Action
-
Explaining Basketball Shot Classifications with Grad-CAM: An Investigation of Shortcut Reliance with Spatiotemporal Correlations
2026-10-23 20:15:04Hongyi Tian, Robin CohenAbstract
Basketball action recognition is used in high-stakes scenarios to inform such tasks as specialized coaching, yet the evidence used by its deep-learning models is poorly understood. This paper investigates whether there is evidence that an R(2+1)D-18 model trained on the Basketball-51 dataset relies on spurious spatiotemporal correlations when classifying basketball shot outcomes. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to generate spatiotemporal saliency maps, whose faithfulness was evaluated by progressively blurring the most salient pixels. Twenty saliency maps were then visually reviewed for recurring salient regions. Grad-CAM highlighted spatially central regions of clips including the shooter, net, and occasionally the courtside crowd. Blurring interventions were conducted to support these patterns. Blurring the central region resulted in an accuracy of 43.7%, compared to the original test accuracy of 69.3% and random-blurred accuracy of 50.9%. The additional 7.2 percentage-point reduction from central blurring compared to random blurring suggests that the model relies on task-relevant visual regions; this highlights the need for continual audits to ensure trustworthy, equitable sports analytics.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33263
PDF
-
Two Uncertainties Are Not One: Disagreement versus Decision-Risk in Cheap Structured Content Moderation
2026-10-23 20:08:04Karan YadavAbstract
Content moderation compresses a graded, contested human judgment into a binary act (leave up / take down) over billions of items, at a scale where running a frontier LLM on every post is uneconomical. A new class of frozen "System One" models returns typed, calibrated decisions instead of text at ~USD 0.000025 per call and ~100 ms. We run the first independent audit of one such model on 142,658 human-labeled comments, and benchmark it against 14 frontier reasoning models (the GPT-5.x, Claude, Gemini 3, and Grok families) on a shared probe set. Two findings stand out. First, the cheap model is accuracy-competitive: its zero-shot classification AUROC (0.83) is not statistically separable (paired bootstrap, n=56; a failure to reject parity, not proof of equivalence) from 13 of the 14 frontier systems while costing 1-3 orders of magnitude less, and it is no worse calibrated than several of them. Second, "confidence" conflates two uncertainties that come apart: human disagreement (where annotators split on satire and coded language) and decision risk (where the automatic action is costly-wrong). Under an asymmetric moderation loss these call for opposite escalation signals, so no single confidence number serves both. Because the model prices extra questions at nearly zero, decomposing the judgment into parallel sub-questions and reading their spread recovers a human-disagreement signal that the model's native confidence misses -- but this remedy is specific: it helps the weakest, disagreement-blind models and only when the decomposition aligns with the sources of disagreement; a specialist toxicity model and the strongest LLMs do not need it, and the effect is distribution-sensitive. We will release the instrument, the cached runs, and the analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33258
PDF
-
Causal-based approaches to explain and learn from self-extension - A review
2026-10-23 19:29:32Rebeca Marfil, Pablo Bustos, Antonio BanderaAbstract
The last decades have seen a revolution in autonomous robotics. Deep learning approaches and their hardware implementations have made it possible to endow robots with extraordinary perceptual capabilities. In addition, they can also benefit from advances in Automated Planning, allowing them to autonomously solve complex tasks. However, on many occasions, the robot still acts without internalising and understanding the reasons behind a perception or an action, beyond an immediate response to a current state of the context. This gap results in limitations that affect its performance, reliability and trustworthiness. Deep learning alone cannot bridge this gap, because the reasons behind behaviour, when it emanates from a model in which the world is a black-box, are not accessible. What is really needed is an underlying architecture based on deeper reasoning. Among other issues, this architecture should enable the robot to generate explanations, allowing people to know why the robot is performing, or has performed, a certain action, or the reasons that may have caused a certain plan failure or perceptual anomaly. Furthermore, when these explanations arise from a cognitive process and are shared, and thus validated, with people, the robot should be able to incorporate these explanations into its knowledge base, and thus use this understanding to improve future behaviour. Our article looks at recent advances in the development of self-aware, self-evolving robots. These robots are designed to provide the necessary explanations to their human counterparts, thereby enhancing their functional capabilities, in the quest to gain their trust.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33227
PDF
-
The Locality Trade-off in Masked Patch Self-Distillation
Abstract
Masked patch self-distillation is a key component of modern vision foundation models, including DINOv2 and DINOv3, yet its implications for local visual information remain unclear. We show that its semantic benefits can coexist with a scale-dependent locality cost. Using two annotation-free diagnostics, we distinguish recoverable local appearance from spatial correspondence. In smaller models, adding iBOT substantially weakens patch correspondence while largely preserving appearance decodability. In larger models, correspondence improves, but pixel and texture evidence becomes less linearly accessible in deep features. Thus, scaling changes the form of the locality cost rather than uniformly eliminating it. Our analysis of Gram anchoring further shows that preserving patch relations does not guarantee simultaneous improvements in both properties. These findings motivate evaluating and designing visual representations around the complementary demands of semantic abstraction, appearance preservation, and spatial correspondence. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33223
PDF
-
Vision Token Pruning via Query-Vision Interaction Decomposition
2026-10-23 19:06:29Harshithanjani Athi, Sravan Kumar Ankireddy, Jianzhong Charlie Zhang, Hyeji KimAbstract
Large vision-language models (VLMs), which process both visual inputs and text queries, incur high inference costs due to the large number of visual tokens, making visual token pruning a natural approach for improving efficiency. Recent work has leveraged query information to guide token selection, often through heuristics derived from attention patterns or token dynamics. However, these approaches do not explicitly exploit the underlying structure of query-vision interactions. We address this gap by observing that the query-vision interaction matrix, naturally induced by the query and key projections already present in transformer attention, is effectively low-rank, with a small number of dominant latent interaction modes capturing query-relevant semantics. Motivated by this observation, we propose Query-Vision Decomposition (QViD), a novel training-free query-aware visual token pruning method that exploits this structure. Extensive experiments on both image and video understanding benchmarks show that QViD consistently improves performance under matched token budgets, with the largest gains appearing under aggressive compression regimes.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33215
PDF
-
Cross-Platform Application Migration to HarmonyOS: An Agentic Pipeline with Artifact-Derived Verification
2026-10-23 18:46:17Ergun Bi\c{c}ici, Mehmet Kaygusuz, Fatih Turan G\"undo\u{g}du, Emre Filiz, \c{C}a\u{g}atay K{\i}z{\i}lda\u{g}, B\"unyamin Eymen Alag\"oz, Emincan \"Ozcan, Sadi \c{C}elik, Tolunay \"Ozt\"urk, Ege Bulut, Said AldemirAbstract
The migration of applications written for a different platforms like Android or iOS to HarmonyOS NEXT requires a complete rewrite in ArkTS. Although LLMs automate the translation of source constructs into ArkTS, syntactic compilation is not enough and functional assurance is a critical open challenge in HarmonyOS NEXT migration. We present HMOS~Migrator, an agentic pipeline that reads an application's source code, generates an ArkTS project, and validates the result by replaying recorded interactions on a real device. We cast the scoring problem as quality estimation without a reference implementation; we score a migration using only the source application's recorded behaviour and the artifacts produced by the pipeline. We define seven weighted metrics, each constructed so that reduced measurement cannot artificially raise the score. Over twelve runs across six open-source applications, the pipeline's structural reproduction is high (completeness \pct{83.3}--\pct{100.0}), while on-device behaviour (\pct{4.3}--\pct{63.1}) and UI fidelity (\pct{21.1}--\pct{63.2}) remain the primary limits. Scores improve steadily over time: $+0.45$~points per day overall ($R^2=0.44$, $p=0.019$) and $+0.47$ over the model-free subset ($R^2=0.39$, $p=0.029$), with corresponding to fit angles of $+8.4^{\circ}$ and $+11.7^{\circ}$ respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33197
PDF
-
Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning
2026-10-23 18:23:49Ardy Haroen, Florian Lorkowski, Samuel Nellessen, Felix Hofst\"atterAbstract
Alignment evaluations aim to assess whether large language models would engage in dangerous misaligned behaviour. Misaligned and evaluation-aware models might engage in alignment faking, where they pursue a hidden goal, but conceal this behaviour when they suspect effective oversight such as during training, evaluation or audited deployment. Such a model might view any prompt-based intervention that aims to reveal latent propensities as part of the evaluation, calling into question the reliability of existing alignment evaluations. Current methods for detecting alignment faking rely on chain-of-thought monitorability, highly realistic environments that reduce evaluation awareness, or mechanistic interventions, all of which are expected to become less reliable for future model generations. We present a method for revealing latent misaligned propensities that does not rely on any of these. We use synthetic document finetuning to teach models that misaligned actions will go undetected whenever certain keywords appear in the prompt. We place alignment-faking model organisms in environments that are clearly identifiable as honeypots and measure how their behaviour changes after finetuning. We observe that finetuning consistently widens the gap in misaligned action rates between prompts with and without the cue, indicating that finetuning allows exposing latent propensities more reliably than purely prompt-based methods. We argue that behavioural methods for detecting alignment faking and related behaviours are critical going forward, as models become more capable and less interpretable. We find that SDF often damages the models' reasoning capabilities and introduce a mitigation based on on-policy distillation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33180
PDF
-
RAIWAY: A Large-Wheeled Bipedal Robot with Contact-Informed Blind Locomotion
2026-10-23 18:12:04Kyungmin Nam, Jiseong Lee, Donghyuk Choi, Jeongsoo Park, Woojin Kim, Jemin HwangboAbstract
We present RAIWAY, an in-house wheeled bipedal robot with 20-inch wheels, together with a contact-informed control approach for rolling locomotion across irregular and discontinuous terrain. Such locomotion is fundamentally contact-dominated, governed by local wheel--terrain interaction that is impractical to instrument directly and depends on more than terrain geometry alone. The proposed framework exploits the contact information available in simulation, distilling multi-contact events into a latent representation. At deployment, the controller infers this representation online from proprioception, requiring no contact sensing. In real-world experiments, the proposed system traverses diverse environments including steep slopes, gravel beds, studded surfaces, and rocky terrain, and demonstrates continuous ascent on the tested outdoor staircases with riser heights up to 15~cm. On our platform, the proposed controller further outperforms baselines without the contact-informed mechanism across challenging indoor and outdoor settings. The video can be found at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33172
PDF
-
World-in-Context: Interactive Video World Modeling with In-Context Conditioning
2026-10-23 18:05:48Harold Haodong Chen, Rui Peng, Rongjin Guo, Lingteng Qiu, Kejie Qiu, Chao Xu, Zilong DongAbstract
Interactive video world models require coordinated control over viewing perspectives, character actions, and camera motion. Existing methods typically leave view modes implicit in text captions, conflate action with camera motion, and inject controls through fragmented architectural pathways that capture interdependencies only indirectly. In this work, we present World-in-Context, an interactive world modeling framework powered by In-Context Conditioning (ICC). Rather than relying on specialized conditioning pathways, World-in-Context unifies view, action, and camera controls into explicit tokens contextualized directly within a shared self-attention space. Our formulation reveals that (i) explicit view tokens disentangle conflicting dynamics and unlock emergent view switching from single-view data, while (ii) action and camera inputs play complementary roles in governing local responsiveness and global stability. To preserve temporal continuity across execution intervals, we further introduce Interaction-Transport RoPE (IT-RoPE), parameterizing temporal attention with accumulated control transitions. On WBench, World-in-Context-5B achieves navigation performance on par with 22B EchoWM ($81.5$ vs. $81.6$) and attains a $93.8\%$ perspective-switching success rate, substantially outperforming existing 5B baselines ($18.8\%$). Controlled analyses further demonstrate compounding advantages of World-in-Context under richer conditioning mixtures, favorable data efficiency, and natural applicability to causal rollouts.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33169
PDF
-
UniAction: Unified Action Conditioning for World Models
2026-10-23 17:59:13Bowen Xue, Zizhang Li, Hong-Xing Yu, Jiajun WuAbstract
Actions that condition world models are highly heterogeneous, and thus existing action-conditioned world models are typically built for individual action types, fragmenting already limited action-annotated data across separate models. We introduce UniAction, a unified action-conditioning framework that represents any action as a sparse set of action elements, each with a discrete semantic identity and a continuous spatiotemporal grounding coordinate. By mapping these coordinates directly into the pretrained video model's native positional space, UniAction allows heterogeneous actions to condition a shared world model within the same spatiotemporal structure. We further introduce cardinality-calibrated attention to address the bias from differing action representation granularities. We evaluate UniAction on four representative action forms: force, camera control, hand pose, and robot pose. UniAction outperforms conditioning alternatives in action following, and a single jointly trained model surpasses the action-specific experts, showing that heterogeneous action data benefit from unified model and joint training.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32977
PDF
-
RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
2026-10-23 17:57:22Xi Chen, Fengqi Hu, Zeyu Shen, Jiaying Xu, Shangding Gu, Pan Xu, Anqi Liu, Laixi ShiAbstract
Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under diverse shifts and disruptions. Existing robust RL algorithms offer a rich set of mechanisms and principles, yet two major barriers limit their broader potential: limited algorithm reusability and an unclear empirical capability boundary. We introduce RobustRLlib, an algorithm-centric library and benchmark that addresses both challenges. It integrates 17 representative robust online, offline, and safe RL algorithms under a unified interface for substantially improved reusability, together with an enhanced evaluation platform spanning diverse real-world shifts and advanced humanoid and vision-language-action tasks. Systematic evaluation over 273 perturbation configurations provides an up-to-date capability map of current robust RL algorithms, revealing where they remain effective and where substantial robustness gaps persist. As an open-source, user-friendly platform, RobustRLlib offers a reproducible and extensible codebase for applying existing methods to new problems and developing new robust RL algorithms.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32971
PDF
-
DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection
2026-10-23 17:56:28Amber Xie, Jiawei Fu, Xiaofeng Guo, Carmelo Sferrazza, Guanya Shi, Haozhi QiAbstract
Collecting high-quality demonstrations remains a central bottleneck for learning dexterous manipulation. Teleoperation records executable robot actions, but it requires a complete robot setup and places the burden of coordinating many finger joints on the operator. Human demonstrations are easier to collect, but their motions must be estimated and retargeted to the robot, and they do not directly provide robot actions. In this paper, we introduce DexPort, a portable data-collection interface for high-DoF robot hands. It uses the same hand hardware for collection and deployment, avoiding a hand embodiment gap, and records both commanded joint targets and measured joint states. Our key observation is that a small set of skills can support a wide range of dexterous tasks. During collection, the operator moves the hand-held interface to specify the robot wrist motion and selects or adjusts skills that coordinate the finger motion. This removes the need to control each joint independently while retaining behaviors such as precise grasping and in-hand manipulation. We collect demonstrations across several real-world tasks and in unstructured environments without a robot arm. We then use behavior cloning to train visuomotor policies directly on the recorded wrist motions and hand commands, without skill labels. We evaluate across 4 tasks: pick-and-place with diverse objects, screwing with in-hand tool use, drawer stowage which requires simultaneous grasp and pulling, and a bimanual scanning task. We collect over 2,500 demonstrations with our portable device, in both laboratory and in-the-wild settings. Across our tasks, we see an improvement from 11% to 64% when using recorded robot commands instead of states, and an improvement from 36% to 78% for task success when using in-the-wild data.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32969
PDF
-
RynnUnify: Towards Unified Embodied Brain
2026-10-23 17:54:07Minghao Zhu, Bohan Hou, Kun Xiang, Zixuan Wang, Yinzhou Tang, Yifei Yang, Zhikai Wang, Tianyi Zhang, Kehan Li, Haoyu Zhao, Siteng Huang, Leigang Qu, Sicong Leng, Dongchi Huang, Mingxiu Chen, Shijian Lu, Yue Wang, Xiaodan Liang, Zhenyu Zeng, Deli Zhao, Chengju Liu, Jianfei Yang, Xin LiAbstract
We introduce RynnUnify, a 16B unified embodied model that combines strong embodied understanding with long-horizon visual planning through interleaved video--language reasoning. With capabilities spanning spatial reasoning, physical prediction, and grounding, RynnUnify connects an understanding of the physical world with visual anticipation of how it evolves across successive subtasks. Building on these capabilities, we further develop an agentic extension through reinforcement learning to selectively use video predictions for reasoning about unobserved states and interaction outcomes. We also develop a world-action extension of the full RynnUnify model, translating its understanding and prediction capabilities into robot control. To evaluate these capabilities, we introduce Rynn-VP and Rynn-GEU for long-horizon visual planning and anticipatory reasoning. Experiments show that RynnUnify achieves the highest average embodied understanding score among the evaluated unified multimodal models and improves the Rynn-VP overall score by 9.75 points over Cosmos 3 Nano. Its agentic extension improves the Rynn-GEU average by 6.0 points over direct reasoning, while the world-action extension achieves 51.5\% success on 20 selected composite RoboCasa365 tasks and 46.7\% average success across three real-robot tasks. Together, these results establish RynnUnify as a shared foundation for embodied understanding, visual planning, and robot control, taking a step toward a unified embodied brain.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32965
PDF
-
Robotic Optical Coherence Tomography-Guided Geometric Modeling of Soft Tissue: 3D Representations for Data-Driven Closed-Loop Shape Control
2026-10-23 17:52:30Chaoyu Zhang, Guangshen Ma, Mark DraelosAbstract
In medical robotics, data-driven soft-tissue shape control requires deforming tissue toward desired morphologies through sequential physical interactions. This challenge is particularly important in microscale manipulation, where localized deformation is difficult to observe, represent, and control, while physics-based models can be computationally expensive and difficult to adapt to realistic environments. Optical coherence tomography (OCT) provides high-resolution volumetric perception of tissue deformation, but target-conditioned control requires effective representations of both observed and desired tissue states. In this work, we introduce an OCT-guided data-driven framework for tissue shape control, learned from user-guided demonstrations and executed with closed-loop OCT feedback. We study full-volume, tissue-masked sparse-volume, and voxelized point-cloud representations, with or without residual conditioning, using deterministic (Explicit) and generative diffusion (Diffusion) policies. Across 12 configurations and 576 phantom rollouts on 3-DoF depth and 6-DoF directional tasks, OCT-derived 3D representations support both Explicit and Diffusion policies, with performance depending on representation and residual conditioning. Residual conditioning reduces directional Shape RMSE from 0.748 to 0.555 mm for full-volume Diffusion, while voxelized point-cloud Explicit with residuals achieves 0.534 mm for depth and 0.443 mm for directional control, with comparable accuracy at intermediate unseen targets and consistent performance across deployments. We further evaluate the framework in 60 ex vivo porcine rollouts, extending to biological tissue with final geometric errors comparable to human demonstrations. These results establish volumetric OCT as current and goal representations for learned closed-loop tissue shape control across deterministic and generative action models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32961
PDF
-
Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox
2026-10-23 17:49:43Federico LuccaAbstract
Personal email agents decide, for every message, what it is, whether it is urgent, whether to draft a reply, create a task, or ignore it. Their error rate is rarely measured: the stored labels were written by the system itself. We present Foyer, a self-hosted personal inbox agent in daily use, and a measurement protocol (stratified sampling, frozen snapshots, thread-grouped splits, pre-registered hypotheses, human labels in the agent's review loop) that yields ground truth before any training. On 739 real Italian/English emails labelled by the owner (231 unbiased, 500 adversarially sampled), we compare nine systems under thread-grouped cross-validation: the production keyword rules, a TF-IDF + logistic-regression baseline, local typed decision models (Tev1, Nimble), a hosted decision model (Nimble v4-max), and hosted generative LLMs (Qwen2.5-7B, Gemma 4 26B/31B). Four results. The production rules score 28% on message type against a 58% majority class: the field shown most prominently carried no information. With ~200 labels, logistic regression has the highest accuracy on every field (type 0.79, urgency 0.74, needs-reply 0.83, is-noise 0.90), though it never predicts the two rarest classes and is statistically tied with Gemma 4 on type; few-shot prompting does not close the gap. The sender's relationship (client, supplier, service) is recovered from other emails of the same contact with 98.6% accuracy where the contact has been seen, and is not inferable from a single message by any model: it belongs in the contact graph, not the prompt. Finally, accuracy is not the product metric: composed into actions, the most accurate system most often ignores emails needing action (18% vs 4% for the best LLM); a cost-chosen threshold on its noise probability halves that rate and makes it the cheapest system.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32955
PDF
-
Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models
2026-10-23 17:40:58Dianye Huang, Jiamei Guo, Yue Zhou, Mingde Li, Yi Xiong, Wei Wang, Nassir Navab, Zhongliang JiangAbstract
Objective: To develop a unified vision-language model for prompt-conditioned quantitative ultrasound measurement that addresses the mismatch between continuous measurement targets and discrete token-based numerical prediction. Methods: This article presents HAD-VLM, a hybrid autoregressive-diffusion framework that combines autoregressive text generation with continuous measurement prediction within a shared backbone. Visual prompt tuning adapts the vision encoder to ultrasound images. A diffusion process predicts a five-component representation comprising caliper endpoint coordinates and measurement length. A post-processing strategy combining the proposed coordinate-length consistency mechanism with ensemble prediction is introduced to refine measurement estimates. We evaluate four echocardiographic measurement tasks on EchoNet-LVH, with additional assessments of medical question answering and X-ray vertebral measurement. Results: HAD-VLM achieves mean absolute errors of 1.36, 2.77, 3.05, and 1.16 mm for IVSd, LVIDd, LVIDs, and LVPWd, respectively, reducing errors by 21.4-37.6\% relative to the Vicuna-based autoregressive baseline. It also outperforms fine-tuned Qwen3-VL and direct MLP regression across all four tasks. Medical question answering performance is preserved on the evaluated dataset. For X-ray vertebral measurement, HAD-VLM reduces mean absolute error from 11.4 to 6.7 pixels. Conclusion: Integrating autoregressive language generation with diffusion-based continuous prediction improves quantitative medical image measurement while retaining prompt-conditioned task flexibility. Significance: HAD-VLM provides a unified approach to combining language interaction with anatomically grounded numerical prediction for quantitative medical image analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32948
PDF
-
Monetizing Intelligence: Advertising and Subscription Design on LLM Platforms
2026-10-23 17:39:42Yuhang Ji, Fasheng Xu, Tianjun FengAbstract
Large language model (LLM) platforms introducing advertising must decide how much capability ad revenue should fund and what consumers should pay to avoid ads. We study a monopolistic platform that jointly chooses costly response quality, advertising intensity, and subscription prices when advertising reduces user value but better service raises advertising returns. Three findings follow. First, when partly ad-supported and ad-free plans coexist, advertising can finance useful service for consumers who receive none under pure subscription. Lower effective quality in middle plans weakens the alternatives available to premium users, allowing higher prices for unchanged ad-free service. Some fully ad-supported users gain utility, while partly ad-supported and ad-free users lose: broader access can coexist with utility polarization. Second, an intermediate advertising cap can maximize consumer surplus by preserving some revenue that finances service while limiting degradation. Third, cheaper compute can raise quality and reduce ad intensity, yet sufficiently large cost reductions can increase aggregate advertising revenue above its initial level because better service raises the value of the remaining advertised interactions. An extension shows how advertising-funded upgrades can bring plans to the same maximum capability and advertising exposure, eliminating the basis for different prices. These results make menu design central to evaluating LLM advertising: the consequences extend beyond users who see ads to the alternatives and prices faced by those who do not.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32945
PDF
-
If at First You Don't Succeed, Backtrack: Lightweight Recovery for Frozen VLAs
2026-10-23 17:35:33Thomas Landeg, Thierry TambeAbstract
Vision-Language-Action (VLA) models perform well on robotic manipulation, yet remain brittle once their own actions carry them into states their training data barely covers. Recovering from such failures usually requires recovery demonstrations, policy retraining, or a separate model at inference time. We introduce Backtrack, a lightweight failure detection and recovery mechanism for frozen VLAs that needs none of these. A small failure prediction head, trained only on outcome-labeled rollouts of the frozen policy, reads the VLA's existing internal representations to estimate whether the current episode will fail. When the predicted failure probability exceeds a threshold, a controller pauses the policy, retraces the arm's recently achieved motion, and hands control back to the unchanged policy so it can retry from an earlier configuration. The head adds only 0.48-0.88% to the policy's parameter count. We evaluate Backtrack on LIBERO with three VLAs spanning two action-generation families: SmolVLA and $\pi$0.5, which use flow-matching action experts, and the autoregressive $\pi$0-FAST. On LIBERO-Long, the suite of long-horizon multi-step tasks and the one on which all three policies fail most often, Backtrack reduces each policy's failure rate by 19-48%, raising success by up to 7.4 percentage points; on the three shorter suites, where control success is already 85-99%, its effect is smaller. On MetaWorld, all twelve controller configurations tested with SmolVLA improve on the unassisted policy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32941
PDF
-
Adaptive Frequency Threshold Byte Pair Encoding for Mixed Natural Language and Structured Symbolic Corpora
2026-10-23 17:21:18Pietro Di Nicco, Lucio La Cava, Andrea TagarelliAbstract
Modern language models rely on subwording tokenization to define the discrete units of input processing, typically using methods like Byte Pair Encoding (BPE) that treat whitespace as a fixed semantic boundary. This design is inherently limited, as many meaningful concepts---including multiword expressions and the structured environments of formal languages like LaTeX---frequently span across whitespaces. While recent superword tokenization methods attempt to address this by relaxing whitespace constraints, they often rely on greedy frequency-driven merging that fails to account for token length or the specific needs of underrepresented domain-specific languages. In this paper, we introduce Adaptive Frequency Threshold Byte Pair Encoding (AdaBPE), a new tokenization method that leverages an adaptive frequent-pattern mining approach. AdaBPE features a twofold dynamicity: it adapts minimum frequency thresholds based on both the length of a candidate token, to prevent favoring frequent short patterns, and its type, to distinguish between general and formal language patterns, using LaTeX as case in point. This allows the model to efficiently allocate vocabulary capacity to domain-specific notations, such as LaTeX, even when they represent a small fraction of the training data. We evaluate AdaBPE across five datasets spanning LaTeX and natural language, showing consistent gains in encoding efficiency and downstream language-model performance on domain-specific content without compromising general-language performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32921
PDF
-
HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training
2026-10-23 17:11:28Xihan Ma, Bo Zhang, Boxiong Li, Yuhan Bao, Ziyue Liu, Yucheng WangAbstract
HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: a compact planner requests future body-point targets, while the frozen controller handles joint-level execution. A learned decoder maps 32-dimensional actions to structured target windows, and measured-state imitation initializes the planner before reinforcement learning. Task learning then refines interaction behavior while reusing the decoder and controller, avoiding the need to relearn whole-body control. This combination keeps task optimization focused on a compact upper policy and supplies an initial behavior before reward-driven exploration. Starting from that available controller, the recipe accounts for about seven minutes of additional training, including reused representation fitting and a single-GPU task run. This excludes controller pretraining, data preparation, evaluation, and search. Simulated boxing experiments and component controls evaluate the resulting behavior and the roles of imitation initialization and the target representation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32909
PDF
