without ground-truth verifiers, and can be scaled further via parallel or sequential recursion. Harnessing-level recursion then extracts experience from these edits to update a continual improvement harness, enabling the agent to better adapt to future tasks. Across three professional benchmarks and four model-harness configurations, a single step consistently improves GLM-5 and Gemini 3.5 Flash over their base harnesses, yielding gains of up to 11.5 points on WorkBuddy-Bench, 4.5 points on JobBench, and 11.8 percentage points on LAB, with further gains as the task-level recursion budget increases. --- ### Learnable Low-Rank Polynomial Sketch for Effective Linear Attention Authors: Zongyue Qin, Haoran Deng, Jason Cong, Yizhou Sun Published: 2026-10-09 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.14219v1 Softmax attention in Transformers suffers from quadratic complexity in sequence length, making it impractical for long-context applications. Linear attention alleviates this issue by replacing the exponential kernel with alternative functions that enable linear-time computation. Among existing linear attention approaches, recent studies have shown that polynomial kernels are particularly effective, as they exhibit sparse and spiky behavior similar to softmax attention, which emphasizes large dot products while suppressing irrelevant interactions. However, the exact computation of high-degree polynomial kernels is infeasible for high-dimensional representations. As a result, prior work relies on approximate polynomial kernels. This introduces a non-negligible approximation error. In this paper, we show that, from the perspective of polynomial kernel approximation, existing linear attention methods are still suboptimal. We propose \textbf{L}earnable \textbf{Lo}w-Rank \textbf{P}olynomial \textbf{S}ketch (LLoPS), a principled and flexible framework for approximating polynomial kernels with linear attention. Our method learns a low-rank polynomial sketch that provably achieves a strictly smaller approximation error than existing approaches. Experiment results show that LLoPS achieves the highest performance across extensive benchmarks, comparing with various linear attention baselines. --- ### Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules Authors: Samuele Giampieri Published: 2026-10-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2610.14216v1 Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the agent may choose to open, and rules that load automatically when the agent reads matching files. We call these files the agent's harness. Developers add to it whenever they correct the agent, but one success proves little: the same agent can pass a task once and fail it the next time. We present Cortex, a tool that tests changes to the harness instead of trusting them. It saves fixes from the developer's sessions as replayable tasks, finds the corrections that recur, writes one skill or rule at a time, and keeps it only if repeated runs with and without it show a net gain and no task made noticeably worse. Existing text is tested the same way before it is deleted, and Cortex neither adds nor deletes text the agent never used. We tested Cortex with Claude Haiku 4.5 on a repository built for the purpose, with conventions the model tends to break, one area with nothing to learn, and a script playing the developer. On held-out tasks, the harnesses it built made the agent follow the conventions far more often than no skills or rules did, left the comparison area unchanged, and added no text read on every turn. Rules, which load automatically, did most of the work; skills helped only when offered with the files a task touches, and those offered on every turn were rarely opened. Cortex kept none of the useless or harmful suggestions we planted, but the agent never opened the useless ones or the harmful skills, and it reached no verdict on the harmful rules, so the test shows that Cortex keeps no unused text, not that it detects damage. Under the stronger Claude Sonnet 5 a single run's harness added little, and on a real open-source project, where the agent was rarely corrected, Cortex found nothing to learn. We release the tool, the lab and its data. --- ### Embedding Graph Kernel Entropy (EGKE): Fine-grained Hallucination Detection for LLMs from Embeddings Authors: Dilrangi Sankalpana, Pragatheeswaran Vipulanandan, Uthayasanker Thayasivam, Kamal Premaratne Published: 2026-10-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.14214v1 Hallucination detection is critical for ensuring the reliability of Large Language Models (LLMs) in real-world deployments. While recent works, such as Semantic Entropy (SE) and Kernel Language Entropy (KLE), identify hallucinations by measuring semantic disagreement across multiple generated responses using Natural Language Inference (NLI) models, these methods depend on separately loaded NLI classifiers to estimate pairwise semantic similarity, introducing significant computational overhead. We propose Embedding Graph Kernel Entropy (EGKE), a variant of Kernel Language Entropy (KLE) that replaces its NLI-derived semantic graph with a Radial Basis Function (RBF) kernel applied to dense sentence embeddings generated by a BGE embedding model, while retaining KLE's graph Laplacian, heat kernel, and von Neumann entropy formulation unchanged. By computing similarities directly in a continuous embedding space, the proposed method provides a symmetric and computationally efficient alternative to NLI-based semantic comparison. We evaluate our approach across 30 experimental setups (covering multiple question-answer datasets and open-weight LLM families) using both AUROC and AUARC, and demonstrate that this RBF-based method achieves competitive hallucination detection performance against state-of-the-art methods. --- ### Modeling the Arrival Time of Information-Bearing Events in Natural Language Authors: Leyi Lao, Yulin Ou, Yang Xu, Hao An Published: 2026-10-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.14212v1 Understanding how information is distributed over time is fundamental to modeling natural language. While existing empirical studies primarily rely on post-hoc analysis of information-theoretic metrics, such as surprisal, little is known about the generation processes under the surface. We propose a novel approach for addressing this gap using the tool of neural temporal point processes (TPPs) by modeling the key information-bearing events in text sequences with learnable event intensity functions. Our model takes the history of event intervals and the contextual semantic representations from LLMs as input, and predicts the future arrival times for two types of events: new-word and high-surprisal-token. The experimental results reveal an interesting distinction in event intensities: LLMs tend to produce new words at significantly higher rates than humans, while high-surprisal tokens do not exhibit the difference. A decaying pattern of intensity over time is found in new-word events for both humans and LLMs, but not in high-surprisal-token events. Our findings revisit and extend previous studies that use simpler methods; provide supplementary evidence for theories about constrained context representation inherent in human language production; and find a new angle to view human and LLM generation differences. --- ### Agreement versus Softmax under Spatial Disambiguation Authors: Michał Zakrzewski, Mariia Shpir, Taras Rumezhak, Volodymyr Karpiv Published: 2026-10-09 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.14210v1 ScanRefer Multiple queries require spatial disambiguation: several instances of the target class are present, and the referencer must pick one. When per-query logits were never logged, a common substitute is cross-epoch agreement. On the full ScanRefer validation set (9,508 queries; GeoClassifier with ground-truth proposals), object-level softmax is similarly miscalibrated on Unique and Multiple (ECE 0.068 vs. 0.102; the scene-bootstrap gap interval includes zero). Fixed-final agreement on the same checkpoints reports ECE 0.041 vs. 0.272 (gap +0.231). Modal-vote agreement is 0.045 vs. 0.318. Most Multiple errors are same-class wrong-instance (45.6%); geometric miss (H2) is 59.6%, and wrong-category (H1) is 16.7%. A non-monotone H1 pattern does not appear under the default fixed-final protocol, and we retract it. Logit-free thresholds rank spatially hard queries poorly. If only agreement was logged, calibrate abstention on Multiple and report wrong-instance rates with H1. --- ### Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs Authors: Boris Radovič, Marco Canini, Veljko Pejović Published: 2026-10-09 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2610.14209v1 The most accurate agents executing user-provided tasks are driven by large, cloud-hosted models, which solve them by reading the private data of the user. Agents powered by models small enough to run on edge devices keep that data local, but yield far worse results. A third option is to have cloud models write a program that devices execute: the data stays local, but as the program is written before any data is seen, it fails whenever a step depends on interpreting content that appears only at run time. We explore an intermediate architecture, in which the cloud-written program defers bounded questions over user data to a small local model through an ordinary function call. On AppWorld this improves the success rate of a code-only agent in all six combinations of backbone model and test partition we evaluate, by up to 14.9pp, recovering a substantial part of the gap to a cloud-hosted ReAct loop while keeping user data on the device. --- ### Token-Budgeted Candidate Retrieval for 3D Scene-Grounded VLMs: Category Names vs. Pairwise Geometry Authors: Michał Zakrzewski, Mariia Shpir, Taras Rumezhak Published: 2026-10-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.14207v1 Under a fixed context budget, which objects and relations should a 3D scene-grounded VLM see first? On ScanNet indoor referring benchmarks (Dai et al., 2017), matching the query to object category names outperforms pairwise geometry scoring at every reported K. The gaps are largest at high recall. Analytic pairwise cues beat per-object cue scoring and query-agnostic kNN graphs, including on paraphrases. MiniLM and BGE-small still score higher on those splits. We evaluate token-budgeted candidate retrieval with axis-aligned boxes, a token-ratio metric, training-free baselines, two small encoders that match q to each object's category name, and QCRR (Query-Conditioned Relation Retrieval), a deterministic pairwise-geometry scorer. Across ScanRefer gt_val plus a custom 20% scan-id split of Nr3D and Sr3D (35,504 queries; not official ReferIt3D val), additive noun matching reaches R@10 0.864 on ScanRefer against QCRR's 0.626; MiniLM and BGE-small reach 0.911 to 0.913 on ScanRefer and 0.941 to 0.947 on Nr3D. A corrected 3DGraphLLM harness (native Acc@0.25 0.67 on the full graph, n=300 ScanRefer queries) shows that context selection changes downstream accuracy under a matched object budget (Random 0.44, QCRR 0.56, MiniLM 0.67, oracle 0.70). Semantic retrieval beats hand-designed geometry on that harness. We will release the protocol, retriever implementations, and per-query outputs so new selectors can be swapped in without rewriting the analysis. --- ### Refined Grid Sampling for Efficient Implicit Neural Representations of Large-Scale Scientific Data Authors: Guang Zhao, Xihaier Luo, Sean McCue, Luke P. Van Roekel, Seungjun Lee, Yihui Ren, Shinjae Yoo, Wei Xu Published: 2026-10-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.14205v1 Implicit neural representations (INRs) offer a powerful framework for modeling high-dimensional physical fields, but their training remains inefficient because evaluating dense coordinate grids is computationally expensive. Existing coordinate-pruning strategies rely on local error functions that can oversample correlated points and incur substantial overhead from full-grid error evaluation. We introduce Refined Grid Sampling (RGS), which combines stratified grid sampling, error-based refinement, and dynamic grid-resolution adjustment. This design reduces spatial redundancy without evaluating errors over the full grid. On high-resolution Navier--Stokes fields, RGS achieves higher reconstruction accuracy within a fixed wall-clock budget and reaches the accuracy of full-grid training up to $6\times$ faster than the evaluated baselines. --- ### ClothCode: Generative Modeling for Garment State Estimation and Dynamics Prediction Authors: Yingdong Ru, Lipeng Zhuang, Shiyu Fan, Zhuo He, Florent P. Audonnet, Gerardo Aragon Camarasa Published: 2026-10-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.14200v1 We introduce ClothCode, a unified generative framework for garment state estimation and action-conditioned dynamics prediction in a shared discrete configuration space. A material-aligned tokenizer encodes garment configuration as residual vector-quantized patch tokens, while task-specific Masked Generative Transformers predict these tokens through parallel confidence-guided refinement. Across three garment templates, ClothCode reduces mean displacement error by 26.6% for state estimation and 37.0% for dynamics prediction relative to the strongest baselines. Dynamics prediction requires only 16.7 ms per window, compared with 556.2 ms for diffusion. Integrated into the same model-predictive controller, ClothCode improves real-world folding and flattening success from 56.7% to 78.9%. Further results and videos are available at: https://anonymous.4open.science/r/ClothCode-DE32 --- ### Simple Linear Corrections for Compression in Late Interaction Authors: Mihir Agarwal, Sabyasachi Basu, Viraj Agrawal Published: 2026-10-09 Categories: cs.IR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.14196v1 Late-interaction (multi-vector) models represent documents using a set of token-level vectors, providing a middle ground between cross-encoders and dense encoders in terms of quality and cost of embedding. However, compared to the latter, the indices are costly to store and score. Pooling and pruning based compression techniques are deployed widely but deteriorate in quality noticeably with aggressive compression. We investigate whether a lightweight change to the scoring function can recover retrieval quality after document-vector compression. For each combination of encoder, compressor, and vector budget, we learn a global linear correction by distilling the uncompressed model's score distributions over candidate documents. The encoder and compressor remain frozen, and the correction can be applied to each query at search time or once, offline, to the stored vectors. We evaluate the method with ColBERTv2 and Jina v4 on MS MARCO and BEIR, and with ColPali2 on the ViDoRe v3 visual document retrieval benchmark. Experiments cover four training-free compression methods, multiple vector budgets, in-domain adaptation, and transfer from MS MARCO to BEIR. In the in-domain setting, the correction improves over baseline compression in 154 of 160 BEIR settings, while transfer from MS MARCO is more variable across models and datasets. We also find that matrices trained with synthetic queries can improve over baseline compression on ViDoRe v3. These results show that a small learned correction can recover some of the quality lost to compression without retraining the encoder or recompressing the documents. --- ### Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models Authors: Laura Yao, Shixing Yu, Jie Peng, Promit Ghosal, Kyra Gan, Tianlong Chen Published: 2026-10-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.14190v1 Explaining a vision--language model (VLM) prediction requires tracing training-example influence to the multimodal evidence that mediates it, yet existing attribution methods largely operate only at the sample level. Recent latent-mediated influence methods provide feature-level attribution in language models, but lack the multimodal and spatial structure needed to ground influence in VLMs. We introduce MOSAIC (Multimodal Orthogonalized Sparse Autoencoders for Influence Characterization). It learns a shared sparse image--text latent space whose concepts are 1) sparse within each modality, 2) supported on contiguous image regions, 3) aligned to the phrases that describe them, and 4) approximately decorrelated. It then applies EK-FAC to decompose training-example influence through these concepts and localize their contributions to specific text phrases and image regions. We evaluate MOSAIC on Qwen and Gemma across captioning, chest X-ray understanding, and visual question answering. The learned features are more localized and coherent without degrading task behavior, and ablating influence-ranked latents changes model outputs more than ablating latents ranked by activation or frequency. We find that visual evidence can substantially reorganize training-data attribution while preserving more of the shared latent structure. MOSAIC thus connects where model behavior comes from with what multimodal evidence carries that influence. --- ### Semantic Edge-Cloud Communication for Real-Time Urban Traffic Digital Twins Authors: Murat Arda Onsu, Arman Dogru, Poonam Lohan, Burak Kantarci, Aisha Syed Published: 2026-10-09 Categories: cs.NI, cs.CV, cs.DC, eess.SP arXiv: https://arxiv.org/abs/2610.14187v1 Urban traffic systems are becoming increasingly complex, demanding real-time traffic perception, proactive collision prediction, and intelligent management to improve safety and reduce congestion. Although AI-driven traffic management has shown strong promise, its success relies on diverse, high-quality data spanning critical scenarios such as collisions, near-collisions, and traffic rule violations. Digital twins offer a powerful solution by enabling synchronized virtual replicas of physical traffic environments for real-time monitoring, collision prediction, traffic-flow optimization, and diverse realistic scenario generation. However, continuously synchronizing a high-fidelity urban traffic digital twin through edge surveillance cameras requires substantial edge-cloud communication, and transmitting raw video streams leads to severe bandwidth and latency constraints. To overcome this challenge, this paper proposes a semantic communication-based edge-cloud framework for real-time urban traffic digital twin applications. By leveraging edge intelligence to extract and transmit only task-relevant semantic traffic information instead of full video feeds, the proposed framework significantly reduces communication overhead while preserving the essential dynamics needed for accurate real-time digital twin reconstruction. Experimental results demonstrate more than 99% transmission savings and an average trajectory reconstruction error of only 0.12 m, confirming the proposed framework as an effective, scalable, and low-latency solution for AI-enabled urban traffic digital twin applications. --- ### Visualizing the World Model in an Agent's Value Function Authors: Shawheen Naderi, Fatemeh Akherati, Yubei Chen Published: 2026-10-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.14186v1 Could model-free reinforcement learning algorithms actually be learning a model of the environment? In this work, we apply counterfactual interventions which hold everything about a state fixed, besides a targeted change, to explore if the value function of a Proximal Policy Optimization agent forms a world model of the Crafter environment. Despite only being trained to optimize reward, we discover that the value function learns concepts such as the rules governing when a diamond is collectible, water and food having an impact on health, heuristics regarding inventory, and more. Finally, we discuss the safety implications of our visualizations and some shortcomings of current reinforcement learning agents that will prevent us from building truly advanced machine intelligence. --- ### ULPack: Reference-Conditioned Lossless Compression of Checkpoint Trajectories Authors: Aniket Srinivasan Ashok Published: 2026-10-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.14184v1 Studying model training requires checkpoint trajectories, whose storage cost limits temporal resolution. Although adjacent checkpoints are numerically close, existing lossless codecs either operate on XOR bit patterns or ignore trajectory-specific conditional structure. We show that a reference weight's exponent predicts the bit length of its displacement in ordered floating-point space without side information. We introduce \textbf{ULPack}, a lossless codec which exploits this dependence by conditioning entropy models of ordered-integer residuals on the reference exponent. Across bfloat16, float16, and float32 trajectories, ULPack reduces storage by up to 27\% against ZipNN, 21\% against zstd-19, and 11.5\% against FM-Delta. Across two dense trajectories, compression improves as updates shrink and reference conditioning strengthens, while near uniform low-order bits set the remaining compression floor and earlier checkpoints add little information. --- ### Unconstrained CTI-REALM with Open-Weights Authors: Sahil Garg, Ruhi Gottumukkala, Vishal Agarwal, Shubham Vishwakarma Published: 2026-10-09 Categories: cs.AI, cs.CL, cs.CY, cs.SE arXiv: https://arxiv.org/abs/2610.14180v1 Organisations that want language-model agents for security work face a choice between open-weight models, which they can run and audit themselves, and far more expensive closed frontier models. We study that choice on CTI-REALM (arXiv:2603.13517), a benchmark in which an agent turns a threat-intelligence report into a working detection by querying a live telemetry store. We evaluate twenty-six models, nineteen open-weight and seven closed, under a common harness, scorer and panel of LLM judges. Our main finding is that an open-weight model can match the strongest closed models at less than a tenth of their cost, provided it is given enough turns. The benchmark's published limit on agent messages is a confound: a task that exhausts the limit scores zero on every checkpoint, including those it had already passed, so results at that limit partly measure which models finish in time. At the published limit the leading open-weight and closed models cannot be distinguished. With the limit relaxed, the models it was truncating recover, and the highest rewards belong to open-weight models. Among the leading models, price is a poor guide to capability: models with similar rewards differ in cost by more than an order of magnitude. Because the benchmark's checkpoint scores largely record what an agent did or mentioned, we also introduce stage-level metrics that score what the agent submits, by executing its detection queries in the telemetry store and judging its outputs against the answer key. Rather than combining them into one more overall reward, we show that different models lead different stages, which suggests routing each stage of the workflow to the model that performs it best rather than choosing a single model by its overall score. We also report how many tokens each model generates, and find that the share of output spent on thinking does not track the reward. --- ### Do you "see" what I "see"? A Multi-panel Visual Question Answer Dataset for Large Language Model Chart Analysis Authors: Daniel J. Evans, J. P. Naiman, JooYoung Seo, J. Stephen Downie Published: 2026-10-09 Categories: cs.DL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2610.14173v1 Digital libraries increasingly host scientific publications whose figures encode primary research findings, yet making this visual content searchable, accessible, and reusable remains an open challenge. Large language and multimodal models (LLMs/LMMs) provide the possibility to automate many figure parsing tasks such as determining data trends or extracting data from plots. In this work, we consider if these models can reliably support task-oriented visual data analysis when presented with synthetic, but realistic, scientific figures that contain multiple charts. Our Visual Question Answering (VQA) process scaffolds our tasks along a four-level description model from basic conceptual answers to interpretive and analytical understanding. Additionally, we outline our process for synthetically generating our single and multi-panel (charts in which there are multiple panels present) plots and testing the data with various LMMs using quantitative analysis. In general, we find LMMs become less accurate with increasing figure complexity as the number of panels, number of plot elements, and difficulty of questions increase. Finally, because LMM accuracy is expected to change rapidly, our analysis also considers cost relative to performance as a metric to inform future user decisions. We provide the detailed question-answer pairs used in this analysis, along with the code used to generate random plots, question-answer pairs and detailed bounding-box metadata for chart elements. The code and data are available at https://github.com/ReadingTimeMachine/LLM_VQA_MultiPanel and https://huggingface.co/datasets/ReadingTimeMachine/visual\_qa\_multipanel --- ### AutoEnvScaling: Automating the Data Flywheel with Terminal Agents Authors: Simon Yu, Baolin Peng, Bo Liu, Zhengyan Shi, Zhaoyang Wang, Hao Cheng, Qianhui Wu, Wenlin Yao, Natasha Jaques, Weiyan Shi, Jianfeng Gao Published: 2026-10-09 Categories: cs.SE, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.14163v1 Terminal agents solve tasks in software engineering and scientific research by executing commands in a terminal. Training them via reinforcement learning (RL) requires diverse and verifiable environments, but these environments are still mostly designed by human researchers, so their supply grows only as fast as researchers can work. We introduce AutoEnvScaling, which treats environment design as a terminal task and uses agents to automate the data flywheel. A proposer agent builds new RL environments from the rollouts of the solver being trained, and the solver's new rollouts guide the next round. By turning environment generation into a terminal task, AutoEnvScaling increases the valid-environment rate by up to 25 times compared to prompt-only generation, at up to 75% lower cost per valid environment. We show that training Qwen3.5-35B-A3B on AutoEnvScaling environments from GPT-5.6-sol improves its Terminal-Bench 2.1 score by 4.3 points over the matched Tmax baseline. The broader goal of AutoEnvScaling is to enable recursive self-improvement (RSI): by making both environment generation and solving terminal tasks, it lets one model co-evolve in both roles. We show that Qwen3.6-35B-A3B, acting in both roles, gains 12.2 points on Terminal-Bench 2.1 and raises its Terminal-Bench 4.0 score from 1.6 to 3.2. The pipeline also generalizes across agentic domains, generating environments for software engineering, computer use, professional work, and GPU kernel programming. Overall, these results show a path toward agents building their own training environments, reducing human reliance and taking a core step toward RSI. --- ### Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation Authors: Hermann Kumbong, Ishan S. Khare, Iddah Mlauzi, Andrew Woen, Charles Ding, E. Kelly Buchanan, Simran Arora, Azalia Mirhoseini, Christopher Ré Published: 2026-10-09 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.14162v1 Diffusion language models (DLMs) offer parallel sampling for faster generation than autoregressive models, an increasingly important advantage as inference becomes a dominant computational workload. However, DLMs degrade quickly with fewer sampling steps, process the full sequence at every step, and require many passes over the dataset to reach good quality. We introduce Next-Concept Modeling (NCM), a two-stage, coarse-to-fine framework: a multiscale residual VQ-VAE encodes text into a hierarchy of discrete codes, and a transformer generates one level at a time, predicting all codes within a level in parallel. At matched parameter scales, NCM achieves better generative perplexity than the strongest DLM baseline on LM1B while running $21\times$ faster. On OpenWebText, NCM is competitive with the strongest DLM while running $10\times$ faster; on XSum, it matches the strongest DLM's ROUGE-L while being $31\times$ faster. On the reasoning task of Sudoku, NCM outperforms autoregressive and diffusion baselines across all difficulty levels, using fewer function evaluations. On the reasoning task of Sudoku, NCM outperforms autoregressive and diffusion baselines across all difficulty levels, using fewer function evaluations. --- ### Disentangling Task-Relevant Latent Dynamics for Reward Modeling Authors: Dayou Li, Jionghao Wang, Peihao Wang, Jiuzhou Lei, Hao Wang, Jichen Chai, Hezhen Hu, Minghui Zheng, Zhangyang Wang, Xin Li, Wenping Wang, Zhiwen Fan Published: 2026-10-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.14159v1 Reward design remains a major bottleneck for reinforcement learning in robotic manipulation. Handcrafted dense rewards can compensate for the limited guidance provided by sparse rewards, but require substantial task-specific reward engineering. Learning rewards from videos provides a scalable, data-driven alternative to manual reward design. However, existing video-based rewards are often computed in entangled visual spaces where task-relevant state changes are confounded with extraneous visual variation. As a result, the learned reward may respond to visual distractors instead of actual task execution. To address this limitation, we propose DiTaR (Disentangling Task-Relevant Latent Dynamics for Reward Modeling), a framework for learning dense rewards from heterogeneous videos. DiTaR learns a continuous task-relevant representation from multi-frame video latents through an asymmetric two-stage procedure that suppresses task-irrelevant visual variation. In the task-relevant latent space, we train a history- and language-conditioned rectified-flow model to capture task dynamics and derive a directional dense reward from temporal changes in dynamics compatibility. Together, these components enable reward modeling directly over task-relevant dynamics rather than generic visual variation. DiTaR substantially improves policy learning on MetaWorld-v3 and ManiSkill over video-based reward baselines, and transfers to real-world offline RL through reward relabeling. Reward analyses further show that DiTaR provides more reliable rewards. --- ### Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability Authors: Kuan Zhang, Yukun Chen, Zhihao Yang, Yue Su, Xiangnan Wu, Zirong Chen, Run Luo, Tao Tan, Yinhe Zheng, Yiming Li Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.14158v1 Understanding and tracking a dynamic world are fundamental to visual intelligence. Existing video benchmarks provide limited insight into whether models can maintain a coherent understanding of evolving world state. Building such a benchmark from real-world videos is challenging because the underlying world state is partially observable, making annotations hard to obtain. To close this gap, we introduce Video-Arena, a benchmark that turns competitive games into scalable, verifiable tests of how well models understand evolving world states from videos. Specifically, inspired by how humans understand dynamic events, we evaluate spatiotemporal world state understanding and tracking through three task categories: perceiving critical events, interpreting state updates, and tracking the resulting states. Our pipeline can generate videos and aligned reference labels from game records at scale. To keep evaluation affordable and reproducible, we curate a golden set of 180 tasks across 9 games and run evaluations under two protocols: native visual understanding and tool-assisted agentic analysis. The best-performing systems achieve F1 scores of and under the two protocols, respectively. The result highlights that native models struggle to perceive events reliably, while tool-assisted systems improve event recovery but still struggle to interpret state updates and track the resulting states consistently over time. Our project page is in https://videoarena-bench.github.io --- ### OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools Authors: Chenyang Yan, Yingying Zhang, Kanzhi Cheng, Qiushi Sun, Zhengyuan Pan, Zheng Ma, Hang Yan, Yian Wang, Nuo Chen, Jialin Cao, Xingdong Gong, Wenpo Song et al. Published: 2026-10-09 Categories: cs.SE, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2610.14157v1 We introduce OpenMobile-2, a near-frontier mobile agent with fully open training environments and recipes. We make three key advances: (1) Diverse environments with simulated commercial apps: We build MobileGym++, featuring 35 realistic, functionally rich commercial-style apps with cross-app workflows, while preserving full controllability for reset and verification. Together with newly configured apps in Android emulators, this yields a diverse playground spanning over 110 apps. (2) Open training data at scale: Building on this foundation, we curate nearly 12K mobile interaction trajectories for supervised fine-tuning and the largest open collection of verifiable RL training data for mobile agents, comprising over 2K executable tasks with automatic rewards. (3) Hybrid GUI and app-native tool use: We explore an experimental mobile-use setting where apps expose selected functionalities as app-native tools alongside their GUIs, allowing agents to interleave GUI actions and tool calls within a task. We implement this setting in MobileGym++ with over 300 carefully scoped tools across 50+ apps. Additionally, we introduce MobileGym++ Bench for complex, long-horizon commercial mobile scenarios, supporting both GUI-only and hybrid GUI-tool evaluation on a shared task suite. OpenMobile-2 performs competitively across established benchmarks, including AndroidWorld (79.9) and MobileWorld (50.4), while showing promising transfer to real-device mobile use, nearly doubling SPA-Bench performance from 31.9 to 59.6. All resources are available at https://os-copilot.github.io/OpenMobile2-Home/. --- ### Axiom-0: Hierarchical Self-Refinement for Vision-Language-Action Policies Authors: Renbin Shu, Jing Yang, Xiangyuan You, Guolin Qiu, Yufei Xia, Yiming Zhu, Nanjun Dai, Fei Zhang, Feng Wu, Keke Tang Published: 2026-10-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.14155v1 Reliable manipulation requires policies that generalize across tasks, layouts, and object interactions. Vision-language-action (VLA) models combine pretrained multimodal understanding with learned control, but their performance remains limited on unfamiliar task compositions. We present Axiom-0, a VLA policy that addresses both the quality of its representations and their use in action generation through hierarchical self-refinement. Intra-VLM Representation Refinement (IVRR) strengthens selected intermediate features through consistency supervision with learned feature projections during training. VLM-Action Interface Refinement (VAIR) recursively updates the resulting conditioning before action generation. Joint optimization of the supervised VLM layers, VAIR, and the action generator connects the two components. On RoboCasa365, Axiom-0 achieves 62.32% overall success in our evaluation, exceeding the highest published leaderboard score (Paimon-0, 58.1%) by 4.22 percentage points and the Xiaomi-Robotics-1 reference by 4.92 points. Under the evaluated profiling setup, mean action-chunk generation latency increases by 1.7% over Xiaomi-Robotics-1. These results demonstrate improved task completion with modest inference overhead. --- ### TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback Authors: Jingyu Liu, Hao Jiang, Yikang Ding, Huafeng Shi, Xu Yang, Xiaoqiang Liu, Guoxin Zhang, Pengfei Wan, Kun Gai Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.14153v1 Classifier-free guidance (CFG) typically applies a shared scale to all latent tokens, although their velocity predictions evolve differently during sampling. We introduce Trajectory-Adaptive Classifier-Free Guidance (TrajCFG), a training-free method for flow-matching models that adapts token-wise guidance using historical changes in guided velocity direction. TrajCFG maps this feedback to bounded scales, assigning stronger guidance to larger directional changes and weaker guidance to more consistent directions. It combines adjacent-step and interval-normalized longer-span feedback, reusing standard CFG predictions without additional model evaluations. Controlled diagnostics and ablations examine the roles of directional feedback, token-wise allocation, and history-span fusion. Experiments on text-to-video, image-to-video, text-to-audio-video, text-to-image, and image-to-3D generation show improvements over base samplers across multiple backbones. For text-to-video generation, TrajCFG improves VBench Total scores by 0.30-0.75 points over the strongest evaluated baseline on each of three backbones. These results support historical directional feedback as a broadly applicable signal for fine-grained guidance allocation. The project page is available at https://jyliu-98.github.io/trajcfg-project-page/. ---