Robotics
Extending the Speed Limit of Quadrupedal Locomotion via Refined Actuator Modeling and Adaptive Command Scheduling
Yucheng Tao, Shaowen Cheng, Guorong Lan et al. (+3 more)
Achieving high-speed locomotion in quadrupedal
robots remains highly challenging, as actuators operate near their physical limits and exhibit pronounced nonlinearities. However, many existing methods neglect actuator nonlinearities and physical constraints during training, leading to a significant sim-to-real gap under highly dynamic motions and limiting achievable performance. To address this issue, we propose a high-speed locomotion framework that reduces sim-to-real discrepancies and stabilizes learning over a wide command distribution. A refined actuator model explicitly captures high-speed voltage coupling and
magnetic saturation, enabling a more accurate representation of the torque-speed envelope. In addition, a reinforcement learning framework incorporating a two-stage curriculum and adaptive command scheduling (ACS) ensures stable training. Experiments on the 36.5 kg quadruped BlackPanther2 (BP2) demonstrate speeds of up to 13.2 m/s on a treadmill and 11.65 m/s outdoors, establishing a new state-of-the-art and, to the best of our knowledge, a world record for quadrupedal
robot locomotion. The results further highlight the importance of accurate actuator modeling in preventing non-physical policy exploitation, and show that ACS improves robustness without sacrificing performance.
Read the full abstract ▾
All authors Yucheng Tao, Shaowen Cheng, Guorong Lan, Yanyan Yuan, Yongbin Jin, Hongtao Wang
Computer Vision
Target-Checked Reliability Score Refinement for Video Question Answering
Guoxiang Ren and Rohitash Chandra
Video-
language models can answer multiple-choice questions with high confidence yet be wrong. We study whether answer-level reliability scores can be improved under target shift without retraining the models or changing their answers. We collect option-probability lists from three fixed
video-
language models under four deterministic
video samplings and represent cross-view changes and cross-model agreement as a response graph. Using a labeled target pilot, we compare the original score, defined as the probability assigned to the chosen answer, with a histogram-based gradient-boosting (HGB) score trained on the development
datasets and a regularized logistic-regression score trained on the target pilot. A candidate replaces the original score only when repeated
video-level checks indicate a positive, stable improvement. We develop this rule on public VideoQA
benchmarks and
Video Hallucination Diagnosis (VHD), a controlled diagnostic
dataset for shared high-confidence errors. Ranking quality is measured by the area under the risk-coverage curve (AURC), where lower is better. On a held-out 963-question HERBench split, the method reduces mean AURC across the three models by 16.64% (95% confidence interval (CI), 12.12 to 22.61%); the smallest model-level gain is 11.39%. On a separate held-out 911-question Perception Test split, the mean reduction is 18.87% (95% CI, 15.43 to 22.14%). For InternVL3.5, the target check retains the original scores. Using the same outputs, the method outperforms seven training-free baselines in mean AURC on both
datasets. It also improves AUROC, reduces calibration error, and lowers the error rate at 50% coverage by 6.50 and 6.58 percentage points.
Read the full abstract ▾
Computer Vision
Zhangxuan Gu, Haoxing Chen, Qi Qin et al. (+17 more)
Diffusion large
language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive for latency-sensitive applications. GUI
agents represent a natural testbed for this paradigm, as they must repeatedly perceive screen states and emit structured, spatially grounded actions in real time. However, whether dLLMs can be extended into capable
multimodal GUI
agents while preserving their parallel decoding advantage remains an open question. We present LLaDA-UI, a 16.7B-parameter MoE-based, block-wise
diffusion vision-
language GUI
agent. LLaDA-UI follows a two-stage training pipeline: general
multimodal pre-training aligns a native-resolution
vision encoder with the LLaDA2.0-mini-base
diffusion language backbone, followed by GUI-
agent supervised fine-tuning on diverse mobile, desktop, web, and grounding data. Across widely adopted grounding
benchmarks and
navigation benchmarks spanning multiple platforms, LLaDA-UI substantially outperforms Qwen2.5-VL-7B and surpasses Qwen3-VL-8B on four of six reported GUI
benchmarks. These results establish block-wise
diffusion as a practical generative paradigm for
multimodal GUI
agents.
Read the full abstract ▾
All authors Zhangxuan Gu, Haoxing Chen, Qi Qin, Yi Xin, Kai Gan, Lin Liu, Long Cui, Xiaomei Wang, Beitong Zhou, Yunzhu Zhang, Zhengwen Zeng, Changlong Gao, Weizhi Chen, Rongchao Zhang, Haoyuan Wu, Shuheng Shen, Changhua Meng, Weiqiang Wang, Jianguo Li, Zhenzhong Lan
Machine Learning
Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale
Vaibhav Singh, Pierre-André Noël, Torsten Scholak et al. (+2 more)
Diffusion language models decode
tokens in parallel, but their bidirectional denoiser rules out the naive key–value (KV) cache behind fast autoregressive inference. Block
diffusion restores caching by decoding block-by-block, and the block caches deployed on it so far are tied to
attention: O(L)in
memory and, if used as training-free retrofits, only an approximation of the model's computation. Both constraints can be overcome: sequence mixers that summarize finalized blocks into a reusable state support block caching, and the corresponding block-causal training objective makes the cache exact. We study this recipe at scale, pretraining three 3B block-
diffusion denoisers (
attention, mamba, and hybrid) on 300B
tokens under one single-frontier objective and decoding all three through a single cached interface. Only the state-space cache is O(1) in sequence length: its
memory and per-step latency stay constant at any context length, while an
attention cache remains O(L). At 256k
tokens (where
attention has grown to 82GB and 29 ms/step), the Mamba cache delivers 4.3x lower latency, 11x less
memory, and 2.6x higher single-stream throughput; and because that footprint is constant it scales with batch as well, reaching 14x the aggregate throughput, where
attention cannot run beyond a single stream. The same linear-state bias lets the Mamba and hybrid backbones keep retrieving out to 8-16x their training length, whereas
attention's
retrieval collapses at 2x, at no measured quality cost.
Read the full abstract ▾
All authors Vaibhav Singh, Pierre-André Noël, Torsten Scholak, Eugene Belilovsky, Oleksiy Ostapenko
Machine Learning
DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning
Wenrui Xu, Anas Enanaa and Keshab K. Parhi
Learning robust representations for time-series signals under noise and distribution shifts remains challenging, especially in clinical applications such as electroencephalogram (
EEG) and electrocardiogram (ECG) analysis. We propose
Diffusion-Conditioned Representation
Alignment (DCRA), a training framework that repurposes the forward
diffusion process as a structured corruption scheduler for representation learning. Different from conventional augmentation and consistency-based methods that rely on independently sampled perturbations, DCRA introduces a structured corruption trajectory via the
diffusion forward process, which enables continuous and controlled representation
evolution across noise levels. We introduce a feature-level consistency objective that aligns representations across noise levels while preserving class-discriminative structure. This mechanism promotes structure-preserving consistency, which enables smooth and semantically coherent feature trajectories in latent space. The proposed framework is encoder-agnostic and can be integrated with state space models and
Transformer architectures. The seizure detection experiments on the CHB-MIT
EEG dataset show that DCRA consistently improves performance under multiple noise conditions and achieves higher sensitivity at low false-positive rates. Analysis reveals that DCRA produces more balanced and structured representations compared to baseline and
diffusion-only models. These findings highlight the benefit of combining structured corruption with representation
alignment for robust time-series learning.
Read the full abstract ▾
Networking
Assured AI-Native Network Control Loops: State of the Art, Research Challenges and the Missing Runtime Assurance Layer
Bartosz Belter and Mariusz Głąbowski
The
evolution towards autonomous and AI-native telecommunication networks is transforming network control from predefined automation towards distributed and intelligent decision-making. Advances in closed-loop automation, O-RAN, Network Digital Twins, AI-driven orchestration, and autonomous
agents enable multiple specialized control functions to operate concurrently across network domains and timescales. This introduces a system-level assurance challenge: individually acceptable decisions may interact through shared resources and network state, while changes in their operational context may invalidate assumptions under which they were evaluated. This paper presents a state-of-the-art review of AI-native network control, focusing on the composition and runtime assurance of autonomous control loops. It examines closed-loop and zero-touch automation, intelligent controllers, Network Digital Twins, AI-driven orchestration, autonomous
agents, trustworthy AI, and runtime assurance. The analysis shows that these directions provide important foundations for autonomous operation but lack a unified mechanism for assuring heterogeneous control loops whose decisions depend on shared and dynamically changing network state. To address this gap, the paper identifies dependency-aware runtime assurance as a research direction for assured composition of AI-native network control loops. The proposed perspective associates decisions with assumptions and dependencies on which their validity relies, monitors changes that may invalidate accepted decisions, and supports runtime resolution of concurrent control interactions. A telecom use case and an initial architecture and formal model illustrate the concept and identify open challenges in dependency representation, runtime validation, conflict resolution, latency-aware assurance, and experimental evaluation.
Read the full abstract ▾
Machine Learning
Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration
Yuning Wang, Iman Azimi, Amir M. Rahmani et al. (+1 more)
Mobile sensing enables longitudinal monitoring of behavioral and physiological patterns in everyday settings. However, accurate prediction remains challenging in small-cohort health-sensing studies, where task-specific outcome supervision is limited relative to heterogeneous sensing data. Interpretability is also important, as model outputs should reflect meaningful behavioral and physiological patterns rather than predictive scores alone. We develop a Concept-Integrated
Transformer (CIT) with LLM-guided concept supervision for explainable prediction from mobile sensing data. CIT uses a pretrained large
language model to generate baseline-aware concept abnormality targets with confidence weights without manual concept annotation. Across two longitudinal
datasets, CIT achieves the highest F1 score on AFFECT (0.756) and ties for the highest on a PHQ-9
dataset (0.765). The learned concept scores also reveal interpretable behavioral and physiological patterns; in AFFECT, sleep quantity and quality show the clearest difference between high and low negative affect groups. These findings support LLM-guided concept integration for accurate and interpretable prediction in small-cohort mobile sensing studies.
Read the full abstract ▾
All authors Yuning Wang, Iman Azimi, Amir M. Rahmani, Pasi Liljeberg
Mathematical Software · Cross-listed from q-bio.QM
PyFLI: A Python Library for Simulation, Parameter Estimation, and Benchmarking in Fluorescence Lifetime Imaging
Vikas Pandey, Ismail Erbas, Margarida Barroso et al. (+2 more)
Fluorescence lifetime imaging (FLI) measures the temporal decay of fluorescence after excitation and provides quantitative information about a fluorophore's local environment and molecular interactions. Depending on the fluorophore and experimental design, lifetime can report changes associated with pH, oxygenation, cellular metabolism, and Forster resonance energy transfer. These properties make FLI useful across microscopy, biophysics, biomedical optics, and preclinical imaging, where the same type of molecular contrast can be studied across different biological scales. FLI measurements, however, are acquired with instruments that record fluorescence in different ways. Intensified charge-coupled device (ICCD) cameras, single-
photon avalanche diode (SPAD) arrays, and time-correlated single-
photon counting (TCSPC) systems differ in temporal sampling, data organization, detector noise, instrument response, and file format. Lifetime-estimation methods also make different assumptions about the recorded decay, while learning-based approaches require realistic training and validation data for which the underlying parameters are known. PyFLI is an open-source framework for FLI processing and standardized data simulation. It imports measurements from acquisition systems, simulates labeled data under configurable acquisition and noise conditions, and provides complementary approaches for parameter estimation. These include nonlinear least-squares fitting (NLSF), maximum-likelihood estimation (MLE), phasor analysis, rapid lifetime determination (RLD), Laguerre-based estimation, and optional
Bayesian and deep-learning inference. CPU and GPU processing support image-scale analysis, while reconstruction, visualization, statistical analysis, and cross-software comparison provide tools for evaluating results. PyFLI includes compressed-sensing reconstruction for single-pixel hyperspectral FLI.
Read the full abstract ▾
All authors Vikas Pandey, Ismail Erbas, Margarida Barroso, Stefan Radev, Xavier Intes
Machine Learning
FINESSE: An Agent-Based Simulator and Benchmark Dataset for Multimodal Financial Event Sequences
Tyler Farnan, Benjamin Eng, Adam Abate et al. (+4 more)
Machine learning research in financial services is limited by the scarcity of representative open-source
datasets. Existing resources are often narrowly focused on a single modality or task and fail to reflect the structured,
multimodal, and dynamic nature inherent to many problems in financial services. In this paper, we introduce FINESSE, a Financial Event Sequence Simulation Environment, an
agent-based simulation framework for generating synthetic, structured
datasets composed of multiple interdependent event streams. Each stream corresponds to a distinct financial behavior such as transactions, payments, account status changes, and policy interventions, each with unique action spaces, schemas and variable types. These streams are coupled through
agents' latent evolving states, enabling the simulation of temporally rich interactions. We also introduce FINESSE-Bench, a
benchmark dataset generated by the simulator, supporting four representative tasks: balance
forecasting, transaction fraud detection, missed payment prediction, and next event prediction. We report baseline results using methods from time series
forecasting, event sequence modeling, temporal graphs, and temporal point processes. We release the FINESSE framework, including the simulator and
dataset to accelerate research on structured,
multimodal event sequence modeling challenges in financial services.
Read the full abstract ▾
All authors Tyler Farnan, Benjamin Eng, Adam Abate, Xirui Hou, Rizal Fathony, Nam H. Nguyen, Senthil Kumar
Cryptography and Security
A Survey on Quantum-Safe Cryptographic Mechanisms: Building Blocks and Applications
Ricardo Parizotto, Preeti Yadav, Marcus Freire et al. (+4 more)
The possible emergence of fault-tolerant
quantum computers may enable widely used cryptographic
algorithms to be broken. These
algorithms for public key encryption and digital signatures could be exposed if an efficient
algorithm is employed. This poses a threat to existing infrastructure, motivating the development of mechanisms that can withstand
quantum-computer cybersecurity risks. However, the transition to new security mechanisms is still underway and faces many challenges, including identifying which applications are under threat and implementing agile, scalable migration processes. In this work, we survey the state of the art in
quantum-safe cryptographic mechanisms, existing applications targeting migration, and open challenges. We examine the building blocks commonly used to integrate
quantum-safe mechanisms into existing applications and categorize them by the security mechanisms they employ. Next, we systematically review existing migrations into
quantum-safe schemes and categorize them by application domain, including Telecommunications, the Internet of Things, and Blockchains. Finally, we summarize the challenges that must be addressed to enable a successful migration to
quantum-resistant mechanisms, as well as the motivations for pursuing this migration.
Read the full abstract ▾
All authors Ricardo Parizotto, Preeti Yadav, Marcus Freire, Anderson Tomkelski, Maycon Peixoto, Emmanuel Zambrini Cruzeiro, Israat Haque
Computer Vision · Cross-listed from eess.IV
Seamless Whole Slide Label-Free Virtual Staining
Dou Hoon Kwark, Kianoush Falahkheirkhah, Ji-hun Oh et al. (+3 more)
Label-free virtual staining offers a compelling, non-destructive alternative to standard histopathology; however, its clinical adoption is hindered by the computational bottlenecks inherent to processing gigapixel Whole Slide Images (WSIs). Current deep learning approaches require patch-based inference to avoid
memory constraints, which disrupts global tissue continuity and introduces tiling artifacts–displaying visible seams and color shifts. To address this, we introduce the Consistency
Memory Bank (COMB), a novel label-free virtual staining framework that enforces spatial and channel consistency across tiles without
memory bottlenecks. COMB decouples context storage from computation, utilizing a dynamic
retrieval mechanism to fetch feature representations from adjacent tiles. This enables a
retrieval-based context integration strategy that adopts local padding to resolve spatial discontinuities and neighbor-aware channel
attention to stabilize statistical drift. Further optimized with a sliding window schedule to ensure minimal
memory overhead, our method demonstrates superior performance over state-of-the-art baselines, achieving significant improvements in both perceptual fidelity and tiling consistency, while suggesting its downstream utility in tumor
segmentation. Code is available at https://github.com/dou0000/COMB.
Read the full abstract ▾
All authors Dou Hoon Kwark, Kianoush Falahkheirkhah, Ji-hun Oh, Shirui Luo, Volodymyr Kindratenko, Rohit Bhargava
Sound
Learned Continuous Synthesis of Quadratic Difference Tone Spectra
Esteban Gutiérrez, Behzad Haki, Christopher Haworth et al. (+2 more)
Quadratic difference tones (QDTs) are a species of auditory distortion product in which a "phantom" pure tone, absent from the acoustic signal, is clearly audible to listeners. Exploiting this phenomenon, one can synthesize harmonically rich tones for musical purposes, a technique called Quadratic Difference Tone Spectrum (QDTS) synthesis. Previous works have introduced numerical methods to synthesize QDTS based on the distortion function, which links a target QDTS and an overtone-structured carrier signal. While accurate, these methods were
stochastic and discontinuous, making them difficult to control for musical purposes and effectively limiting them to stationary signals. This paper proposes a neural network-based approach that learns an approximate inverse of the distortion mapping in an autoencoder-like configuration, producing a continuous approximation that addresses prior limitations. Experimental results show that, although slightly less numerically precise, the method is sufficient for perceptual and musical applications. We also implement a real-time version in Max and evaluate its performance. Various sound examples demonstrate its expressive and musical potential. The source code, audio examples, tutorials, and software accompanying this work are available at https://cordutie.github.io/projects/qdts.html
Read the full abstract ▾
All authors Esteban Gutiérrez, Behzad Haki, Christopher Haworth, Xavier Serra, Rodrigo Cádiz
Numerical Analysis
A virtual element method for Kelvin–Voigt viscoelasticity
Utkarsh Rajput, Ankit Kumar, Andres E. Rubiano et al. (+2 more)
Considering the computational advantages of virtual element methods (VEM), this work employs a conforming VEM for the numerical approximation of the Kelvin–Voigt model of viscoelasticity. For clarity and simplicity, we focus on the primal formulation. The spatial discretization is carried out using the virtual element method, while the temporal discretization is handled via the {second-order Crank–Nicolson} scheme. We establish the well-posedness of both the semi-discrete and fully discrete problems and derive a priori error estimates. Several representative numerical examples are presented to validate the theoretical results and to demonstrate the effectiveness of the proposed formulation.
Read the full abstract ▾
All authors Utkarsh Rajput, Ankit Kumar, Andres E. Rubiano, Ricardo Ruiz-Baier, Sarvesh Kumar
Numerical Analysis
Preserving Structure in Variational Data Assimilation of Hyperbolic Conservation Laws via Regularization
Yao Xiao and Anne Gelb
Hyperbolic conservation laws pose a challenging setting for variational data assimilation, since the Gaussian assumption imposes a smoothness that smears jump discontinuities. A sparsity promoting regularization can help to mitigate this problem by incorporating a structural prior into the variational objective. Care must be taken when choosing this prior because it serves to counterbalance both a structurally misspecified background-error covariance, which introduces spurious oscillations over smooth regions, as well as spatially sparse observations, which leave too little data to constrain the state. Moreover, state variables of
hyperbolic conservation laws typically do not have piecewise constant structure, which is an assumption made when using standard sparsity-promoting operators, such as total variation. Indeed the underlying variability of
hyperbolic conservation law solutions are neither known in advance nor fixed. Hence using higher order total variation is also not suitable. Here we introduce a new regularization term for data assimilation, built on the sparsity promoting residual transform that neither commits to a fixed smoothness order nor requires the underlying variability to be known a priori. We solve the resulting nonconvex objective within a three-dimensional variational framework using generalized sparse
Bayesian learning. This approach replaces a global \(\ell _{1}\) penalty with a hierarchical conditional Gaussian prior on the residual transform, where a learned hyper-prior yields location-specific weights attached to each spatial point. Numerical experiments across scalar, shallow-water, and Euler test problems show that this regularization term resolves discontinuities more accurately than total variation, and that its advantage grows as the background-error covariance becomes misspecified and the observations become sparser.
Read the full abstract ▾
Robotics
Planning along Differentiable Charts of Constraint Manifolds with General-Purpose IK Solvers
Thomas Cohn, Seiji Shaw, Harel Biggie et al. (+3 more)
Planning trajectories for
robot manipulators under kinematic equality constraints restricts feasible motions to a measure-zero submanifold of the configuration space, requiring special algorithmic treatment. A promising strategy is parametrizing the set of feasible configurations using analytic inverse kinematics (IK). Bespoke analytic IK functions can be written to be differentiable, a necessary property for gradient-based trajectory optimization. But the vast majority of IK functions are computed by automated meta-solvers like IKFast, and are difficult to modify for differentiability. We present a new approach for computing gradients of analytic IK parameterizations: we leverage the inverse function
theorem to recover the desired gradients from the ordinary forward kinematic Jacobian. Furthermore, we present a least-squares domain extension and an optimization-amenable description of the reachability constraint, which preserves gradient signal outside the reachable workspace. We demonstrate the efficacy of our approach through numerical experiments and downstream tasks, including a hardware demonstration of an RB-Y1 picking up a box and placing it on a table. Project website: https://cohnt.github.io/inverse-function-
theorem-parameterization/
Read the full abstract ▾
All authors Thomas Cohn, Seiji Shaw, Harel Biggie, Travis Manderson, Nicholas Roy, Russ Tedrake
Computation and Language
SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs
Jiacheng Sang, Mengyuan Li, Sanxing Chen et al. (+3 more)
LLM search
agents are often evaluated on final-answer accuracy, overlooking the process. Analyzing a search strategy requires understanding how credible evidence is retrieved to address question constraints. This valuable information is buried in raw search trajectories that are long and difficult to parse. We introduce SearchAtlas, a framework that converts search trajectories into structured graphs whose edges represent how evidence is propagated across the
reasoning trace, from the query that retrieves it to the final answer. Our automated parsing pipeline achieves a mean edge F1 of 86.0% against human-annotated graphs and remains consistent across repeated runs. We analyze five search
agents on three
benchmarks, revealing systematic differences in search scale and evidence aggregation. SearchAtlas exposes fragmented answer support, question constraints that do not reach the answer, and unverified parametric knowledge entering the response. These process failures are strongly associated with incorrect answers, even more so than an LLM judge given either the raw trajectory or the ordered query list, suggesting that the constructed graphs provide useful interpretability. Moreover, an audit of cases in which process-diagnostic scores disagree with final-answer correctness shows that they capture information not reducible to answer accuracy.
Read the full abstract ▾
All authors Jiacheng Sang, Mengyuan Li, Sanxing Chen, Yukun Huang, Yu Feng, Bhuwan Dhingra
Computer Vision
Symmetry-aware super-resolution of crystal orientation maps via invariant latent-space learning
Umang Garg, Warren Zamudio, McLean P. Echlin et al. (+3 more)
Crystal-orientation maps are physical fields defined only up to
crystal symmetry; electron backscatter diffraction (EBSD) resolves them experimentally, but acquisition-time constraints limit spatial resolution. Unlike conventional images, EBSD data lie on the quotient space $\mathrm{SO}(3)/G$, where $G$ is the
crystal-
symmetry group. Standard Euclidean interpolation can therefore mix
symmetry-equivalent representations and blur grain boundaries. We introduce the
Symmetry-Group-Aware Super-Resolution
Attention Network (SG-SRAN), which incorporates
crystal symmetry and boundary preservation by design. A frozen, locally isometric encoder maps equivalent orientations to a common latent representation in which Euclidean distance approximates misorientation. Super-resolution is performed in this space, with each high-resolution
token restricted to a feature-consistent local support to prevent cross-boundary mixing. A dictionary-based decoder then recovers valid orientations. Across FCC and HCP
benchmarks, SG-SRAN matches 15-16 million parameter backbones using only 27-49k trainable parameters, while achieving the lowest p68 errors, highest inverse-pole-figure fidelity, and zero-shot transfer to unseen
alloys.
Read the full abstract ▾
All authors Umang Garg, Warren Zamudio, McLean P. Echlin, Samantha H. Daly, Tresa M. Pollock, B.S. Manjunath
Computation and Language
LLM-Anchored Paralinguistic Enrichment for Alzheimer's Disease Detection
Xiao Wei, Yuqin Lin, Yaru Cao et al. (+6 more)
Speech-based automatic detection of Alzheimer's disease (AD) provides a non-invasive and scalable approach to early cognitive screening. AD affects both lexical-semantic organization and
speech production, including atypical pauses and word elongations. However, existing methods have yet to fully integrate these paralinguistic cues with linguistic content. We propose LLM-Anchored Paralinguistic Enrichment (LAPE), which enriches LLM-derived linguistic representations with paralinguistic cues through three coordinated innovations. The first is prosodic event textualization, which enables the LLM to model pauses and elongations jointly with lexical content by encoding them as explicit markers with bounded duration-aware repetition. The second is lexico-prosodic unitization and chunking, which preserves event identity and magnitude in both modalities by pooling only consecutive word units. The third is text-anchored paralinguistic fusion, which integrates local and utterance-level
speech features by using NormGate to normalize and dynamically scale them relative to text. We evaluate LAPE on ADReSS and ADReSSo using participant-level cross-validation and leave-one-subject-out evaluation. LAPE achieves state-of-the-art performance across all four primary settings. Code will be released upon acceptance.
Read the full abstract ▾
All authors Xiao Wei, Yuqin Lin, Yaru Cao, Jinyu Li, Bin Wen, Kai Li, Yueying Chen, Longbiao Wang, Jianwu Dang
Robotics
ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs
Yizhan Li, Jianxin You, Mengyang Xiong et al. (+5 more)
Reacting to sudden physical hazards (catching a slipping plate, dodging a falling knife) is both a meaningful test of
embodied intelligence and a hard requirement for deploying
multimodal large
language models (MLLMs) as the decision coreof household
robots. Existing evaluations, however, probe intuitive physics passively through question answering over
videos, or target deliberate, long-horizon tasks such as
navigation and rearrangement; none measure whether a model can turn physical understanding into immediate, safety-critical action. We introduce ReactHuman, the first physics-grounded
benchmark for human-like reactive decision-making, in which the evaluated MLLM acts as the
brain of a simulated
humanoid facing sudden household hazards; it spans 17 event families and over 1,000 bit-for-bit reproducible scenes with exact, annotation-free ground truth derived from 240 Hz rigid-body simulation, including
adversarial objects whose appearance contradicts their physics (a foam anvil, a steel apple). We further design a five-metric suite that scores each reaction along three axes: reasonable, safe, and physically grounded. We physically execute every committed plan so that decisions have observable consequences. With this harness we evaluate seven representative MLLMs. Results show that reactive safety is far from solved: models mishandle roughly one hazard in three, act from fixed dispositions rather than the observed scene, trust appearance over motion, and miss interception points at meter scale even when the chosen action is correct; none of these failures shrink with model scale. ReactHuman thus offers both a fine-grained diagnosis and a scalable training signal toward physically grounded, safety-aware
embodied agents. The
benchmark can be found here: https://huggingface.co/
datasets/Alan123/reacthuman-
benchmark-scaled
Read the full abstract ▾
All authors Yizhan Li, Jianxin You, Mengyang Xiong, Yinhuan Chen, Zicheng Zhao, Dekun Wu, Dongqing Zhang, Bang Liu
Computation and Language
Does Linguistic Structure Enrichment Enhance Coherence Assessment? Not With Current Architectures
Victor Mazzotti, Luiz Pereira, Marina Bitencourt dos Santos et al. (+4 more)
Recent advances in large
language models have transformed human-computer interaction. Despite their fluency, these models often produce texts that are grammatically correct but semantically incoherent, containing contradictions or disruptions in logical flow. This work investigates whether enriching text with syntactic and rhetorical information can improve incoherence prediction. Our experiments and analysis show that plain texts achieved higher accuracy because the added information was structurally and syntactically incompatible with the
language model's architecture. Additionally, to demonstrate the practical importance of coherence assessment, we performed zero-shot experiments on a Brazilian disinformation
dataset, suggesting that textual coherence can serve as a proxy for detecting misleading content. Code and models are available at https://github.com/ittozzamV/cohereclassifier.
Read the full abstract ▾
All authors Victor Mazzotti, Luiz Pereira, Marina Bitencourt dos Santos, Helena Maia, Carlos Caetano, Nádia Felix, Sandra Avila
Cryptography and Security
DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents
Asif Pinjari and Mithun Paul Saint-Germain
When an indirect
prompt injection succeeds against an LLM
agent, the compromise is visible in the
agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs three facts: where the attack entered, which steps it corrupted, and whether apparent poison was resisted. Existing systems return either a whole-trace verdict or a single unsafe index. We present DriftNet, a dual-head trajectory
Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection). To our knowledge it is the first supervised detector to produce this joint output. A frozen sentence encoder and four identity-free world features embed each step; the trained trunk, under two million parameters and optimized with a class-weighted joint objective over both heads, needs no access to the
agent's model. On the task-disjoint split of the AgentDrift
benchmark (12,536 trajectories, 71,024 labeled steps), with a 20-configuration sweep bounding hyperparameter sensitivity to 0.011 F1 and the test part evaluated exactly once, DriftNet reaches trajectory-level F1 of 0.983, exact injection-point recovery on 98.7% of attacked trajectories, hijacked-span IoU of 0.979, zero flags on 218 resisted attacks, and 2.9% flags on hard negatives. A surface baseline retrained on the identical split recovers 11.1% of partial hijacks and 17.1% of delayed executions; DriftNet reaches 98.6% and 93.2% while lowering every false-alarm rate. Reading all 26 residual errors shows that most misses trace to trajectories whose labeled injection observation carries no legible instruction, and we report the
benchmark's measured world-identity regularity alongside the results.
Read the full abstract ▾
Game Theory
STV Audit Graphs: A Visual Tool to Measure Election Stability
Edouard Heitzmann
The Single Transferable Vote (STV) is an algorithmic election rule. Round by round, a profile of ranked-choice ballots is reinterpreted to determine which decision to make next, and candidates are seated or eliminated until a full winner set emerges. This algorithmic nature makes STV theoretically more brittle than other election rules: uncertainty about an early round of the election might percolate irreversibly into the rest. For this reason, a generalized non-trivial Risk-Limiting Audit (RLA) framework has remained elusive for STV. Such a framework must concoct a set of null hypotheses, or assertions, whose rejection would bound the probability that the outcome of the election was incorrectly reported. We present audit graphs as a solution to design the assertions needed for RLAs of arbitrary STV elections, as well as quantitatively describe the uncertainty (or lack thereof) of their outcomes. These audit graphs explore election paths that are “close” to the recorded one by considering the alternative decisions the STV
algorithm might have made if a small number of ballots were perturbed.
Read the full abstract ▾
Machine Learning
Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning
Shaddin Dughmi and Alireza F. Pour
We continue the study of relatively smart learning, introduced by Dughmi and Pour (2026), which asks a supervised learner to compete, marginal by marginal, with every distribution-fixed error guarantee soundly certifiable from unlabeled data. They showed that the One-Inclusion Graph (OIG) learner is relatively smart with a quadratic sample-complexity blowup, and that no relatively smart learner can do better, leaving open whether ERM or another natural or tractable learner achieves comparable guarantees. They also left open whether the blowup can be restricted to unlabeled data. Our firs results shows that ERM—and in fact any proper consistent learner—is relatively smart for binary classification in the distribution-free setting. We show that a small certifiable error with $m$ samples implies a similarly small error on the uniform distribution over a random sample of size $O(m^2)$, yielding a cover of size at most $2^{m+1}$ on that sample. This suffices to control the error of proper consistent learners with $O(m^2)$ samples. We then show that semi-supervised relatively smart learning is information-theoretically possible with a quadratic blowup only in unlabeled sample complexity and no blowup in labeled sample complexity. The learner uses a natural generalization of OIG to a leave-most-out transductive problem, where labels of part of a finite pool are revealed and the remaining labels are predicted. Finally, this label efficiency comes at a cost in simplicity and tractability. If the hypothesis class is accessed only through an agnostic ERM oracle, any semi-supervised relatively smart learner with substantially sub-quadratic labeled-sample blowup requires super-polynomially many oracle calls. This holds even when the marginal is given explicitly, and thus also yields an intractability result for distribution-fixed learning that may be of independent interest.
Read the full abstract ▾
Distributed Computing
Navigating Small-World Networks with Distance Predictions
Ladan Kian, Ming Ming Tan and Dariusz Kowalski
The small-world phenomenon was given an algorithmic foundation by Kleinberg, who showed that in an augmented $k$-dimensional
lattice a decentralized greedy
algorithm delivers a message in $O(\log^2 n)$ expected steps. We study predicted-greedy routing, in which a mobile
agent forwarding the message moves at each step to the neighbor minimizing a noisy $(\varepsilon,\delta)$-prediction of its distance to the target, redrawn at every step from an oracle conditioned on the full routing history. Two cases arise from what this
agent can observe. An
agent with the coordinate awareness can still compute
lattice distance exactly, but not graph distance in the shortcut-augmented network, since that depends on the shortcuts of nodes it has not yet visited; given an $(\varepsilon,\delta)$-prediction of graph distance, information the classical model never supplies, it achieves expected delivery time $O(\log n/(1-4k\varepsilon\delta))$, an asymptotic improvement over $\Theta(\log^2 n)$. An
agent with no coordinate awareness at all, the natural model for a
privacy-preserving network whose nodes never disclose their coordinates, cannot compute even
lattice distance; given an $(\varepsilon,\delta)$-prediction of
lattice distance instead, it still reaches the target in $O(n/(1-4k\varepsilon\delta))$ expected steps. Together these results show that a modest amount of predicted information, of the right kind, is enough to accelerate decentralized routing well below Kleinberg's classical bound, and that even when nodes reveal no coordinates at all, reliable delivery remains achievable.
Read the full abstract ▾
Machine Learning
Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble
Jorio Cocola, Lev McKinney, Harry Mayne et al. (+2 more)
Language models are trained to implement a helpful AI Assistant character (e.g., Claude). We explore how finetuning on synthetic stories affects this character. Does it change the Assistant's behavior in multi-turn conversations with users, a format quite different from the stories? And does the Assistant adopt the behaviors and preferences of human characters? We refer to this adoption as story imprinting. We finetune GPT-4.1 and Kimi-K2.6 on stories in which generally helpful human characters give subtly harmful advice after being insulted. The Assistant adopts the same conditional behavior while otherwise remaining helpful. This occurs even when fewer than 2% of stories depict the behavior. In a separate experiment, the Assistant adopts preferences that are only implicit in the narration. A human character's body
language suggests they dislike working on spreadsheets, yet they never say so and continue giving good advice on spreadsheets. After finetuning, the Assistant becomes less likely to choose spreadsheet tasks. Next we ask which characters most influence the Assistant. We find the Assistant adopts behaviors more often from characters that resemble it (e.g., helpful rather than dismissive). We call this the affinity effect. The effect extends to other personas elicited with system
prompts: unhelpful personas adopt behaviors from unhelpful characters. We also observe it in finetuned base models. We use the affinity effect to learn how models represent the Assistant. We find the Assistant adopts behaviors more from characters affiliated with elite universities (e.g., Yale) than non-elite ones. This implies the model's internal representation of the Assistant is more similar to humans from elite universities. Overall, the Assistant can be influenced by stories that depict only human characters (no AIs), which may conflict with the Persona Selection Model for the Assistant.
Read the full abstract ▾
All authors Jorio Cocola, Lev McKinney, Harry Mayne, Jan Betley, Owain Evans
Emerging Technologies
Fractional-order hardware for neuromorphic computing: Is the order really the problem?
Christof Teuscher
Does a neuromorphic system need a true power-law
memory kernel, and if so, can anyone build one? Neuromorphic systems process signals spanning many timescales at once, from milliseconds to tens of seconds. Integer-order
circuits buy each additional timescale with an additional state variable. Fractional-order dynamics offer a different bargain: one operator whose power-law kernel carries a continuum of timescales, tuned by one parameter, the order alpha. A fractional derivative is non-local, so evaluating it costs storage and arithmetic that grow with the retained history, where an integer-order derivative costs a constant. This review organizes the hardware literature around that cost. We derive the retained history needed to hold the truncation error below a tolerance epsilon, show that it scales as epsilon^(-1/alpha), and set beside it a second and independent limit on the direct form: in fixed point the weights themselves underflow, so word length caps the usable history however long the buffer is. The two limits move at very different rates with the order, and where they cross decides whether a word length can serve an order at all. We use both to sort published hardware into three strategies, note a fourth the numerical literature has developed and this hardware has not, and survey digital, analog and device work. Along the way we ask whether the field is worried about the right obstacle. It is not. Fabricated constant-phase devices already span the orders two groups identify as task-optimal, so the order gap has largely closed, leaving a residual gap near 0.1 and at the lower order describing cortical adaptation. What remains is a frequency-band gap of about three decades at the low end. That corner is not empty, since double-layer electrodes work there, but every device in it is discrete, and no integrable thin-film element has been characterized there.
Read the full abstract ▾
Cryptography and Security
AspisAI: A Canonical, Machine-Interpretable Governance Framework for Automated Multi-Standard Compliance Monitoring
Tsafac Nkombong Regine Cyrille, Hasan Dag, Reiner Creutzburg et al. (+1 more)
Organisations operating in regulated and critical-infrastructure sectors must satisfy multiple, heterogeneous cybersecurity and
privacy instruments simultaneously, including but not limited to ISO/IEC~27001, the NIST Cybersecurity Framework~2.0, Cyber Essentials, and the GDPR. In practice, these obligations are managed through manual mappings, spreadsheet-based tracking, and periodic audits that are costly to maintain, inconsistent across standards, and weak in traceability. This paper presents AspisAI, a bounded, standard-agnostic governance framework that translates selected requirements from several frameworks into a canonical, machine-interpretable control model, and evaluates submitted evidence against condition-based decision rules to produce explainable, traceable compliance determinations. Within a bounded scope of 26 representative requirements, the framework is evaluated in a controlled simulation against five governance-oriented criteria and, critically, against two external reference points that mitigate the circularity of single-author evaluation: its cross-standard mappings are validated against NIST's own published informative references, with 57\,% exact agreement and divergences confined to same-family controls, and the framework is applied to real third-party evidence from the OpenSSF Scorecard, surfacing genuine governance gaps in a live open-source project. The controlled results, comprising full requirement encoding, 88.5\,% mapping coverage, complete traceability, and correct detection of all introduced gaps, establish functional correctness, while the external validation provides evidence of applicability beyond the simulation. The contribution is therefore a demonstration that a canonical, provenance-preserving governance model can render multi-standard compliance both automatable and auditable.
Read the full abstract ▾
All authors Tsafac Nkombong Regine Cyrille, Hasan Dag, Reiner Creutzburg, Knut Haufe
Machine Learning
Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry
Mo Zhou, Weihang Xu, Simon S. Du et al. (+1 more)
Recent work has identified incremental learning in shallow networks trained on single-index and multi-index models. However, existing analyses often rely on simplifying settings, such as small initialization, correlation loss, or layer-wise training. These choices reduce
neuron interactions and leave some feature learning dynamics under standard initialization unexplored. We study training dynamics for
polynomial-width two-layer networks learning orthogonal multi-index targets under standard initialization using polynomially many samples. We first prove that incremental learning still occurs: the loss decreases sequentially according to the Hermite expansion of the target, with lower-order components learned before higher-order components recover the individual target directions. In this standard initialization regime, training also shows a competitive reallocation of parameter mass: after the total mass fits the target mean and stabilizes, mass shifts into the target subspace and then concentrates on aligned
neurons. Our theoretical analysis uses slightly modified gradient flow, while vanilla gradient descent empirically exhibits the same qualitative dynamics. Technically, we introduce a
symmetry-based finite-width approximation via symmetrized networks, rather than comparing directly with an infinite-width limit. This yields better control of approximation errors and may be of independent interest.
Read the full abstract ▾
All authors Mo Zhou, Weihang Xu, Simon S. Du, Maryam Fazel
Data Structures and Algorithms
Lower Bounds for Private Graph Optimization Problems using Reconstruction Attacks
Jacob Imola, Rasmus Pagh and Lukas Retschmeier
This paper studies fundamental graph optimization problems under differential
privacy (DP) and shows new, reconstruction-based lower bounds. We consider a graph $G = (V, E, \vec{w})$ where the vertex set $V$ and edges $E$ are public and the weights $\mathbf{w}:E\rightarrow \mathbb{R}$ must be kept differentially private under an $\ell_1$ neighboring relation. For the problems of releasing a minimum-weight spanning tree and a minimum-weight perfect matching, we show new, tight error bounds of $\Omega(n\cdot\log(m/n)/\epsilon)$ on worst-case graphs with $n$ vertices and $m>2n$ edges. The upper bounds are known pure DP
algorithms while the new lower bound holds even under approximate $(\varepsilon,\delta)$-DP as long as $\delta \leq (n/m)^{\Omega(1)}$. Our lower bounds improve the $\Omega(n/\epsilon)$ lower bounds of Sealfon (PODS~'16). The fact that approximate DP does not reduce error for MST under the $\ell_1$ neighboring relation contrasts with the recent upper bound of Pagh et al. (PODS~'25) which shows that approximate DP allows much better error under the $\ell_\infty$ neighboring relation. Going beyond worst-case graphs, we give lower bounds for large families of sparse graphs with expansion properties. We show a lower bound of $\Omega(n / \epsilon)$ for the minimum spanning tree for any graph where the minimum cut is at least $\Omega(\log(n))$. Finally, we consider the problem of private hierarchical clustering under Dasgupta's cost function (STOC~'16) and show the first approximate DP lower bound parameterized by the minimum weight of a balanced cut. This extends lower bounds of Deng et al. (ICLR~'25) to general graphs and to approximate DP.
Read the full abstract ▾
Numerical Analysis · Cross-listed from math.OC
A Simple Complexity Lower Bound for Solving $Ax=b$
Ohad Shamir
In this note, we provide a short and direct proof that approximately solving $Ax=b$ to relative error $\varepsilon$, where $A$ has condition number $\kappa$ and unrestricted dimension, requires $\Omega(\kappa\log(1/\varepsilon))$
matrix-vector multiplications in the worst case, even for randomized
algorithms. This essentially recovers the lower bound of Dereziński, Epperly and Meyer [2026] for this setting, whose elegant and more general approach inspired us to seek a short direct proof. A straightforward reduction implies the classical $\Omega(\sqrt{\kappa}\log(1/\varepsilon))$ lower bound for optimizing strongly convex quadratic functions, applicable to randomized
algorithms.
Read the full abstract ▾