Computation and Language
RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue
Yuqi Wang, Fengyuan Liu, Haochen Luo et al. (+2 more)
Speech-to-
speech dialogue models increasingly support persona control, yet existing spoken role-playing
benchmarks remain largely character-centric and short-horizon. This leaves open whether spoken dialogue models can sustain diverse roles over extended interactions, especially beyond predefined fictional characters. We introduce RoleBreak, an open
benchmark for long-horizon role-playing robustness in spoken dialogue. RoleBreak contains 310 character-based and user-centered roles, 6,688 human-verified dialogue turns, and 11,743 fine-grained evaluation criteria, with 1,856 turns carrying expressive
emotion targets for evaluating vocal
emotion. Its scenarios are designed to stress role consistency, interaction quality, safety, and affect over extended conversations. We evaluate nine configurations spanning full-duplex, omni-modal, and cascaded ASR–LLM–TTS paradigms. We find four key patterns. First, current systems are substantially stronger at semantic role adherence than at vocal
emotion. Second, semantic robustness remains brittle over long interactions: even the strongest evaluated system encounters its first persona and safety failures after only 10.4 and 11.6 turns on average. Third, scaling the LLM substantially improves semantic robustness and delays failure, but yields little improvement in vocal
emotion. Finally, user vocal
emotion affects role-playing behavior even when linguistic content is fixed. These findings highlight persistent gaps in both long-horizon robustness and vocal expressiveness in spoken role-playing systems.
Read the full abstract ▾
All authors Yuqi Wang, Fengyuan Liu, Haochen Luo, Zhiqi Yu, Qi Liu
Sound
Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal corpora using frozen audio encoders
Mudit Sinha and Sanika Chavan
Comparing acoustic structure across very different vocal corpora is difficult because the recordings use different native event units, contain different amounts of sequence, and were collected under different conditions. We develop a matched procedure for comparing such corpora without forcing them into the same event definition. Frozen audio encoders provide a common acoustic representation for recorded events, while matched sampling gives each corpus the same amount of evidence for acoustic and sequence analysis. We apply this procedure to sperm-whale codas, human
speech phones, Bengalese-finch syllables, and common-marmoset calls. The comparison reveals different patterns across the four corpora. Sperm-whale recordings stand out broadly: new acoustic forms continue to appear, while their sequences also show strong organization and repetition. Finch recordings show the strongest organization of sounds over time, especially in how neighboring sounds and repeated patterns are arranged. Direct temporal and spectral measurements show that these differences are also present in the recorded sounds themselves. The comparison provides a practical way to measure acoustic diversity and temporal organization across very different vocal corpora by combining a common acoustic representation with matched observation opportunity, without treating their native sounds as equivalent.
Read the full abstract ▾
Computer Vision
EgoPathBench: Evaluating Zero-Shot Egocentric Waypoint Decision-Making in Vision-Language Models
Yang Zhao, Zhuo Chen and Xubo Yang
Zero-shot waypoint
navigation requires
vision-
language models to select, from the current first-person observation, a sequence of spatial actions that is feasible for the
agent and reaches the goal, placing joint demands on the integrated spatial intelligence of today's foundation VLMs. Existing spatial-intelligence
benchmarks primarily evaluate isolated judgments of relations, directions, or targets and therefore do not directly measure the integrated
navigation ability required to combine target recognition, action-consequence assessment, distance estimation, and path planning. To fill this evaluation gap, we introduce EgoPathBench, a
dataset and five-task
benchmark for first-person waypoint decision-making. Each question presents an
egocentric RGB image, a natural-
language goal, and numbered visible waypoints; a model returns traversable candidates or an ordered route. Predictions are evaluated for candidate feasibility, adjacent-edge legality, and goal arrival under point-
agent or
embodied geometry. EgoPathBench contains 31,852 training, 1,345 validation, and 1,111
benchmark questions and retains at least one geometrically verified reference route for every route question. Across nine VLMs, the highest EgoPath Score is only 28.3. The top-ranked model reaches 35.9% success on Point Path, but only 2.9% and 4.0% on
Embodied Path and Intent Path, respectively, showing that current models remain limited in forming complete, goal-consistent routes under embodiment constraints. Beyond the evaluation data, we release the corresponding training resource. Fine-tuning Qwen 3.5 4B on the released training split raises its EgoPath Score from 3.9 to 38.9 and improves all four reported evaluations across three external spatial
benchmarks, with gains of 1.4–9.6 points.
Read the full abstract ▾
Information Theory · Cross-listed from quant-ph
Strong converse for the quantum capacity of the pure-loss bosonic channel
Mark M. Wilde
This paper reports the proof of a strong converse for the unconstrained
quantum capacity of the pure-loss bosonic channel. At every fixed rate above capacity, the
entanglement-generation fidelity of every code is bounded by a constant times the reciprocal of the number of channel uses. The bound holds without an energy constraint and for arbitrary encoded states, including states correlated across all input modes, and arbitrary joint decoders. The proof combines
quantum Chebyshev and hockey-stick testing inequalities with a uniform relative-
entropy-variance bound for the balanced pure-loss channel, corresponding to transmissivity $\eta=1/2$. The variance bound follows by expressing the balanced beam splitter in bright and dark modes: the dark modes are exactly in
vacuum, and any state orthogonal to that
vacuum contains at least one dark
photon. For general transmissivity, dilating the degrading attenuator reduces the problem to this balanced-channel setting and bounds the decoder test by precisely the factor that produces the known
quantum-capacity threshold. The resulting argument establishes the strong converse at the unconstrained
quantum capacity for every pure-loss bosonic channel.
Read the full abstract ▾
Information Retrieval
Measuring Decision-Scale Use in Tool-Augmented LLMs: A Contrastive Urban Benchmark
Ray Chen, Vivian Wong and Christan Grant
Urban decision-support often asks whether activity is unusually high or low for a specific place, not which place has the larger raw count. Twenty pickups in a quiet neighborhood can be more abnormal than 180 at an airport. We introduce URBANCONTRASTIVEQA, a
benchmark that asks whether tool-augmented
language models can make this baseline-relative comparison. Each item pairs two urban situations from public mobility data in NYC, Chicago, and Seattle, labeled by how far current activity deviates from that place's historical baseline. We evaluate six instruction-tuned models under five tool-output formats. With only raw counts, models often pick the larger number even when it is less abnormal for its zone. Server-computed baseline scores and ordinal labels raise accuracy, but gains vary by model. For heterogeneous urban feeds, tool interfaces need to expose local baselines, not just activity volumes. We release the pair bank, labels, scoring scripts, and data card.
Read the full abstract ▾
Machine Learning
A Weighted Kernel Method for Approximation that Adapts to Learned Multivariable Structure
John E. Darges and Laura Weidensager
Approximating the input-output behavior of a multivariable black-box function from limited data is challenging when blind to the importance of its inputs and their interactions. We introduce total sensitivity kernels (TSKs), a method based on families of weighted ANOVA kernels that learn and adapt to this multivariable structure. TSKs parameterize the weights on each multivariable component of the target function by factors for each input. We propose learning these factors directly from function evaluations by selecting the reproducing kernel
Hilbert space (RKHS) in which the target function has minimum norm. Under suitable conditions, we show that this norm-minimization problem admits a unique solution, and we establish consistency of a finite-data formulation based on minimum-norm interpolation. The learned TSK factors characterize the participation of individual inputs across interactions and main effects, providing a kernel-dependent notion of input sensitivity related to total Sobol indices. Numerical experiments demonstrate that adapting the kernel to learned multivariable structure can substantially improve approximation accuracy over a standard product kernel.
Read the full abstract ▾
Software Engineering
An Exploratory Study of Dependabot Cooldown Adoption in Open-Source GitHub Projects
Hidetake Tanaka, Rikuto Tsuchida, Kazumasa Shimari et al. (+2 more)
Automated dependency updates can rapidly propagate malicious package releases before maintainers and the broader community have enough time to detect them. In July 2025, GitHub made Dependabot cooldown generally available as a defense against software supply chain attacks. However, the effects of its early adoption remain unknown. In this exploratory study, we empirically examine how popular open-source GitHub repositories adopt and configure the feature and investigate their motivations. We find that security concerns motivated 83 of 92 adoption events with known motivations. Security linter warnings triggered 43 of 75 security-only adoptions. Among 251 ecosystems within repositories that retained cooldown, 97.2% set a general delay. Of these, 64.3% used seven days, while use of each update type setting was below 10%. Early adopters therefore favor simple default delays over fine-grained controls. These findings suggest that tools could provide robust defaults reflecting ecosystem support and reserve fine-grained controls for dependencies with clear update priorities.
Read the full abstract ▾
All authors Hidetake Tanaka, Rikuto Tsuchida, Kazumasa Shimari, Raula Gaikovina Kula, Kenichi Matsumoto
Software Engineering
ExecuCritic: Calibrated Critic Shaping for Code Generation with Verifiable Rewards
Junjie Cao and Yingjie He
Execution feedback is a useful supervision signal for code models because unit tests are objective and directly measure program correctness. Its weakness is that an entire program is often reduced to one pass or fail bit, leaving RLVR to solve a difficult credit assignment problem. At the same time, coding systems often include separate reviewer or tester roles, but these critics are usually prompted rather than trained and are not calibrated against execution. We propose ExecuCritic, a joint training framework in which a coder and a critic are updated on the same execution rollouts. The critic predicts pass or fail outcomes and gives short diagnostic feedback; the coder uses this signal only when the critic agrees with the executor on the current rollout group. Across eight code
benchmarks and two recent open backbones, ExecuCritic improves over GRPO without a critic, prompted reviewer systems and scalar reward model baselines, while requiring fewer policy gradient steps and fewer sandbox executions. Ablations and reliability analyses suggest that the gains come from better credit assignment rather than larger sampling budgets.
Read the full abstract ▾
Computer Vision
G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration
Jeng Wen Joshua Lean, Ting-Yu Yen, Wei-Fang Sun et al. (+3 more)
Full-context neural visual geometry is impractical for thousands of images, while sequence-based chunking poorly captures irregular non-local overlap in multi-sequence aerial collections. We present Graph-Guided Neural Visual Geometry for Aerial Registration (G3AR), a graph-guided framework for scalable dense neural geometry. Before local inference, G3AR builds a geometrically verified image-proximity graph that guides bounded overlapping chunks and induces a chunk graph whose maximum spanning tree defines
alignment topology. Compatible backbones process chunks independently; shared-image predictions then estimate three-dimensional similarity (Sim(3)) transforms that register local cameras and geometry in a common frame. Across four real aerial scenes, G3AR improves pose error and runtime in matched VGGT- and Pi3-backed comparisons, while its DA3 variant achieves the lowest pose error among evaluated neural-geometry methods.
Read the full abstract ▾
All authors Jeng Wen Joshua Lean, Ting-Yu Yen, Wei-Fang Sun, Simon See, Hung-Kuo Chu, Shih-Hsuan Hung
Computer Vision
SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation
Zixiu Ding, Zilin Zhao, Yingjie He et al. (+3 more)
Multimodal large
language models (MLLMs) have made strong progress on visual question answering and image captioning, yet they still produce fluent claims about objects, attributes, or relations that are not grounded in the image. Many remedies either modify decoding at test time, which adds latency, or fine tune with preferences such as DPO variants, which teach which answer is preferred but not when the model's own answer is unreliable. We argue that calibrated self assessment is the missing signal. We introduce Savor, a training framework that (i) augments the output schema with
token and answer confidence, (ii) optimises the policy with a Group Relative Policy Optimisation (GRPO) objective that penalises calibration error and poor abstention decisions, and (iii) uses the learned confidence at inference time to revisit visual evidence only when the model is uncertain. Experiments on POPE, HallusionBench, AMBER and MMHal-Bench across two recent backbones (InternVL3-8B and Qwen3-VL-8B) show that Savor reduces
hallucination while preserving general capability on MME and MMBench, with lower Expected Calibration Error than DPO and decoding baselines.
Read the full abstract ▾
All authors Zixiu Ding, Zilin Zhao, Yingjie He, Xinlang Kang, Guansu Wang, Wei Zhang
Hardware Architecture
A 420 GOPS/W CGRA with a Configurable MAC and Dynamic Truncation
Yi Sheng Chong, Rakshith Harish, Rajesh Chandrasekhara Panicker et al. (+2 more)
Edge devices demand for highly efficient yet flexible processing capability to handle dynamic real-time workloads. Coarse grain reconfigurable architecture (CGRA) emerges as a suitable accelerator candidate in edge devices, because they are as flexible as general purpose processors and offer high efficiency close to that of domain specific accelerators. However, a typical CGRA requires two cycles for a multiply-and-accumulate (MAC) operation, and workloads such as neural network inference and signal processing involve many MAC operations, resulting in long CGRA processing time. This work proposes a CGRA that has configurable MAC units in the processing elements (PEs) that can perform an addition (ADD) or multiplication (MUL) or a MAC by using the same multiplier and adder, in a single cycle. The readout precision of MAC result can be adjusted by a truncation block. The proposed CGRA is implemented with 40nm CMOS technology. It attains an energy efficiency of 420.6GOPS/W operating at supply of 0.6V and frequency of 21MHz, which is 1.4 times higher than the state-of-the-art.
Read the full abstract ▾
All authors Yi Sheng Chong, Rakshith Harish, Rajesh Chandrasekhara Panicker, Vishnu P. Nambiar, Anh Tuan Do
Systems and Control
Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems
Haiping Du and Linping Chan
Modern networked control systems (NCSs), cyber-physical systems (CPSs), and complex multi-
agent network systems (CNSs) increasingly rely on large
language models (LLMs) for high-level decision-making. However, the slow,
stochastic nature of LLMs directly conflicts with the strict stability and safety guarantees required by these physical systems. This survey presents a unified analysis of how LLMs can be admitted into the control loop of NCS, CPS, and CNS without compromising closed-loop guarantees. We organize this around a core principle: the LLM operates as a slow supervisor adjusting high-level goals and constraints, while a fast, certified inner loop maintains physical stability. Under this framework, LLM integration maps directly to classical networked control challenges, where inference latency acts as delay, API failures as packet dropouts, tokenization as quantization, and
hallucinations as bounded disturbances. We assess current developments across all these three domains, highlighting that rising model capabilities are frequently accompanied by a drop in formal safety assurances. Finally, we propose concrete future research directions, identifying the widespread lack of formal stability proofs as the field's central open problem.
Read the full abstract ▾
Human-Computer Interaction
CATVis: A Collaborative Multi-Agent Workflow for Turbomachinery Simulation Data Visualization
Zhe Wang, Zehao Lou, Guanghui Zhao et al. (+6 more)
Recent advances in AI for Science have enabled natural
language (NL) interfaces for scientific data analysis. In turbomachinery CFD post-processing, translating ambiguous high-level analytical goals (e.g.,
vortex identification) into precise visualization procedures supporting complex domain-specific analysis is challenging. We present CATVis, a Collaborative multi-
agent workflow system that bridges this gap by transforming NL intents into structured middle representation for visualization. Our approach reformulates domain-specific visualization procedures as composable workflow representations, and use multi
agent to generate workflow representations via intent planning, template generation, and error-aware refinement, where each stage incrementally updates a shared structured representation. We evaluate the impact of external knowledge and workflow structuring on generation accuracy, demonstrating that the proposed approach significantly improves complex workflow generation correctness while reducing
prompt complexity.
Read the full abstract ▾
All authors Zhe Wang, Zehao Lou, Guanghui Zhao, Yu Dong, Guan Li, Pengyi Xu, Gaorong Liang, Jun Liu, Guihua Shan
Computer Vision
A Vision-Language Foundation Model for Precise and Comprehensive Brain Tumor Diagnosis from Preoperative Multimodal Data
Yinong Wang, Jianwen Chen, Zhou Chen et al. (+27 more)
We developed BrainVLM to classify all 12 World Health Organization (WHO) 2021
brain tumor types. BrainVLM integrates an uncertainty quantification strategy to indicate prediction reliability and a module for generating radiology reports to elucidate the clinical rationale. BrainVLM was trained on multi-modal data (MRI scans, demographics, and radiology reports) from 40,043 individuals. It was validated on 5,211 patients with pathologically confirmed
brain tumors, including 3,877 held-out patients from the primary hospital and 1,334 patients from 11 independent hospitals. We further conducted two proof-of-concept studies to validate its clinical utility in AI-clinician workflows: 1) a blinded multireader study where 12 neuroradiologists across varying experience levels interpreted 248 retrospective cases with or without AI assistance, and 2) a real-world prospective study in which 1,009 patients were independently and blindly assessed by BrainVLM and radiologists before surgery. Additionally, we demonstrated BrainVLM's utility in preoperative molecular subgroup prediction for adult-type diffuse gliomas, using a multi-center cohort of 632 patients. In primary evaluation, BrainVLM achieved an area under the curve (macro-AUC) of 0.85 (95% CI: 0.84-0.86), and an F1 score of 0.82 (95% CI: 0.81-0.83), surpassing neuroradiologists (F1 = 0.80 (95% CI: 0.79-0.81)). In external validation across 11 centers, BrainVLM achieved an AUC = 0.80 (95% CI: 0.79-0.82) and F1 = 0.75 (95% CI: 0.73-0.78), compared with F1 = 0.71 (95% CI: 0.69-0.73) for neuroradiologists. In prospective real-world evaluation, BrainVLM maintained performance comparable to neuroradiologists. The BrainVLM project page is available at https://hku-healthai.github.io/brainvlm_project.github.io/.
Read the full abstract ▾
All authors Yinong Wang, Jianwen Chen, Zhou Chen, Shuwen Kuang, Haoning Jiang, Yanzhao Shi, Huichun Yuan, Yan-ran Wang, Bing Wang, Lei Wu, Bin Tang, Li Meng, Baihua Luo, Bin Zhou, Wei Ding, Weiming Zhong, Wei Hou, Yuanbing Chen, Zhiping Wan, Wei Wang, Zhenkun Xiao, Wenwu Wan, Allen He, Yuyin Zhou, Longbo Zhang, Feifei Wang, Zhixiong Liu, Michael Iv, Xuan Gong, Liangqiong Qu
Computer Vision
FRPSS: Feature Rearrangement in Pre-Shape Space for Single-Image Generation
Yuexing Han, Haoxuan Zhang and Bing Wang
Generative models trained on a single image often struggle to balance global structural integrity and local diversity. Existing single-image generation methods commonly rely on random noise to drive the generation process and lack explicit global structural constraints, making the generated results prone to spatial structural misalignment when structural variations occur. To address the issue, Feature Rearrangement in Pre-Shape Space for Single-Image Generation (FRPSS) is proposed in this paper. The core of FRPSS is the
Manifold Structural Rearrangement with Feature Augmentation on Geodesic Surface (MSR-FAGS) module. MSR-FAGS replaces the randomly initialized features of the low-scale generator with rearranged Pre-Shape features and uses the features to guide image generation at subsequent scales, thereby reducing the risk of structural misalignment. To support downstream tasks such as stylization, a Scale-adaptive Sliding-window Patch Extraction (SSPE) strategy is further designed, and a directional Contrastive
Language-Image Pre-training supervision module with SSPE (CLIP-SSPE) is constructed. Qualitative and quantitative experiments demonstrate that FRPSS achieves the best Single Image Fréchet Inception Distance (SIFID) scores on all three
datasets while maintaining competitive Learned Perceptual Image Patch Similarity (LPIPS). Further qualitative experiments verify the effectiveness of FRPSS across multiple downstream tasks with the CLIP-SSPE module.
Read the full abstract ▾
Artificial Intelligence
A Framework for Generating Valid Context-Specific Benchmarks through Expert Guidance
Kimberly Le Truong, Nari Johnson, Anna Kawakami et al. (+1 more)
This paper presents an end-to-end approach for generating context-specific large
language model (LLM)
benchmark datasets by combining expert input with synthetic data generation. Existing
benchmark construction methods often trade off validity and scalability:
datasets designed with domain experts can produce high-quality evaluations but are slow and costly to create, while synthetically generating data may scale efficiently but often results in unrealistic, redundant, or out-of-scope examples. To address this gap, we introduce a schema eliciting key information about the goals, scope, and context of an evaluation task, and use this information to guide synthetic data generation. We further define four criteria grounded in measurement validity for assessing
dataset quality: coverage, diversity, content realism, and stylistic realism. Using these criteria, we show how expert-informed scaffolds can guide synthetic data generation toward more valid
benchmarks. Through quantitative evaluations and a real-world case study with domain experts, we demonstrate that our approach improves
benchmark data quality over existing methods while preserving validity. We additionally analyze how different types of schema information affect different
dataset quality criteria, and provide practical guidance on which information to prioritize collecting under resource constraints.
Read the full abstract ▾
All authors Kimberly Le Truong, Nari Johnson, Anna Kawakami, Hoda Heidari
Computer Vision
FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation
Guangyu Sun, Shlok Kumar Mishra, Wentao Bao et al. (+8 more)
Traditional
multimodal representation learning and generation are two stages: a contrastive or self-supervised visual encoder is trained first, followed by a separate downstream generative model. This setup bottlenecks generative performance behind frozen
embeddings. To bridge this gap, we revisit joint
multimodal representation learning and generation to produce linearly interpolatable
embeddings that are directly consumable by generative decoders. We present FLAT (Flexible-Length Aligned Transmodal representations), a representation pre-training framework that jointly optimizes a shared
multimodal encoder alongside downstream text-to-image (T2I) and image-to-text (I2T) decoders. By combining contrastive
alignment with bidirectional cross-modal generative objectives, FLAT ensures its representations function as both discriminative semantic descriptors and generative conditions. Architecturally, FLAT maps visual and textual inputs into a unified continuous 1D sequence space, applying nested dropout over prefix-K
tokens to enable dynamic output lengths. A single pre-training stage allows FLAT to perform cross-modal
retrieval and generation across variable prefix K, achieving a T2I GenEval score of 71.1. Task-specific fine-tuning aligns model performance with state-of-the-art baselines: 83.1 GenEval on T2I generation; 40.5 BLEU-4 and 138.6 CIDEr on MS-COCO image captioning; and Recall@5 scores of 86.8 (I2T) / 75.8 (T2I) on MS-COCO alongside 98.3 (I2T) / 93.6 (T2I) on Flickr30K. Finally, qualitative evaluations demonstrate that FLAT representations natively support linear interpolation, latent space arithmetic, and zero-shot composed
retrieval.
Read the full abstract ▾
All authors Guangyu Sun, Shlok Kumar Mishra, Wentao Bao, Robert Zhenheng Yang, Xiao Wang, Xiyuan Wang, Yujunrong Ma, Chen Yuan, Max Xiangjun Fan, Jun Xiao, Jianpeng Cheng
Computation and Language
Challenges of Auditing: Variability in Outputs of Large Language Models for Health
Yuan Pu, Yewon Chang, Furong Jia et al. (+4 more)
People increasingly use frontier AI models for health advice, but via different access modes (e.g., ChatGPT, ChatGPT Health, APIs) with varying settings. Here, we find systematic differences across access modes. Because evaluations typically rely on APIs while consumers interact through chatbot interfaces, these discrepancies limit evaluation validity. Our findings underscore an urgent need for model providers to enable faithful replication of consumer experiences and settings for rigorous audits.
Read the full abstract ▾
All authors Yuan Pu, Yewon Chang, Furong Jia, Xunjian Yin, Jessica Ma, Ayman Ali, Monica Agrawal
Artificial Intelligence
Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models
Keqing Zhang, Jingyu Chen, Yufan Liu et al. (+6 more)
As Large
Language Models (LLMs) increasingly handle complex subjective tasks, aligning their intentions and behaviors with human values has become a critical scientific challenge. However, current efforts are confounded by a striking behavioral paradox: they fluctuate unpredictably under minor wording changes ("swing"), yet stubbornly ignore explicit instructions to correct ingrained biases ("
rigidity"). Resolving this duality is critical for reliable AI
alignment. To systematically understand and safely steer these latent subjective preferences, our study is structured around three fundamental questions. First, do LLMs possess an intrinsic value system? By projecting responses from 106 LLMs (150,000 queries per model) and 95,000 human survey profiles into a shared sociological space, we empirically confirm that they do. However, they do not mirror human diversity, instead crystallizing into a highly concentrated, idealized value core. Second, how can these values be quantified? We propose the Prior-Environment-Cognition (PEC) framework. This model mathematically defines value expression as the joint outcome of inherent dispositions like parameter weights (Prior), external contexts such as user
prompts (Environment), and internal
reasoning processes like Chain-of-Thought (Cognition). Finally, how can LLMs' values be aligned toward a desired target? Using PEC diagnostics, we establish an adaptive "
Alignment Prescription". Rather than blindly applying resource-intensive training, this method identifies the minimum effective intervention needed for each dimension, ranging from zero-cost
prompts to targeted parameter updates. Extensive empirical validation confirms that our approach successfully verifies the presence of LLM values, accurately quantifies their shifts, and achieves more efficient and precise steering than conventional blind training, all without degrading general capabilities.
Read the full abstract ▾
All authors Keqing Zhang, Jingyu Chen, Yufan Liu, Yongqiang Zhu, Nai Ding, Lai Jiang, Congyan Lang, Bing Li, Weiming Hu
Robotics
ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation
Yushan Bai, Boyu Zheng, Zhiyang Mao et al. (+4 more)
Multi-finger dexterous manipulation relies on stable hand-object interactions, yet these interactions are partially observable in practice. Visual observations are often occluded by the hand, tactile sensors introduce hardware-specific modalities and calibration burdens, and existing policies rarely model how these cues evolve under actions, making them brittle under contact uncertainty. To address these, we present ProxiDex, a dynamics-guided proximity policy framework that treats hand-object proximity as an interaction state for dexterous manipulation. ProxiDex reconstructs interaction point clouds and converts
geometric distances into proximity cues, forming a hardware-agnostic contact representation that provides immersive feedback during VR teleoperation. Built on this representation, ProxiDex learns action-conditioned proximity dynamics with a coupled forward-inverse design: future observation latents are predicted from actions, while proximity variations are decoded from latent changes. Leveraging these dynamics, ProxiDex adaptively reweights proximity
tokens across manipulation phases and uses dynamics-consistency supervision to guide policy inference, stabilizing action generation under unreliable visual feedback. Simulation and real-world experiments demonstrate improved success rates and robustness over representative baselines across standard, unseen objects, and perturbation scenarios. Additional visualizations are available at https://proxidex.github.io/.
Read the full abstract ▾
All authors Yushan Bai, Boyu Zheng, Zhiyang Mao, Hongzheng Sun, Yuchuang Tong, En Li, Zhengtao Zhang
Sound
CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection
Qiyang Sun, Xudong Li, Yupei Li et al. (+4 more)
Spoken sarcasm detectors may exploit lexical content, prosody, or their interaction, yet conventional evaluation cannot reveal which cues drive their predictions. We introduce CLASH (Controlled Lexical-Acoustic Separation Harness), a bilingual counterfactual diagnostic framework that evaluates each utterance under original, lexical-preserving, prosody-preserving, and approximately neutralised conditions. We evaluate handcrafted acoustic-feature systems, self-supervised learning (SSL) probes, and large audio
language models (LALMs) on CMMA and MUStARD. For target-only Qwen3-Omni, lexical-preserving
speech retains a 0.135–0.148 AUROC advantage over prosody-preserving
speech after duration balancing, with cluster-bootstrap intervals above zero; alternative lexical resynthesis preserves this advantage. Acoustic interventions shift scores without consistently improving discrimination or changing binary predictions under the evaluated conditions. Context and interaction estimates vary across corpora. These findings distinguish acoustic sensitivity from sarcasm discrimination while exposing duration, identity, and transformation effects.
Read the full abstract ▾
All authors Qiyang Sun, Xudong Li, Yupei Li, Jiabin Xue, Yuhang Dai, Jiaming Li, Bjorn W. Schuller
Human-Computer Interaction
EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
Panyu Zhang, Minseo Park, Soowon Kang et al. (+7 more)
We introduce a three-wave, in-the-wild
multimodal dataset for affect sensing that integrates smartphone sensing, wearable sensing, and dense experience-sampling-method (ESM) labels collected annually from 2020 to 2022. The
dataset supports moment-level affect modeling through a shared dimensional label core across all waves, with additional affective descriptors available in the third wave (D-3). We describe the resource in terms of study design, temporal density of in-situ labels, and sensing and label coverage across waves. To support evaluation within this resource, we define an initial three-setting
benchmark spanning temporal prediction from within-user history, within-wave cross-user generalization, and cross-wave generalization in which each wave is treated as a separate
dataset. Our
benchmark results show that the strongest method family depends on the evaluation setting: supervised baselines perform best in the temporal setting, unsupervised domain adaptation is strongest overall in the within-wave cross-user setting, and domain generalization shows the strongest overall cross-wave performance, although its margin over strong baselines is modest. These findings indicate that robust mobile affective computing is constrained not only by label availability but also by substantial participant-level variability and realistic cross-wave differences inherent in longitudinal in-situ deployments.
Read the full abstract ▾
All authors Panyu Zhang, Minseo Park, Soowon Kang, Tomiris Ismatzoda, Azizbek Mustafakulov, Otabek Najimov, Woohyeok Choi, Jumabek Alikhanov, Surjya Ghosh, Uichin Lee
Machine Learning
Recovering Governing Dynamics from Distributed Observations via Exact Spline Merging
Naveen Mysore
Scientific observations are frequently distributed across locations, time periods, and institutions. Combining such observations into a continuous, differentiable field enables recovering governing physical parameters from its derivatives. This paper makes two contributions in this setting. First, the established additive structure of fixed-basis ridge-regression statistics is applied to tensor-product spline fields: each data holder computes a local Gram
matrix and moment vector, and the merged solution is mathematically identical to centralized fitting, with no raw data shared and no iterative synchronization. This property is specific to the fixed-feature squared-error setting; the present derivation does not establish an analogous guarantee for general jointly trained multilayer networks. Second, a complete pipeline connects distributed observations to physical parameter inference through field reconstruction, derivative extraction, and linear regression. The pipeline is validated on four PDEs:
diffusion, wave, heat-with-source, and the nonlinear viscous Burgers equation, recovering governing parameters to sub-percent accuracy in the linear cases and 5% for Burgers. In all cases, distributed merging introduces zero degradation relative to centralized fitting. Synthetic experiments validate parameter recovery; application to 41 years of NOAA sea-surface temperature data validates field reconstruction and aggregation equivalence on real spatiotemporal observations. Source code to reproduce all experiments is available at https://github.com/NAVEENMN/splinemerge.
Read the full abstract ▾
Computer Vision
GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration
Hu Gao, Lizhuang Ma and Yulong Chen
The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing methods rely on predefined multi-scale hierarchies and aggregate features through fixed fusion or
attention, leaving the representation scale itself largely determined by the network architecture. This limitation becomes more pronounced when a task-specific backbone is extended to heterogeneous degradations in all-in-one restoration. Inspired by level-of-detail (LOD) rendering in computer graphics, we propose GraLoD, a plug-and-play framework that treats restoration scale as a spatially varying and stage-dependent continuous variable. GraLoD reuses the native encoder hierarchy, aligns its multi-scale features into a shared LOD representation space, and predicts a stage-conditioned LOD field at each decoder stage. Each spatial location then continuously queries only two neighboring representation levels, enabling the effective restoration scale to adapt to both local image content and reconstruction progress. To prevent degenerate or arbitrary scale selection, we further introduce minimal-sufficient footprint calibration (MSFC) together with structure-aware regularization (SAR) to encourage restoration-effective and spatially coherent LOD assignments. GraLoD can be directly integrated into existing restoration backbones without redesigning their fundamental feature-processing blocks. Extensive experiments demonstrate consistent improvements in task-specific and all-in-one restoration.
Read the full abstract ▾
Digital Libraries
Testing Our Foundations: Citation Trends, Errors, and Emerging Hallucinations in the Computing Education Literature
Paul Denny, Gweneth Barbre, Musa Blake et al. (+5 more)
Accurate references are foundational to scholarly work, enabling verification, attribution, and systematic review. However, the rapid adoption of large
language models has introduced a serious integrity concern: plausible-looking but fabricated citations. Although hallucinated references are widely discussed, their visibility within specific research communities remains unclear. We address this gap by examining reference integrity at key computing education venues using ACM Digital Library data. We analyze referencing trends across 24,751 computing education papers and compare them with the broader ACM corpus of more than 723,000 papers and 15 million references. We then examine reference lists from these venues, classify common bibliographic errors, and manually identify LLM-generated
hallucinations containing verifiably false information, including impossible page ranges, invented titles, and misattributed authors. In 2025, hallucinated references appeared across five SIGCSE-sponsored or in-cooperation venues. At the Technical Symposium alone, verified hallucinated references increased from 3 in 2025 to 17 in 2026, appearing in 2.3% of 2026 proceedings papers. Although still relatively rare for now, this growth poses an integrity risk our community should not ignore.
Read the full abstract ▾
All authors Paul Denny, Gweneth Barbre, Musa Blake, Yan Cathy Hua, Juho Leinonen, Andrew Luxton-Reilly, James Prather, Brent N. Reeves
Machine Learning
AsyncCouple-Flow: Asynchronous Cross-Modal Coupling and Flow Matching for Spatio-Temporal Forecasting
Zhixiang Wu, Yining Liu, Bo Zhao et al. (+4 more)
Multi-modal spatio-temporal
forecasting (MM-STF) supports weather nowcasting, traffic prediction, and earth-system modeling by combining heterogeneous sources such as physical fields, satellite imagery, and in-situ sensors. Three obstacles persist: (i) modalities have different spatio-temporal sampling rates, forcing lossy interpolation onto a unified grid; (ii) modalities are frequently missing at deployment due to sensor outages or revisit gaps, while most methods train with full availability; and (iii) autoregressive decoders accumulate errors over long horizons, amplified by multi-modal conditioning. We propose AsyncCouple-Flow to address these issues jointly. A Modality-Aware
Token Sparsification (MATS) module performs scale-aware tokenization and uses a shared importance scorer to select top-k
tokens per timestep, producing equal-length sequences. An Asynchronous Cross-Modal Coupling Graph (ACCG) replaces fixed cross-
attention with a learnable graph whose edges encode time offsets, semantic similarity, and modality-specific physical priors, enabling fusion under arbitrary asynchrony and missingness. A Flow-Matching
Forecasting Head models multi-step prediction as a conditional ODE, trained with
stochastic modality dropout and integrated jointly to avoid autoregressive drift. Experiments on ERA5+GOES+ISD weather
forecasting and PEMS-BAY traffic prediction with multi-source side information show that AsyncCouple-Flow outperforms state-of-the-art baselines and remains robust with up to two missing modalities. The code will be released upon acceptance.
Read the full abstract ▾
All authors Zhixiang Wu, Yining Liu, Bo Zhao, Szu-Yu Chen, Huiran Duan, Chu Lin, Chuanguang Yang
Computer Vision
Efficient Text-to-Image Generation: An Adaptive Step Schedule Controller for Diffusion Models
Kuluhan Binici, Cihan Acar, Shivam Aggarwal et al. (+2 more)
Text-to-image
diffusion models often use a fixed number of denoising steps, balancing time costs and image quality. However, the optimal number of steps depends on the complexity of the input text
prompt. We propose an adaptive
diffusion controller that dynamically adjusts the number of steps to generate high-quality images efficiently, without additional model training. By leveraging a mixture of step schedules with varying step sizes and evaluating the error term discrepancy at each timestep, our method transitions between schedules to optimize performance. Experiments on COCO and DiffusionDB show that our approach reduces inference time while maintaining visual fidelity, offering a more efficient alternative for text-to-image
diffusion models.
Read the full abstract ▾
All authors Kuluhan Binici, Cihan Acar, Shivam Aggarwal, Siying Liu, Tulika Mitra
Systems and Control
Joint Freshness and Age-Dispersion Control over Finite-State Markov Wireless Channels
Aresh Dadlani, Hina Tabassum, Muthukrishnan Senthil Kumar et al. (+1 more)
Age of information (AoI) has become a standard design objective for timely monitoring as it measures the freshness of the latest update at a receiver. AoI alone, however, is insufficient in goal-oriented applications where decisions depend on consecutive observations. Age dispersion complements AoI by measuring the generation-time separation between consecutive updates. In this paper, we study joint freshness and dispersion control for a generate-at-will status update link modeled as a finite-state Markov wireless channel. The objective is to minimize the long-run probability that either AoI or age dispersion exceeds a prescribed threshold under an average transmission rate constraint. For channel-dependent randomized transmission policies, we derive exact
matrix expressions for the stationary joint distribution of AoI and dispersion. For reversible channels, mean dispersion is lower bounded by the reciprocal of the delivery throughput, and the difference is an explicit non-negative variance term for which we establish the exact equality condition. We then formulate the adaptive joint-threshold control problem as a constrained Markov decision process and prove that it admits an exact finite-state representation whose size scales linearly with the number of channel states and the threshold levels. Simulation results show that the controller reduces joint threshold violations by 37.3% relative to adaptive AoI-only control under the same transmission budget, while increasing mean AoI by 8.3%.
Read the full abstract ▾
All authors Aresh Dadlani, Hina Tabassum, Muthukrishnan Senthil Kumar, Masoumeh Moradian
Computer Vision
Counterfactual Reasoning for Robust Visual Question Answering
Truong-Binh Duong, Thanh-Ngan Tran, Ngoc-Thao Nguyen et al. (+1 more)
Modern Visual Question Answering (VQA) models often exploit spurious correlations in training data, leading to poor out-of-distribution (OOD) generalization due to
language bias. Although counterfactual learning has shown promise, existing methods can be improved to better guide
attention toward causal evidence and strengthen feature discrimination. To address this, we propose a novel training framework that enhances counterfactual contrastive learning for VQA. Our framework introduces three key contributions: (1) a three-stage curriculum for stable multi-objective optimization, (2) an enhanced Batch-Contrastive loss for more discriminative feature learning, and (3) two novel regularizers, Answer-Contrastive (AC) loss to refine the prediction space and Gradient-Discrepancy (GD) loss to enforce causal visual grounding. Our model achieves a competitive accuracy of 61.64% on the bias-sensitive VQA-CP v2
benchmark while maintaining 62.80% on the standard VQA v2
dataset, yielding a small generalization gap of 1.16%. This demonstrates a strong balance between OOD robustness and in-distribution performance.
Read the full abstract ▾
All authors Truong-Binh Duong, Thanh-Ngan Tran, Ngoc-Thao Nguyen, Bac Le
Computer Vision
Vision And Text Transformer For Predicting Answerability On Visual Question Answering
Tung Le, Huy Tien Nguyen and Le Minh Nguyen
Answerability on Visual Question Answering is a novel and attractive task to predict answerable scores between images and questions in multi-modal data. Existing works often utilize a binary mapping from visual question answering systems into Answerability. It does not reflect the essence of this problem. Together with our consideration of Answerability in a regression task, we propose VT-
Transformer, which exploits visual and textual features through
Transformer architecture. Experimental results on VizWiz 2020
dataset show the effectiveness and robustness of VT-
Transformer for Answerability on Visual Question Answering when comparing with competitive baselines.
Read the full abstract ▾