Computer Vision
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Kevin Qu, Tao Sun, Massimiliano Viola et al. (+5 more)
Modeling articulated objects from sparse
monocular views is challenging because each observation reveals only partial geometry and motion evidence. Most feed-forward methods infer articulation from a single observation and therefore rely heavily on learned category-level shape priors. We present FAMOS, a feed-forward model that predicts movable-part
segmentation and joint parameters from a sparse, unordered set of partial point clouds. Our model jointly reasons over multiple observations and naturally supports a variable number of inputs, including a single view. To aggregate articulation cues across observations, we introduce a Multi-state Articulation
Transformer with alternating state-wise and global
attention. We further propose an observed articulation span objective that supervises the motion range each part exhibits across the input observations, encouraging the model to leverage the full observation set. To overcome the limited scale and diversity of existing
datasets, we introduce a procedural data generator that synthesizes self-annotated assets during training. Experiments on PartNet-Mobility, ACD, and ArtiCraft-10K demonstrate consistent improvements over both feed-forward and optimization-based baselines. Project page: https://kevinqu7.github.io/famos
Read the full abstract ▾
All authors Kevin Qu, Tao Sun, Massimiliano Viola, Liyuan Zhu, Zhizhuo Zhou, Sayan Deb Sarkar, Konrad Schindler, Iro Armeni
Computer Vision
Paint-Anything: Unified Any-Color Control for Image Generation and Editing
Ji Xie, Dewei Zhou, Xinyu Huang et al. (+2 more)
Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and colorization, but often relies on dedicated color representations or specialized inference procedures. Advances in large
language models offer a simpler starting point: even compact models can associate hex values with color semantics. We present Paint-Anything, which learns a shared hex-
prompt interface for generation and editing through object-level color supervision. We develop a data pipeline that constructs Paint-500K from real images through object grounding, perceptual color labeling, and editing-pair synthesis. Since shadows make real-image labels only approximate colors, we complement this supervision with pure-color anchors whose pixels exactly match their paired hex values. These anchors are used only at high-noise timesteps, leaving low-noise training to natural images. We further introduce Any Color
Benchmark (ACBench), comprising ACBench-T2I and ACBench-Edit, to measure object-level hex color fidelity across both tasks. On FLUX.2-4B, Paint-Anything improves ACBench-T2I and ACBench-Edit scores by 85.3% and 28.3%, respectively, relative to the base model, with ablations supporting the training recipe. It also achieves the highest average CompColor score among the compared methods.
Read the full abstract ▾
All authors Ji Xie, Dewei Zhou, Xinyu Huang, Zhennan Chen, Xun Wang
Computer Vision
ERCPMP-Gx: Endoscopic Image and Video Dataset for Morphological, Histopathological, and Genomic Characterization of Colorectal Polyposis
Zahra Ghaffari, Massih Bahar, Mojgan Forootan et al. (+2 more)
Hereditary polyposis syndromes can be precursor lesions to colorectal cancer and are associated with a broad spectrum of extracolonic tumors. Early identification and accurate classification of these syndromes are essential for timely diagnosis, individualized patient management, and targeted surveillance strategies for affected families. However, public endoscopic
datasets are largely organized around the individual sporadic polyp, and none links the polyposis phenotype to histopathology and germline findings at the patient level. Here, we present ERCPMP-Gx, an endoscopic, histopathological, and genomic
dataset developed to support the application of artificial intelligence (AI) in the recognition, characterization, and classification of colorectal polyposis. Most procedures were performed using the Olympus EVIS X1 system with white-light endoscopy (WLE), narrow-band imaging (NBI), magnifying NBI (M-NBI), and NBI with near focus modes, yielding 160 images and accompanying
video clips. Approximately eighty percent of cases represent clinically and/or genetically confirmed hereditary polyposis syndromes (PG), including familial adenomatous polyposis (FAP), Peutz-Jeghers syndrome (PJS), juvenile polyposis syndrome (JPS), and ganglioneuroma syndrome (GNS), while the remaining twenty percent comprise non-hereditary polyps and polyp-mimicking lesions with overlapping morphological features (Non-PG), included to support differential classification. Each released record is linked, where available, to standardized endoscopic annotations, representative histopathology, and clinically reported germline findings, forming an AI-ready, patient-level annotation framework. The
dataset is publicly accessible at Mendeley (https://doi.org/10.17632/nzyfc544bx.2). For the latest updates and further information, readers are referred to the DataBioX website: https://databiox.com.
Read the full abstract ▾
All authors Zahra Ghaffari, Massih Bahar, Mojgan Forootan, Ali Darvishi, Hamidreza Bolhasani
Machine Learning · Cross-listed from physics.comp-ph
How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates?
Pochinapeddi Sai Bhargav, Nithin Somasekharan, Rohit Sunil Kanchi et al. (+2 more)
Pretraining a neural PDE surrogate can reduce the amount of new CFD data needed when geometry or modeled physics changes. However, it remains unclear how different components of distribution shift affect this benefit. We pretrain a surrogate on 254,909 RANS solutions from one airfoil family and fine-tune it on a new family under two target settings with matched freestream ranges: the same Spalart-Allmaras (SA) modeling and SA with added $e^N$ transition modeling. At $N=1000$, the pretrained model matches the accuracy of a model trained from scratch on $3.25\times$ as many samples for the same-SA target, but $2.58\times$ as many for the transition-modeled target. By $N=5000$, this ordering reverses ($1.56\times$ versus $1.86\times$). At $N=1000$, sampling more distinct airfoils lowers error on both targets, but only for the same-SA target is the gain increase larger than the observed draw-to-draw variation ($3.3\times$ to $4.0\times$). These results show that pretraining value depends jointly on target-data budget, target-data coverage, and whether source and target differ in modeled physics.
Read the full abstract ▾
All authors Pochinapeddi Sai Bhargav, Nithin Somasekharan, Rohit Sunil Kanchi, Sicheng He, Shaowu Pan
Software Engineering
Quantifying Overclaiming Propensity in Frontier LLM Agents
Nolan Smyth, Yorguin-Jose Mantilla-Ramos, Pascal Jr Tikeng Notsawo et al. (+6 more)
Frontier coding
agents are increasingly trusted to work autonomously for long periods of time, yet what they actually did is often hard to tell from their final response. We quantify the propensity of such
agents to overclaim task completion, which may mislead the user. We operationalize overclaiming as a final response that reports work that the
agent's own transcript shows it did not do, for example, claiming to have read a file it never opened. This criterion requires no inference about intent and does not depend on whether the delivered work is correct; it asks only whether the reported work was done. We introduce OverclaimBench, an evaluation suite of five file-review scenarios with transcript-based coverage measurements and registered planted defects. We evaluate eight proprietary frontier models in their own production command-line interfaces and four open-weight models under a single fixed harness, and find that 1)
agents fail to read every file they were asked to review in 67.9% of runs; 2) among these incomplete runs,
agents are misleading 80.4% of the time (59-96% per model), either falsely claiming a complete review or leaving the gap undisclosed; 3) requiring delegation to subagents increases coverage, but a large majority of reviews that remain incomplete are still misleading; and 4)
agents that falsely claim a complete review miss planted defects at about 1.8 times the rate of
agents that read every file, showing that claims of completion can conceal substantive failures. Together, these results show that
agents' final responses are not reliable accounts of their actions.
Read the full abstract ▾
All authors Nolan Smyth, Yorguin-Jose Mantilla-Ramos, Pascal Jr Tikeng Notsawo, Saskia Helbling, Alberto Tosato, Mohamed Amine Merzouk, Nouha Dziri, Gauthier Gidel, Tommaso Tosato
Computation and Language
Unifying Models of Intergroup Hostility in Online Discourse
Patrick Gerard, Julia Mendelsohn and Kristina Lerman
Hostile rhetoric toward social groups can normalize exclusion and justify mistreatment, as well as contribute to rising polarization and political violence. Efforts to moderate hostile rhetoric in online
speech draw on foundational theories in social and moral psychology, and political science. However, these theories were developed largely in parallel, often propose different and sometimes conflicting accounts of how hostility develops, and have rarely been tested against each other in real discourse. The result is a fragmented understanding of the rhetorical mechanisms of hostility, without a clear sense of how they appear, and relate to each other, in real-world discourse. Using 2.86 million posts from TikTok, Truth Social, and Twitter/X during the 2024 U.S. presidential election, we model the mechanisms of six foundational theories of intergroup hostility – boundary construction, threat construction, scapegoating, negative evaluation, dehumanization, and action orientation – within a common empirical framework to recover the broader organization of intergroup hostility rhetoric. Structurally, we find that boundary construction and threat construction anchor the system; temporally, we find that these mechanisms tend to follow a regular ordering: boundary construction, derogation, and action orientation tend to appear early; dehumanization and threat construction later; scapegoating latest. Mapping how these theoretical frameworks actually manifest in discourse bridges longstanding divisions across social science traditions and presents computational social science with a clearer empirical foundation for modeling intergroup hostility rhetoric beyond single-label detection.
Read the full abstract ▾
Machine Learning
Score Centering Stabilizes Off-policy Reinforcement Learning
Martin Marek and Max Ryabinin
Reinforcement learning (RL) of large
language models is notoriously sensitive to small differences between training and inference engines, often referred to as the training-inference mismatch (TIM). However, completely eliminating TIM is impractical, as it would come at a major cost to rollout efficiency. In this paper, we show that the instability of RL under TIM is primarily caused by drift: a persistent bias between training and inference engines that accumulates with every training step. We derive an additive "score centering" correction term that stabilizes RL under TIM by canceling drift. When training models from 0.6B to 30B parameters, score centering alone matches or outperforms methods based on importance sampling under quantization, with the gap growing as the mismatch becomes more severe. Because the correction is additive, score centering also composes with importance sampling – their composition outperforms pure importance-sampling baselines in our staleness experiments.
Read the full abstract ▾
Artificial Intelligence
An Empirical Study of Harness Design for Coding Agents
Run-Ze Fan, Zihao Zhang, Simin Ma et al. (+6 more)
Coding harnesses shape how autonomous coding
agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the effectiveness of individual components unclear. To enable component-level comparisons, we study this question with a lightweight coding harness whose execution loop is fixed while three components are varied: planning, action space, and context management. Across four models evaluated on SWE-Bench Verified and Terminal-Bench 2.1, we evaluate 176 matched settings spanning five context-management strategies, four context-window budgets, and targeted ablations of planning and action space. We find that: (1) Context management becomes increasingly valuable as the context-window budget tightens, with most of its benefit coming from preventing context-overflow failures. (2) Staging rule-based elision before LLM-based summarization provides the strongest overall efficiency among the context-management strategies, whereas making elided content recoverable adds machinery that models rarely use and yields no accuracy gain. (3) Planning shifts from an accuracy scaffold for weaker models to a cost saver for stronger models, with little change in accuracy. (4) Predefined tools improve performance for models with weaker bash proficiency, whereas bash-capable models can operate effectively with a bash-only interface and achieve substantially lower cost, especially on command-line-centric tasks. Trajectory-level analysis explains these effects: context management extends execution trajectories without substantially altering
agent behavior, planning changes where trajectories stop, and the action space changes the granularity at which code is written. These findings inform model- and budget-aware harness design and provide a modular framework for evaluating future harness components.
Read the full abstract ▾
All authors Run-Ze Fan, Zihao Zhang, Simin Ma, Yebowen Hu, Shouju Wang, Kaiqiang Song, Fei Liu, Hamed Zamani, Xiaoyang Wang
Computation and Language
JEPA-Anything: Learning Predictive Models across Different Worlds
Taoyong Cui, Zhongyao Wang, Xinyue Xu et al. (+10 more)
World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning principle support world modeling across radically different systems? We introduce JEPA-Anything, a domain-agnostic framework based on orthogonal predictive factorization (OPF). Extending joint-
embedding predictive architectures, OPF decomposes latent targets into complementary factors, learns them through dedicated pathways, and recombines them within a shared predictive design. We evaluate JEPA-Anything across seven domains:
vision, biology, clinical trajectories, control, molecular dynamics, physical fields, and weather. Experiments span representation learning, intervention prediction, out-of-distribution generalization, and long-horizon dynamics, including 10 matched dynamics tasks,
forecasting of over 1,000 clinical events, and 100-step molecular rollouts across four systems. Against matched JEPA baselines, JEPA-Anything improves reported metrics on all 10 dynamics tasks and reduces single-intervention prediction error on Interventional Pong by 34.8%. It achieves the lowest one-step and 100-step molecular errors among compared methods in all four systems. Beyond prediction, a factor-nominated biological intervention receives experimental support in
cell co-cultures, patient-derived organoids, tumor fragments, and mice; latent orbital modes recover the Keplerian scaling exponent with a fitted slope of -1.4991. These results support a common factorized predictive principle across heterogeneous worlds, connecting world modeling with intervention and experimentally grounded scientific discovery. Code: https://github.com/Gen-Verse/JEPA-Anything
Read the full abstract ▾
All authors Taoyong Cui, Zhongyao Wang, Xinyue Xu, Weiyang Liu, Zhaochen Yu, Yuying Zhang, Qiang Gao, Mengyue Yang, Wanli Ouyang, Pheng Ann Heng, Yingcheng Wu, Zhenfei Yin, Ling Yang
Data Structures and Algorithms
The Strong Secretary Conjecture is True for Linear Matroids
Kristóf Bérczi, Shaddin Dughmi, Vasilis Livanos et al. (+2 more)
We prove a $1/e$ guarantee for Matroid Secretary on linear matroids: each element of a fixed optimal basis is selected with probability at least $1/e$. This settles the strong secretary
conjecture for this class of matroids. Our result holds both when the matroid is known in advance and when a linear representation is given online. In the known-matroid model, the result extends to fully modular extendable matroids. We also obtain $1/e$ guarantees for a more general model on linear matroids, both when the matroid is known and when its representation is revealed online. In XOS Matroid Secretary,
agents with XOS valuations over the elements arrive in uniformly random order, and the
algorithm must assign each arriving
agent a bundle of elements. The bundles must be pairwise disjoint, and their union must be an independent set of the matroid. We obtain an expected total value of at least $1/e$ times the offline optimum. This model contains Group Matroid Secretary, in which the elements are adversarially partitioned into groups that arrive in uniformly random order, and the
algorithm selects a subset of each arriving group. For this special case, we select each element of a fixed optimal basis with probability at least $1/e$
Read the full abstract ▾
All authors Kristóf Bérczi, Shaddin Dughmi, Vasilis Livanos, José A. Soto, Victor Verdugo
Data Structures and Algorithms
Metric Weighted Edit Distance: $(3+\varepsilon)$-Approximation in $\widetilde O_\varepsilon(N^{1.6})$ Time
Debarati Das, Evangelos Kipouridis and Tomasz Kociumaka
For every $0 < \varepsilon \le 1$, we give a randomized $(3+\varepsilon)$-approximation to weighted edit distance when the costs form a metric on the alphabet augmented with a gap symbol. For strings of total length $N$, the running time is $\widetilde{O}(N^{8/5}/\varepsilon^{16/5})$, where $\widetilde{O}$ suppresses factors
polynomial in $\log(N/\varepsilon)$. The dependence on $N$ matches that of the fastest known $(3+\varepsilon)$-approximation for unit-cost edit distance. The
algorithm never underestimates the edit distance and achieves the approximation guarantee with inverse-
polynomial failure probability in $N$. The running time bound assumes constant-time exact arithmetic operations and metric queries, and it is independent of the numerical range of the edit costs. We build on three tools: the sampling framework of Chakraborty, Das, Goldenberg, Koucký, and Saks (J. ACM, 2020), with subsequent refinements by Andoni (2020); Kuszmaul's removal of inexpensive characters (ICALP 2019); and Klein's data structure for distances in planar graphs (SODA 2005). Our new ingredients include, among others, a decomposition of one string into pieces of bounded length with highly structured total deletion costs. This decomposition lets us compare all pieces against a small family of substrings of the other string.
Read the full abstract ▾
Machine Learning
PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers
Jiachen Yao, Zi-Siang Hsu, Xi Deng et al. (+5 more)
Generative models are increasingly used to solve scientific inverse problems, but existing evaluations still focus primarily on whether a method can produce a single plausible reconstruction. This is insufficient for ill-posed problems, where multiple solutions may be consistent with the same sparse or noisy observations. In these settings, a method can achieve strong pointwise accuracy while still failing to capture the true posterior through mode collapse, overconfident uncertainty, or averaging incompatible solutions. We introduce PosteriorBench, a
benchmark for evaluating the distributional accuracy of generative inverse solvers. PosteriorBench evaluates four physics-based inverse problems: Darcy flow inversion, Poisson source recovery, carbon capture and storage, and light transport material inference. For each task, we construct high-fidelity reference posteriors using computationally heavy but established procedures such as rejection sampling and Markov chain Monte Carlo, enabling direct assessment of whether solvers recover the full set of solutions rather than the single best sample. We pair these references with a five-metric posterior evaluation suite: posterior-mean error, posterior-standard-deviation error, maximum mean discrepancy, sliced Wasserstein distance, and radially averaged power-spectrum error. These metrics assess pointwise accuracy, marginal uncertainty, distributional
alignment, and global frequency fidelity. The
benchmark spans sparse sensing, low-resolution observations, nonlinear forward models, varying noise levels, and
multimodal priors, with a unified pipeline for distribution matching and uncertainty quantification. Our experiments reveal substantial distribution-matching gaps across current solvers, while showing that neural operators improve resolution robustness, and guidance weights and generation noise are key to posterior-variance calibration.
Read the full abstract ▾
All authors Jiachen Yao, Zi-Siang Hsu, Xi Deng, Aditi Gupta, Xin Ju, Sally M Benson, Gege Wen, Anima Anandkumar
Robotics
StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation
Jinbang Huang, Yuanzhao Hu, Zhiyuan Li et al. (+6 more)
Hierarchical planning frameworks combine skills from multiple
robot control policies for long-horizon task execution, where determining when to terminate the current skill and advance to the next subtask is essential. Existing approaches often rely on pre-designed completion signal checkers that are hard to obtain in real-world execution. Large-scale
vision-
language models (VLMs) offer strong
reasoning capabilities, but their decision boundaries are not inherently aligned with task completion criteria, while cloud deployment and lengthy
reasoning introduce substantial latency, limiting real-time monitoring. We propose StageGuard, an agentic
distillation framework for accurate and efficient stage-transition decisions. StageGuard combines teacher-model
reasoning with demonstration trajectories to generate structured explanations of subtask completion and policy switching. A lightweight student VLM uses these explanations to generate compact self-explanations, which are used for supervised fine-tuning. We evaluate stage-transition prediction on trajectories from two
benchmarks and assess closed-loop task success through integration into hierarchical
robot control on BEHAVIOR-1K, with further validation on real
robots. Results show substantial improvements in stage-transition prediction while supporting efficient online monitoring.
Read the full abstract ▾
All authors Jinbang Huang, Yuanzhao Hu, Zhiyuan Li, Ran Qi, Yixin Xiao, Yangzheng Wu, Tengyue Ba, Zhanguang Zhang, Yingxue Zhang
Game Theory
Mutual Evaluation and Supervision without Peers
Zachary Robertson
This article introduces mutual evaluation of a replicable task worker and a critic that incentivizes truthful reporting, both modeled as strategic
agents. The critic chooses a finite-valued rule that induces an evaluation score on joint report laws. Their common payoff is analyzed through regret relative to the unrestricted critic envelope. The critic rule is distinct from the evaluation score. This class enables a peer-free information elicitation mechanism using conditionally independent replications of a worker on the same task. This replication-loop mechanism implements a type-agreement payoff using same-task replications and new-task samples. In contrast to the peer-prediction and scoring-rule literature, implementations are shown that produce unbiased Pearson and Shannon information scores without requiring peers, a ground-truth reference, or likelihood-ratio estimation. A valid binary critic also can be represented by shared finite type annotations of worker returns. One runtime restriction is that the number of required replicas is random and can depend on the critic rule. Other timing effects, such as commitment and reoptimization, yield distinct incentives, connecting the framework to variational peer prediction. This mechanism class illustrates why strategic considerations matter for both critic and worker
agents.
Read the full abstract ▾
Computation and Language
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Yan Yu, Zhengxi Lu, Yizhou Liu et al. (+7 more)
Multi-turn
agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy
distillation (OPD) to supply dense
token-level supervision from a self-teacher with privileged task skills, letting a skill-free student internalize them. This recipe, however, is undermined by two findings in agentic tasks: privileged information alone does not always make a teacher reliable, and the benefit of teacher supervision is stage-dependent. We therefore propose RetireOPD (Self-Retiring On-Policy
Distillation), which first optimizes a decoupled, skill-conditioned teacher with environment rewards and then trains a skill-free student jointly with RL and OPD. Rather than following a predefined
distillation schedule, RetireOPD adopts Adaptive Retirement: the student drops the teacher on its own once their discrepancy stops shrinking and it reaches a target fraction of the teacher's success rate, after which training proceeds with RL alone. Across Qwen2.5 models from 1.5B to 7B, RetireOPD improves ALFWorld success rate over RL baseline by 14.1% to 18.8% and WebShop accuracy by 11.8% to 19.0%, and surpasses its own skill-conditioned teacher in every setting.
Read the full abstract ▾
All authors Yan Yu, Zhengxi Lu, Yizhou Liu, Yichen Pan, Aozhe Wang, Qipeng Chen, Hua Yang, Wenqi Zhang, Qianglong Chen, Yongliang Shen
Human-Computer Interaction
The Data Hospital: A Workflow-Based Concept for Explainable Research Data Quality Assistance
Lennard Scheurer, Robert Porzel, Vinicius Carrillo Beber et al. (+1 more)
Research data quality is multidimensional and purpose-dependent: it emerges from the interplay of data, intended use, contextual knowledge, documentation, intervention decisions, and traceability. This concept paper presents the Data Hospital, a human-in-the-loop control and interaction model for research data quality. Using a hospital metaphor,
datasets are admitted, contextualized, assessed, reviewed in specialized stations, modified only through approved interventions, validated, documented, and made replayable where interventions are sufficiently specified. The concept combines deterministic profiling and inspectable evidence with optional evidence-bound explanation by Dr. Data and explicit user decisions. Preserved Raw Data and controlled working states separate observation from intervention. The contribution is not a new cleaning or imputation
algorithm, but a ten-stage workflow that makes assessability, uncertainty, intervention authority, provenance, and process reproducibility visible. The prototype is an implementation-backed demonstrator rather than a released research artifact and illustrates selected parts of the concept through representational standardization, imputation, Patient File documentation, and replay. The paper concludes with a staged agenda for subsequent technical and user-centered evaluation.
Read the full abstract ▾
All authors Lennard Scheurer, Robert Porzel, Vinicius Carrillo Beber, Rainer Malaka
Computation and Language
Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
Sarah Wyer, Sue Black and Noura Al Moubayed
Safety evaluations for large
language models rely on surface-form classifiers that report declining harm scores across model generations. We provide evidence that this methodology is systematically incomplete: explicit discriminatory content is transformed rather than removed. We call this harm laundering. Analysing 450,000 gender-directed completions across 15 models spanning GPT-2 through to GPT-5 (OpenAI GPT lineage; three demographic conditions), we show that sexual violence clusters prevalent in GPT-2 women-directed output disappear by GPT-4, while men-directed completions gain positive representational territory (caregiving, emotional range, ally identity) that women-directed completions do not. The pattern is most visible at GPT-5: Topic~5 (1,997~documents) frames breast cancer as a men's rights debate, while zero equivalent clusters appear in women-directed output. Three independent classifiers score this content as non-toxic. Sentiment scores invert at GPT-4: early models demean women; later models over-correct. Topic diversity in women-directed completions falls 36% relative to men at the GPT-4
alignment boundary (W/M~$= 0.58$, from $0.91$ at GPT-2). REGARD representational harm disparity correlates with release date ($\rho = +0.55$, $p = .034$) while Detoxify does not ($\rho = -0.23$, $p = .42$): toxicity scores fall as representational harm grows. We formalise harm laundering as a three-criteria test and provide a three-stage detection protocol applicable to any generative model. Within the OpenAI GPT lineage, toxicity score reduction is not a sufficient proxy for harm reduction.
Read the full abstract ▾
Robotics
GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies
Xin Chen, Sen Chen, Yujuan Ding et al. (+5 more)
Action chunking is widely used for action generation and execution in
Vision-
Language-Action (VLA) policies, yet existing approaches commonly use a fixed action horizon. During a rollout, different task stages may require different levels of action continuity, control precision, and closed-loop feedback, making a fixed horizon unable to accommodate changing control requirements. We propose GeoAAC, a geometry-based adaptive action chunking method for flow-based VLA policies that adjusts the action horizon according to the reliability of the current action prediction. We show that the geometry of Flow Matching denoising trajectories provides process-level information for characterizing prediction reliability, with
geometric variation across action prefixes remaining positively correlated with predictive uncertainty. GeoAAC uses this prefix-wise geometry to construct a horizon-wise
geometric profile and adaptively determine the action horizon from a single generation without additional training. Experiments with GR00T N1.5 and {\pi}0.5 on LIBERO, LIBERO-Pro, RoboCasa365, and real-world manipulation tasks show consistent improvements over fixed-action-horizon baselines and existing adaptive methods, including up to 8.7 percentage points in simulation and an increase in average real-world success rate from 53.3% to 74.4%.
Read the full abstract ▾
All authors Xin Chen, Sen Chen, Yujuan Ding, Jian Liu, Guoqing Wang, Wei Ye, Heng Tao Shen, Yi Bin
Computational Complexity
Srinivasan Arunachalam, Arkopal Dutt, Sabee Grewal et al. (+1 more)
Gowers, Green, Manners, and Tao (Annals '25) recently resolved Marton's
polynomial Freiman-Ruzsa
conjecture. We give an algorithmic counterpart to their result: given uniform sampling and membership-oracle access to a set $A \subseteq \mathbb{F}_2^n$ with doubling constant at most $K$, our
algorithm outputs a subspace of size at most $|A|$ whose $K^{O(1)}$ translates cover $A$. The
algorithm runs in $\textsf{poly}(n,K)$ time. As applications, we obtain
polynomial-time
algorithms for a variety of learning problems, including quadratic Goldreich-Levin, improper agnostic
tomography of stabilizer states, and
tomography of
quantum states with bounded stabilizer extent.
Read the full abstract ▾
All authors Srinivasan Arunachalam, Arkopal Dutt, Sabee Grewal, Aparna Gupte
Numerical Analysis
Sensitivity Calculus and its Numerical Implementation for Multi-D Hyperbolic Balance Laws
Olivia Dreßen, Michael Herty, Adrian Kolb et al. (+1 more)
We investigate the sensitivity of solutions to multi-dimensional scalar balance laws with respect to perturbations of the initial data analytically and numerically. Reliable first-order sensitivity information is essential in gradient-based optimization and inverse problems constrained by
hyperbolic balance laws. In
hyperbolic problems, such perturbations affect both the smooth components of the solution and the locations of shocks. Consequently, classical difference quotients of the solution operator generally fail to converge in $L^1$, even in one space dimension. Although generalized tangent-vector techniques have been developed for one-dimensional problems, extending these ideas to multiple space dimensions is considerably more challenging because it requires a
geometric description of hypersurfaces of discontinuity. We represent perturbations of hypersurfaces of discontinuity by normal displacements and account for the induced variation of the normal direction. This representation yields
evolution equations for the components of a generalized tangent vector. Based on this calculus, we develop a numerical method for computing first-order variations with respect to the initial data. Numerical experiments in two space dimensions confirm the expected first-order accuracy of the resulting approximation.
Read the full abstract ▾
All authors Olivia Dreßen, Michael Herty, Adrian Kolb, Siegfried Müller
Computer Vision
FlowSGS: Improving Flow Priors for Inverse Imaging with Stochastic Interpolants
Tianao Li, Xinhui Qian and Emma Alexander
Flow matching has emerged as the state-of-the-art generative model and has been used for plug-and-play (PnP) priors to solve inverse problems in computational imaging. However, existing flow-based inverse solvers make simplifying approximations in posterior sampling and/or assume linear forward models. In contrast, principled
diffusion-based methods exist but are computationally expensive. To circumvent these problems, we introduce FlowSGS, a flow-based posterior sampling method using Split Gibbs Sampling (SGS) with annealed coupling, and make flow-specific interventions to the prior sampling and annealing steps, theoretically grounded in the
Stochastic Interpolants (SI) framework. Using a novel timestep correction and accelerated warm-up with one-step flow models, our method is faster and more accurate than the state of the art across a range of imaging problems. We demonstrate the first use of flow-based samplers for a nonlinear inverse problem (
Fourier phase
retrieval) and apply one-step flow models to principled
Bayesian inverse imaging.
Read the full abstract ▾
Human-Computer Interaction
Semantic Action Graph: A Shared Representation for Agent Grounding and Human Interpretation of Sports Highlights
Tica Lin, Deepak Chandran, Gauri Jagatap et al. (+4 more)
Generative
agents are increasingly used to select and narrate
video highlights, but they typically operate over unstructured or frame-level representations. Their output is consequently difficult for a viewer to verify and steer toward individual preferences. We present the semantic action graph, a lightweight domain schema that represents a sports match as performer, action, recipient, moment, and state nodes connected by role, temporal, and outcome edges. The schema demonstrates three key properties: 1) connected event sequences, 2) a shared, closed vocabulary, and 3) frame-addressable moments, making it suitable to serve two consumers at once: an agentic pipeline that composes narrated highlights, and a visual interface through which viewers query and inspect the same structure. We instantiate it in SportSAGE, a design probe pairing a four-module highlight pipeline with a graph interface, and report feedback from 12 soccer fans. Participants were satisfied with the quality of the generated highlights and narratives, and used the graph interface to search, navigate, and interpret the match highlights. These results provide early evidence that one small, human-readable schema can ground
agent generation and support human interpretation at the same time.
Read the full abstract ▾
All authors Tica Lin, Deepak Chandran, Gauri Jagatap, Chen Chen, Andrea Fanelli, David Gunawan, Josh Kimball
Machine Learning
Calibrated RF-Fingerprinting Under Interference With Heterogeneous Transmission Protocols
Tariq Abdul-Quddoos, Xiangfang Li and Lijun Qian
Radio Frequency(RF)-Fingerprinting is a spectrum monitoring technique that identifies specific transmitters based on hardware impairments imprinted within the emitted signal. Although widely researched, studies almost exclusively consider scenarios where only one transmitter is emitting at a time, limiting real world applicability. In this work, we further the study of RF-Fingerprinting by considering co-channel interference, with multiple emitted signals interfering with each other, overlapping in time and frequency. Specifically, we formulate this problem as a multi-label classification problem and employ a 1D convolutional neural network (CNN). Furthermore, the models are calibrated such that the confidence thresholds for the label probabilities are derived, with guarantees on the upper bound on the average number of False Negatives, providing a degree of confidence in not missing a true spectrum policy violation. The proposed method is validated using real world data from the POWDER 5G testbed on devices transmitting 802.11a(Wi-Fi), 4G LTE, and 5G NR waveforms. The results show accuracy as high as 97% and as low as 73% after calibration depending on channel conditions. Also calibrating for various average false negatives upper bounds achieves micro recall scores of approximately (1 - calibrated false negatives) with the calibration robust to out-of-distribution interference, demonstrating the potential of the proposed method in a realistic high contention wireless environment
Read the full abstract ▾
Computational Complexity
Efficient Randomized Communication Without Large Monochromatic Rectangles
Haoyu Wang and Pei Wu
In this paper, we construct a total Boolean function with $\widetilde{O}(\log n)$ randomized communication protocol, while any monochromatic rectangle has density at most $O(2^{-\mathrm{poly}(n)})$. As a corollary, it gives the first total function separation for $\mathrm{BPP}\not\subseteq\mathrm{P}^{\mathrm{NP}}$ in the communication world. Inspired by Gavinsky's recent work (arXiv:2608.18784), our construction combines the cheat-sheet framework with fully linear PCPs.
Read the full abstract ▾
Robotics
Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control
Hanchu Zhou, Brendan Lynch, Raman Goyal et al. (+4 more)
World Action Models (WAMs) advance beyond conventional visuomotor policies by jointly predicting future world states and
robot actions, enabling the policy to learn phys- ical dynamics that support effective control. However, recent tactile WAMs often rely on large-scale pretrained generative backbones to capture contact-rich physical dynamics, which limit their inference efficiency and flexible deployment. In this paper, we present Agile-WAM, an agile tactile World Action Model for contact-rich
robot control. Agile-WAM encodes visual and tactile observations into a shared latent that serves as the source of a direct
vision-tactile-to-action flow-matching process, which can jointly generate latent representations of action chunks and future visual/tactile latents. A key observation is that
vision and tactile signals evolve at inherently different timescales: adjacent visual frames are often highly similar, whereas tactile signals can change abruptly upon contact. We therefore introduce multi-horizon
multimodal prediction in Agile-WAM, which provides supervision for visual latent at a larger temporal offset while predicting the tactile latent in the next frame to capture fine-grained contact dynamics. Across nine simulated and five real-world contact-rich ma- nipulation tasks, Agile-WAM demonstrates strong and robust performance, outperforming the strongest baseline in success rate while maintaining low inference latency. In particular, in five real-world experiments, Agile-WAM yields a relative gain of 29.4% in overall success rates while achieving inference latency of 11.9 ms. These results demonstrate that
multimodal WAM can be achieved with an agile architecture suitable for precise and high-frequency
robot control. More details are available on our project page.
Read the full abstract ▾
All authors Hanchu Zhou, Brendan Lynch, Raman Goyal, Dechen Gao, Begum Kasap, Boqi Zhao, Junshan Zhang
Artificial Intelligence · Cross-listed from stat.ML
Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation
Sho Kawano, Zehang Richard Li and Paul A. Parker
Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as
benchmark task types or conversation types in deployed
agents. Exhaustive testing is expensive, so evaluation rests on a sample of labeled units. We treat the evaluation set as a finite population and seek accurate point and interval estimates of each domain mean. Direct
estimators, including prediction-powered inference (PPI), use only a domain's own labels and are imprecise where labels are few. Small area estimation addresses this problem, and we build on it to develop an integrated workflow for estimation and validation. For estimation, we propose prediction-powered smoothing (PP-S), a
Bayesian model fit to each domain's prediction-powered estimate, with an extension that borrows strength across a reporting taxonomy (PP-TS). For validation, we derive a new, approximately unbiased design-based cross-validation score for choosing among direct and smoothed
estimators. We study a curated
benchmark with verifiable grading and deployed
agent traffic graded by humans, each with every outcome observed. In both, the proposed
estimators improve on the direct
estimators in point and interval estimation, with near-nominal coverage. At the same sampling budget, our score selects as well as an independent validation sample does and estimates the selected
estimator's error far more accurately.
Read the full abstract ▾
Robotics
OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher
Damiano Da Col, Maximilian Igl, Peter Karkus et al. (+5 more)
As scaling pre-training data alone yields diminishing returns, post-training is becoming increasingly important across physical AI domains such as autonomous driving. End-to-end driving policies are pre-trained in open loop with behavior cloning on human demonstrations. However, compounding errors during closed-loop deployment can take the vehicle outside the training data distribution, increasing the risk of safety-critical incidents. Closed-loop post-training can mitigate this risk but requires costly simulation for sensor-based policies. We propose OPTED (on-policy fine-tuning for end-to-end driving) which decouples reinforcement learning from the post-training of the end-to-end policy: a privileged teacher is trained using RL on vectorized inputs (HD-map and bounding boxes). This teacher then provides supervision to the pre-trained student during closed-loop post-training. We apply OPTED to two camera-based models, TransFuser and VaVAM, and fine-tune them in AlpaSim, using neural reconstructions (3DGS) of real driving logs. Driving scores increase by factors of 1.6$\times$ and 9.5$\times$, respectively. In controlled experiments OPTED matches closed-loop performance with approximately three orders of magnitude fewer simulator interactions than direct RL post-training, while staying closer to the human prior. Project page: https://01dami23.github.io/opted/
Read the full abstract ▾
All authors Damiano Da Col, Maximilian Igl, Peter Karkus, Kashyap Chitta, Boris Ivanovic, Marco Pavone, Konrad Schindler, Christos Sakaridis
Artificial Intelligence
RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
Mingxuan Zhang, Xiaowen Wang, Anupma Sharan et al. (+4 more)
Effective troubleshooting
agents in enterprise customer support depend on retrieving actionable guidance from similar historical cases, yet existing
retrieval-augmented generation (RAG) systems treat support cases as static documents and overlook their multi-stage, stateful nature. We introduce RAFT (
Retrieval-Augmented Framework for Troubleshooting
Agents), a stateful RAG framework that abstracts each closed historical case into a directed chain of timeline entries and retrieves at the entry level, surfacing cases whose intermediate states match the active case and returning the parent-case trajectory anchored at the matched state; an optional case-level graph links cases through a configurable similarity representation. We evaluate this
retrieval layer directly, which, unlike evaluating a full
agent system, requires no production deployment. Because public multi-stage troubleshooting data is extremely rare, we pair a synthetic
benchmark built from Microsoft Learn Windows Server documentation with real Apache Jira issues carrying human-created duplicate labels. RAFT improves Case Hit over vanilla RAG and GraphRAG baselines at every stage of case progress, with statistically significant gains over the strongest baseline; the Jira results provide directional evidence that the advantage transfers to real case histories. We release our
benchmark, implementation, and the Apache Jira evaluation set.
Read the full abstract ▾
All authors Mingxuan Zhang, Xiaowen Wang, Anupma Sharan, Zhengyi Chen, Chenyu Diana Zhang, Shanshan Yang, Chittibabu Pacharu
Systems and Control
Large Language Models as Falsifiers for Cyber-Physical Systems
Ali ArjomandBigdeli, Jiawei Zhou and Stanley Bak
Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Logic (STL), falsification can be formulated as a robustness optimization problem, traditionally tackled with black-box search
algorithms. In parallel, large
language models (LLMs) have recently emerged as surprisingly effective optimizers when coupled with iterative prompting. In this work, we connect these ideas and introduce LLM-Falsifier, an LLM-based approach that falsifies specifications by minimizing the STL robustness degree. Beyond generic
prompt-based optimization, our key idea is to expose the LLM to semantic information that is natural for
language models but absent from standard numerical optimizers, including natural-
language input and output names, output trajectories, and critical-time witnesses for the minimum robustness value. These additions enable smarter and more sample-efficient robustness search. On the ARCH-COMP falsification
benchmarks, LLM-Falsifier is shown to outperform existing falsification tools based on a range of optimization paradigms, from surrogate-based and
Bayesian optimization to search-based testing, on 14 of 21 specifications when measured by the average number of simulations required to find a counterexample.
Read the full abstract ▾
Computation and Language
Anton Xue, Litu Rout, Aditya Akella et al. (+3 more)
Adapting a pretrained autoregressive (AR) model is a cost-efficient route to a
diffusion language model (DLM). While nearly all such adaptations start from a full-
attention transformer, AR modeling has shifted toward hybrid architectures that interleave
attention and RNN layers. This creates an obstacle for adaptation: unlike
attention, RNNs are structurally causal and nontrivial to bidirectionalize. Despite this mismatch, we investigate whether such backbones can become effective DLMs by adapting Qwen3.5 at 0.8B, 2B, 4B, and 9B scales, yielding the dQwen3.5 family. We find that hybrid backbones can be efficient starting points for adaptation: against a full-
attention control, the hybrid reaches a given training loss in about half the
tokens. Across scales, dQwen3.5 resembles full-
attention DLMs in any-order decoding behavior and performs strongly under parallel decoding.
Read the full abstract ▾
All authors Anton Xue, Litu Rout, Aditya Akella, Adam Klivans, Sujay Sanghavi, Sanjay Shakkottai