Robotics
Behaviora - A Conceptual Architecture for External and Internal Behavior of Robots and Agents
Gote Nyman
Behaviora is a preliminary conceptual architecture for representing
agent and
robot behavior, external and internal alike, in an addressable form. A behaving
robot or
agent performs a Behavior Episode composed of episode components, which can be derived from behavior taxonomies (BTax) and assigned persistent identifiers. We denote these identifiers as IoB (Internet of Behaviors) Addresses. A Behavior Episode specifies what the system does, while a Style Profile (SP) specifies how this behavior is expressed. Style can communicate characteristics of the actor and qualities such as competence and cultural manners. An Experience Profile (EP) represents behaviorally relevant internal state that modulates the execution of an Episode. Finally, a Behavior Compiler maps these behavioral representations to platform-specific actions. We use a primitive touching arm model to show these components and their relations. External Behavior is a result of addressable movements and their styles. Internal Behavior is represented through the same episodic principle and can be rendered as inner
speech. Sensing, perception and complex task contexts have not been included in the present implementation, although a conceptual place is reserved for them.
Read the full abstract ▾
Multiagent Systems
KITE: Scaling Jev Population Experiments with Sparse Flagship Calibration
Hengyu Li
KITE queries a typed behavioral kernel once per unique state, then executes populations of any size from the table with event-keyed randomness and common random numbers. An expensive flagship model is reserved for sparse paired anchors that estimate intervention effects. Measured human-model discrepancy is propagated as shared error into every conclusion. Population-experiment cost thus scales with unique states and anchors, while uncertainty is governed by evidence about people rather than Monte Carlo noise. On Epstein experiments with 9,070 participants, anchors covering 1.7% of states reduced effect error by 41% (absolute MAE reduction 0.0125). On 37 held-out SocSci210 experiments, 0.5-1.5% anchor coverage raised captured decision gain from 0.27 to 0.39. The kernel passed content-fidelity criteria in all 15 new countries of a 16-country study. Shared discrepancy yielded retrospective coverage of 93% and 96% at nominal 80% and 90%, versus 29% and 36% from human sampling uncertainty alone. A million
agents executed 20 tabulated steps in 0.9 seconds on a laptop. This architecture offers a route to screening candidate interventions before human trials, multi-country content audits, and uncertainty-aware policy comparison at the cost of a few thousand kernel calls with sparse flagship anchors. Property-specific evidence records connect each use to its validation scope, correction provenance, and uncertainty, making these applications auditable.
Read the full abstract ▾
Computer Vision
ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather
Boying Li, Chang Liu, Britta Ayano Wilde et al. (+4 more)
Unsupervised domain adaptation (UDA) for semantic
segmentation remains challenging under adverse weather conditions because severe appearance changes enlarge the domain gap and degrade the reliability of pseudo labels in the target domain. To address this problem, we propose an Intra-Class Mixing Consistency (ICM) framework that enforces prediction consistency between an intra-class mixed image and its original counterpart. Unlike previous mixing-based consistency methods that combine regions across different images or domains and may introduce unrealistic semantic inconsistencies, ICM performs mixing within the same image and semantic class, preserving realistic semantic layout for consistency regularization. With ICM, we establish a new state-of-the-art performance for clear-to-adverse-weather unsupervised domain adaptation (UDA) in semantic
segmentation. On the Cityscapes $\rightarrow$ ACDC
benchmark, our method achieves 75.7% mIoU, outperforming the previous state of the art by +1.9 pp, demonstrating its effectiveness in mitigating class confusion under challenging environmental conditions. The code is provided in the supplementary material.
Read the full abstract ▾
All authors Boying Li, Chang Liu, Britta Ayano Wilde, György Kovács, Tosin Adewumi, Björn Backe, Hamam Mokayed
Machine Learning
ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
Ming Ma, Yi Zhu, Yiran Zhong et al. (+7 more)
Long-horizon agentic tasks require an
agent to modify an environment through a sequence of tool calls, with success determined by the final state. The standard recipe assigns a single outcome reward at the end and compares trajectories sampled for the same task. As a result, a group with no successful trajectory yields no training signal, failed attempts cannot be told apart by how close they came to completion, and turns that advance the task receive the same credit as turns that only query the environment. Prior work refines the unit of comparison from the trajectory to the step, or trains a reward model to supply intermediate signal: the former still derives its signal from final success alone, and the latter estimates it with a model. We observe that the acceptance checks that decide success can also be run on intermediate states, so progress is as verifiable as the outcome. We propose ProCredit, which turns this verified progress into credit: it reruns the acceptance checks after each turn, rewards the turn by its change in progress, and uses these rewards to assign credit both across attempts at the same task and across the turns within a trajectory. Starting from Qwen3.5 base models at three scales on AppWorld, ProCredit outperforms outcome-reward baselines and progress-based baselines in task completion rate at every scale on both test sets, exceeding the strongest outcome-reward baseline by 4.1 percentage points at 4B, and results in a second environment show the same direction of improvement. Ablations show that adding the final progress to the trajectory score alone does not improve performance: the gain comes from crediting progress to the turn where it occurs.
Read the full abstract ▾
All authors Ming Ma, Yi Zhu, Yiran Zhong, Feida Zhu, Chonghan Liu, Pengkun Jiao, Qichao Wang, Yanhao Jia, Tianming Yang, Steven Hoi
Cryptography and Security
MDRC: A Deployable State-Recovery Defense for Traffic Signal Control under Sensor Corruption
Mingyuan Li, Chunyu Liu, Xiao Liu et al. (+5 more)
Traffic Signal Control (TSC) is a safety-critical cyber-physical system that relies on real-time sensing. Corrupted observations caused by
adversarial perturbations or sensor failures can propagate from the sensing layer into the controller and degrade traffic efficiency. Existing robust Reinforcement Learning (RL)-based TSC methods often suffer from limited cross-city generalization, high inference latency, and weak recovery under partial observability. We present MDRC (Meta-
Diffusion-based framework for Resilient traffic signal Control against
adversarial attacks and sensor failures), a post-detection state-recovery defense inserted between sensing and control. MDRC reconstructs trustworthy traffic states before they are consumed by the controller. It combines Denoising
Diffusion Implicit Models (DDIM) for efficient state recovery with Reptile meta-learning for a transferable initialization across cities. We provide an optimization-based view of the DDIM recovery dynamics and establish a recovery-error bound that separates score approximation, numerical discretization, and initialization mismatch. Across seven real-world-derived CityFlow
benchmarks, MDRC reduces Average Travel Time by 6.77% under
stochastic and policy-aware attacks and by 12.75% under structured sensor loss, while improving state-recovery fidelity. We further evaluate 3,600 seconds of real roadside measurements with 50% of detector channels disabled and integrate MDRC into a hardware-in-the-loop traffic-signal stack. Over a 9.16-hour run with 32,389 sensing/control cycles, the system achieves 99.79% decision availability, produces no out-of-plan recommendations, and requires approximately 38 ms of component-wise processing per one-second control interval.
Read the full abstract ▾
All authors Mingyuan Li, Chunyu Liu, Xiao Liu, Yanna Jiang, Guangsheng Yu, Xu Wang, Wei Ni, Ren Ping Liu
Robotics
Jingyang Liu, Sujia Yao, Jiayuan Gu et al. (+1 more)
Long-horizon
navigation requires an
agent to revise its intermediate objectives as evidence accumulates. Full visual histories are costly to process, while compact summaries may omit details needed to reconsider earlier decisions. We introduce NavProbe, a hierarchical zero-shot
navigation agent that couples a dynamic subgoal agenda with active evidence
retrieval. A compact index links summaries of visited places, transitions, and landmarks to their visual and
geometric records. When the current context is insufficient, a task executive retrieves targeted evidence to generate, revise, or resolve subgoals. Reusable conclusions are used to update the index, and a skill policy converts the revised task state into parameterized
navigation actions. NavProbe achieves 71.7% SR and 55.8% SPL on R2R-CE and 55.3% SR and 38.6% SPL on RxR-CE, outperforming strong zero-shot baselines. It also achieves 79.3% SR on HM3D-v2 ObjectNav, with qualitative real-
robot demonstrations illustrating physical deployment. Code is available at https://github.com/liujy25/NavProbe.
Read the full abstract ▾
All authors Jingyang Liu, Sujia Yao, Jiayuan Gu, Lan Xu
Computer Vision
M3D-Net: Hierarchical Coordination of Spatial Context, Feature Reuse, and Differential Attention for Mammography Classification
Zheng Yu, Xinhang Li, Jiabao Gao et al. (+2 more)
Breast image classification requires local detail and global tissue context, yet these cues can weaken as representations deepen. We present M3D-Net, a mammography encoder that hierarchically coordinates multi-scale coordinate
attention, bounded dynamic feature reuse, and differential
attention through resolution-aware operator placement. Within-stage
retrieval preserves access to earlier features, coordinate-aware aggregation integrates local and global context, and differential
attention operates at coarse resolutions. We evaluate image-only classification on AISSLab mammography and an adapted image–clinical model on BrEaST ultrasound. Against EdgeNeXt, RepViT, and TransXNet, the proposed implementations achieve the highest recorded validation accuracy and late-training accuracy, with the lowest endpoint cross-
entropy loss. Validation accuracies reach 97.78% and 80.39%, respectively. These results support further evaluation of hierarchical coordination across breast imaging settings; repeated-seed, component-controlled, and independent evaluations remain necessary.
Read the full abstract ▾
All authors Zheng Yu, Xinhang Li, Jiabao Gao, Boyang Wang, Xiang Li
Numerical Analysis
Component-wise accurate fixed point iterations for computing the square root of a singular M-matrix
Dario Andrea Bini, Bruno Iannazzo, Beatrice Meini et al. (+1 more)
We analyze two fixed-point iterations for computing the principal square root of an M-
matrix $A$. Although these iterations, with customary initialization, converge sublinearly when $A$ is a singular M-
matrix, we show that, under suitable mild conditions on the initial approximation, the convergence is linear. Moreover, we provide component-wise accurate versions of these iterations, which allow us to approximate the principal square root with a component-wise relative error uniformly bounded by a small multiple of the machine precision. Numerical experiments demonstrating the effectiveness of the proposed
algorithms for certain classes of problems are presented.
Read the full abstract ▾
All authors Dario Andrea Bini, Bruno Iannazzo, Beatrice Meini, Jie Meng
Information Theory
Block Erasure Channel and Block z-Channel with Bounded Decoders and Finite Blocklength
Bin Han, Yao Zhu, Rafael F. Schaefer et al. (+5 more)
Block error rate is a standard metric in finite blocklength (FBL) communication, yet it conflates two qualitatively different failure modes: block confusions, where the decoder selects a wrong codeword, and block erasures, where it declares a loss. Higher-layer protocols treat physical-layer failures as erasures, but this cross-layer assumption lacks FBL justification. We derive a rigorous upper bound and a companion lower-side estimate on the block confusion probability (BLCP) and block erasure probability (BLEP) for bounded-distance decoders over additive white Gaussian noise (AWGN) channels at finite blocklength, recasting the coding problem as a
geometric sphere packing one. We analyze the sensitivity of these bounds to blocklength and signalto-noise ratio, characterize the envelope of the upper bound, and derive closed-form Chernoff approximations. Extending the model to idle transmission blocks, we bound the false alarm probability (FAP) and show that a block z-channel abstraction emerges from the bounded-decoding geometry. Numerical results confirm that confusion and false alarm probabilities lie far below the error rate constraint, providing quantitative physicallayer support for the block erasure channel and block z-channel abstractions assumed in protocol design.
Read the full abstract ▾
All authors Bin Han, Yao Zhu, Rafael F. Schaefer, Wenwen Chen, Giuseppe Caire, Anke Schmeink, H. Vincent Poor, Hans D. Schotten
Artificial Intelligence
Not What You Meant: Can LLMs Follow a Specified Negation Semantics?
Qiming Bao, Agnieszka Mensfelt, Michael J. Witbrock et al. (+1 more)
Negation does not carry a uniform interpretation across domains. In legal, regulatory, and medical
reasoning, the intended interpretation depends on the reading in force – open- versus closed-world, two- versus three-valued, and credulous versus skeptical. We study which reading of negation large
language models adopt by default and whether they can override that preference when a different reading is explicitly specified. To this end, we introduce NAFBench, a procedural generator of solver-certified instances spanning four semantic viewpoints: SLDNF, well-founded semantics (WFS), and credulous and skeptical
reasoning under stable-model semantics. The generator emits ground normal logic programs with controlled depth, width, and cycle structure. Each program is solved under all four viewpoints using SWI-Prolog, a well-founded semantics solver, and clingo, yielding up to four divergent labels. The programs are then verbalized into natural
language under multiple framings and rule orderings that leave the answer invariant. The results expose a consistent gap. Across open-source models, following a specified negation semantics remains unsolved: the strongest models score 59–74% across the four semantic viewpoints, while the weakest score 31–67%. All models are order-sensitive on more than half of logically identical rule shufflings, while the two weaker models frequently overcommit on well-founded "undefined." Two frontier models reach 100% on the main fixed-complexity evaluation set, and a third, o4-mini, is near-perfect, falling only to 81% on well-founded "undefined." Delegating
reasoning to a solver, fine-tuning on certified traces, or forcing an explicit three-valued verdict each partly closes the gap.
Read the full abstract ▾
All authors Qiming Bao, Agnieszka Mensfelt, Michael J. Witbrock, Kostas Stathis
Sound · Cross-listed from eess.AS
The Second MLC-SLM Challenge: Multilingual Conversational Speech Diarization, Recognition, and Understanding
Bingshen Mu, Mingchen Shao, Zhennan Lin et al. (+7 more)
This paper summarizes the Interspeech2026 second
Multilingual Conversational
Speech Language Model (MLC-SLM) Challenge, which aims to advance the development of effective
multilingual conversational
speech language models. We describe the two challenge tasks:
multilingual conversational
speech diarization and recognition, and
multilingual conversational
speech understanding, together with the released real-world conversational
speech dataset, evaluation protocols, and baseline systems. The challenge attracted 91 teams worldwide, with 704 valid leaderboard results and 14 technical reports across the two tasks. Based on the participating systems, we summarize representative approaches and distill practical insights into
multilingual conversational
speech recognition and understanding to support future research in the community.
Read the full abstract ▾
All authors Bingshen Mu, Mingchen Shao, Zhennan Lin, Liumeng Xue, Hexin Liu, Lei Xie, Eng Siong Chng, Longshuai Xiao, Qiangze Feng, Daliang Wang
Robotics
Behavior-Aligned Action Tokenization for Robot Policy Learning
Junbo Dong, Ze Chen, Zhendong Xie et al. (+5 more)
Autoregressive
robot policies learn continuous control by predicting discrete action
tokens from observations. Different tasks often share local motions, yet behavioral correspondence across demonstrations receives limited explicit supervision in existing tokenizers. Motions with different timing can therefore lack a shared representation despite following similar patterns. We propose Behavior-Aligned Action Tokenization (BAAT), which uses soft dynamic time warping (Soft-DTW) to select corresponding action chunks and aligns their quantized coordinates jointly with reconstruction. This objective encourages similar motions across tasks to occupy nearby quantized representations while retaining executable action detail. A history-conditioned
diffusion decoder reconstructs continuous action chunks from these
tokens, and a downstream autoregressive policy learns to predict them. We evaluate BAAT on selected tasks from three simulation
benchmarks and two real
robot tasks. BAAT achieves a mean simulation success rate of approximately 45.2%, exceeding OAT by approximately 7.2 percentage points. In the controlled LIBERO-All
alignment ablation, policy success rises from 70.2% to 79.0% while trajectory replay success decreases. These results support behavioral correspondence as supervision for organizing shared motion structure in action tokenizers and improving downstream
robot policy learning.
Read the full abstract ▾
All authors Junbo Dong, Ze Chen, Zhendong Xie, Junjie Li, Lixin Xu, Xuemin Chi, Yiming Song, Zhaoyuan Ma
Numerical Analysis · Cross-listed from physics.flu-dyn
Concentration of Stationary Measures onto Large Scales in the Fast-Advection Limit of the Stochastically Forced Two-Dimensional Navier-Stokes Equations
Tobias Rohner
We investigate the fast-advection limit ($\varepsilon \to 0$) of the stochastically forced two-dimensional incompressible Navier-Stokes equations on the
torus. Numerical simulations are performed at resolution $N = 128$ for four different forcing shells on both the square
torus and a thin
torus, with the advection parameter $\varepsilon$ varied over approximately one decade. We find that the stationary distributions become increasingly concentrated on the lowest
Fourier modes as $\varepsilon \to 0$, with the energy-to-enstrophy ratio $E/\Omega$ and the fraction $R$ of enstrophy in the lowest modes both increasing monotonically. At finite $\varepsilon$ the degree of concentration depends on the forcing shell through the effective spectral value $B_1/B_0$, in agreement with the condensation bound of Sznitman and Widmayer. Linear extrapolation to $\varepsilon = 0$ suggests that the limiting values may be forcing-independent, with $B_1/B_0$ governing only the rate of convergence. The same qualitative behaviour persists on the thin
torus.
Read the full abstract ▾
Computer Vision
NV-Reason-CT: 3D Visual Language Model for CT Analysis
Andriy Myronenko, Dong Yang, Yucheng Tang et al. (+15 more)
We present NV-Reason-CT, a generative
vision–
language model for chest and abdominal CT combining native 3D visual encoding with radiologist-guided
reasoning. The model couples a native 3D
vision transformer with a
language model, passing all visual
tokens and their explicit 3D coordinates into
language decoding without further spatial
token merging. This retains volumetric spatial information within the
vision encoder and through the
language model's positional encoding during joint processing with text. We train on a curated corpus of approximately 550,000
multimodal instruction examples from 70,111 unique CT image inputs, combining standardized reports, abnormality-focused and anatomy-specific questions, multi-turn interactions, and radiologist-authored
reasoning from recorded and transcribed expert CT interpretations. Expert annotations provide direct supervision and guide additional report-grounded synthetic
reasoning. End-to-end supervised fine-tuning (SFT) is followed by Group Relative Policy Optimization (GRPO), with verifiable rewards over chest and abdominal abnormality sets. The model supports abnormality classification, report generation, and interactive
reasoning with reviewable observations, differential diagnoses, and uncertainty. Evaluation spans public CT
benchmarks and a held-out NIH cohort. On CT-RATE, NV-Reason-CT achieves a macro-F1 of 0.614 and macro-AUROC of 0.871 without a task-specific classification head; generated reports achieve a report-derived macro-F1 of 0.592. In a preliminary study with expert radiologists, AI-assisted review received favorable confidence ratings and was associated with a 50% reduction in average reported interpretation and reporting time. We release the model and training code to support reproducible research on explainable AI for volumetric medical imaging.
Read the full abstract ▾
All authors Andriy Myronenko, Dong Yang, Yucheng Tang, Baris Turkbey, Benjamin Simon, Stephanie Harmon, Rikhil Makwana, Mariam Aboian, Sena Azamat, Ibrahim Ethem Hamamci, Sezgin Er, Bjoern Menze, Zongwei Zhou, Wenxuan Li, Marc Edgar, Yufan He, Pengfei Guo, Daguang Xu
Computation and Language
Uncheatable Eval: Dynamic Compression-Based Evaluation of Language Models
Kaifeng Tan, Yudong Li and Linlin Shen
Modern large
language models are pretrained on massive
datasets, making it difficult to prevent
benchmark data from entering their training sets and undermining the reliability of evaluation results. Reliable evaluation is particularly challenging for base models, whose limited instruction-following ability complicates task-based assessment. We introduce Uncheatable Eval, a dynamic
benchmark that regularly collects newly published text to evaluate base
language models and reduce the risk of data contamination. Drawing on the relationship between a model's predictive ability and its ability to compress data losslessly, we use compression rate to evaluate how well models predict new text. We evaluate 80 models across 14 text categories, study how compression changes with context length, and examine the correlation between compression rate and zero-shot MMLU accuracy. Our results yield three main findings: (1) compression performance follows a consistent scaling trend with model size; (2)
attention-based, hybrid, and recurrent models differ in how their compression performance changes as more context becomes available; and (3) lower compression rates are strongly associated with higher zero-shot MMLU accuracy. Code is available at https://github.com/Jellyfish042/uncheatable_eval.
Read the full abstract ▾
Computer Vision
Know-Your-Scene (KYS)-SLAM: Hierarchical Semantic-Motion Priors for Feature Matching in Stereo Visual SLAM
Preeti Chatterjee, Jin Lu, Jin Sun et al. (+1 more)
Stereo visual SLAM systems built on local descriptors suffer from semantic ambiguity, instance-level confusion, and independently moving objects, each corrupting data association and accumulating as trajectory drift. Prevailing semantic and dynamic SLAM methods address this through binary feature rejection, sacrificing correspondence density for outlier suppression. We contend that contextual implausibility is better expressed as a graded quantity than an exclusion criterion. We present Know-Your-Scene (KYS)-SLAM, a modular extension of ORB-SLAM3 that supplants feature rejection with continuous correspondence modulation. The contribution is the reframing of contextual evidence as correspondence cost, applied within feature matching and leaving the
geometric backend unmodified. Each keypoint is augmented with semantic, panoptic, and motion priors fused through a hierarchical compatibility formulation, in which semantic class and instance identity enforce structural plausibility while a zero-shot motion score down-weights features on independently moving objects. That score comes from a training-free module fitting a depth-aware ego-motion model to background optical flow and classifying panoptic segments via self-calibrating, coverage-aware thresholds, so only segments with sufficient motion evidence are penalized and static structure is left unpenalized. Penalizing correspondences rather than discarding them preserves the
geometric support bundle adjustment depends on. Under one fixed configuration, no coefficient retuned per sequence or
dataset, KYS-SLAM reduces per-sequence ATE RMSE by 17.4% on outdoor KITTI and 27.7% on indoor EuRoC across 21 stereo sequences with no regressions, and by 6.6% on dynamic subsets of KITTI Tracking and 17.8%, up to 31.2%, on Virtual KITTI 2 – cross-domain transfer across outdoor driving, indoor flight, and synthetic imagery under one set of constants.
Read the full abstract ▾
All authors Preeti Chatterjee, Jin Lu, Jin Sun, Suchendra M. Bhandarkar
Distributed Computing · Cross-listed from math.OC
Distributed Stochastic Approximation Algorithms and Heavy-Tailed Age of Information
Adrian Redder, Arunselvan Ramaswamy and Holger Karl
Algorithms in multi-
agent systems such as
federated learning, mobile robotic swarming, and consensus control can be designed and analyzed as distributed
stochastic approximation
algorithms. Such
algorithms involve information exchanges between
agents for various computations. The freshness of the information can be quantified using the Age of Information (AoI) metric. Consider robotic teams operating in highly obstructed geographical settings, such as subterranean or dense urban environments. Because of spatial disconnections, AoI has empirically been observed to be heavy-tailed with unbounded moments. However, most analyses assume AoI with bounded moments, creating a gap between theory and practice. To the best of our knowledge, ours is the first analysis under general heavy-tailed AoI with potentially infinite mean. We study the stability (almost sure boundedness of the distributed iterates) and convergence of multi-
agent systems that are strictly dissipative in the scaling limit (system at “infinity”). Examples include most gradient-based and consensus
algorithms under the Robbins-Monro step-size regime.
Read the full abstract ▾
Discrete Mathematics · Cross-listed from math.CO
A New Upper Bound for the Turán Density of the Tetrahedron
Gyeongwon Jeong, Seonghun Park, Seonghyuk Im et al. (+2 more)
We prove that the Turán density of the tetrahedron $K_4^{(3)}$ satisfies $\pi(K_4^{(3)}) \le 14993367693127837/26880000000000000 < 0.557789$, improving Baber's upper bound of $0.5615$ and closing about $62\%$ of the gap to the conjectured value $5/9$. The proof uses an exact seven-vertex flag-
algebra certificate incorporating degree-stationarity from Razborov's differential method. To find the certificate, we combine the established techniques of cutting planes and column generation to optimize jointly over flag families whose types have at most five vertices. We give a complete formal proof of this Turán density bound in Lean 4.
Read the full abstract ▾
All authors Gyeongwon Jeong, Seonghun Park, Seonghyuk Im, Joonkyung Lee, Hongseok Yang
Computer Vision
Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality
Cheng Yuan, Jiawei Shao and Xuelong Li
Under the AI Flow framework, communication networks distribute intelligence across devices, edge servers, and clouds, and computation at the receiver becomes a resource that can substitute for transmitted bits. Generative
video compression (GVC) embodies this exchange by sending compact
tokens with ultra-low bitrate and letting a generative decoder synthesize the
video, yet how much bandwidth savings a unit of decoder compute actually achieves has never been quantified. To fill this vacancy, we model reconstruction quality as a two-factor power law in data rate and decoder compute, which fits measured DISTS of two GVC decoders with a mean error below 3%, and define the information capacity (IC) as the negative logarithmic slope along an iso-quality contour, namely the fraction of rate saved per fractional increase in compute at identical quality. IC is dimensionless and unit-invariant, thus enabling an architecture-agnostic comparison. It forms a field over the operating plane, locating where additional denoising steps are worth their cost. Across five
datasets, the 14B decoder trades more compute for fewer rate about ten times more efficiently than the 1.3B decoder. IC also varies significantly across
datasets, indicating imbalanced performance on the rate-compute trade-off in GVC methods.
Read the full abstract ▾
Artificial Intelligence
WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents
Jingjie Ning, Xueqi Li, Yibo Kong et al. (+1 more)
AI research
agents must predict the effects of computational changes after budgeted experiments. WhatWorkedBench evaluates this experimental understanding through a delivered response surface of configuration scores.
Agents inspect workflow code and buy measurements; exhaustive CPU references score conditional component effects, mean pair interactions, configuration choice, and delivery. The catalog spans 36 task conditions, 30 sources, 8 workflow families, and 1248 indexed configuration records, with 4,206 numerical controls. At eight purchased measurements plus two free anchors, pair-effect ridge selects an exact optimum on 15 of 22 sources; 13 of these cases have at least one conditional-effect error exceeding 10% of the task utility range. Shared-
estimator comparisons measure acquisition and reconstruction on common observations. In a prospective typed study on 12 four-factor sources, DeepSeek Flash submits 12/12 direct tables and gains 0.147 recovery over a Gaussian process (GP) fitted to the same observations. Pro delivers 11/12 artifacts, with an all-attempt GP difference of -0.001 and a delivered-only difference of +0.063. On six prespecified new
agent-evaluation sources, Flash and Pro gains are 0.149 and 0.074. In eight typed six-factor episodes, seven final tables satisfy verified code equivalences. Four fresh
agents pass all six registered rules through named
estimators and deliver consistent tables at 0.682 recovery versus 0.710 for separate direct-table runs. WhatWorkedBench links acquisition, inference, program structure, and delivery.
Read the full abstract ▾
All authors Jingjie Ning, Xueqi Li, Yibo Kong, Dongting Li
Sound
Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound
Akira Takahashi, Chihiro Nagashima, Zhi Zhong et al. (+2 more)
This paper introduces Passing, an interactive audiovisual installation that generates an endless journey from a single continuous monorail-window recording by reconstructing it as a spatiotemporal volume. Rather than replaying the footage linearly, the work resamples its spatial and temporal structure along nonlinear trajectories, producing a continuously passing landscape whose depth, speed, and temporal order become unstable. A camera-based viewer-presence detection system estimates whether a viewer is present in the viewing zone and uses this presence state to influence transitions among rendered
video sequences. The resulting
video stream is fed into SpecMaskFoley, a real-time
video-to-audio synthesis model that generates a synchronized soundscape for the reconfigured image. The model is not used to reconstruct an objectively correct soundtrack, but functions as a speculative listener, proposing a possible auditory interpretation of a world whose conventional spatial and temporal premises have been disrupted. Passing distributes creative agency across the artist, who defines the rules of spacetime reconstruction; the AI model, which interprets the emergent visual flow as sound; and the audience, whose
embodied presence influences the audiovisual trajectory. Through this structure, the work investigates how authorship and listening may be negotiated among human intention, machine inference, and audience interpretation. Artwork page: https://ryufurusawa.com/passing
Read the full abstract ▾
All authors Akira Takahashi, Chihiro Nagashima, Zhi Zhong, Shusuke Takahashi, Yuki Mitsufuji
Discrete Mathematics · Cross-listed from math.CO
Constructing longer snakes and improved asymptotic bounds in hypercubes
Tom Taylor
We give snakes that are longer than the previous best known in dimensions 13 through 20 and improve the general lower bound for every dimension $d \geq 21$. Our explicit snakes reach 371,711 edges in dimension 20. Twenty compatible paths in that cube allow generalisation to give snakes of length at least $(17/48)2^d$ for every $d \geq 21$. Their controlled overlaps allow copies to be joined across the layers of a larger cube without creating shortcuts. Four additional paths give the same bound for coils. We explain the construction, prove the joining rule, and then count its length. The finite paths and their required intersections are independently verifiable.
Read the full abstract ▾
Distributed Computing
CerebroSim: Scalable Whole-Brain Simulator at 100-Trillion-Synapse Scale on the LineShine Supercomputer
Guangnan Feng, Tianxiang Lyu, Hao Huang et al. (+4 more)
Building executable
brain models is essential for moving neuroscience from description to mechanism and prediction. Human-
brain-scale spiking simulation is constrained by highly irregular communication, multithreaded spike delivery, and the
memory cost of sparse connectivity. We present CerebroSim, a scalable framework for whole-
brain simulation. CerebroSim combines Delay-aware Spike Broadcast (DSB) for aggregated delay-aware communication, Race-free Synaptic Dynamics Computation (RSDC) for lock/atomic-free multithreaded delivery with HBM-aware optimization, and Sparse Synapse Storage Compression (3SC) for compact indexing with deterministic synapse regeneration. Using a model derived from
magnetic resonance imaging and
diffusion-weighted imaging, CerebroSim simulates 86 billion
neurons and 100 trillion synapses on 18,432 nodes across 11.2 million cores of the LineShine Supercomputer, sustaining 24.44 PFlop/s, 91% weak-scaling efficiency, and 94% strong-scaling efficiency. This capability makes biologically constrained human-
brain models practical for mechanistic studies of
brain disorders and controlled in silico testing of intervention hypotheses.
Read the full abstract ▾
All authors Guangnan Feng, Tianxiang Lyu, Hao Huang, Honghui Liang, Jingjing Li, Zhiguang Chen, Yutong Lu
Robotics
RoboCafé in the Open: Interaction Continuity in Long-Term Public Human-Robot Interaction
Kaitlynn Taylor Pineda, Kush Kumar Kushwaha, Jie Wang et al. (+5 more)
As
robots remain in public spaces over extended periods, they must maintain interaction continuity by preserving and correctly applying context as people, encounters, and circumstances change. To study interaction continuity in long-term public human-
robot interactions, we developed RoboCafé, an autonomous conversational coffee
robot designed to support repeated interactions through task-aware dialogue, real-time
multimodal perception, and
memory of prior encounters. We deployed RoboCafé for 12 days in a university building, where it received 148 orders. The deployment involved repeat customers, passersby, changing groups, and back-to-back orders that repeatedly crossed the boundaries assumed by the system's order-centered interaction model. We found that successful interaction continuity requires a
robot to determine who is currently present, which prior context belongs to whom, where interactions begin and end, and whether its representation of an interaction matches what is occurring in the physical world. From these observations, we derive four system design requirements for maintaining interaction continuity in longitudinal public human-
robot interactions: contextual interaction state, persistent person grounding, explicit interaction life-cycle management, and interaction observability.
Read the full abstract ▾
All authors Kaitlynn Taylor Pineda, Kush Kumar Kushwaha, Jie Wang, Jiaming Du, Anvii Mishra, Emilie Basu Suri, Angela Guo, Chien-Ming Huang
Machine Learning
Learning Where to Look: A Shared Relative-Alignment Module for Time-Series Forecasting and PPG-to-Vital-Sign Reconstruction
Ragamayi Puli and Shunya Nagashima
PPG-to-vital-sign reconstruction turns a wrist-worn photoplethysmogram into clinical waveforms such as the ECG. Long-horizon multivariate time-series
forecasting underpins planning in energy, weather, and traffic. Both generate a target sequence from a condition sequence, and current models hard-code where each target position reads it, as a same-position copy or seasonal recurrence, so neither transfers between tasks. We propose ROOSTER, one conditioning module that handles vital-sign reconstruction and time-series
forecasting alike by learning this correspondence. Its core is a periodic-comb bias over the target-condition offset whose center, period, and sharpness are learned per head, so one module settles on the identity
alignment or a seasonal lag and reports which it found. On vital-sign reconstruction from PPG, ROOSTER outperformed the published baselines on four heart-rate and respiratory-rate
benchmarks. On multivariate time-series
forecasting, it achieved the best horizon-averaged MSE on four
benchmarks and outperformed the
forecasting model it extends on 20 of 24
dataset-horizon settings under matched three-seed training. An ablation study indicated that the relative bias, not content matching, carried the
alignment.
Read the full abstract ▾
Computer Vision
DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video
Taeyoun Kwon, Seungjin Kim, Hyeonyu Kim et al. (+1 more)
Recent
video-
language models increasingly adopt hybrid architectures that interleave linear and full
attention layers for efficient long-context processing. While the recurrent state of linear
attention remains fixed in size, the KV cache of full
attention continues to grow with the
video stream, making eviction necessary under a bounded
memory budget. The key challenge in streaming is that eviction must occur before the question arrives, so what to retain has to be decided without the question. Existing eviction methods derive
token scores from the KV cache itself, using position,
attention, or key-value representations, and
attention-based scores further require proxy queries or extra computation. Hybrid backbones offer another source of signal. In gated-delta linear
attention, the recurrent state is updated by the residual between each input and what can already be retrieved from the state, so its change over a chunk of frames reflects how much new information the chunk brings. We propose DeltaS, a query-agnostic, training-free method that retains
video chunks inducing larger normalized state change, or state drift. In a controlled comparison with the budget and retention policy held fixed, state drift outperforms position-,
attention-, and key-value-based signals. With a signal costing only 1.9% of the forward pass, DeltaS surpasses the strongest query-agnostic bounded-
memory baseline by 2.1 points on average across six long-
video benchmarks and by 5.6 points on the longest
benchmark. These results suggest that the two
memories of hybrid architectures can work cooperatively. Code is available at https://github.com/MaumAI-Company/DeltaS.
Read the full abstract ▾
All authors Taeyoun Kwon, Seungjin Kim, Hyeonyu Kim, Moon Hwan Kim
Robotics
Collocated Shape Regulation for Soft Robots
Pietro Pustina, Ebrahim Shahabi, Daniel Feliu-Talegon et al. (+2 more)
Controlling the shape of a continuum soft
robot typically requires an accurate dynamic model and actuation of all degrees of freedom. We show that regulating only the actuated coordinates, through collocated shape control, achieves provably stable convergence of those coordinates and, under an explicit compatibility condition, of the entire
robot shape. While collocated control is a cornerstone of high-performance motion control in rigid robotics, extending this formulation to continuum soft
robots has remained challenging due to the complexity of their dynamics. We present the first general framework for collocated control of continuum soft
robots and derive a unified family of controllers, including PD, PID, PsatID, and their counterparts with compensation and cancellation components. The framework unifies existing approaches while introducing new controller designs. In particular, we develop three classes of PD and PID like regulators with local, semi-global, and global stability guarantees, and provide rigorous convergence analyses for each. Extensive experimental validation demonstrates the effectiveness of the proposed methods across different model discretizations and controller parameters. The resulting framework provides practical design guidelines for selecting and implementing controllers with known stability guarantees, without requiring a complete dynamic model of the
robot
Read the full abstract ▾
All authors Pietro Pustina, Ebrahim Shahabi, Daniel Feliu-Talegon, Alessandro De Luca, Cosimo Della Santina
Computer Vision
CereVLA: Cerebellum-Inspired Consequence-Aware Residual Governance for Efficient Vision-Language-Action Execution
Shuai Zeng, Yuxuan Liang, Hangmiao Hu et al. (+4 more)
Action-chunked
vision-
language-action (VLA) policies improve inference efficiency, but limited feedback within committed action chunks can lead to accumulated execution errors. Residual adaptation can correct such deviations without retraining the VLA; however, existing corrections are typically optimized for reference-action consistency without explicitly considering their downstream consequences. To address this limitation, we present Cerebellum-Inspired Consequence-Aware Residual Governance (CereVLA), a unified framework that integrates lightweight residual refinement and predictive consequence evaluation into frozen VLA execution. Corrective actions are first generated by flow-based residual refinement, and their short- and interval-horizon consequences are then evaluated by a recurrent state-space model and a history-aware classifier. Residual corrections predicted to be unfavorable are selectively suppressed by a lightweight governor. Comparisons with state-of-the-art methods on LIBERO-10 and LIBERO-GOAL demonstrate the effectiveness of CereVLA. On SO-101, CereVLA increases task success from 57.5% to 90.0% and reduces mean control steps by 19.6% among successful trials, relative to the frozen SmolVLA baseline.
Read the full abstract ▾
All authors Shuai Zeng, Yuxuan Liang, Hangmiao Hu, Fobao Zhou, Zixiang Wang, Wenxi Hong, Hang Zhao
Robotics
Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs
Iacopo Catalano, Julio A. Placed, Javier Civera et al. (+1 more)
Long-term autonomy in human-populated environments requires anticipating whether and how people will move at times a
robot has not yet observed. Existing representations of pedestrian motion face a tradeoff: they either forecast future activity, reducing each location to a scalar rate, or model the full directional distribution, holding it fixed in time. We present Kairos, a predictive directional-flow
memory that extends a hierarchical 3D scene graph (3DSG) to a 4D scene graph (4DSG). Every observed voxel of the reconstructed geometry stores a directional mixture and a presence rate, and spectral predictors forecast, for any future query time, both the probability that people are present and the full directional distribution of their motion. Pairwise flow dependence between adjacent voxels supports conditional queries, and per-voxel predictive variances yield calibrated credible intervals that tighten as observations accumulate. We evaluate Kairos on three real pedestrian environments: a
robot-collected campus
dataset, a shopping mall, and a station concourse recorded continuously for eleven months. Its learned state remains consistent under loop-closure corrections, and its forecasts are competitive with dedicated occupancy and flow models trained on the full detection stream, although Kairos learns from only the small fraction available to a patrolling
robot. Finally, we validate the representation on a downstream encounter-probability planning task, where plans computed over the Kairos forecasts encounter more people than plans computed over any time-invariant map at an equal success rate. We provide the code at https://github.com/IacopomC/kairos.
Read the full abstract ▾
All authors Iacopo Catalano, Julio A. Placed, Javier Civera, Jorge Peña Queralta
Robotics
A Modular Dual-Arm Robotic Cell for Disassembly and Repair of Industrial Control Electronics
Maximilian Ruhe, Fabian Harlacher, Christian Friedrich et al. (+1 more)
Industrial control electronics such as programmable logic controllers, servo drives and operator panels are routinely repaired in plant maintenance, but were never designed for automated disassembly. This paper presents a modular dual-arm robotic
cell for repair-oriented disassembly, using two collaborative manipulators, interchangeable tools, red-green-blue-depth (RGB-D) and wristlevel perception, force/torque sensing and a
Robot Operating System (ROS) 2- based control with Behavior Tree (BT) execution, teleoperation, digital-twin support and bounded learning-based contact skills. The process is decomposed into sequence planning, symbolic execution with fallbacks, force-limited tool skills, visual condition assessment and demonstration-based adaptation. A CADderived device graph encodes the disassembly order, access constraints, tools, feasible removal directions and verification states and converts them into operation objects for the BT and motion layers. Grounded in three representative devices, the
cell covers screw removal, damaged-fastener fallback, snap-fit opening, connector release, cooperative printed
circuit board (PCB) extraction and condition-based repair decisions. The main contribution is an architecture linking sequence knowledge, perception, verification and force-aware skills through one ROS 2 interface across simulation, teleoperation and real hardware.
Read the full abstract ▾
All authors Maximilian Ruhe, Fabian Harlacher, Christian Friedrich, Martin Kipfmueller