Artificial Intelligence
When Does Exercise-Specific Joint Selection Help? An Audit of Evaluation and Control Design
Haotian Chen, Jingkun Yu, Yuning Zhang et al. (+1 more)
Exercise-specific joint selection can improve skeleton-based correctness classification, but what does that gain establish? We audit 1,057 repetitions from ten REHAB24-6 subjects, separating evaluation aggregation, subset structure, and temporal representation. The manual-subset kNN gain changes from 0.055 for pooled out-of-fold AUROC to 0.020 for equal-weight within-person AUROC; both paired intervals include zero. Among 1,000 dimension-matched random maps, 14 match or exceed the manual pooled result, versus 145 when bilateral structure and trunk inclusion are also matched. RBF-SVM retains a positive within-person gain, whereas logistic regression and a random-convolution comparator have negative point gains under that estimand. Sequence-order and paired-seed controls further qualify the interpretation. This exploratory audit shows why joint-selection claims require explicit estimands and structurally appropriate controls; it does not establish a new
algorithm or clinical benefit.
Read the full abstract ▾
All authors Haotian Chen, Jingkun Yu, Yuning Zhang, Bowen Ye
Numerical Analysis · Cross-listed from q-fin.CP
On the Pricing of American Options under Stochastic Local Volatility and Stochastic Correlation via the RBSDE Framework
Long Teng
In this work, we study the pricing of American options under
stochastic local
volatility (SLV) models extended by including
stochastic correlation driven by an additional
stochastic process. We generalize the class of SLV models by incorporating a flexible
stochastic correlation structure. To price options within these extended models, we derive the corresponding reflected forward-backward
stochastic differential equations (RBSDEs) and employ data-driven numerical methods to solve them for both pricing and hedging purposes. The RBSDE framework enables the modelling of the future
evolution of the option price. Furthermore, we conduct a convergence analysis of the proposed numerical method and present numerical experiments that illustrate the performance of the extended models, as well as the accuracy and efficiency of the RBSDE-based approach.
Read the full abstract ▾
Hardware Architecture
From Physical Devices to RTL Models: Abstraction and Validation in Hardware Engineering
Wolfgang Ecker, Natalie Simson, Johannes Ecker et al. (+1 more)
This paper introduces the foundational principles underlying hardware engineering models and argues that abstraction is their defining characteristic. Because abstraction necessarily omits detail and constrains what engineers can build, models are inherently incomplete in specific respects - or, as George Box famously observed, "All models are wrong, but some are useful". At the same time, abstraction is essential for simplification, which is key to managing complexity. More abstract models also tend to simulate faster because fewer details must be considered. This paper subsequently examines a range of abstraction methods in digital design - sometimes referred to as design disciplines - including lumped models, value-discrete models, and time-discrete models. Together with constraints that define the validity of the abstraction and design guidelines, these abstraction methods establish design disciplines. This paper further relates these forms of abstraction to pre-clustered design elements such as transistors, gates, registers, and transfer functions. These pre-clustered elements define abstraction levels, such as the gate level, and are presented as a key enabler of increased design productivity.
Read the full abstract ▾
All authors Wolfgang Ecker, Natalie Simson, Johannes Ecker, Endri Kaja
Robotics
AFD-CAMLs: Agile Force-Distribution-Aware Planning and Control for Cable-Suspended Aerial Multi-Lifting Systems
Antreas Kourris and Sihao Sun
Multiple
UAVs can cooperatively transport heavy payloads while controlling their position and orientation. Trajectory-based methods offer high agility while satisfying system constraints, but can produce uneven force distributions when the tension-to-wrench allocation is redundant or ill-conditioned, particularly under
geometric mismatch and low-level tracking errors. We propose a hybrid planning-and-control framework to address this problem. A global planner generates payload trajectories and cable-force references by exploring the allocation null space under a prescribed internal-force setting. These references augment the cost of a centralized local planner, promoting feasible force distributions while generating trajectories for all
UAVs. An admittance filter then compares the planned forces with onboard cable-tension estimates and adjusts the kinematic references to improve force tracking in degenerate or near-degenerate configurations. Simulations and experiments involving four to ten
UAVs demonstrate more balanced tension distributions during both hovering and demanding agile maneuvers, without compromising agility or payload-tracking performance.
Read the full abstract ▾
Cryptography and Security
ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning
Bingchen Pei, Lichong Chen, Bingxi Zhao et al. (+8 more)
Remote
multimodal models offer strong numerical
reasoning capabilities over charts and
speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satisfy fixed media interfaces, while identity anonymization leaves the underlying task content exposed. We introduce ReCast, an agentic plug-in framework that replaces source-specific content while preserving task-relevant relations and the required input modality. ReCast locally converts inputs into a shared textual evidence-query record, jointly rewrites entities and topics with a distilled 4B model, and substitutes values through a locally invertible, role-aware numerical map. A reconstruction
agent generates and validates the required media from the protected record. The remote solver returns a program whose protected operands are restored locally before execution. On 4,000 held-out ChartQA and NMSQA examples, ReCast achieves 75.10% accuracy, retaining 92.43% of unprotected remote accuracy, while a model-based audit flags source-content leakage in 7.95% of solver-bound requests. It outperforms all evaluated local baselines, preserving the benefit of remote
reasoning while reducing source-content exposure under existing media interfaces.
Read the full abstract ▾
All authors Bingchen Pei, Lichong Chen, Bingxi Zhao, Ziang Wu, Sirui Wang, Min Zhang, Yanhao Chen, Qingxu Liu, Qiang Gao, Chang-Tien Lu, Bo Gao
Sound
Toward Elastic Speech Inference: Training-Free Wake-Word Detection from Pretrained ASR
Hwayeon Kim, Youngwon Choi and Hyeonyu Kim
Recent ASR development has placed growing emphasis on generalization across diverse domains and acoustic conditions. Existing approaches typically adapt pretrained ASR models to front-end functions such as wake-up word (WuW) detection through additional training or task-specific modules. In this work, we explore the use of a shared pretrained ASR backbone for WuW detection without gradient-based fine-tuning and examine whether a compact encoder can be extracted using the PCA-based structured
pruning approach of SliceGPT. Experiments with Parakeet-TDT-0.6B-v3 and Moonshine-base show that WuW detection performance remains relatively stable when the encoder channel dimension is reduced by 50%. These results suggest that task-relevant compact encoders can be derived from pretrained ASR models without fine-tuning.
Read the full abstract ▾
Machine Learning
Fully Online Decentralized Learning in Stochastic Games with Unknown Independent Chains
S. Rasoul Etesami
We consider
stochastic games with independent controlled chains and unknown transition kernels, where players observe only their local states and realized payoffs. We develop a fully online, decentralized, and uncoordinated mirror-descent
algorithm that operates in the dual space of occupancy measures for approximating stationary Nash
equilibrium (NE) policies. The
algorithm uses a single transition/reward sample at every primitive time step, relies only on local information, and requires neither coverage of the joint state space nor synchronized episodes. Under uniform-ergodicity and finite-coverage assumptions, we show that, with high probability, the time-averaged fixed-comparator regret decays at the canonical $O(T^{-1/2})$ rate, up to logarithmic factors and
polynomial dependence on the game parameters. In particular, the complexity depends on the cover times of the individual local state spaces rather than the product state space, avoiding exponential dependence on the number of players and the sizes of the joint state and action spaces. The resulting finite-time regret bound further yields an approximate coarse-correlated-
equilibrium guarantee, which is natural for arbitrary reward functions since computing a stationary $\epsilon$-NE is PPAD-hard in this setting. Under an additional global variational-stability condition, we show that the same fully online
algorithm converges asymptotically in the last iterate to a stationary $\epsilon$-NE. Our results provide a fully online and scalable learning framework for
stochastic games with unknown independent chains. The
algorithm can also be viewed as a primal-dual framework for Markov games that exploits the independence and local structure of the players' controlled transition chains.
Read the full abstract ▾
Computer Vision
Skeleton-and-Strategy Prompting: Training-Free Negation Understanding for Vision-Language Models
Yuliang Cai, Mohammad Rostami and Jesse Thomason
Despite the strong performance of
Vision-
Language Models (VLMs) on a wide range of visual question answering (VQA) tasks, these models consistently struggle to understand negation and produce incorrect answers when questions involve negated clauses. To address this limitation, we propose Skeleton-and-Strategy Prompting (SSP), a training-free, in-context learning method that improves VLM negation understanding capabilities without any parameter updates. Given a negation question, our method first abstracts the underlying question structure into a skeleton, retrieves a small set of same-skeleton questions from a lightweight question pool, then
prompts the VLM to analyze their shared negation pattern and synthesize a single-sentence answering strategy. The skeleton and strategy are prepended to the test sample to guide the model correctly tackle the negation problems. Experiments on multiple negation VQA
benchmarks show that SSP achieves state-of-the-art performance on negation-focused VQA tasks while remaining computationally efficient.
Read the full abstract ▾
Multimedia
Supporting Perspective Acquisition and Opinion Formation on Societal Issues Through AI-Generated Japanese Rap Battle Debates
Ryota Mibayashi, Toru Urakawa, Dai Takanashi et al. (+9 more)
Acquiring diverse perspectives and forming informed opinions on societal issues are essential for critical thinking and informed decision-making. Although observing debates between opposing viewpoints can promote perspective acquisition, conventional debates require substantial time and human resources, limiting their accessibility. This study investigates whether brief AI-generated rap battle-style debates can support perspective acquisition and opinion formation on societal issues. Rap battles are debate-style performances in which opposing viewpoints are expressed through rhymed verses, making them engaging while preserving the structure of argumentative dialogue. To conduct this investigation, we automatically generated rap battle-style debates using GPT-5.4-mini and presented them to participants with synthesized audio through a web-based viewing interface. We evaluated the educational effectiveness of this approach through a user study involving six participants who viewed 40 debates generated from topics on societal issues used in the All Japan Junior and Senior High School Debate Championships. The results showed that watching approximately 1.5 minute rap battle-style debates nearly doubled the number of opinions and discussion points identified by participants. Furthermore, participants reconsidered or changed their stances in 52.5% of the evaluated cases. These findings demonstrate that even brief AI-generated rap battle-style debates can effectively support perspective acquisition and opinion formation on societal issues.
Read the full abstract ▾
All authors Ryota Mibayashi, Toru Urakawa, Dai Takanashi, Tomoya Morohoshi, Kanata Yamagishi, Ryuho Sekikawa, Yasuhiko Nishimura, Yuta Takeuchi, Hideaki Tamori, Takehiro Yamamoto, Hidenari Kiyomitsu, Hiroaki Ohshima
Robotics
Recova: Agent-Guided Failure Recovery for Autonomous Robotic Manipulation
Isabella Liu, An-Chieh Cheng, Johan Bjorck et al. (+6 more)
Manipulation failures can leave scenes in states from which a task policy cannot recover. Learning corrective behaviors requires scalable failure exploration and physical grounding. We present Recova, an
agent-guided framework that jointly develops task execution and recovery in a reconstructed digital twin, then verifies and refines both through real-world experience. In the twin, the
agent diagnoses failures, tests corrective programs, and collects successful task and recovery rollouts for separate policies. During deployment, it monitors progress, invokes a learned or programmatic recovery, verifies scene restoration, and resumes execution. When no suitable recovery is available, a human demonstration resolves the failure and enters the learning loop, allowing the system to expand its recovery capabilities. Physical rollouts and human demonstrations are routed to the corresponding policy for DAgger training. Across six LIBERO-Pro settings and four MolmoSpaces categories, Recova achieves 78.8% and 64.9% mean success, compared with 71.7% and 38.0% for the strongest baselines. With parallel collection across four real-
robot workstations, DAgger fine-tuning raises mean success from 23.8% to 77.5%, and recovery skills further raise it to 87.5%. Over four collection rounds on one task, observed human intervention falls from 87.5% to 0%. Together, these results show how
agent-guided recovery turns failures into reusable capabilities, improving robustness while progressively reducing human intervention. Project page: https://www.liuisabella.com/Recova
Read the full abstract ▾
All authors Isabella Liu, An-Chieh Cheng, Johan Bjorck, Zhiding Yu, Hongxu Yin, Jan Kautz, Linxi Fan, Yuke Zhu, Sifei Liu
Computation and Language
Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models
Darpan Aswal and Céline Hudelot
This work presents
Diffusion Layer Integrated Gradients (DLIG), a
token attribution method for
diffusion language models (DLMs) that extends Integrated Gradients (IG~\cite{sundararajan2017axiomatic}) to arbitrary layers and denoising steps. DLIG attributes a DLM's progressive commitment to a self-generated or fixed completion for an input
prompt. We establish direct correspondences between DLIG and the IG axioms of completeness, implementation invariance, linearity, and
symmetry preservation. As a lightweight complement to interventional analysis, DLIG provides an inexpensive first check of mechanistic hypotheses across the denoising trajectory. We demonstrate this on word-sense disambiguation, multi-hop graph
reasoning, and sentence infilling, revealing how DLMs draw on inputs across positions, layers, and denoising steps.
Read the full abstract ▾
Machine Learning
Rethinking the Information Bottleneck: Structured Decomposition under Label-Induced Partitions
Jingyao Zhang, Yuxuan Li, Lu Han et al. (+2 more)
Standard information bottleneck (IB) regularization constrains representations via a single scalar I(Z;X), implicitlytreating all information as homogeneous. However, a single global compression control couples label-relevant structurewith residual within-condition variation, rather than regulating their allocation independently, allowing nuisanceinformation to persist in learned representations. For example, in medical imaging applications, residual variation oftenstems from acquisition conditions, background factors, or subject-specific appearance. This issue becomes particularlypronounced in data-limited settings, where models tend to overfit such variation, hindering generalization. While existingregularization methods can stabilize training, control capacity, or shape representation geometry, they do not explicitlyseparate nuisance-like variation from task-supporting structure. To address this limitation, we revisit IB from a structuredperspective based on a label-induced partition, where condition-level structure and within-condition information playdistinct roles. This leads to a dual-bottleneck formulation: a standard KL term controls global information capacity, while aconditional KL term targets within-condition information. We show that the conditional KL admits an exact decompositioninto a within-condition information term and a prior-mismatch term, explaining its
alignment with the design objective.With a simplex-structured conditional prior, the method provides controllable latent geometry and integrates seamlesslyinto existing pipelines. Experiments on classification and
segmentation show the clearest gains in low-data classificationand consistent improvements across dense prediction
benchmarks.
Read the full abstract ▾
All authors Jingyao Zhang, Yuxuan Li, Lu Han, Ali Anaissi, Nguyen H. Tran
Computers and Society
WIP: DBWorkout: A Gamified SQL Practice Platform to Support Formative Learning in Database Courses
Sehrish Basir Nizamani, Deepika Devaraj, Tien Nguyen et al. (+4 more)
This research WIP paper presents DBWorkout, a web-based platform that supports formative SQL learning through sandbox-based execution, automated result-based feedback, and session-based gamification. Learning Structured Query
Language (SQL) remains challenging for undergraduate students due to limited opportunities for interactive practice and immediate feedback. Students iteratively practice SQL on live database instances while receiving multi-dimensional feedback on query correctness, including row values, column structure, and ordering. To reduce instructor workload, DBWorkout incorporates large
language model (LLM)-assisted tools for schema and task generation within a human-in-the-loop workflow. A pilot study with teaching assistants and a classroom deployment involving 170 undergraduate students across two in-class sessions show strong perceived learning value (90% agreement) and engagement (87% enjoyment), alongside low reported pressure (22%). However, only 42% of students found the automated feedback sufficiently actionable, a finding independently corroborated by 40% of open-ended responses raising feedback quality concerns, providing cross-method triangulation of this gap. These findings demonstrate the technical feasibility and early pedagogical potential of DBWorkout while identifying directions for enhancing feedback quality and supporting sustained SQL learning.
Read the full abstract ▾
All authors Sehrish Basir Nizamani, Deepika Devaraj, Tien Nguyen, Khyati Goyal, Saad Nizamani, Sally Hamouda, Jaren Goldberg
Machine Learning
CAGE-NAS: Certified Functional Descent for Efficient Model Growth
Santiago Florido Gomez and Stéphane Rivaud
The progressive growth of neural networks requires deciding when the current representation remains sufficient for optimization and when it should be expanded. CAGE-NAS formulates this decision in function space through an admissibility criterion on approximations of the functional gradient. As long as a representation enables a certified Functional Gradient Descent step, the architecture remains fixed; when the criterion fails, a function-preserving expansion is applied and the resulting representation is evaluated again. As the main instance, we study the family induced by the tangent space, using a regularized projection of the functional gradient. In a controlled setting with exact certification, CAGE-NAS produces architectures positioned above the 99.8th performance percentile by held-out RMSE among all admissible alternatives within the same parameter budget, without enumerating them during the growth trajectory.
Read the full abstract ▾
Machine Learning
Learning Rate Transfer for Hybrid Transformer-SSM Architectures
Jimin Seo, Gyubok Lee, Yeonsik Jo et al. (+11 more)
We study learning rate (LR) scaling for hybrid architectures combining
Transformer and State-Space Model (SSM) blocks, a class adopted by several recent production
language models. In particular, we focus on the gap between the theoretical scaling rules derived for SSMs under zero-order-hold (ZOH) discretization at infinite width with growing state size, and the field-standard practical implementations using simplified-ZOH Mamba at fixed state size. Surprisingly, in this practical regime hybrid architectures achieve a near-zero LR transfer gap across widths 256-2048 and depths 4-32 up to billion-parameter scale using only the original $\mu$P prescription, even though SSM operations fall outside its Tensor Programs representability conditions and every parameterization we test fails the standard coordinate-check diagnostic of $\mu$P correctness. We attribute this to a two-condition decomposition of LR transfer in hybrid architectures: a global update-to-weight invariance, enforced by $\mu$P's initialization and LR scaling; and a local per-component balance, provided by AdamW's per-parameter normalization. Our observations show that the optimal LR is invariant to width up to 8$\times$, that this width invariance holds across depth, sequence length, batch size, and
Transformer-to-SSM ratio, and that it transfers to Nemotron-H, a production hybrid outside our custom architecture set. We hope these findings fill the gap between theoretical scaling rules and practical hybrid implementations, and stimulate further research toward bridging it.
Read the full abstract ▾
All authors Jimin Seo, Gyubok Lee, Yeonsik Jo, Kiwoong Yoo, Yeongoon Kim, Minhae Oh, Jin Woo Koo, Suhwan Kim, Nakyung Lee, Minsik Seol, Idris Nechnech, Jaehyeon Kim, Giho Lee, Jungwoo Lee
Robotics
Experience-Based Feasibility-Aware Generative Adversarial Imitation from Observation under Embodiment Mismatch
Yoshiki Takebayashi, Giovanni Perantoni, Hikaru Sasaki et al. (+2 more)
With the increasing use of
robot-free demonstration interfaces that provide state trajectories without action labels, imitation from observation has become a promising approach for learning
robot behaviors from human demonstrations. However, due to differences in embodiment and dynamics between humans and
robots, demonstrated human motions may not be feasible for the
robot, potentially degrading policy performance. In this study, we propose Experience-Based Feasibility-Aware Generative
Adversarial Imitation from Observation (EF-GAIfO), which estimates the feasibility of state-only demonstrations from the
robot's own experience rather than relying on explicit dynamics models or large prior exploration
datasets. A key feature of EF-GAIfO is that the notion of feasibility evolves with policy learning: as the policy improves and the
robot experiences a broader range of state transitions, the feasible region is progressively expanded, allowing additional demonstrations to be incorporated into learning. This enables feasibility-aware imitation that adapts to the current stage of policy learning, rather than relying on a pre-designed feasibility criterion. We validate the effectiveness of EF-GAIfO on a locomotion task in simulation and on a real quadruped
robot performing a object-reaching-and-grasping task.
Read the full abstract ▾
All authors Yoshiki Takebayashi, Giovanni Perantoni, Hikaru Sasaki, Matteo Saveriano, Takamitsu Matsubara
Computation and Language
HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix
Zirui He, Haiyan Zhao, Jingyu Hu et al. (+5 more)
Alignment does not eliminate behavioral errors in
language models. Models may still refuse benign requests, call unnecessary tools, or yield to false user claims. Current methods mitigate such errors as a computation problem, and rarely explore if the desired behavior is already encoded in the model's representation. Motivated by the observation that behavior-relevant information remains linearly decodable from the final hidden state even when the resulting logits produce the undesired behavior, we introduce HeadEdit, a gradient-free method that calibrates model behavior through the unembedding
matrix. HeadEdit extracts a low-rank behavioral subspace from paired completions and uses each
prompt's coordinates within it to generate a vocabulary-wide correction, thereby implementing implicitly adaptive steering without manually specified target
tokens or parameter updates. HeadEdit improves all nine experimental settings across three tasks and three model families, with negligible inference overhead and no systematic loss of general capabilities. It also reveals a connection to gradient-based
alignment. HeadEdit's low-dimensional representation partly predicts how preference tuning changes output logits on unseen
prompts. The subspace learned from the model can also be reused after tuning, improving performance without re-extracting or retuning. These results show that HeadEdit provides a practical, lightweight, and interpretable way to calibrate model behavior through the unembedding
matrix.
Read the full abstract ▾
All authors Zirui He, Haiyan Zhao, Jingyu Hu, Yinghao Wu, Chenxi Yuan, Yingcong Li, Yandong Bai, Mengnan Du
Game Theory
STAKE: Preventing a colluding majority from double spending
Zahra Naderi and Vincent Gramoli
Blockchains typically operate in open networks where it is hard to control the delay of messages. While classic blockchain protocols assumed synchrony, newer protocols try to remain secure despite unexpected network delays. Unfortunately, in the traditional model where $n$ participants can either be honest or Byzantine, we need a supermajority, or $\lfloor 2n/3\rfloor + 1$, of them to be honest. Recent work have explored the question of reducing the number of needed honest nodes in a game theory model to a majority sometimes by introducing $k$ rational players and $t$ Byzantine players. Yet, to our knowledge, no blockchain protocol managed to reduce it further. In this paper, we offer a blockchain protocol called Secure and Tolerant
Algorithm through ($k,t$)-robust
Equilibrium (STAKE) that works with only $\lfloor n/3\rfloor + 1$ honest players. STAKE requires each consensus participant to stake a sufficiently large amount $s$ compared to their liquidity $\ell$. We show that the probability that a coalition manages to execute $\zeta$ double spending attacks (we call them a $\zeta$-uple attack) drops exponentially fast with $\zeta$. This allows us to demonstrate that STAKE reaches a ($k,t$)-robust
equilibrium, or that rational players do not collude with Byzantine, even with a relatively low $s/\ell$ ratio.
Read the full abstract ▾
Machine Learning
Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability
Roberto Stanzione, Jules Barbe, Magali Parrino et al. (+2 more)
Time Series Anomaly Detection has received increasing
attention, driven by the growing availability of complex time series data. This surge has led to the development of numerous detection methods, as well as a variety of
benchmarks aimed at thoroughly evaluating their performance. However, most existing detectors remain largely agnostic to domain context, overlooking explainability and interpretability. One of the main reasons for this gap is that current
benchmarks primarily focus on detection accuracy, and only few of them evaluate spatial explainability. Moreover, no
benchmark currently provides sufficiently rich semantic annotations to support the generation of human-understandable interpretations of anomalies. To address these limitations, we introduce SHAD (Scality High-dimensional Anomaly Detection
benchmark), a fully annotated
benchmark composed of 215 multivariate, high-dimensional time series collected from real-world distributed cloud storage systems operated by Scality. The proposed
dataset includes rich contextual information, covering three families of anomalies with varying degrees of severity. As further contribution, we provide a foundation for future work by evaluating baseline methods for Detection, Explainability, and Interpretability, covering all stages of a TSAD pipeline. For Detection, we
benchmark a wide range of existing anomaly detectors, testing their effectiveness on the proposed real-world
dataset. Then, we consider explainability by evaluating whether measuring the contribution of each dimension in the generated anomaly score can provide accurate anomaly attributions. Finally, for interpretability, we investigate the effectiveness of frozen LLM baselines in localizing and interpreting anomalies.
Read the full abstract ▾
All authors Roberto Stanzione, Jules Barbe, Magali Parrino, Jérémie Fourmann, Paul Boniol
Computer Vision
CineMR: Tool-Integrated Vision-Language Reasoning for Quantitative Cardiac MRI Assessment
Kunyang Li, Hai Nguyen, Joshua Lowe et al. (+6 more)
Cardiovascular
magnetic resonance (CMR), including cine imaging, is a reference standard for the noninvasive assessment of cardiac morphology and ventricular function. Cine CMR interpretation integrates qualitative visual assessment with quantitative measurements of ventricular volumes, ejection fraction, myocardial mass, wall thickness, and regional wall motion. Current medical
vision-
language models (VLMs) cannot reliably derive quantitative measurements from multidimensional cine images without analysis tools. We present CineMR, a tool-augmented VLM that invokes cardiac image-analysis tools and integrates their outputs into interleaved
reasoning for quantitative CMR assessment. We also construct a multi-cohort visual question answering
benchmark covering quantitative metric extraction, multiclass diagnosis, and differential diagnosis, together with tools for
segmentation, phase selection, volumetry, morphometry, and regional wall motion analysis. CineMR is trained with supervised fine-tuning (SFT) on tool-interaction traces followed by Group Relative Policy Optimization (GRPO) with conditional tool-use rewards. On the multi-cohort cine CMR
benchmark, CineMR achieves 35.9% pass@1 and 58.9% pass@4, compared with 1.5% pass@1 for the Qwen3-VL-8B backbone and 0.0% and 7.0% pass@1 for LLaVA-Med v1.5 and MedGemma-4B, respectively. Correct tool invocation reaches 99.8% after GRPO, up from 78.9% after SFT. Live tool outputs improve ventricular measurement accuracy by 20.4–23.7% over direct model predictions, and removing all tools reduces pass@1 from 35.9% to 27.9%. These results highlight the importance of reliable tool use for quantitative cine CMR
reasoning and support CineMR as a promising approach for assistive cardiac image assessment. Code,
benchmark resources, and model weights are available at https://github.com/AI-MIND-Lab/CineMR.
Read the full abstract ▾
All authors Kunyang Li, Hai Nguyen, Joshua Lowe, Chenguang Zhao, Peace C. Madueme, Mehdi Hedjazi Moghari, Mubarak Shah, Pegah Khosravi, Yuzhang Shang
Machine Learning
Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining
Shengye Tao, Yinzhu Cheng and Haihua Xie
Layer interventions are widely used to probe the internal organization of
language models, yet most analyses examine a single training checkpoint even though model representations and computations evolve throughout pretraining. This leaves open which depth-dependent intervention responses reflect persistent organization and which are transient consequences of training. We study this question using single-block identity bypass on fixed teacher-forced contexts across five released trajectories and 11 model-domain combinations. We find that block-bypass responses retain recognizable depth ordering while their magnitudes redistribute: nearby checkpoints preserve stronger rank correspondence than distant ones, and large changes concentrate at positions that recur across text samples and transfer across evaluation domains. Controlled experiments further show that changes in the natural bypass effect cannot be reduced to a single downstream sensitivity: in replicated Pythia runs, local missing-update magnitude grows while the pooled matched downstream response decreases, whereas OLMo-2 7B exhibits a different balance. These matched responses also depend on perturbation strength and direction, without identifying targeted compensation. Together, our results show that longitudinal layer sensitivity is structured but not static, and that single-checkpoint intervention responses should be interpreted in the context of how the underlying perturbation pathway evolves during training.
Read the full abstract ▾
Computer Vision
PhysicsLENS: Diagnosing Physical Property Blindness in Video Generation Models
Isaiah Milkey, Som Sagar, Aditya Taparia et al. (+3 more)
Reliable
video world models could provide scalable predictive environments for
robot learning, planning, and evaluation. However, generated
robot videos can violate physical principles and complete tasks through physically implausible behavior, limiting their reliability for
robot learning and planning. Current
video-generation
benchmarks exclude physics that are inherently hidden by visuals (e.g., weight, viscosity, friction). Due to this,
video models are evaluated on the fidelity of physics, not the underlying accuracy of physics. We introduce PhysicsLENS, a
dataset and
benchmark for evaluating plausibility of physical properties grounded in robotics. PhysicsLENS uses matched scenario pairs that hold the same conditioning frame and task, while varying underlying physics in the scene description. Scenarios are curated from public
robot video sources and annotated across seven physical domains: collision,
gravity, momentum, friction, deformation, fluid, and causality. We evaluate across four
video generation models, producing over 400 human-annotated labels. Results show that plausible-looking
videos often ignore the stated property (34 of 47), and that stating the property lowers plausibility only slightly and not significantly.
Read the full abstract ▾
All authors Isaiah Milkey, Som Sagar, Aditya Taparia, Xinyuan Liu, Jiqing Wen, Ransalu Senanayake
Computation and Language
My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning
Yihua Zhu, Qianying Liu, Weixu Qiao et al. (+10 more)
Agentic reinforcement learning (RL) has emerged as a powerful approach for training large
language model
agents on multi-step tasks, yet reliance on terminal outcome rewards creates two credit-assignment problems, particularly in long-horizon tasks. First, same-outcome rollout groups provide no learning signal from terminal rewards. Second, terminal rewards provide only trajectory-wide feedback, making it difficult to identify which decisions caused a failure. Recent work supplements terminal rewards with finer-grained information from trajectory analysis, such as natural-
language reflections on intermediate decisions and errors. However, natural-
language diagnoses are difficult to use directly for credit assignment: their error claims may be unreliable, and they do not quantify how much each error should affect learning. We propose Self-Diagnosis-guided Terminal Credit Redistribution (FAULT), which turns diagnosed errors into explicit step-level credit anchored by terminal outcomes. FAULT checks diagnostic evidence and learns relative error costs from task outcomes. During training, the policy and self-diagnoser co-evolve, while error costs are updated online from recent outcomes. On ALFWorld, FAULT recovers learning signals from same-outcome groups, reaching 95% signal coverage versus 41% for GRPO and 72% for GiGPO, while better localizing credit to specific error steps. Across two model scales, FAULT delivers strong. improvements on the long-horizon ALFWorld and WebShop tasks while remaining competitive on short-horizon Search-based QA.
Read the full abstract ▾
All authors Yihua Zhu, Qianying Liu, Weixu Qiao, Xuan Ren, Weiwei Xu, Wenbo Li, Wei Wang, Ruijia Chen, Xinmiao Luan, Yin Luo, Hao Huang, Xiang Zheng, Hidetoshi Shimodaira
Distributed Computing
Serving a Revisable World: Versioned Execution for Interruptible Agents
Yanxin Zhang, Rahul Sharma, Nitin Vegesna et al. (+3 more)
LLM
agents revise running tasks when users change instructions, tools fail, or new information changes a plan. Today's servers express a revision as aborting old requests and submitting replacements. Yet the old execution's buffered output and outstanding work must stop affecting the application, while completed KV state may still be useful to its replacement. Handling these obligations separately can leave obsolete effects publishable and force the successor to rebuild valid state. We present \retire, a serving control-plane redesign around versioned execution. Requests own scheduling and
memory resources; execution versions own authority, the permission to publish output or install state for the current execution. \retire first revokes obsolete work, then bounds its remaining execution and certifies the completed prefix its successor can inherit. The successor runs from that state while isolated old resources are reclaimed asynchronously. This unifies fast invalidation and selective preservation in one version transition. We implement \retire in vLLM across output publication, GPU execution, KV handoff, tiered recovery, and distributed and multi-tenant serving. Correctness experiments verify current-version output and valid state inheritance across these paths. Combining invalidation with inheritance reduces revision-to-successor time-to-first-
token by a median 17.1% in controlled paired experiments. A replay of recorded coding-
agent interruption arrivals emits no obsolete output and keeps every final version progressing through repeated revisions. \retire turns abort-and-restart into a coordinated handoff that stops obsolete work quickly and preserves useful work for its successor.
Read the full abstract ▾
All authors Yanxin Zhang, Rahul Sharma, Nitin Vegesna, Zheyu Fu, Chang Liu, Trivikram Krishnamurthy
Computers and Society
Understanding Student Use of Large Language Models Across Computer Science Subfields
Sehrish Basir Nizamani, Yoonje Lee, Nikitha Donekal Chandrashekar et al. (+2 more)
This research full paper examines how undergraduate students use large
language models (LLMs) across computer science subfields. As LLMs become increasingly integrated into computing education, understanding how their use varies across technical and pedagogical contexts is essential for designing effective, subfield-aware instruction. This paper presents a cross-subfield analysis of LLM usage among 211 undergraduate students in a problem-solving course intentionally designed to support responsible and effective LLM use through structured instruction and reflection. Using post-assignment reflection data collected across seven instructional modules spanning multiple computer science subfields, we examine
prompt counts, LLM role conceptualization, and verification behavior. Results show that LLM adoption varies substantially by assignment, with higher usage in
algorithms and web development and lower usage in software engineering. Students predominantly treat LLMs as assistive tools rather than authoritative sources, and verification is common across all subfields, with most students using multiple strategies. Verification behavior also varies by assignment context, with testing more common in structured tasks and web search more common in open-ended tasks. These findings suggest that assignment characteristics play a central role in shaping how students interact with and evaluate LLM outputs, even under a single, consistently applied instructional design. This work contributes empirical evidence on how LLM adoption, role conceptualization, and verification behavior vary across computer science subfields, extending our prior work on structured, reflective LLM instruction to show how its effects differ by task rather than only in aggregate.
Read the full abstract ▾
All authors Sehrish Basir Nizamani, Yoonje Lee, Nikitha Donekal Chandrashekar, Margaret Ellis, Naren Ramakrishnan
Machine Learning
Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts
Di He, Pengxiang Li, Da Chang et al. (+3 more)
Looped
Transformers introduce recurrent depth as a new scaling axis for LLMs: by repeatedly applying shared
Transformer blocks, they increase effective depth without increasing parameter count. However, the benefits of looping remain unclear for large MoE LLMs under FLOPs-matched comparisons. The main reason is that the gains from additional iterations diminish quickly and can even turn into degradation, so the extra FLOPs spent on looping yield little substantial improvement. Consequently, prior work typically settles on two loops. We identify two main obstacles to scaling looped MoE. First, looping inherits and amplifies the curse of depth: hidden-state variance grows with each iteration as residual updates accumulate, which destabilizes deep recurrence and causes representations to drift. Second, looped MoE suffers from expert selection collapse: routers repeatedly select the same experts across loops, so extra iterations add computation without adding computational diversity. Guided by this diagnosis, we propose LOOM, built on a single principle: each loop should contribute new computation while keeping the recurrent state stable. LOOM stabilizes recurrence by scaling residual updates to bound variance growth and re-injecting the input
embedding at every loop, and diversifies it through per-loop routers that engage different experts and a Looping Residual that carries earlier outputs forward. Experiments across 100M-1.7B models show stable scaling to 9-12 loops. Under near-iso-FLOP, the 700M model performs best at 5 loops, reducing perplexity from 18.36 to 16.54 and improving average zero-shot accuracy from 38.84% to 39.53% over the non-looped baseline. Without FLOP matching, the 1.7B model trained on 60B
tokens peaks at 9 loops, reducing perplexity from 9.62 to 7.77 and improving average zero-shot accuracy from 42.4% to 47.7%. Code is available https://github.com/hed-ucas/LOOM.
Read the full abstract ▾
All authors Di He, Pengxiang Li, Da Chang, Qingyan Meng, Lu Yin, Shiwei Liu
Computation and Language
BanglaDial-Abuse: A Corpus-Grounded Dataset for Regional Dialect Identification in Abusive Bangla Text
Hasin Almas Sifat
Regional linguistic variation remains an important challenge for Bangla natural
language processing, particularly in informal and non-standard text. This paper introduces BanglaDial-Abuse, a balanced Bengali-script
dataset developed for regional dialect identification in abusive and hostile Bangla text. The
dataset contains 1,000 sentences distributed equally across four linguistic varieties: Standard Bangla, Chattagram, Sylhet, and Barishal, with 250 samples per class. The resource was constructed using a corpus-grounded synthetic procedure incorporating regional variation in pronouns, possessive forms, verb morphology, negation, interrogative structures, postpositions, vocabulary, and Bengali-script spelling conventions while preserving the underlying hostile or abusive meaning. Descriptive analysis shows broadly comparable sentence-length distributions but partially distinct lexical spaces across the four classes. Pairwise Jaccard vocabulary similarity ranges from 0.37 to 0.56. The primary task is four-class regional dialect identification rather than binary abusive-text detection. The
dataset is publicly available through Zenodo under a Creative Commons Attribution 4.0 license. The current version is intended as a research and prototyping corpus rather than a native-speaker-validated gold-standard linguistic resource. Keywords: Bangla, Bengali, dialect identification, regional dialect, abusive
language, low-resource NLP, Chattagram, Sylhet, Barishal,
dataset
Read the full abstract ▾
Data Structures and Algorithms
When Is Deletion Ordering Tractable? From Update Dynamics to Permutation Structure
Xinyu Wang, Ziyu Zhao, Yixuan He et al. (+1 more)
Given a fixed set of pending deletion requests, retraining from scratch after each request is prohibitive, so a prescribed request-wise policy processes them sequentially. The resulting terminal model can depend on their order. Rather than prescribing an ordering rule, we study the permutation objective induced by the fixed policy and ask when it admits simpler structure. We identify two independent reductions: position additivity represents the objective by request–position costs, reducing optimization to assignment and, with a shared positional profile, sorting; suffix localization removes dependence on the distant prefix while retaining interactions among the surviving requests. Under shared affine updates, we characterize the quadratic interactions that obstruct additivity, prove the reductions' independence, and show that suffix-conditioned assignment improves the approximation rate from O(p^L) toO(p^(2L)). Experiments recover both structures in executed objectives. A controlled damped-Newton sweep shows that stronger contraction shifts the objective toward shorter, more suffix-specific dependence, while two full-network policies exhibit distinct positional and within-suffix structure. Structures identified from compact execution sets also predict unseen orders. These results frame deletion ordering as identifying the computational structure induced by the executed updates.
Read the full abstract ▾
All authors Xinyu Wang, Ziyu Zhao, Yixuan He, Xiaowen Chang Alex Smola
Computer Vision
OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots
Mazhar Iqbal, Xuanmeng Sha, Naoya Chiba et al. (+2 more)
Generating compact and geometrically faithful 3D meshes directly from point clouds remains a fundamental challenge. Point clouds are unordered and sparse, whereas meshes exhibit irregular structure and varying
topology. As a result, many existing approaches rely on implicit representations followed by surface extraction or reconstruction. Although effective, these pipelines can produce dense or over-smoothed meshes, often requiring computationally expensive post-processing and simplification. We present OptimusMesh, a framework for direct compact triangle mesh generation from point clouds using sparse latent pivot conditioning. Our key idea is to compress $2{,}048$ oriented input points into only $16$ sparse latent pivots, reducing the
geometric conditioning set by $128\times$. These pivots provide a compact structural representation shared across a two-stage autoregressive framework that first generates mesh vertices and then predicts triangular faces conditioned on the generated vertices and the same pivots. Compared with the evaluated recent point-cloud-conditioned autoregressive methods, which use $257$ decoder-conditioning
tokens, OptimusMesh uses only $16$, yielding a $16.1\times$ shorter conditioning sequence. Experiments show that OptimusMesh produces the most compact outputs among the compared recent autoregressive methods, using $25.7\%$–$94.1\%$ fewer faces while maintaining competitive
geometric fidelity and distributional quality.
Read the full abstract ▾
All authors Mazhar Iqbal, Xuanmeng Sha, Naoya Chiba, Yuki Uranishi, Tomohiro Mashita
Computers and Society
Virtual Global Collaboration in Data Analytics and Machine Learning Education: A Mixed-Methods Study of Asynchronous Cross-Border Teamwork
Sehrish Basir Nizamani, Saad Nizamani, Khyati Goyal et al. (+2 more)
This innovative practice full paper examines a structured Virtual Global Collaboration (VGC) activity between undergraduate computing courses in the United States and Pakistan. The project was designed to support technical and intercultural skill development through asynchronous international teamwork in data analytics and introductory machine learning. Students worked in mixed-institution teams through a six-phase project including cultural orientation,
dataset selection, data cleaning, analysis, introductory machine learning, and structured reporting. Using shared computational tools, teams coordinated across time zones to complete a joint data-driven project. Survey and qualitative reflection data were analyzed to examine collaborative experience, communication and cultural dynamics, learning outcomes, perceived value, and global readiness. Results show consistently positive student experiences across both cohorts, with collaborative processes strongly associated with learning and perceived value, and cross-cultural communication emerging as the primary driver of global readiness. These findings demonstrate how short-term, structured VGC can be effectively integrated into computing courses to support both technical learning and global competence.
Read the full abstract ▾
All authors Sehrish Basir Nizamani, Saad Nizamani, Khyati Goyal, Sarwat Nizamani, Zannah Zeiw