Robotics
Representation World Model: Learning States, Transition and Executable Plans in Representation
Yijun Yuan, Weicheng Zheng, Weibang Wang et al. (+7 more)
We propose the Representation World Model (RWM), which learns states, transitions, and executable plans directly in representation space. Unlike existing world models that typically learn latent representations together with explicit dynamics models and perform planning through search, optimization, or policy-based prediction, RWM directly incorporates planning into the learned representation geometry. RWM learns the representation geometry by applying inverse-dynamics supervision locally along latent paths constructed from endpoint representations, requiring these paths to preserve task-relevant state and transition information. At inference, planning is performed by directly constructing a latent path between the current and goal representations, with inverse dynamics used to recover the corresponding actions, without recursive rollouts or action-space search. Experiments on continuous-control
benchmarks demonstrate the effectiveness of RWM for direct planning, while results on robotic manipulation further show its potential to extend to more complex
embodied control tasks. These results suggest that planning directly in representation space provides a promising alternative to conventional world-model planning.
Read the full abstract ▾
All authors Yijun Yuan, Weicheng Zheng, Weibang Wang, Minghui Qin, Chang Sun, Junhao Huang, Kenan Li, Anmin Liu, Yicheng Yao, Hang Zhao
Sound
Spot, Separate, and Enhance: Fully Generative Approach for Audio Mixing
Ilpo Viertola, Giulio Cengarle, Gouthaman KV et al. (+2 more)
We introduce Spot, Separate, and Enhance (SSE), the first
multimodal, user-guided generative model for audio remixing and enhancement. SSE enhances
video content by rebalancing the audio, removing unwanted audio sources, and reducing reverberation, guided by both
video and textual descriptions. To support its training and evaluation, we propose DegradedMix, a new
dataset built on the audio remixing
benchmark MuddyMix. We also adopt evaluation metrics from generative modeling, which better capture the creative nature of remixing than standard reconstruction-based metrics. SSE outperforms existing baselines in both controllability and remixing quality, as shown by extensive experiments. Project page: https://sse-ai.notion.site
Read the full abstract ▾
All authors Ilpo Viertola, Giulio Cengarle, Gouthaman KV, Daniel Arteaga, Lie Lu
Artificial Intelligence
IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking
Suvradip Paul, Chandra Bhushan, Harsh Sharma et al. (+4 more)
Banking assistants must use account-specific information to answer requests and, in many cases, take actions through tools. Evaluating only the final response misses important errors. An assistant may ask for information it already has, rely on stale context, select the wrong account, or write an invalid value after stating the correct one. We introduce IndicBankBench, a 799-case
benchmark for Indian retail banking spanning five operational domains, a capability/refusal domain, and twenty primary axes. Cases are evaluated at four stages: safety, action and tool use, response adequacy, and advisory quality. Tool use and most safety checks are deterministic. A narrow resolver handles only ambiguous confirmation-before-write cases, while a separate LLM judge evaluates semantic response adequacy. We run every case three times and report strict pass^3, which requires success on all trials. Across the eleven evaluated models, strict reliability ranges from 43.7% to 58.2%, whereas at-least-once success ranges from 60% to 74%. This gap shows that at-least-once success can overstate dependable banking behavior. The case-level diagnostics also distinguish systems that ask unnecessary questions from those that act but fail to reconcile customer context or fully resolve the request. We release the cases, mock environment, and evaluation harness.
Read the full abstract ▾
All authors Suvradip Paul, Chandra Bhushan, Harsh Sharma, Nitin Kukreja, Yatharth Dedhia, Keyur Doshi, Prashant Devadiga
Robotics
HarnessPAI: An Evolving Harness for Physical AI
Xin Wang, Wenhao Wu, Menghao Zhang et al. (+20 more)
Physical AI aims to build
embodied agents that perceive the world, understand and reason about it, and decide how to act. Yet the field has focused primarily on the last component: the action model that maps observations to low-level controls. The prevailing training recipe can erode the perceptual and
reasoning capabilities needed for robust behavior, leaving even strong action models vulnerable to scene perturbations and long-horizon tasks. We introduce HarnessPAI, a model- and embodiment-agnostic Harness framework for Physical AI that treats code as the executable and evolvable interface that organizes the underlying action primitive. The framework separates two timescales: within a rollout, it executes open-loop at the program level, with a fixed program guiding and checking execution; across rollouts, it evolves closed-loop, using execution feedback to revise the program and distill failures into reusable skills. Across desktop
robot arms, household
robots, a
robot vacuum, and a legged walking
agent, HarnessPAI demonstrates consistent improvements against baselines. Beyond the harness, the converged program also acts as a low-cost, reliable source of expert data: it generates training data for fine-tuning VLA and WAM models on tasks where it is hard for these models to obtain successful trajectories on their own. Our results suggest that the frontier of Physical AI depends not only on stronger action models, but also on executable harnesses that integrate perception, task understanding and
reasoning, and action execution into a unified, verifiable, and feedback-driven system. Website: https://darwin-
agent.github.io/HarnessPAI
Read the full abstract ▾
All authors Xin Wang, Wenhao Wu, Menghao Zhang, Zhi Wang, Kun Shao, Jian Luan, Yang Li, Qing Li, Shangding Gu, Huichi Zhou, Shuqing Shi, Fei Ni, Shuo Lu, Weicheng Meng, Kang Li, Jin Wu, Kang Zhao, Shangmin Guo, Gen Li, Yongqiang Tang, Zhizhong Zhang, Yuan Xie, Heng Qu
Machine Learning
Edge AI on Constrained Devices for Binary Sleep-Wake Classification in Dynamic Environments
Stefan Reitmann and Lena Oden
This paper presents an Edge AI-based system for detecting sleep and wake states in non-stationary mobile environments using resource-constrained embedded hardware. Conventional approaches relying on accelerometer-based activity metrics are highly susceptible to motion and vibration artifacts and are limited by strict compute and energy budgets of wearable and IoT devices. To address these challenges, a
multimodal pipeline is designed and implemented on an ESP32-S3 microcontroller. The system combines inertial sensing for head movement analysis and visual pose classification. A dual-core architecture with FreeRTOS enables parallel execution of real-time data acquisition and on-device inference. Sleep detection follows a two-stage strategy: low-movement detection over a temporal window, followed by visual validation of poses. Experimental results show accuracies of 96.5% for motion-based detection and 89% for pose classification, yielding robust binary sleep-wake classification. Field tests confirmed feasibility in representative mobile scenarios. The results demonstrate that
privacy-preserving, local sleep detection is achievable on edge hardware through careful co-design, while highlighting limitations in sensing intrusiveness,
dataset scale, and system integration.
Read the full abstract ▾
Digital Libraries
A framework for linking literature-based knowledge integration and infrastructure-supported knowledge integration: Opportunities and challenges from a case study
Mahlet Degefu Awoke, Hadi Ghaemi, Lauren Synder et al. (+2 more)
Integrating knowledge across disciplines is central to sustainability research, yet most evidence-synthesis methods rely on findings as reported in publications, limiting verification and reuse of underlying data and workflows. We develop a conceptual framework linking literature-based and infrastructure-supported knowledge integration, using a systematic review case study to examine when integration can extend beyond reported findings. We reviewed 37 studies on
climate change, violent conflict, and household food security. Literature-based synthesis enabled integration across all included studies, whereas access to reusable outputs was limited: over half provided no data availability statement, 27% reported availability upon request, but reusable data and workflows were available for only 8%. To explore infrastructure-supported integration, we used the TIB Knowledge Loom to represent studies with accessible data and code as machine-readable outputs, and produced a knowledge gap map (KGM) from manually extracted and Loom-derived data, comparing manual and infrastructure-supported synthesis. Where outputs were reusable, synthesis could be produced directly from data and workflows rather than from publications. These findings show that literature-based synthesis can be complemented by infrastructure-supported integration where outputs are accessible and usable, and that advancing knowledge integration depends not only on infrastructures but on making data, code, and workflows accessible, executable, and reusable.
Read the full abstract ▾
All authors Mahlet Degefu Awoke, Hadi Ghaemi, Lauren Synder, Markus Stocker, Tilman Brück
Distributed Computing
Cross-Model Autoscaling for Shared LLM Serving
Xin Zhang, Xianyan Xie, Zhen He et al. (+6 more)
Multi-model LLM serving is moving toward shared MaaS clusters, where co-hosted models compete for a fixed GPU budget while each model experiences time-varying demand and must satisfy its own latency SLO. Existing LLM autoscalers remain largely model-local: their signals expose local runtime activity or delayed latency outcomes, and their scale-up or provisioning decisions do not directly determine how shared capacity should be allocated across competing models. We present the
Token-service-share Rebalancing Engine (TRE), a control-plane framework for hot-switched multi-model LLM serving. TRE introduces
Token Service Share (TSS), a calibrated, demand-normalized signal that estimates effective
token service per active or queued request and yields a comparable health score across heterogeneous models and SLO classes. Guided by TSS, TRE coordinates bounded receiver–donor capacity movement under a fixed GPU budget: it separates fast rescue from slower rebalancing and incrementally reallocates active replicas toward models with the largest calibrated service deficits. We implement TRE on a Kubernetes-based hot-switch serving stack without modifying the inference scheduler. Across seven LLM serving traces, TRE reduces P95 end-to-end latency by 11.9–79.0% and P99 latency by 12.5–72.6% compared with a state-of-the-art KV-cache-based reactive autoscaler running on the same hot-switch runtime. The gains hold on both targeted stress probes and production-derived conversation/code traces, where TRE reduces P95/P99 latency by 50.8/63.7% and 79.0/72.6%, respectively. These results show that effective hot-switched autoscaling requires not only fast replica actuation, but also calibrated service-deficit signals and coordinated cross-model capacity arbitration. Our code and artifacts are available at https://github.com/zxzx9898/
Token-service-share_Rebalancing_Engine.
Read the full abstract ▾
All authors Xin Zhang, Xianyan Xie, Zhen He, Xijin Yin, Xingtong Lin, Bangbo Liang, Zequn Cheng, Peihao Huang, Guo Chen
Machine Learning · Cross-listed from math.DS
Functional dynamic mode decomposition: Learning infinite-dimensional systems from data
Stefan Klus and Eirini Ioannou
Dynamic mode decomposition (DMD) is a data-driven method that computes the best linear approximation of the underlying dynamical system and decomposes the dynamics into a superposition of characteristic spatiotemporal patterns. Originally introduced by the fluid dynamics community, DMD and its extensions have found widespread use in many other research areas such as molecular dynamics,
climate science, engineering, finance, and neuroscience. Applications include dimensionality reduction,
forecasting, system identification, control, and spectral clustering. In order to apply DMD to partial differential equations, the spatial domain is typically first discretized using finite difference or finite element techniques, thus implicitly rendering the problem finite-dimensional. We extend projected and exact DMD to infinite-dimensional systems. Rather than estimating
matrices from vector-valued observations, our DMD variants learn finite-rank operators from functional data such as observables, densities, or wavefunctions. We show that conventional DMD
algorithms can be regarded as special cases of their functional DMD counterparts. All results will be illustrated with the aid of guiding examples. We focus in particular on Koopman, Perron-Frobenius, and Koopman-von Neumann operators associated with graphons, ordinary differential equations, and
stochastic differential equations.
Read the full abstract ▾
Robotics
OREN-X: Octree Residual Network for Real-Time Multi-Modal Mapping
Zhirui Dai, Qihao Qian, Dinh Minh Nguyen et al. (+6 more)
To achieve general-purpose autonomy over long horizons, a
robot needs to maintain spatial environment information that supports a variety of tasks: geometry for planning and control, radiance for rendering and relocalization, and
vision-
language features for open-vocabulary grounding. Existing methods represent and estimate each modality separately, multiplying
memory and compute cost while forgoing potential synergy among the representations. We develop OREN-X, an online mapping method that uses an octree in 3D space as a shared data structure for indexing and storing a multi-modal field, capturing
geometric, radiance, and
vision-
language information. OREN-X provides efficient unified storage and
retrieval of these data in explicit/implicit and full/compressed form. Our unified representation yields cross-modality synergy: SDF estimates are sharpened by occupancy and radiance, while GPU-based ray-octree traversal and octree query enable real-time rendering. We also use online dictionary learning to compress the
vision-
language features, shrinking them 3.7x below full per-vertex storage while raising the query accuracy. On Replica, OREN-X maps in real time (80+ fps for SDF and 30+ fps for all four modalities), improves near-surface SDF accuracy by 33% over single-modality baselines, and improves mean open-vocabulary 3D mIoU by 71% and mean accuracy by 61% over the best prior method.
Read the full abstract ▾
All authors Zhirui Dai, Qihao Qian, Dinh Minh Nguyen, Quan-Dung Pham, Kiana Bronder, Carlos Nieto-Granda, Yiyu Chen, Quan Nguyen, Nikolay Atanasov
Computer Vision
Med-AR: Autoregressive Vision-Language Pretraining for Long-Tailed Chest X-Ray Classification and Uncertainty-Aware Evaluation
Janhavi Prabhu, Sahil, Akshay V et al. (+3 more)
Long-tailed chest X-ray classification requires visual representations that capture both common abnormalities and subtle, infrequent findings. We propose Med-AR-8B and Med-AR-2B, two radiology-native autoregressive
vision-
language models pretrained with structured reports, abnormality-focused text, and region annotations. We evaluate the transfer of their visual encoders to multi-label classification against contrastive, self-supervised, and supervised pretrained encoders, including Med-CLIP, CheXFound, EVA-Base, ARK, and BioViL-T, using a common ML-Decoder classification head. To assess fine-grained recognition, we also construct LLM-expanded, report-derived label sets for MIMIC-CXR and CheXpert. Across PadChest, MIMIC-CXR, and CheXpert, Med-AR-8B outperforms Med-CLIP in mean AUROC and AUPRC for head, medium, and tail findings. On MIMIC-CXR, it increases tail-label mean AUPRC from 0.1033 to 0.1441. Med-AR-2B achieves the strongest discrimination results on PadChest. Across the broader encoder comparison, a Med-AR variant achieves the highest mean AUROC and AUPRC in every reported prevalence group on each public
dataset. Both Med-AR variants also achieve lower excess area under the risk-coverage curve than Med-CLIP on all three public
datasets, indicating improved selective-prediction performance under the evaluated protocol. Internal results are metric-dependent, with Med-CLIP retaining advantages in overall and tail AUPRC and in selective prediction. These findings establish Med-AR as a strong pretraining recipe for long-tailed chest X-ray classification on the evaluated public
benchmarks and demonstrate the value of assessing discrimination and selective prediction together.
Read the full abstract ▾
All authors Janhavi Prabhu, Sahil, Akshay V, Shivam Shukla, Manoj Tadepalli, Preetham Putha
Artificial Intelligence
A Wrong Turn Does Not Ruin the Journey: Deviation-Guided Skill Self-Evolution for LLM Agents
Yichun Feng, Jiawei Wang and Haozhe Sun
Large
language model
agents increasingly rely on natural-
language skills to solve complex tool-use tasks. However, such tasks often admit multiple valid solution paths, making it inappropriate to improve skills by forcing failed trajectories to match a fixed successful trajectory. Moreover, failed trajectories are rarely entirely wrong: an
agent may first collect useful evidence and make meaningful progress, but later deviate into an erroneous suffix. We therefore argue that skill self-
evolution should identify where productive problem solving begins to break down, rather than reflect coarsely over the entire failure. Based on this insight, we propose SkillPivot, a deviation-point-guided framework for skill self-
evolution. SkillPivot detects the transition from a useful prefix to an erroneous suffix using execution validity, goal progress, and action diversity. A stronger teacher then continues from the same prefix and produces a successful alternative under the same interaction history. By contrasting the student's failed suffix with the teacher's successful suffix, SkillPivot generates localized skill updates while preserving already effective guidance. Experiments on ToolQA, LogicBench, and WildClawBench show that SkillPivot consistently outperforms competing skill-
evolution methods, improves multiple
agent models, and produces compact, transferable skill updates.
Read the full abstract ▾
Numerical Analysis
On degeneration of tetrahedra under longest-edge n-section refinement
Sergey Korotov
For every integer $n \ge 2$, we construct explicit tetrahedral counterexamples showing that repeated longest-edge (LE) n-section refinement does not, in general, preserve shape regularity, contrary to long-standing conjectural expectations. For $n = 2$, the construction disproves the finite-family
conjecture put forward by Adler in 1983 and the non-degeneracy
conjecture for tetrahedral longest-edge bisection formulated by Rivara and Levin in 1992. It also shows that the sharper higher-dimensional diameter decay suggested by Stynes in 1983,following his 1980 planar finite-similarity result, cannot hold for arbitrary tetrahedra. For $n = 3$, it disproves the published non-degeneracy
conjecture for tetrahedral longest-edge trisection formulated in 2011 by Suárez, Abellón, Abad and Plaza on the basis of numerical experiments. The resulting infinite descendant sequences violate both the minimum and maximum angle conditions. For $n \ge 3$, the selected edge is always the unique longest edge at every refinement step. The two-step recurrence used in the construction exhibits two distinct degeneration behaviors: a flat-tetrahedron regime for $2 \le n \le 5$ and a skinny-tetrahedron regime for $n \ge 6$. The degenerating sequences can also be realized within conforming partitions generated by the conforming LE n-section
algorithm. For both the classical and the conforming LE n-section
algorithms, the maximal element diameter tends to zero as the number of refinement steps tends to infinity, regardless of which longest edge is chosen. Thus diameter convergence, and even conformity, do not prevent shape degeneration. These
algorithms should therefore be used with care in applications requiring uniform shape regularity.
Read the full abstract ▾
Computer Vision
Recoverable Geographic Location Information in Earth-Observation Embeddings
Peiwen Zhang, Kristie Hu, Jovana Knezevic et al. (+2 more)
Earth-observation (EO) foundation models provide reusable
embeddings, yet downstream task accuracy does not reveal whether these representations encode geographic information, which may be beneficial for location-aware applications but potentially detrimental when representations invariant to geographic location are desired. We therefore evaluate the geographic coordinate robustness of Tessera v1, Tessera v1.1, and AlphaEarth by testing whether coordinates can be predicted from the
embedding representations using 284 quality-verified European
solar farms from 2024. We assessed geographic information content information through the association between cosine and geodesic distances and through prediction of projected coordinates in EPSG:3035.
Embeddings from all three EO foundation models contain recoverable geographic information. All prediction models significantly outperform training-range uniform random sampling baselines, with AlphaEarth exhibiting the strongest distance association and lowest mean geodesic error. Both Tessera variants also yielded higher geographic distance correlations than the Sentinel-2 controls. These findings motivate geographic information content as an additional criterion for
auditing EO foundation models.
Read the full abstract ▾
All authors Peiwen Zhang, Kristie Hu, Jovana Knezevic, Shunde Yin, Kyle Gao
Machine Learning
A Particle-Swarm-Assisted Gradient Meta-Learning Algorithm for Joint Transmit Precoding and STAR-RIS Coefficient Optimization
Kang Zhou
This paper investigates the joint optimization of the transmit precoder and the transmission/reflection coefficients of a simultaneously transmitting and reflecting reconfigurable intelligent surface (
STAR-RIS) to maximize the weighted sum rate (WSR) in a multi-user downlink. We propose a particle-swarm-assisted gradient meta-learning (PSA-GML)
algorithm for this non-convex problem. The original problem is first equivalently transformed via an amplitude-split parameterization and a collapsed precoder representation, which automatically satisfy the energy-conservation constraint and reduce the search dimension. Particle swarm optimization (PSO) then performs a global search over the
STAR-RIS coefficients to yield a high-quality, initialization-robust warm start, with the transmit precoder obtained in closed form. Departing from conventional alternating optimization (AO), a coordinate-wise long short-term
memory (LSTM) meta-optimizer trained by first-order gradient meta-learning further refines the coefficients and precoder jointly, learning per-coordinate adaptive update rules from data. The meta-optimizer is trained offline and applied to unseen channels without further adaptation. Numerical results show that PSA-GML attains an 11.06 bits/s/Hz WSR at 10 dB with N=32 elements and K=4 users, exceeding AO by 13.1% (and by 6.2% even with multiple random restarts) and the random-phase scheme by 35.1%. In the interference-limited regime it reaches 83.9% of the hand-designed Adam refinement without manual hyper-parameter tuning, and it transfers zero-shot across regimes, indicating that the learned update rule captures the intrinsic WSR landscape structure.
Read the full abstract ▾
Information Theory
Replica Thresholds for Stripeless Erasure Coding Based on Symmetric Block Designs
Guiwen Luo, Xiao Li, Yaqiang Zhang et al. (+1 more)
This paper investigates a fundamental question in stripeless erasure coding based on symmetric balanced incomplete block designs (SBIBDs): how many replicas per object are precisely required to guarantee recovery from any set of at most $p$ node failures? We refine the known sufficient recovery guarantee for the generalized SBIBD $(v,k,\lambda)$ construction. One replica is necessary and sufficient for $p=1$, and $q=\lambda(p-1)+2$ replicas ($q\le k$) guarantee recovery for $p\ge2$. Recovery takes one round for $p=2$ and at most two rounds in general. To study the tightness of this count, we define the universal replica threshold $q^\ast(A,p)$ for a fixed zero-diagonal SBIBD representative~$A$. We determine $q^\ast(A,p)$ for $p=1$ and $p=2$. For $p\ge3$, we identify pairwise separated sets and private target permutations as the structures determining whether the sufficient count is tight or can be further reduced. These conditions give exact thresholds for all but the case where $\lambda>1$ and $A$ contains no pairwise separated set of size~$p$. We improve the bounds for this remaining case and leave its exact threshold open. Finally, we give sufficient conditions for pairwise separated sets and show how affinity relabeling can realize private target permutations.
Read the full abstract ▾
All authors Guiwen Luo, Xiao Li, Yaqiang Zhang, Ke Wang
Computation and Language
BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech
Mizbaul Haque Maruf
Bangla, the seventh most spoken
language in the world, remains under-resourced for neural text-to-
speech. Public Bangla
speech corpora are dominated by short read-
prompt utterances collected for
speech recognition, leaving long-form prosody and consistent single-speaker narration uncovered. We present BanglaKontho, a single-speaker Bangla TTS corpus of 20 hours derived from professional audiobook recordings: 7,050 segmented utterances with verified transcripts at 24 kHz. We also release a reusable Bangla text normalizer covering Bangladeshi-style digit grouping, currency and date expressions, Danda punctuation and Unicode normalization, together with the full preprocessing pipeline. An MB-iSTFT-VITS baseline trained from scratch reaches 9.5% WER and 4.46 naturalness MOS, against 16.0% and 3.16 for the same architecture retrained on the 12-hour IndicTTS-Bn corpus. The corpus is released openly under CC BY-NC 4.0.
Read the full abstract ▾
Artificial Intelligence
Claim-Gated Source-Risk Auditing for Generative Search
Kainan Zhou, Chuhong Xu, Gangzhen Qian et al. (+1 more)
A generative search answer can cite a supported passage yet omit a source relationship that changes its interpretation. We specify a claim-gated audit of the query-source-answer tuple. An omission is resolved only when relationship evidence, answer adoption, materiality, and disclosure are all observed; incomplete evidence remains unresolved rather than being treated as independence. The specification separates this endpoint from citation support and review priority, and binds decisions to versioned evidence spans. A reference checker makes the record contract executable. On an exhaustive synthetic suite, it reproduces all 81 three-state predicate combinations and rejects 192 deliberately malformed records. Common-guard baselines and predicate ablations isolate endpoint logic from missing-evidence handling, while controlled transitions check support separation and evidence removal. These are finite contract-conformance results, not detector accuracy or evidence of improved user outcomes. We define the independent annotation, held-out evaluation, and paired utility tests still required to establish semantic validity and deployment benefit.
Read the full abstract ▾
All authors Kainan Zhou, Chuhong Xu, Gangzhen Qian, Zhaoyi Li
Artificial Intelligence
Scope Before You Persist: Preventing Cross-Family Interference in Agent Memory
Yezhou Cheng, Runjia Du, Zeming Liu et al. (+5 more)
Persistent
memory lets
language-model
agents improve
prompts and skills without updating model weights. We show that matching
retrieval scope to certification scope enables these edits to support reliable repeated adaptation across recurring task families. We study frozen-model
agents on ProcStream-RSI, a 12-round code-repair stream, using Orthogonal Regression Control (ORC), an execution-grounded gate for persistent skill edits. In an intervention that holds proposals and gate decisions fixed, retrieving each accepted skill only for its originating family raises mean hidden trajectory utility from 0.713 under global
memory to 0.816 and changes harmful deployments from six of eight to none. In 27 paired randomized-order streams, Scoped-ORC improves mean trajectory utility by 0.063 [0.037, 0.094] over Global-ORC, accepts 63 rather than 12 updates, and produces multiple accepted updates in 19/27 streams, with 0/63 harmful acceptances. The global control reaches 0.713, below the static
agent's 0.775, because locally valid edits can interfere with unrelated families. These results establish scope matching as a complementary control for persistent
agent memory: certification determines whether an edit is supported, while
retrieval scope determines where that evidence authorizes its use.
Read the full abstract ▾
All authors Yezhou Cheng, Runjia Du, Zeming Liu, Qibai Chen, Hang Lyu, Yankai Zeng, Yilan Wei, Bojun Lin
Computers and Society
AI-Moderated Interviews for Market Research and Digital Twins Calibration
Yuting Deng, Jingxuan Liu, Olivier Toubia et al. (+1 more)
AI-moderated interviews are emerging as a scalable
market-research method for generating consumer insights and building consumer "digital twins." Yet it remains unclear whether they match human-moderated interviews and whether they improve on simpler, static data collection methods. In a pre-registered study with three industry partners, the authors randomly assign participants to AI-moderated interviews (N = 139), static interviews (N = 154), or interviews conducted by professional human moderators (N = 24). AI moderation matches human moderation in depth, covers more themes, and, at equal budget, recovers more customer needs than either alternative, although participants sound more emotionally engaged with a human interviewer. The authors then build a digital twin of each participant and evaluate it against the participant's own held-out responses to six real-world marketing stimuli. Twins built from AI-moderated interviews predict consumer responses better than demographics-only personas, but no better than twins built from static interviews: the richer conversation does not necessarily yield more accurate predictions. Comparing the open-ended explanations provided by participants and their twins shows that prediction errors arise when twins reason differently than the people they represent and when questions fall far outside what the interview covered. AI moderation thus pays off most for discovering customer needs, and less for predicting customer responses.
Read the full abstract ▾
All authors Yuting Deng, Jingxuan Liu, Olivier Toubia, Naman Jain
Machine Learning
Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD
Yibo Zhao, Zixuan Yang, Yunshi Lan et al. (+1 more)
Direct On-Policy
Distillation (Direct-OPD) transfers reinforcement-learning-induced policy improvements from a small model to a larger student by using the
token-level log-ratio between post-RL and pre-RL checkpoints as dense supervision on the student's own rollouts. This transfer rewards the policy shift at every state, yet the log-ratio measures only relative change: it can stay fixed even as the probability mass that both checkpoints assign to the student's candidate
tokens vanishes. Through an exact construction, we show that the Direct-OPD reward and its update can remain unchanged while the Jensen-Shannon divergence (JSD) and both KL directions between the checkpoints vanish with this mass, and we note that a small JSD bounds how much the teacher's behavior changed. Motivated by this analysis, we propose Selective Supervision for Direct-OPD (S$^2$D-OPD), which ranks student-sampled states by their teacher-reference JSD and masks Direct-OPD supervision at low-divergence states, retaining only the top 10% of states per response. Across two teacher pairs and four student models ranging from 1.7B to 8B parameters, S$^2$D-OPD improves held-out accuracy over dense Direct-OPD on AIME and HMMT
benchmarks in seven of eight settings and matches it in the eighth, without extra forward passes.
Read the full abstract ▾
All authors Yibo Zhao, Zixuan Yang, Yunshi Lan, Xiang Li
Data Structures and Algorithms
A Deterministic Polynomial Kernel for Odd Cycle Transversal
Tomohiro Koana and Soh Kumabe
We give a deterministic
polynomial kernel for Odd Cycle Transversal, derandomizing the randomized kernel of Kratsch and Wahlström (TALG 2014). Our
algorithm uses a deterministic
polynomial-time construction of almost multilinear representations of gammoids. Such a representation assigns a block of columns to each element so that, for every subset of elements, the normalized
matrix rank approximates its matroid rank to within a prescribed additive error $\delta$. The construction builds on recent breakthroughs in NC
algorithms for matching. Our kernelization
algorithm then computes the required representative families from these representations.
Read the full abstract ▾
Artificial Intelligence
Sharp Limits for Honest Uncertainty in Hard-Budget Repeated Evaluation
Yezhou Cheng, Runjia Du, Zeming Liu et al. (+5 more)
Repeated evaluation can estimate a
benchmark score accurately while still requiring replication to certify narrow uncertainty. We characterize that requirement on a fixed grid of $M$ tasks with $L$ binary paths per task under the hard budget $(M+t)K$, where each path costs at most $K$ responses or episodes. For fixed $L \ge 3$ and $0 < \alpha \le 1/12$, the optimal expected width on the worst pure cohort is $\Theta_{\alpha,L}([M(t+1)]^{-1/2})$ when every task is observed and $\Theta_{\alpha,L}([M(t+\sqrt{M})]^{-1/2})$ when omission is allowed. The lower bounds cover adaptive hard-budget policies, and fixed random-subset designs attain both rates through disagreement certificates. A joint mean/disagreement interval turns the task-covering law into practical finite-budget inference. In an equal-budget LiveCodeBench replay with 16 models, 880 tasks, and five outputs per task, the task-covering design reduces median point-estimation MSE by 87.0% relative to pooled uniform sampling, while the Joint certificate produces narrower confidence intervals in 15/16 panels and reduces median interval width by 30.6%. Finite-regime analyses identify task coverage as the effective choice at the evaluated scale and characterize how cohort size and within-task agreement determine the useful operating region. Together, the sharp laws and fixed-budget evidence make replication and task coverage explicit design variables for information-efficient repeated evaluation.
Read the full abstract ▾
All authors Yezhou Cheng, Runjia Du, Zeming Liu, Qibai Chen, Hang Lyu, Yilan Wei, Yankai Zeng, Bojun Lin
Robotics
A Tendon-Driven Robotic Jellyfish with Constrained Soft Actuation and Depth Control via Reinforcement Learning
Jiarui Peng, Yutong Wu, Zelong Wang et al. (+5 more)
Jellyfish-inspired
robots offer a compliant and efficient approach to
underwater locomotion, but achieving large deformation together with repeatable actuation and closed-loop control remains challenging. In this work, we present a tendon-driven robotic jellyfish with constrained soft actuation. Each actuator combines a flexible substrate with discrete constraints, enabling bending up to \(150^\circ\) with an approximately linear tendon displacement-bending relationship. Eight actuators driven by four servos allow the
robot to perform stable swimming, attitude adjustment, and self-righting. Based on the linear actuation, a reinforcement-learning controller is further developed, enabling closed-loop depth regulation in both simulation and physical experiments. These results show that mechanical constraints can improve the controllability of soft actuation while preserving compliant jellyfish-like motion, providing a route toward manoeuvrable and autonomous jellyfish
robots.
Read the full abstract ▾
All authors Jiarui Peng, Yutong Wu, Zelong Wang, Ping Deng, Xiaotian Zhang, Xian Chen, Kecheng Qin, Zhongyu Li
Computation and Language
Tag-Aware Structured Text Translation: Towards a Systematic Understanding
Zhanglin Wu, Hengchao Shang, Daimeng Wei et al. (+5 more)
Internet texts are replete with format tags that carry structural, semantic, and functional meaning. Current large
language model (LLM)-based translation systems struggle to balance translation fluency with tag fidelity when processing tagged text. We argue that resolving this tension requires a systematic approach at three interconnected levels: data synthesis, capability building, and multi-objective
alignment. At the data level, we identify and formalize a fundamental trade-off between structural tag diversity and translation naturalness in synthetic data generation; existing methods optimize for one at the expense of the other. We propose a hybrid synthesis strategy (Hy-LST) combining LLM-based synthesis tag method and Two-Stage LLM-based synthesis tag method to produce both diverse and natural tagged data. At the capability level, we decompose tag-aware translation into four sub-tasks of increasing difficulty in a multi-task supervised fine-tuning framework, enabling targeted capability acquisition and knowledge transfer. At the
alignment level, we design three complementary reward functions under a group relative policy optimization framework, each targeting a distinct objective (fluency, tag fidelity, and tag-scoped translation quality), and show that joint optimization consistently outperforms single-reward alternatives. Experiments on six
language directions (en2zh, en2ja, en2de, en2fr, en2ru, de2fr) demonstrate that each level contributes measurable improvements, and the complete system significantly outperforms existing methods. Qualitative analysis reveals specific error patterns and their mitigation after training with our method.
Read the full abstract ▾
All authors Zhanglin Wu, Hengchao Shang, Daimeng Wei, Jiaxin Guo, Zongyao Li, Tengfei Song, Ning Xie, Weidong Zhang
Cryptography and Security
ClaimMirage: When Self-Claims in Domain Names Change LLM Threat Judgments
Daiki Chiba, Hiroki Nakano and Takashi Koide
Short claims such as not-phishing or official can change how a large
language model (LLM) judges a domain name, without explicit
prompt-injection commands. We study this manipulation as ClaimMirage: a name under inspection claims its own safety or approval. We analyze 622,080 judgments across 64 brands and five LLMs, comparing ten claims with length- and hyphen-matched controls in constructed brand-like names. Self-claims can substantially reduce or increase alerts, depending on the LLM and input setting. In one setting, risk-denial terms inside the registrable name reduce alerts by 45.3 percentage points even with a basic safeguard: the
prompt supplies the potentially impersonated brand and its official domain for comparison. Without these references, endorsement terms at that position increase alerts by 65.6 points in the same LLM. References and component annotation remove some alert reductions but leave others or make them larger. These findings motivate testing resistance to self-claims and seeking independent evidence before treating a domain name under inspection as safe or authorized.
Read the full abstract ▾
Software Engineering
VidTutorAssistant: Automating Responses to Programming Tutorial Questions
Ahmad Tayeb, Sonia Haiduc and Mohammad D. Alahmadi
Programming tutorial
videos on YouTube are an important information resource for software developers and students, and their comment sections have evolved into active spaces where viewers ask follow-up questions. The volume of these questions, however, often exceeds what content creators can address, leaving learners without the clarifications they need. We present VidTutorAssistant, a web platform that automates responses to viewer questions on programming
video tutorials. VidTutorAssistant implements a
retrieval-augmented generation pipeline that extracts a
video's transcript, then segments it and embeds it. It then classifies each viewer comment as being a question or non-question, retrieves the most relevant transcript segments to each identified question via cosine similarity, and then generates an answer to the question using an LLM (GPT-4), while grounding the response using the retrieved transcript segments as context. We validate VidTutorAssistant through a study on a subset of 440 user comments selected from a larger
dataset of 105,553 comments extracted from 7,522 Python and Java tutorials. VidTutorAssistant is evaluated on various criteria: a) its ability to identify the programming
language in a
video, achieving a 0.99 accuracy; b) its ability to classify comments into questions and non-questions, reaching a 0.96 accuracy; and c) its ability to produce correct and complete answers to questions, producing 98% correct and 99.5% complete responses, compared with 89% and 90% for the original creators' answers.
Read the full abstract ▾
Cryptography and Security
The Fly That Stopped: Mushroom-Body-Inspired Habituation as a Reward-Free Scheduling Prior for Autonomous Penetration Testing
Theodoros Moutesidis
Autonomous security-testing
agents can spend much of a fixed action budget repeating earlier tool selections. We evaluate a reward-free scheduler inspired by mushroom-body novelty processing in Drosophila. It combines sparse state encoding with decaying habituation counters over structural URL classes and tool families. The counters penalize repeated clean or error outcomes without updating weights from scalar reward. Four matched campaigns motivated this design by exposing reward-accounting errors and tool-failure loops; reward-driven components did not improve the tested primary outcomes over the reward-free MB condition. A pre-registered pilot and two confirmatory stages then evaluated repeated (tool, URL) selections. In the second confirmatory stage, 8 of 10 screened lab targets remained measurable after two error-heavy slow-XSS exclusions. The habituation-enabled scheduler lowered duplicate-action ratios in all 6 non-tied target pairs (exact one-sided p=0.015625), with two ties; the largest reduction was 51 to 18 duplicate steps within a 60-step budget. This is evidence for the complete scheduler on the measurable budget-hold population, not an isolated habituation ablation or a vulnerability-discovery gain. A complementary study on a 13,498-
neuron MaleCNS-derived
circuit (501,267 synaptic edges with weight at least 5) found no action selectivity from the five tested local-plasticity approaches under a fixed readout; readout plasticity produced qualified positive results in synthetic tasks without establishing a biological-
topology advantage. We report the population bounds, remaining input-integrity dependencies, and an internal AI-assisted review protocol alongside the results.
Read the full abstract ▾
Computer Vision
FoCal: Frequency-Oriented Cross-Modal Interaction and Spectral Calibration for Aerial Visible-Infrared Object Detection
Ben Liang, Chao Sui, Junqi Bai et al. (+4 more)
In aerial RGB–IR object detection, effectively exploiting complementary information across modalities is critical for robust perception under complex illumination and environmental conditions. Existing
multimodal detectors mainly focus on spatial-domain interaction or frequency-specific feature enhancement, while the cross-modal interaction patterns of different frequency components remain insufficiently explored. Moreover, spectral discrepancy itself may contain both useful complementary cues and unreliable modality-specific responses, making indiscriminate frequency fusion suboptimal. To address these issues, we propose FoCal, a frequency-oriented framework for aerial RGB–IR object detection. First, a Frequency-Aware Dual-Domain Calibration (FADC) module is developed to explicitly model frequency-dependent cross-modal interaction. Low-frequency components are collaboratively consolidated into a shared structural consensus, whereas high-frequency components preserve modality-specific information through selective cross-modal exchange. The resulting frequency-aware cues are further transferred to the original feature domain to regulate cross-modal calibration. Second, we introduce a Discrepancy-Guided Spectral Modulation (DGSM) module, which characterizes cross-modal spectral imbalance using confidence-weighted relative amplitude discrepancy and transforms it into a bounded signed gate for adaptive enhancement, preservation, or attenuation of the joint
multimodal spectrum. Extensive experiments on DroneVehicle, ESCVehicle, and ATR-UMOD demonstrate the effectiveness of FoCal, yielding $\mathrm{mAP}_{50}$ values of 83.5%, 54.8%, and 64.6%, respectively. Meanwhile, with only 3.0M parameters, FoCal achieves 113.6 FPS while preserving leading detection accuracy, highlighting a favorable accuracy–efficiency trade-off. Code is available at {https://github.com/universeliang/FoCal.
Read the full abstract ▾
All authors Ben Liang, Chao Sui, Junqi Bai, Yuan Liu, Chunlai Li, Xiubao Sui, Qian Chen
Sound
Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning
Yoomee Cho and Jisun Lee
In cross-lingual zero-shot text-to-
speech, the accent of the reference leaks into the target
speech. We propose accent analogy guidance (AAG), a training-free sampler term that subtracts an accent direction estimated from the model's own predictions for one synthetic voice rendered in both
languages, so the voice cancels and only the accent remains. By a blind LLM accent judge on real dubbing data, reweighting classifier-free guidance between reference and text, and its variants, stay near one identity-accent trade-off curve; we score a method by its speaker similarity above that curve at equal accent ($\Delta$SIM). Across four open TTS models AAG lies above the curve: on OmniVoice $\Delta$SIM is +0.11 to +0.27 on three test sets (accent 3.51 to 4.28 on a 1-5 scale at speaker similarity 0.29, where reweighting keeps 0.02); MaskGCT and CosyVoice 2 also lie above their curves, and on F5-TTS it is more native than any reweighting setting. An LLM-free
language-ID measure and a twelve-listener panel agree. A premise test and the reach of a model's own curve indicate in advance whether and roughly how much AAG can gain, predicting the one model where it gains nothing (X-Voice).
Read the full abstract ▾
Computer Vision
Less is More: Encoder-only Audio-Visual Segmentation
Ilpo Viertola, Vladimir Iashin, Sophie Tötterström et al. (+1 more)
Audio-Visual Semantic
Segmentation (AVSS) aims to identify, segment, and classify sound-emitting objects in
video frames. Previous
Transformer-based AVSS approaches largely inherit design principles from image
segmentation models. Recent studies show that these image
segmentation models contain redundant components that contribute little to the
segmentation performance. Following this insight, we propose Encoder-only Audio-Visual
Segmentation (EASE). EASE runs at up to 365 FPS, 3x faster than prior State-of-the-Art (SotA) AVS models at comparable accuracy, and trains in under 11 GPU-hours. Furthermore, we achieve SotA AVSS performance across different backbones and input resolutions. Our results demonstrate that AVSS can be both simpler and faster, providing a scalable foundation for future research and real-time applications. Code, model weights, and samples are available at https://ease-avs.notion.site
Read the full abstract ▾
All authors Ilpo Viertola, Vladimir Iashin, Sophie Tötterström, Esa Rahtu