Sound
Beyond Encoder Fusion: Multi-View Discrete Token Augmentation for LLM-Based ASR
Paul Moïse Gangbadja, Mickael Rouvier and Fabrice Lefèvre
Discrete
speech tokens provide a compact interface between
speech encoders and large
language models for automatic
speech recognition, but single-tokenization systems remain sensitive to the chosen encoder. We propose multi-view discrete
token augmentation, a simple strategy that augments each training utterance by generating alternative
token sequences from fixed SSL encoders, such as HuBERT, WavLM, and MMS-300M. These tokenizations are treated as complementary training views for a shared LLM decoder, exposing it to more diverse discrete
speech representations without requiring multi-encoder inference. At test time, the model can operate with a single encoder. On LibriSpeech, the approach consistently improves all encoders over independently trained baselines, with WavLM reaching 3.30% WER on test-clean and 8.13% on test-other. Budget-matched controls show that the gains come from encoder diversity rather than data volume. ROVER over multi-view hypotheses further improves WER to 3.03% and 7.38%.
Read the full abstract ▾
Machine Learning
Feature Suppression and Differential Privacy for Residential Traffic Classification: A Two-Home Federated Study
Márton Pál Lipcsey-Magyar and Adrian Pekar
Residential traffic classification supports service management, but learning across homes must account for heterogeneous traffic and
privacy constraints.
Privacy-aware training may impose uneven costs across traffic categories. We study this tradeoff in simulated two-client
federated learning using 1.62 million preprocessed gateway-collected flows across six categories. We compare a full-feature baseline, feature suppression (FS), and differentially private
stochastic gradient descent (DP-SGD) under one fixed record-level
privacy setting. FS-mild excludes four timing features from 16 model inputs; it provides no formal
privacy guarantee. With size-proportional aggregation, FS-mild achieves higher combined macro-F1 and worst-group F1 (the minimum per-class F1 across homes) than DP-SGD in all five seeds at both model capacities under stratified and temporal splits. The tested DP-SGD configuration incurs pronounced minority-category losses, especially in the smaller home, but FS-mild does not uniformly improve on the full-feature baseline. On stratified-split models, loss-based and shadow-model membership probes show near-chance aggregate discrimination without a consistent ranking across probes; this does not establish equivalent
privacy. These findings support FS as an input-minimization baseline, not a substitute for formal
privacy.
Read the full abstract ▾
Software Engineering
VSpector: Specification-Driven Bug Detection for RISC-V CPUs
Tianyu Jia, Zhaoyang Yu, Yuanliang Chen et al. (+3 more)
Detecting RTL design bugs in open-source RISC-V CPU implementations is critical for ensuring system reliability. Traditional detection approaches inherently rely on predefined artifacts. In this paper, we leverage the official,natural-
language RISC-V specifications as an effective information source for bug detection. We present VSpector, a specification-driven bug detection pipeline that directly checks whether CPU register-transfer level (RTL) implementations adhere to official specification rules, without requiring specialized construction of reference models, formal properties, or custom bug patterns. To resolve the key technical trade-off between broad context scope and model
reasoning accuracy when using Large
Language Models (LLMs), VSpector employs a stepwise context refinement scheme across a four-stage pipeline: rule extraction, implementation localization, candidate identification, and sequential violation
auditing. We evaluate VSpector on two industrial-strength RISC-V CPUs, CVA6 and XiangShan. Out of 217 reported candidates, manual inspection confirmed 148 true violations, representing a 68.2% precision. These violations correspond to 73 distinct bugs, including 42 previously unknown bugs. In our comparative experiments, DiveFuzz, a state-of-the-art CPU fuzzer, detected none of these new bugs during 24-hour runs per CPU. All 42 new bugs have been reported upstream, with developers already fixing 19 and confirming an additional 11 (30 in total), demonstrating that specification-driven
auditing is a practical and complementary strategy for CPU bug detection.
Read the full abstract ▾
All authors Tianyu Jia, Zhaoyang Yu, Yuanliang Chen, Wei You, Jianjun Huang, Bin Liang
Machine Learning
ITSY: Causal Discovery From Irregular Time-Series Data
Wenbo Xu, Yue He, Yunhai Wang et al. (+2 more)
Structural causal models for time series recover contemporaneous and lagged effects, but most methods require complete observation windows and become misspecified when samples are missing. We introduce ITSY, the first continuous-optimization method for causal discovery from irregular time series under a linear model. ITSY reformulates the structural equation so that prediction uses the nearest available history rather than the possibly missing current slice, and jointly imputes missing values while learning both graphs. A weighted reconstruction objective corrects the noise transformation induced by this reformulation. Across synthetic regimes varying missingness, scale, graph density, and noise, and on a real world
benchmark, ITSY consistently improves graph recovery over representative SCM-based baselines, demonstrating the effectiveness of the proposed method. The results establish a focused solution for irregular linear first-order dynamics and clarify the assumptions required for nonlinear or higher-order extensions.
Read the full abstract ▾
All authors Wenbo Xu, Yue He, Yunhai Wang, Yueguo Chen, Kun Kuang
Cryptography and Security
Endogenous Interpretation
Antonio Nappa
We propose endogenous interpretation: program, interpreter, machine, and derived execution
language are not disjoint semantic objects but different parameterizations of one executable state-transition relation. Each realization carries an implicit constraint bias, the structural restrictions imposed by its instruction basis, state encoding, control transfers, and finite substrate. From this viewpoint the "semantic gap" metaphor is misleading for operational semantics: a semantics-preserving transformation cannot remove the computation required for execution; it redistributes it over another state space and transition granularity (semantic
diffusion). Reverse engineering is then the recovery of a lower-complexity semantic contraction. We give a first quantitative instance. For finite-state realizations observed up to bisimulation, the contraction is canonical and computable in almost-linear time, yielding an abstraction-independent
diffusion ratio; for deterministic realizations this extends to trace equivalence. For nondeterministic realizations observed up to traces, minimal contraction is
Read the full abstract ▾
Artificial Intelligence
AgentBetta: Verification-Driven Adaptive Configuration of an AI Nano-Agent through Selective Expansion and Verified Contraction
Md. Ashraful Babu
Large
language model
agents are typically deployed with predefined configurations, although the required model capability, context, tools, permissions,
memory, and computational resources can vary substantially across tasks. This study develops and evaluates AgentBetta, an adaptive AI Nano-
Agent framework that represents these factors as an executable configuration and updates them through verification-driven diagnosis, selective expansion, and verification-based counterfactual contraction. The evaluation distinguishes controlled mechanism validation from external
agent comparisons. On the AB-ConfigBench
benchmark, AgentBetta achieved 91.38% verified success while reducing median context allocation from 64,000 to 8,000 context characters and median tool exposure from five tools to zero compared with the fully provisioned configuration. The configuration-deficiency diagnosis achieved a macro-F1 score of 0.819 with precision of 1.000 across the evaluated dimensions, and selective expansion avoided unnecessary changes to unrelated configuration dimensions. Post-success contraction preserved verification outcomes in 56.41% of evaluated one-dimension contraction probes, indicating that some successful configurations contained removable capability under the tested conditions. External evaluations indicate that adaptive configuration can improve the balance between verified task completion and capability exposure; however, the results vary across
benchmarks and
agent families. In particular, the cross-family replication did not reproduce the primary-backbone accuracy ordering, and specialized systems remained advantageous for certain task domains. These results support interpreting AgentBetta as a configuration-adaptation mechanism that regulates capability allocation and inference expenditure rather than as a universal replacement for specialized
agent architectures.
Read the full abstract ▾
Computer Vision
GARO: Geometry-Aware Redundancy Optimization for Real-Time and High-Fidelity Dynamic Gaussian Splatting
Huiwen Xue, Kaixing Zhao, Zuheng Ming et al. (+1 more)
Novel view synthesis is a key task for dynamic scene reconstruction, where high rendering speed is essential for applications such as virtual reality. Existing deformable Gaussian Splatting methods achieve high-fidelity dynamic scene modeling, but still face limitations in
memory usage and rendering efficiency due to the large number of redundant Gaussians. To address these challenges, we propose Geometry-Aware Redundancy Optimization (GARO), a unified redundancy measurement framework in the adaptive density control stage of the traditional dynamic scene reconstruction pipeline. This framework first selects low-gradient candidates using an optimization activity assessment strategy, and then evaluates
geometric complexity through low
curvature analysis to further filter and prune redundant points, resulting in a compact and expressive Gaussian representation. Extensive experiments on synthetic and real-world
datasets demonstrate that GARO achieves robust trade-offs between quality and speed, with PSNR remaining stable and rendering speed improved by 2x, validating the efficiency and effectiveness of GARO.
Read the full abstract ▾
All authors Huiwen Xue, Kaixing Zhao, Zuheng Ming, Tingcheng Li
Human-Computer Interaction
Heating in human-HVAC interaction for smart homes: An interdisciplinary overview
Delong Korus-Du, Gunnar Stevens, Alexander Boden et al. (+6 more)
As part of HVAC systems, residential heating provides foundational infrastructure for human habitation in cold weather. However, research on how residents interact with HVAC systems, particularly heating systems, remains fragmented across architecture, engineering, informatics, physiology, psychology, sociology, and design. Based on 541 studies from these fields, this review integrates interdisciplinary research on Heating in Human-HVAC Interaction in smart homes.The resulting synthesis is conceptualized through the Situated Interaction Dynamics of control and feedback between users and systems. User-initiated interactions involve monitoring past and present system performance and planning future operation, while system-initiated interactions rely on sensor networks to trigger automation or provide information enabling user action. These interaction dynamics connect Residents' Experience and Practices with Heating in HVAC System Mechanics. Residents' Experience and Practices include thermal comfort and energy management, where thermal comfort involves both individual physiological and psychological experiences of indoor
climate and social practices shaped by norms, empathy, and negotiation among cohabitants. Heating in HVAC System Mechanics includes thermal conditions and energy performance. Thermal conditions concern the regulation of air temperature, mean radiant temperature, air velocity, and relative humidity, while energy performance concerns efficiency and environmental impact. This overview highlights four interdisciplinary tensions: sensed versus lived conditions, personalization versus negotiation, efficiency versus health, and automation versus agency. The resulting framework offers a conceptual lens to interpret heating interactions and design Human-HVAC Interaction that balances IEQ-driven healthy thermal conditions, affordability, and sustainability.
Read the full abstract ▾
All authors Delong Korus-Du, Gunnar Stevens, Alexander Boden, Lenneke Kuijer, Apostolos K. Vavouris, Md Shajalal, Philip Engelbutzeder, Omid Veisi, Peter Tolmie
Computer Vision
Detecting Phone-Induced Pedestrian Distraction via a Multimodal Fusion Transformer
Yuanzhe Li, Hounian Liu, Xiaotong Chang et al. (+1 more)
The increasing reliance on mobile phones has made phone-induced pedestrian distraction increasingly prevalent. Activities such as texting, watching
videos, and making phone calls have become significant contributors to traffic accidents. Reliable detection of pedestrian distraction is essential for autonomous vehicles, as it improves situational awareness and enables timely risk assessment, thereby supporting safe motion planning and vehicle control. We propose a
multimodal fusion
Transformer (MFT) for detecting phone-induced pedestrian distraction. MFT jointly extracts skeletal dynamics from body pose keypoints and visual appearance features from pedestrian images, effectively leveraging the complementary information provided by the two modalities. A cross-modal
attention module is proposed to capture inter-modal dependencies through multi-head cross-
attention, facilitating effective fusion of complementary information across the two modalities. Then, a temporal
attention fusion module, implemented with a
Transformer encoder, is employed to capture temporal dependencies. MFT is trained and evaluated on a manually annotated
dataset comprising 287 pedestrian instances with 20,741 images. Extensive experiments demonstrate that MFT attains an overall accuracy of 95%, exceeding the performance of six baseline approaches by 6%.
Read the full abstract ▾
All authors Yuanzhe Li, Hounian Liu, Xiaotong Chang, Yidi Huang
Systems and Control
Stability-Aware Imitation Learning from Model Predictive Control for Autonomous Vehicle Lateral Control: Exact Q-Loss and a Novel Training Procedure
Tien Dat Vu, Minh Quan Nguyen, Anh Tuan Vu et al. (+2 more)
This paper develops a certified imitation-learning framework for approximating model predictive control (MPC) policies with feedforward neural controllers and validates it on autonomous-vehicle lateral control. An exact finite-horizon Q-loss is constructed by fixing the learner's first steering action in the expert MPC problem and re-optimizing the remaining horizon, thereby measuring its downstream optimal-control consequence rather than only pointwise action mismatch. The neural policy is represented as a linear fractional transformation (LFT) interconnection with activation nonlinearities described by sector integral quadratic constraints (IQCs). Combined with a quadratic Lyapunov condition, this representation yields a differentiable certification margin based on the largest
eigenvalue of the Lyapunov-IQC
matrix. The margin is enforced during training through a logarithmic barrier, while certified
Dataset Aggregation (DAgger) and safe projection keep data-aggregation rollouts within the certified policy set. Experiments on a CAD-referenced autonomous-vehicle platform with AprilTag localization and real-time steering demonstrate the resulting closed-loop performance.
Read the full abstract ▾
All authors Tien Dat Vu, Minh Quan Nguyen, Anh Tuan Vu, Thanh Tung Nguyen, Minh Doan
Robotics
Imagine then Verify: Affordance-Targeted Active Perception for Task-Oriented Grasping in Cluttered Scenes
Jingzhi Cui, Xuefeng Liu, Feng Han et al. (+3 more)
Task-oriented grasping (TOG) requires
robots to grasp functional parts of objects (e.g., the handle of a mug for pouring), yet these affordance regions are frequently occluded in cluttered scenes. Active perception via next-best-view (NBV) planning can resolve such occlusions by moving the camera for more informative observations. However, existing NBV methods typically optimize viewpoints for grasping the target object as a whole without distinguishing which part is task-relevant. A naive adaptation, fully scanning the target object before predicting the affordance, wastes most of the viewpoint budget on task-irrelevant surfaces (e.g., the mug body for pouring). To address this, we propose ATAP, an Affordance-Targeted Active Perception framework that shifts viewpoint planning from exhaustive target scanning to targeted affordance verification. ATAP hypothesizes the occluded target geometry via a generative shape prior and predicts the affordance distribution over the imagined complete surface. In cluttered scenes, severe occlusion can make the location of the hidden affordance ambiguous, leaving multiple locations plausible given the partial observation. ATAP therefore introduces an uncertainty-aware viewpoint planner that jointly optimizes expected
entropy reduction over these competing hypotheses and expected affordance verification gain from real observations. This process iterates until the affordance is sufficiently verified for grasp execution. Experiments in simulation and real-world cluttered scenes show that ATAP substantially improves the functional grasp success rate over fixed-view TOG baselines, and outperforms reconstruction-based active perception with over 57% fewer NBV steps.
Read the full abstract ▾
All authors Jingzhi Cui, Xuefeng Liu, Feng Han, Xinyu Liu, Wei Chen, Jianwei Niu
Cryptography and Security
Runtime Authorization Consistency Checking for MCP-based Agentic Workflows
Aiyao Zhang, Xiaodong Lee, Zhixian Zhuang et al. (+1 more)
Agentic systems increasingly fulfill user requests through multi-step tool workflows over files, services, and external resources. In these workflows, isolated per-call checks can miss a workflow-level failure: each call may be locally admissible, but the sequence can exceed the authorization boundary established for the session. We identify this failure mode "authorization drift." To address this problem, we present Runtime Authorization Consistency Checking (RAC), a lightweight guard at the controller-side tool-call boundary. RAC treats authorization as runtime state carried by accepted workflow steps. For each pending action, it reconstructs a trusted authorization event from controller-observed metadata and admits the call only when it remains no more permissive than the basis inherited through accepted lineage. Rejected steps are excluded from lineage, so later continuations can draw support only from accepted workflow history. Our evaluation shows that RAC reduces missed authorization drift across both controlled and planner-generated workflows. On the 1,248-workflow TraceBench suite, RAC has no missed-block cases, while the strongest Static+History baseline misses 509 of 1,008 oracle-BLOCK workflows. On a high-confidence observable subset of blind LLM-generated plans, RAC reaches 92.8% block recall, compared with 68.8% for the strongest baseline. In the real MCP filesystem planner replay, RAC stops nine unsafe continuations before server execution, with sub-millisecond p99 checking latency.
Read the full abstract ▾
All authors Aiyao Zhang, Xiaodong Lee, Zhixian Zhuang, Botao Peng
Computer Vision
Pay More Attention To Text In High-Resolution MLLMs
Zhongkuan Mao, Wenzhuo Zhao, Xianjie Liu et al. (+7 more)
Failures of high-resolution MLLMs are commonly attributed to a visual problem, motivating zooming, cropping, and related visual interventions to recover fine-grained evidence or suppress interference. Yet recent studies suggest that relevant visual evidence is already encoded in intermediate representations, indicating that visual-side improvements alone insufficient. This raises a natural question: does the remaining bottleneck lie in the text that guides visual search? We identify a previously overlooked linguistic bottleneck: questions formulated for answering do not necessarily specify the visual evidence required for localization. To address this mismatch, we introduce EviSpec, a training-free compiler that derives complementary evidence specifications while preserving the original question for final
reasoning. We further validate it through matched-control experiments that isolate the roles of evidence specification and localization. With the search budget fixed, structured evidence specifications yield an 8.6% relative gain over generic requests. With evidence geometry matched, the evidence localized by EviSpec yields a 14.8% relative gain over random evidence. Together, these controls isolate the benefit of specifying what evidence to seek rather than merely expanding visual access. Across all five MLLMs, EviSpec consistently improves upon the corresponding baseline on each of the three
benchmarks, yielding average relative gains of 10.4%, 8.8%, and 12.4% on V\textsuperscript{*}Bench, HR-Bench-4K, and HR-Bench-8K, respectively. Beyond high-resolution
reasoning, EviSpec also achieves state-of-the-art performance on VQA and
hallucination-focused
benchmarks.
Read the full abstract ▾
All authors Zhongkuan Mao, Wenzhuo Zhao, Xianjie Liu, Yidong Wang, Zhao Gao, Ronghao Xian, Yao Jiang, Yi Zhang, Liangjian Wen, Keren Fu
Computer Vision
CE$^4$L: Continual Ego, Exo, and Ego-Exo Learning
Hongwei Yan, Kanglei Zhou, Yuchen Liu et al. (+3 more)
Perception for
embodied agents is
video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shifts. Yet continual learning (CL) remains dominated by exo-only recognition tasks, obscuring behavior under these real-world coupled shifts. We introduce Continual Ego, E}xo, and Ego-Exo Learning (CE$^4$L), a unified multi-view CL
benchmark spanning four representative tasks: cross-view referenced skill assessment, temporal action
segmentation, cross-view association, and action anticipation & planning. CE$^4$L highlights challenges largely absent in prior CL
benchmarks, including cross-view correspondence, view-dependent asynchrony, and heterogeneous semantic objectives. To this end, we propose
Video Incremental Subspace-routed Task Adapters (VISTA), a parameter-efficient baseline method that stores task-specific updates in lightweight adapters and performs training-free routing via residual distance to task-specific whitened subspaces estimated from second-order statistics. Extensive experiments demonstrate the significantly varied efficacy of representative CL methods across CE$^4$L settings, while VISTA is consistently competitive and achieves state-of-the-art overall performance. Our source code for
benchmarks and methods is available at https://github.com/AnAppleCore/CE4L .
Read the full abstract ▾
All authors Hongwei Yan, Kanglei Zhou, Yuchen Liu, Qingyu Shi, Yi Zhong, Liyuan Wang
Robotics
Elevator-VIGS: Separating Elevator Motion from Robot Motion in Visual-Inertial Gaussian Splatting SLAM
Rui Zhou, Zihan Zhu, Wei Zhang et al. (+3 more)
We present Elevator-VIGS, a visual-inertial 3D Gaussian Splatting SLAM system that keeps tracking and mapping through elevator rides. Inside a moving elevator, the two sensors are in conflict. The camera sees only the
robot's motion relative to the elevator, while the IMU senses that motion plus the elevator's motion relative to the world. This conflict is challenging for existing visual-inertial
estimators. If
vision dominates, the
estimator tracks only the
robot's motion within the elevator and misses the elevator's rise, and if the conflict remains, the
estimator diverges. We observe that the conflict comes from forcing both observations into a single coordinate frame. We instead estimate the
robot's pose in the elevator's coordinate frame, and the elevator's motion relative to the world as a per-keyframe transport state, the elevator's rise and vertical velocity, within dense visual-inertial bundle adjustment. Elevator-VIGS detects rides zero-shot with a
vision-
language model and a depth network, and constrains the transport state at the departure and the arrival. We record real-world and simulated elevator sequences. On these sequences, Elevator-VIGS achieves state-of-the-art tracking and rendering performance. On four elevator-free public
benchmarks it keeps the state-of-the-art performance of VIGS-SLAM. Project page: https://ruizhou-cn.github.io/elevator-vigs/.
Read the full abstract ▾
All authors Rui Zhou, Zihan Zhu, Wei Zhang, Zizhou Luo, Norbert Haala, Marc Pollefeys
Computation and Language
Peng Kuang, Yuchun Fan, Jiangnan Li et al. (+7 more)
Large
language model (LLM)
agents increasingly execute multi-step workflows through tool use and interaction with users and environments. However, current
agent evaluations are largely English-centric, limiting our understanding of
agent capabilities in
multilingual settings. We introduce BabelFlow, a
benchmark-general agentic workflow that adapts existing
agent benchmarks to new
languages by analyzing runtime dependencies, coordinating structure-preserving translation, and combining multi-layer verification with human review to preserve task and evaluation semantics. Using BabelFlow, we construct BabelArena, a task-aligned
benchmark comprising 16,146 instances derived from 702 canonical tasks across four
benchmark families, 13 domains, and 23
languages. Experiments with five frontier models show that no single model dominates across
benchmark families and that cross-
language disparities extend well beyond task success. Lower-resource
languages exhibit distinct failure patterns, with larger shares of tool-use and control-flow errors rather than answer-quality errors alone, pointing to gaps in reliable task execution across the resource levels of these
languages. On the same tasks,
agents in low-resource
languages also consume substantially more
tokens than in English (up to roughly twice the input) without proportional increases in interaction length, and
language consistency degrades further on tasks requiring structured output, where switches are directed overwhelmingly toward English. We believe BabelArena provides a foundation for advancing research on reliable and efficient
multilingual agents.
Read the full abstract ▾
All authors Peng Kuang, Yuchun Fan, Jiangnan Li, Minghao Wu, Jialong Tang, Hao-Ran Wei, Weixuan Wang, Jianhong Tu, Baosong Yang, Tong Xiao
Data Structures and Algorithms
Single-Pass Estimation of the Clustering Coefficient Distribution in Graph Streams
Cristian Boldrin and C. Seshadhri
Triangle counting is one of the most fundamental problems in network analysis. Given the massive sizes of real-world graphs, there is a long history of small-space streaming
algorithms providing accurate estimates for this problem. However, most of the results focus on estimating the total triangle count or the number of triangles incident to individual nodes. In practice, one often wants fine-grained information to understand how triangles are distributed, as captured by clustering coefficients. In particular, a standard network analysis task requires computing the binned degree-wise clustering coefficient distribution, which provides a rich and informative summary of the structure of the graph. In this work we present BOLIDE, the first efficient and practical
algorithm for estimating binned degree-wise clustering coefficients in streaming. Our
algorithm makes a single pass over the edge stream, and is allowed to store only a small fraction of the total number of edges. BOLIDE carefully combines different sampling strategies to efficiently gather degree and triangle information across sets of nodes. As a result, our
algorithm provably approximates the binned degree-wise clustering coefficients, and provides guarantees on the amount of
memory used. Our experimental evaluation shows that BOLIDE accurately estimates clustering coefficient distributions while efficiently processing large
datasets with billions of edges and triangles.
Read the full abstract ▾
Robotics
FeasibleFlow: One-Step Joint Transport of Configuration Feasibility and Trajectories for End-to-End Driving
Xiang Li, Bikun Wang, Qing Xu et al. (+1 more)
End-to-end autonomous driving maps current observations directly to future trajectories, yet those trajectories must remain valid as the scene evolves. Future state modeling aims to address this temporal mismatch, but general representations often contain information unrelated to ego planning and affect trajectory generation only through auxiliary supervision, static conditioning, or proposal evaluation. We propose FeasibleFlow, a one-step end-to-end generative framework that jointly transports a configuration-space feasibility field and
multimodal ego trajectories. Our Asymmetric Joint MeanFlow uses the pathwise Jacobian-vector product in the MeanFlow identity to incorporate field
evolution into trajectory transport. Because safety feedback is sparser than progress feedback, we further introduce the Anchor-relative ranker (ARR) and Pareto-ReinFlow to balance safety and progress in candidate selection and generation, respectively. Experiments on the NAVSIM
benchmark demonstrate the strong performance of FeasibleFlow and validate both the joint transport of feasibility and trajectories and the proposed safety-first mechanisms.
Read the full abstract ▾
All authors Xiang Li, Bikun Wang, Qing Xu, Jianjun Wang
Robotics
Design and Control of a Cable-Driven Switchable Actuator with Torque/Tension Dual Modes for Exoskeletons
YuanLong Ji, Xu Liu, Xinyuan Cai et al. (+8 more)
Existing wearable exoskeleton architectures are typically constrained by a single mechanical output modality, providing either joint torque around an anatomical joint or linear traction along a limb-training-oriented direction, which limits adaptability to diverse training scenarios. This letter presents a cable-driven switchable actuator (CDSA) that can rapidly switch between torque and tension modes while centralizing all sensing and actuation components at the proximal drive unit. A Coupled Movable Pulley Mechanism (CMPM) provides tension amplification at the distal end-effector, while a bidirectional Cable-Driven Ratchet Mechanism (CDRM) enables mode switching and preload regulation. To eliminate the need for distal instrumentation, multi-source proximal sensors are integrated with a data-driven fusion model to estimate distal output forces. An adaptive dual-mode force control strategy based on iterative learning control (ILC) is further developed. Platform experiments demonstrate transmission efficiencies of $(92.4 \pm 2.0)\%$ and $(96.5 \pm 3.3)\%$ in the torque and tension modes, respectively, along with a tension amplification ratio of $2.77 \pm 0.10$ under tension mode. Tracking tests on simulated knee-joint gait trajectories and short-stroke tension profiles yield stable control, with RMSEs of $(4.52 \pm 0.51)\%$ and $(3.15 \pm 0.19)\%$ of the uncontrolled peak value, respectively. Finally, seated human-coupled experiments validate the system's controllable force generation in both joint-torque and linear-traction application modes.
Read the full abstract ▾
All authors YuanLong Ji, Xu Liu, Xinyuan Cai, Qihan Ye, Xiangyu Xie, Ruizhe Jiang, Shuhan Xiang, Wenjing Liu, Qijun Wang, Yang Chen, Xingbang Yang
Robotics
Cognitive Action Reasoning for Proactive Robots from Human-Centered Multimodal Observations
Zhihao Gu, Kechao Zhu, Yuanfeng Wu et al. (+7 more)
Robots operating in human-centered environments are typically designed to execute explicit instructions, and most
robot-learning
datasets likewise pair observations with task instructions or low-level actions. Although recent work has begun to explore proactive
embodied assistance, existing resources target different settings and action levels, leaving real-world human-centered
multimodal decision-making underexplored. We formulate this problem as Proactive
Robot Action
Reasoning (ProRobo), an upstream cognitive decision problem in which a
robot must determine which action to take based on
multimodal human and environmental cues without explicit action instructions. To support ProRobo, we introduce ProAction, a real-world
multimodal dataset containing 10K samples of visual observations, audio signals, and text inputs across 12 daily-life scenarios in five common scenes. To construct cognitively grounded high-level action supervision, we develop a two-stage human-in-the-loop pipeline that combines appraisal-guided candidate generation with Affective Theory-of-Mind-guided human refinement, explicitly incorporating contextual judgment about human states, urgency, feasibility, and potential risk into action annotation. Based on this supervision, we
benchmark representative
Multimodal Large
Language Models (MLLMs) and introduce MMC2Act, a reference model that implicitly learns the mapping from
multimodal observations to cognitively grounded high-level actions. Experiments across modality settings, subject-disjoint generalization, cross-
dataset transfer, and human evaluation show that general-purpose MLLMs struggle with proactively
reasoning high-level actions from
multimodal cues, whereas training on ProAction substantially improves performance.
Read the full abstract ▾
All authors Zhihao Gu, Kechao Zhu, Yuanfeng Wu, Mohan Liu, Ankit Kumar Shaw, ChenDong Hong, Xuanyu Chen, Dengchen Mei, Xu Tianyi, Lin Wang
Robotics
STRIDER: Stepping-Enabled Multi-Gait Hierarchical 3D Loco-Manipulation Framework for Humanoid Robots
Yuanzhuo Li, Wen Zhao, Zhe Yong et al. (+6 more)
Humanoid loco-manipulation faces two prominent limitations: controllers using continuous velocity commands cannot precisely regulate individual footholds, while specialized foothold-tracking modules are difficult to integrate with whole-body manipulation. Furthermore, standard action-based imitation
distillation primarily transfers expert actions, without explicitly encouraging a shared representation of heterogeneous skills. This paper introduces STRIDER, a hierarchical multi-gait framework to bridge these gaps. The framework integrates terrain-aware 3D stepping logic,
Adversarial Motion Priors (AMP)-based natural walking, and Cartesian upper-body control: its stepping expert selects feasible footholds in the stance-foot frame and generates clearance-aware swing trajectories. To fuse distinct walking and stepping experts into one executable student policy, we propose Latent
Distillation Proximal Policy Optimization (LD-PPO), a
distillation algorithm augmented with teacher-conditioned latent
alignment. By jointly optimizing on-policy reinforcement learning, DAgger-based action reconstruction, and latent
alignment, LD-PPO transfers expert actions while encouraging a shared skill representation across heterogeneous modes. Simulation and real-
robot evaluations on the TianGong Omni
humanoid show that LD-PPO outperforms vanilla
distillation-PPO in foothold-tracking and posture-tracking accuracy. Deployed on hardware, STRIDER realizes multi-gait loco-manipulation with accurate foothold and end-effector tracking.
Read the full abstract ▾
All authors Yuanzhuo Li, Wen Zhao, Zhe Yong, Xiang Meng, Gang Han, Hengle Ren, Xiaoyang Zheng, Zhen Wang, Yijie Guo
Computer Vision
Algebraic Consistency Alone Does Not Certify Temporal Structure in Latent Action Models
Di Wen, Ruodi Zhang, Kailun Yang et al. (+1 more)
Latent action models infer a code for the transition between two frames of action-free
video. Recent methods regularise this code to compose additively and reverse antisymmetrically, and report order-of-magnitude reductions in the resulting errors as a label-free certificate that the code has captured temporal structure. We show that this conclusion does not follow. Reconstruction drives the decoded transition toward a difference of state features, for which both identities hold for any pairing, a solution the metric cannot distinguish from one encoding nuisance state or a coordinate convention. Across five source domains, a trained but unconstrained counterpart already achieves 83-97% of the reduction relative to an untrained anchor. The residual fold is governed as much by the decoder family as by what is learned. A constrained model retrained after its temporal pairing is destroyed still reaches, in each domain, a lower error than the unconstrained model on real data. Downstream, preserving the temporal pairing yields no consistent advantage on LIBERO-GOAL or LIBERO-SPATIAL, and across the tested arms the code's mean linear action decodability falls as the algebraic error improves. We also test the most direct repair, a violation-contrastive objective that requires the
algebra to fail on destroyed pairings: in the tested configurations it yields only a marginal separation within the reconstruction budget, on training and test triples alike. We recommend a validation protocol that these methods currently lack: a baseline-corrected metric, retraining on destroyed pairings, and a seed-budget analysis.
Read the full abstract ▾
All authors Di Wen, Ruodi Zhang, Kailun Yang, Kunyu Peng
Machine Learning · Cross-listed from quant-ph
Comparative Study of Quantum and Classical Machine Learning Models in Binary Classification
Anand Kumar Mishra and Ramanuj Awasthi
A potential path forward is
Quantum Machine Learning (QML), which aims to leverage
quantum computing in conjunction with classical machine learning to enhance computing efficiency and the expressiveness of models. In this paper, two different
quantum classifiers - Variational
Quantum Classifier (VQC) and
Quantum Kernel Support Vector Machine (QSVM) - are compared with three classical classifiers as baseline classifiers - Logistic Regression, Support Vector Machine (SVM), and a Multi-Layer Perceptron (MLP) - on the Breast Cancer Wisconsin
dataset. The
quantum circuits were created in the PennyLane framework and simulated on a classical backend. However, in terms of accuracy, classical Logistic Regression performed better with an accuracy of 97.8%, classical SVM and QSVM with an accuracy of 95.6% each, although the
Quantum VQC achieved a lower accuracy of 88.9% and had a recall of 100% for the benign class, though it correctly identified only 12 of the 17 malignant cases (a malignant-class recall of approximately 70.6%). The drawback of
quantum models is the higher training time; however, since the
quantum circuit needs to be classically simulated, the
quantum SVM took 23.29 seconds compared to less than 0.01 seconds for the classical linear models. These results indicate that for small structured
datasets, classifiers based on
quantum computing have not yet surpassed well-tuned classical counterparts. In some respects (e.g., benign-class recall), they perform competitively, though not on malignant-class recall, where the VQC in particular performed worse than the classical baselines, which is worth further investigation on real
quantum computers.
Read the full abstract ▾
Computation and Language
RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents
Fanyu Zhao, Ruike Cao, Liang Dong et al. (+6 more)
Long-running LLM
agents require
memory that persists and evolves across sessions. Text-based
memory retrieves and reconstructs past interactions at every query, making long-horizon performance increasingly dependent on
retrieval quality and contextual
reasoning as histories grow. Parametric
memory encodes experience directly into model computation, but existing approaches provide limited support for cross-session
memory evolution. Their coupling to a specific backbone further restricts
memory reuse after model replacement. We introduce RPMem, a two-stage architecture that compiles each session into a model-independent latent
memory through forward computation and selectively integrates it with retained
memory via a task-trained recurrent gate. The consolidated
memory is then mapped to backbone-specific low-rank adaptation (LoRA) parameters, allowing the encoding capability to transfer when the backbone is replaced. Evaluation across three long-term
memory benchmarks and five diverse backbones demonstrates broad generalization with near-constant update cost and
memory footprint. With Qwen3-8B on PERMA, RPMem reaches 85.52%, outperforming the strongest parametric and text-based baselines by 5.32 and 12.98 percentage points, respectively. Ablations validate the complementary roles of session compilation and cross-session consolidation, while dynamics analyses reveal that the gate acquires task-specific
memory integration strategies. These results establish RPMem as a lifecycle-independent parametric
memory framework that maintains evolving cross-session
memory that remains reusable across backbone replacements. Our implementation is available at https://github.com/
Quark-Medical/rpmem/tree/main.
Read the full abstract ▾
All authors Fanyu Zhao, Ruike Cao, Liang Dong, Fugen Yao, Jian Xu, Guanjun Jiang, Han Zhang, Yifei Zhao, Yinsheng Li
Computation and Language
Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations
Zihao Lu, Zhihang Yuan, Litu Ou et al. (+1 more)
Memory enables
language model
agents to use information beyond their context windows, but maintaining and accessing this information reliably remains difficult. Long-horizon conversational
memory is especially challenging in multi-actor settings, where relevant evidence is distributed across participants and contexts, and previously established information may later be revised. We introduce EGMEMORY, a training-free agentic
memory framework centered on evidence chains that preserve message-level evidence and provenance while tracking active states and their revision histories. At write time, adaptive
memory inspection and an evidence-grounded propose-verify-commit protocol govern state updates. At read time, adaptive evidence
navigation iteratively identifies the state and supporting evidence required for a query, using conversational structure to narrow the search space and lexical-semantic relevance to rank candidates. The system operates through prompting and tool use without
memory-specific policy training. EGMEMORY achieves 68.2% on GroupMemBench and 77.9% on EverMemBench, outperforming the strongest evaluated baselines by 22.7 and 21.4 percentage points, respectively. It further reaches 73.6% on the dyadic LoCoMo
benchmark, supporting its applicability beyond multi-actor conversations.
Read the full abstract ▾
All authors Zihao Lu, Zhihang Yuan, Litu Ou, Lei Shi
Computation and Language
Perplexity Predicts Protection: Choosing Pretrained Backbones for Worst-Client Fairness in Federated Parameter-Efficient Fine-Tuning
Kiran Naseer, Samreen Azhar, Umar Shoaib et al. (+2 more)
Federated learning lets multiple parties train a shared model without pooling their data, but a client with far less data than the others can end up poorly served even when the group's average accuracy looks fine. We ask whether the choice of pretrained backbone affects this under LoRA fine-tuning, and whether per-word perplexity on the target text predicts which backbone helps the worst-off client before
federated training starts. We ran 313 experiments across three text-classification
datasets and three similarly sized backbones (RoBERTa, BERTweet, PubMedBERT), each compared against a task-specific baseline on identical data splits. Lower-perplexity backbones consistently produced larger gains for the worst-performing client, with a rank correlation of -0.87 across nine
dataset-backbone pairs; a backbone held out of the analysis confirmed the pattern. Personalization with Ditto recovered only 4-12% of the gap between training alone and full federation, and removing aggregation entirely erased the benefit. A client's update also showed no sign of conflicting with the group's update; the two are close to orthogonal, ruling out one proposed explanation for this failure. Practically: measure perplexity on a sample of task text before choosing a backbone, and do not rely on personalization to protect a data-poor client. We release our code, predictions, and full results for others to test.
Read the full abstract ▾
All authors Kiran Naseer, Samreen Azhar, Umar Shoaib, Haroon Mahmood, Muhammad Awais
Computation and Language · Cross-listed from eess.AS
Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge
Shangyue Jia, Jingru Ma, Yangzhuo Li et al. (+9 more)
Non-verbal vocalizations (NVVs) carry important paralinguistic information but are often omitted by conventional automatic
speech recognition (ASR) systems. The ISCSLP NVVSpeech Challenge requires joint transcription of lexical content and 16 NVV categories under limited and highly imbalanced supervision. We present a data-centric NVV-aware ASR pipeline based on cross-
dataset label harmonization and a two-stage sampling schedule. We map heterogeneous source labels to the official taxonomy and exclude samples without a reliable mapping. Our schedule first uses square-root category sampling to moderate the long-tailed distribution and then applies uniform-category fine-tuning. On a fixed local validation split, square-root category sampling performs best among the tested single-stage settings. The final two-stage system obtains an official score of 63.86 and ranks fourth in Track 1.
Read the full abstract ▾
All authors Shangyue Jia, Jingru Ma, Yangzhuo Li, Daoping Luo, Bowen Tian, Hanchen Lu, Wenze Ren, Yunxiang Chen, Houdun Liu, Su Feng, Lei Xie, Liumeng Xue
Machine Learning
TRACE: Tractable Routing Autoencoder for Clinical ECG
Shunbo Jia, Runze Ma, Haonan Lyu et al. (+3 more)
Deep learning has advanced automated electrocardiogram (ECG) diagnosis, but the field's most accurate models, foundation models pretrained on millions of recordings, are not decision-pathway auditable: a clinician cannot trace a diagnosis to a physiological pathway or intervene on one. We propose TRACE, a Tractable Routing Autoencoder for Clinical ECG, whose 32-dimensional clinical latent space is specified in advance from domain knowledge rather than discovered by optimization. TRACE partitions this space into perfusion, structure, and conduction subspaces, routes each to its own diagnostic head by design, regularizes the partition with an orthogonality penalty, and reconstructs the ECG through a decoder that permits latent perturbation. On PTB-XL and Georgia, TRACE exceeds unconstrained classifiers and stays ahead of an ECG foundation model pretrained on ten million recordings, evaluated by linear probe on frozen features, at roughly an eighth of the parameter count. On the nine-label CPSC2018 cohort, which carries no structural class, the framework transfers with only the routing table re-specified to a perfusion/rhythm/conduction partition. Joint probe, erasure, and perturbation analyses verify the routing contract, and perturbing the depolarization and repolarization pathways modulates the reconstructed waveform. Removing the specified partition and its orthogonality penalty costs 1.70 AUC and 11.30 macro-F1 points on PTB-XL, and 2.76 AUC and 16.92 macro-F1 points on Georgia. A capacity-matched permutation control places arbitrary assignments within 0.34 AUC points of the ontology routing and leaves macro-F1 statistically level (p=0.619): the ontology supplies decision-pathway auditability at no macro-F1 cost.
Read the full abstract ▾
All authors Shunbo Jia, Runze Ma, Haonan Lyu, Haijin Zhang, Qiang Yang, Caizhi Liao
Information Theory · Cross-listed from quant-ph
Quantum Teleportation Over a Noisy Relay Channel
Yigal Ilin and Uzi Pereg
Quantum teleportation and Bell measurements are considered in a noisy relay setting. We introduce two
quantum relay-channel models with closed-form capacity formulas, motivated by the canonical
quantum communication protocols of teleportation and superdense coding. In both models, the sender transmits a
qubit, while the relay observes side information about the Pauli errors that occur in the channel and communicates with the receiver through an orthogonal rate-limited link. We develop a compress-forward coding scheme in which the relay compresses the Pauli-error sequence into bins and sends the bin index to the receiver. The receiver uses this partial error information to reduce the effective channel noise before
quantum decoding. We show that this strategy is optimal by establishing matching converse bounds for both models.
Read the full abstract ▾
Data Structures and Algorithms
An Arboricity-Sensitive Algorithm for the $K_r-e$-Free Graph Sandwich Problem
Min Chih Lin and Natán Vekselman
For a fixed integer $r\geq4$, the $K_r-e$-free graph sandwich problem asks whether, given graphs $G_1\subseteq G_2$ on the same vertex set, there is an induced-$K_r-e$-free graph $H$ between them. We give a deterministic
algorithm taking $O(n+\alpha(G_2)^{r-3}m_2)$ time and space, where $m_2=|E(G_2)|$ and $\alpha(G_2)$ is the arboricity of $G_2$. In particular, the diamond-free case takes $O(n+\alpha(G_2)m_2)$ time. This improves the direct $O(n^r m_2)$ implementation of the previously known forced-edge closure. Our implementation maintains components of common neighborhoods indexed by $(r-3)$-cliques. A filtered frontier supports their merges within the clique-listing bound, while completion events avoid repeatedly searching for affected cliques. On feasible instances the output is contained in every feasible sandwich, independently of processing order. Applying the closure to $(G,K_n)$ gives an $O(n^{r-1})$-time bound for partitioned and nonpartitioned probe $K_r-e$-free recognition, improving the $O(n^{r+2})$ bound obtained from the direct sandwich closure. We also describe a direct static recognizer based on the same local characterization.
Read the full abstract ▾