Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

Week Month Quarter All

Newest Most relevant

Papers

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

Week Month Quarter All

Newest Most relevant

Papers

arXiv cs.LGOct 12
Sequence Composition in EHR Foundation Model Pretraining
Joshua Placidi, Inigo Stibbe, Alfred J. Balston, Marek Rei, A. Aldo Faisal
Autoregressive electronic health record (EHR) foundation models predict the next event token in patient trajectories: sequences of structured medical events. A typical pretraining strategy is to concatenate all trajectories into a global stream and sample token windows from it. This gives patients with longer sequences more training exposure and allows tokens to attend across patient boundaries. We argue that these choices create a misalignment between pretraining and downstream clinical tasks. To explore this, we investigate how the composition of pretraining sequences affects clinical prediction performance. Using the global-stream approach as a baseline, we propose alternative sequence composition methods that control how patient trajectories contribute to pretraining sequences. Across four MIMIC-IV v2.2 tasks, our best method improves macro AUROC, AUPRC, F1, and balanced accuracy, with relative gains of 9.3% in F1 and 2.7% in AUPRC under a fixed training recipe. We find that these gains generalize across four additional evaluation settings, including the INSPIRE and eICU-CRD datasets, with improvements in macro AUROC, AUPRC, and F1 score. Our results show that simply changing…
PDF
arXiv cs.AIOct 12
CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives
Yuhan Wang, Rui Hu, Batian Di, Tan Jiang, Dongsheng Ma +3
Target-aware multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresent similar content without optimizing this balance; group-level methods face coarse units, predefined set-level validation signals, and costly or inaccurate mixture search. We propose CLIVO, a target-aware framework connecting fine-grained semantic allocation, automatically learned validation objectives, and differentiable mixture search. Specifically, semantic clusters provide independently adjustable shares at the hundred-cluster scale. Correlations between per-example merged-proxy losses and real probe performance identify target-relevant validation examples; learned nonnegative weights combine their losses into an objective. A single backward pass through the merged proxy supplies gradients for all shares, avoiding an additional mixture-response regression model. Selecting 100K instructions from an 8M pool, CLIVO attains 97.2% of the full-data four-target average score with only 1.25% of the data. It improves on the strongest evaluated selection baseline by 1.16 points using random within-cluster sampling; combining learned…
PDF
arXiv cs.CLOct 12
SpecGuardBench: Can Coding Agents Construct Reliable Validation Harnesses from Natural Language Specifications?
Zhiqing Zhong, Mingyu Chen, Aoyang Fang, Yuzhong Zhang, Haoye Tian +3
As coding agents become more capable, tests remain the primary evidence for judging whether their code is correct. Yet passing available tests does not establish that an implementation satisfies its natural language specification. Reliable validation requires checks that faithfully capture the specification and scenarios that thoroughly exercise the code, but current benchmarks provide limited insight into whether agents can construct such evidence themselves. We introduce SpecGuardBench, a benchmark of 291 tasks from 13 real-world repositories, covering 8 types of verification logic such as functional postconditions and interaction protocols. Given a natural language specification, repository context, and a reference implementation, an agent constructs a validation harness comprising executable checks and test scenarios. The checks should reject implementations that violate the specification while accepting those that satisfy it, and the scenarios should thoroughly exercise the code. Across four proprietary and open-weight coding agents, none constructs a harness scored as faithful on the benchmark's implementations for more than 63% of the tasks. The bottleneck lies less in…
PDF
arXiv cs.LGOct 12
From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon
Tom Jacobs, Rebekka Burkholz
Simplicity bias, which can arise from sequential feature learning during training, has been proposed as a general explanation for the success of deep learning. An important driver of this phenomenon is saddle-to-saddle behavior, in which the gradient flow trajectory remains close to a sequence of saddle manifolds while learning one feature at a time. However, Muon, a state-of-the-art optimizer based on spectral descent, does not exhibit such dynamics in the full-batch setting and instead learns features in parallel. How is it then that Muon is so successful in deep learning settings? We show that stochastic gradient noise fundamentally changes this behavior: small-batch noise restores sequential feature learning, providing a mechanism for simplicity bias that is absent from full-batch Muon. We explain this transition through stochastic smoothing of the spectral descent operator underlying Muon. When gradients are small relative to the noise scale, the expected spectral update becomes approximately proportional to the actual gradient, which restores gradient-flow-like dynamics. We formalize this mechanism for deep linear models by deriving the effective continuous dynamics of…
PDF
arXiv cs.LGOct 12
Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments
Xiaoyang Yuan, Ji Zhao, Xingyu Hu, Wenhan Wang, Yutao Hu +5
Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were achieved. Scaling either trajectory coverage or verification alone is insufficient as new environments introduce distinct states, rules, and dependencies that must also be reflected in the success criteria. To address this challenge, we introduce Davinci-Tool, a 30B tool-use model, and Davinci-ToolData, an execution-grounded dataset designed to scale environment coverage and outcome verification together. Davinci-ToolData preserves restorable states, execution traces, outcomes, and verifiers as a unified substrate for supervision. Two complementary pipelines populate this substrate: Execution-Grounded Task Synthesis (EGTS) derives verified demonstrations from independently authored systems, and Executable Environment Synthesis (EES) synthesizes auditable environments, state-grounded tasks, and executable verifiers across single and coordinated domains. These pipelines yield 30,395 verified trajectories spanning 2,260 invoked tool names. We first train on these demonstrations with supervised fine-tuning, then reuse EES states and…
PDF
arXiv cs.LGOct 12
Efficient Resource-Shiftable RL Post-training with Generative Rewards
Yanfeng Zhao, Haoyang Li, Sheng Lin, Yuming Zhou, Jiawei Jiang +2
Reinforcement learning (RL) post-training with generative reward models (GenRM) has become a central recipe for improving large language models (LLMs), and it is also increasingly resource-intensive: policy rollout, GenRM-based reward evaluation, and policy training all compete for GPU resources. However, existing colocated and disaggregated systems rely on static resource allocation for these roles. Such allocation cannot adapt as each role's workload changes during RL and therefore leaves a role's resources underutilized. We present PivotRL, an RL post-training system that dynamically shifts resources among different roles according to their runtime demands. PivotRL introduces a resource-shiftable runtime built on a Global Parameter Storage, together with a unified mechanism that efficiently shifts role-specific context. A shift-aware scheduler enables sequence migration upon a shift, while a planner considers the aggregate throughput benefit and the shift overhead to determine when and how to shift. We evaluate PivotRL on a 128-GPU cluster using four model groups spanning dense and mixture-of-experts models. PivotRL enables resource shifting within seconds and improves…
PDF
arXiv cs.HCOct 12
Better together? A performance theory of human-machine skill policies under generalization difficulty
Riccardo Zanardelli
Organizations pairing a human and a machine on a task decide, often by default, which executes each instance and what happens when both do. We account for what this attains under the squared rule, with performance distributed over instances to capture generalization difficulty. A gross stake lies between the skills' mean and best per instance. It splits at the best single skill into a systematic part, known from separate assessments and secured by commitment, and a residual, the expected value of perfect information on which skill each instance favors, known only from paired observation and split further by classes. Skills set the stake; workflows decide the take, via two channels. Routing directs work, weighting or selecting responses; with binary truth it is capped by the best skill per instance. Reading responses as joint evidence is not routing; what they jointly reveal caps it. Synergy lets skills interact before responding; bounded by no skill either way, its lift over independent responses must clear a break-even and can fall below one. As algorithms, arrangements form a ladder stating what each reads, holds and records, and a procedure whose checks keep earlier gains when…
PDF
arXiv cs.CVOct 12
From Volpiano to Pixels: 30,000 Lines of OMR Ground Truth for Medieval Chant
Robert Klugseder
Optical music recognition (OMR) for medieval chant lacks training data linking manuscript images to musical symbols across notational families. Using existing Volpiano transcriptions from the Cantus Database, we created 30,567 image-target pairs from ten sources in eleven exports, including 339 verse fragments. Their target sequences contain 1,952,143 tokens. The pipeline locates staff systems, infers clefs and maps known pitches to staff positions. Six detector families handle the different layouts and notations. Where heuristics failed, two small U-Nets learned staff lines and clef letters from manual annotations. Reviews of sampled export lines found zero to four pitch or clef errors, but used different error definitions and do not provide a uniform audit of the corpus. A CRNN trained from scratch achieved a symbol error rate of 9.6 % on 3,086 test lines. The earlier model, trained mainly on Austrian sources of the 15th and 16th centuries, scored 45.3 %. In three separate training runs, each excluding one manuscript, error rates on the excluded manuscript were 21.5-31.0 %. Model-assisted alignment recovered a further 2,686 lines.
PDF
arXiv cs.LGOct 12
GpFlash: Maximizing Speed and Minimizing Memory for Gaussian Process Training and Prediction
Andre Marchildon
This paper presents GpFlash, a Gaussian process library that is focused on fast training and posterior evaluations, minimal memory usage, and scalability to high-dimensional problems. GpFlash was compared to the popular GP libraries scikit-learn, GPy, GPflow, GPyTorch, and SMT on a MacBook Pro and the supercomputer Trillium. GpFlash was found to use less memory and to be faster for training and posterior evaluations relative to the other GP libraries for all cases considered. For example, when using $\nx = 10^4$ training points in a 10-dimensional space GpFlash required 9.6 to 35 times less memory and was 2.6 to 54 times faster than the other GP libraries for the evaluation of the marginal log likelihood and its gradient. The memory reduction was achieved by only using one matrix of size $\nx \times \nx$ to store different symmetric matrices in its lower and upper triangular entries. The computational speedup was the result of designing algorithms to access memory efficiently, using BLAS and LAPACK methods extensively, and factoring kernel equations so that expensive exponential calculations could be reused. GpFlash was more than 440 times faster than all of the other GP…
PDF
arXiv cs.CVOct 12
Vision Models Capture Complementary Representations in Children That Converge in Adults
Domenic Bersch, Timothy Schaumlöffel, Michela Proietti, Antonia Franaszek-Traczewska, Hannah Elisabeth Zwad +9
How the relationship between image-text aligned and vision-only models changes across development remains unknown. We applied time-resolved representational similarity analysis to EEG data from 8-year-olds, 12-year-olds, and adults. CLIP showed significant model-brain alignment already in children, whereas vision-only models aligned more strongly later in development. Residual analyses revealed complementary structure, with CLIP retaining alignment beyond an architecture-matched vision-only model from age 8. Much of the model-brain alignment reflected semantic structure, with EEG representations of category and animacy strengthening toward adulthood, while alignment with low-level image properties remained weak across age. Together, these findings suggest that image-text aligned and vision-only models capture complementary aspects of developing visual representations and may provide useful constraints for AI systems that aim to learn and adapt over time.
PDF
arXiv cs.CLOct 12
ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding
Wenqiang Zhu, Xinping Lei, Zhiyi Lai, Zhengshuo Gong, Tianzhuang He +15
For repository-grounded coding agents, a functionally correct patch is not necessarily an acceptable one: developers also constrain how the task must be carried out-modification scope, workflow order, validation, tool use, and reporting. This capability, which we call engineering constraint following, remains largely invisible to current evaluations. We introduce ANCHOR (Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding), a benchmark built on naturalistic, multilingual repository tasks spanning eight language groups. ANCHOR combines (i) a hierarchical taxonomy of 10 categories and 78 leaf types distilled from real developer interactions, (ii) an automated pipeline that instantiates task-grounded atomic constraints and composes them into typed AND/THEN/PRIORITY relations, and (iii) a trajectory-grounded evaluation framework that checks both the code diff and the execution trajectory with rule-based and LLM judges. Across 19 agent configurations spanning 2 scaffolds and 10 foundation models on 358 tasks, the strongest measured system, Claude Opus 4.8 under Cline, reaches 70.1% atomic compliance and 63.7% relation compliance, while…
PDF
arXiv cs.CVOct 12
Towards Cost-Efficient Video Dataset Construction with Large Language Models
Mohammed Shabot, Jonathan Adams, Jan Van den Stock, Joost Vennekens
Research on video classification models has witnessed significant growth recently, accompanied by a significant increase in the demand for datasets to train such models. Existing video dataset curation approaches share a common bottleneck: candidate videos must be downloaded before any relevance judgment is made, which results in storage, time and annotation costs. In this work, we present a filtering step, using Large Language Models (LLMs) to pre-screen videos based on their metadata, before actually downloading these videos, thereby saving on these costs. We evaluate the LLMs against a strict human majority vote derived from four independent annotators and validate the reliability of the annotations through inter-annotator agreement analysis (Gwet's AC1). We compare the LLM pre-filter against two no-LLM baselines, namely two keyword heuristics. Via a Leave-One-Rater-Out (LOO) mechanism and an Add-One-Rater-In (AORI), we evaluate the performance of the LLMs as virtual annotators. Finally, we report cost comparisons relative to existing approaches. To ensure reproducability, we made our implementation available on github.
PDF
arXiv cs.LGOct 12
Radial Tail Repair: Post-Training Correction for Diffusion and Flow Models
Hamza Cherkaoui, Hélène Halconruy, Antonio Ocello
Diffusion and flow-matching models may struggle to accurately represent distributional tails, especially for heavy-tailed data. Existing approaches often use heavy-tailed noise or modify the generative dynamics, requiring dedicated retraining and more difficult estimation. We take a simpler approach: rather than relearning the full distribution, we correct only the model's behavior in the extreme regime. Our method builds on the radial-angular decomposition of multivariate heavy tails, where radius and direction become asymptotically independent. This allows us to preserve the directional structure learned by the pretrained model and correct only its radial tail. We estimate the tail onset from reference and generated samples, then rescale generated extremes so that their radial survival matches the target distribution. The resulting method is a lightweight post-training correction applied to a frozen diffusion or flow-matching model, requiring neither retraining nor changes to its sampling dynamics. Experiments on challenging synthetic heavy-tailed distributions and real weather and wildfire datasets show that this simple correction substantially improves extreme-tail coverage…
PDF
arXiv cs.CVOct 12
A Multi-Task Deep Learning Framework for Pose-Invariant Face Recognition and Facial Landmark Localization
Ali Ashkeyev, Zukhra Abdiakhmetova
Face recognition systems often experience performance degradation under large pose variations due to changes in facial appearance and visibility of discriminative features. This study presents a multi-task deep learning framework that jointly addresses pose-invariant face recognition and facial landmark localization within a unified architecture. To enable simultaneous optimization of identity recognition and facial structure learning, the original Cross-Pose Labeled Faces in the Wild (CPLFW) dataset was adapted into a multi-task learning dataset by associating facial images with identity labels and five-point landmark annotations. The proposed framework consists of two task-specific branches operating on a common facial input: a ResNet50-based branch for identity recognition and an EfficientNetV2B0-based branch with spatial attention for facial landmark localization. The two objectives are jointly optimized using a weighted multi-task loss, allowing the model to learn complementary semantic and spatial facial representations. The proposed framework was evaluated on the prepared CPLFW-based multi-task dataset. Unlike the original CPLFW benchmark, which focuses primarily on…
PDF
arXiv stat.MLOct 12
Feature Normalization under Finite Training Budgets
Johan Larsson
Standardizing a rare feature can help stochastic gradient descent learn its effect within a finite budget, but it also changes the noise cost of learning. We characterize the lowest rare-subgroup risks attainable by standardized and unscaled training when each chooses a nonnegative constant learning rate and a deterministic stopping time under the same observation cap. For two independent binary features, we derive both optimized risks as prevalence vanishes while the expected number of rare observations remains finite. Uniform control over rates and stopping times reduces each limiting oracle to a scalar minimization. With positive noise, the preferred scaling changes exactly once as we move signal to the rare feature while the limiting risk at initialization stays fixed and positive. The formulas also explain how noise and budget affect the comparison. Separate finite-prevalence bounds favor standardization on a rare-dominant signal family and unscaled training on a common-dominant family. The results concern final iterates with population preprocessing and fresh observations. Exact-moment searches assess the approximation at finite prevalence. In a controlled study, both…
PDF
arXiv cs.LGOct 12
Few-for-Many Best-Arm Identification in Multi-Objective Bandits
Bo Xue, Yilu Liu, Haodong Jing, Hongzong Li, Xi Lin +1
Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback. Modeling each option as an arm in a multi-objective bandit, we introduce \emph{few-for-many best-arm identification}, which seeks a small set of arms minimizing the worst weighted degradation from the objective-wise optima, rather than the best arm for every objective. We consider both known objective groups and latent groups specified only by a representative budget, and propose \textsc{GFM-Elim} and \textsc{AFM-Elim} with instance-dependent sample-complexity guarantees. For Gaussian rewards, we further derive a lower bound for the latent-group setting and show that it is asymptotically attainable with high probability by an oracle-based Track-and-Stop procedure. Our results show that sharing observations across objectives and ignoring irrelevant objective-wise distinctions can substantially reduce the sampling cost, as confirmed by experiments on synthetic and real-world tasks.
PDF
arXiv cs.CLOct 12
Label Collapse in Diffusion Language Model In-Context Learning
Ziye Guo, Ye Yuan
In-context learning (ICL) applies large language models to new tasks by prepending a few labeled demonstrations to a query. Prior work has studied how demonstration ordering affects ICL, but the interaction between label arrangement patterns and model biases has not been systematically examined. We define label collapse as the failure mode in which the model generates query-independent labels, and show that it is architecturally universal at the tested 8-9B scale: five models spanning autoregressive (Llama-3, Qwen3.5) and discrete diffusion (LLaDA, iLLaDA, LLaDA-Instruct) families all exhibit label collapse even under the class-balanced alternating arrangement, with some label word pairs collapsing in virtually every tested condition and others flipping their collapse direction with arrangement. Critically, accuracy alone cannot detect this collapse: models can achieve near-chance accuracy while generating query-independent labels, a score indistinguishable from balanced performance, so the failure can persist undetected in deployment. We measure separation, the log-odds of the two label words at the query position (the quantity that label-bias calibration operates on), as a…
PDF
arXiv cs.AIOct 12
Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization
Huihao Jing, Shaojin Chen, Wenbin Hu, Yuxuan Liu, Haochen Shi +3
As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central safety problem. Guardrails are often placed in front of these actions, yet few evaluations ask whether their decisions follow authorization: blocking unauthorized actions while still allowing the same actions under valid permission. We introduce \bench{}, a benchmark that contrasts authorization evidence for the same operation in its language track. It combines expert-annotated natural-language scenarios with executed and verified operations, plus externally sourced native-policy requests. \bench{} checks each decision for correctness, usability and resulting effect, and tracks each request across guardrail changes. Our experiments show that many blocked operations stem from failed reviews, not correct denials. Repairing the output format restores usable decisions but changes which authorized requests are honored, and adding a second reviewer removes some errors while rejecting valid authorization. Guardrails should therefore be evaluated on both the unauthorized actions they stop and the authorized actions they let through.
PDF
arXiv cs.CLOct 12
A Scaled-Up Empirical Study of Syntactic Language Models
Pengcheng Wang, Zhexuan Zhang, Chao Lou, Kewei Tu
Syntactic language models (SLMs) that generate sentences along with their syntactic tree structures have shown promise in both syntactic generalization and downstream tasks. Prior studies, however, have mostly evaluated smaller models trained on less pretraining data and tested on narrower task suites. In addition, the design space of tree linearization and attention masks remains underexplored. We conduct a large-scale empirical study of 12 controlled configurations---one terminal baseline and 11 SLM variants spanning different linearizations and masks---at scales up to 1B parameters and 100B training tokens, evaluated across 11 downstream tasks and two syntactic benchmarks. The experimental results show that SLMs with standard causal attention match or exceed structural-mask variants across downstream and syntactic benchmarks. They require no architectural modifications and remain compatible with FlashAttention. We also observe that when scaling up to the 1B-parameter scale, the top-performing SLM variant no longer shows a clear advantage over a compute-matched non-structural baseline, suggesting that SLMs may become less competitive with scale. Our code is available at…
PDF
arXiv cs.CROct 12
Beyond User-Side Defenses: Image Protection in Open-Weight Diffusion Models
Jihye Kang, Jiwon Park, Namhyuk Ahn
Model providers can support image protection, but open-weight deployment introduces practical constraints. We propose four requirements: protection effectiveness, clean fidelity, compatibility, and tamper resistance. We incorporate long-horizon attack simulations to strengthen resistance to protection removal. Experiments with a single protection tool show improved resistance to re-alignment at a cost to clean fidelity, motivating further research toward practical model-side protection.
PDF

Papers

Open problems across fields

Real-time request execution in streaming video generation1 paper raises it · 0 address it
Models struggle to reliably follow incremental user requests while maintaining state consistency in interactive video generation.
- StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
Brain-body mismatch in recursive self-improving agents1 paper raises it · 1 addresses it
Evolving execution scaffolds (harnesses) can outpace or restrict the capabilities of the underlying model, leading to misalignment.
- CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?raises · addresses
End-to-end deep search in open web environments1 paper raises it · 1 addresses it
Agents fail to autonomously explore, integrate, and verify evidence from diverse, interactive, and heterogeneous web sources.
- Deep Search in Real-World Web Environmentsraises · addresses
Length generalization in state tracking1 paper raises it · 1 addresses it
Models trained on short sequences often fail to generalize to much longer sequences without explicit progress alignment.
- PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses
Fine-grained geometry and appearance recovery in 3D Gaussian Splatting1 paper raises it · 1 addresses it
Feed-forward models struggle to capture detailed structures and textures in 3D scene reconstruction.
- FineSplat: Fine Patches, Local Groups, Detailed Splatsraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Rising research topics

Adversarial training41−8.9%
CAD models12−14.3%
Efficient spiking neural5−28.6%
Federated learning33−29.8%
Forecasting time54−33.3%
Anomaly detectors24−35.1%
Teacher policy distillation42−35.4%
Frontier LLMs330−36.3%

Rising research topics

Ask the research

Sample

Papers

arXiv cs.LGOct 12
Sequence Composition in EHR Foundation Model Pretraining
Joshua Placidi, Inigo Stibbe, Alfred J. Balston, Marek Rei, A. Aldo Faisal
Autoregressive electronic health record (EHR) foundation models predict the next event token in patient trajectories: sequences of structured medical events. A typical pretraining strategy is to concatenate all trajectories into a global stream and sample token windows from it. This gives patients with longer sequences more training exposure and allows tokens to attend across patient boundaries. We argue that these choices create a misalignment between pretraining and downstream clinical tasks. To explore this, we investigate how the composition of pretraining sequences affects clinical prediction performance. Using the global-stream approach as a baseline, we propose alternative sequence composition methods that control how patient trajectories contribute to pretraining sequences. Across four MIMIC-IV v2.2 tasks, our best method improves macro AUROC, AUPRC, F1, and balanced accuracy, with relative gains of 9.3% in F1 and 2.7% in AUPRC under a fixed training recipe. We find that these gains generalize across four additional evaluation settings, including the INSPIRE and eICU-CRD datasets, with improvements in macro AUROC, AUPRC, and F1 score. Our results show that simply changing…
PDF
arXiv cs.AIOct 12
CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives
Yuhan Wang, Rui Hu, Batian Di, Tan Jiang, Dongsheng Ma +3
Target-aware multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresent similar content without optimizing this balance; group-level methods face coarse units, predefined set-level validation signals, and costly or inaccurate mixture search. We propose CLIVO, a target-aware framework connecting fine-grained semantic allocation, automatically learned validation objectives, and differentiable mixture search. Specifically, semantic clusters provide independently adjustable shares at the hundred-cluster scale. Correlations between per-example merged-proxy losses and real probe performance identify target-relevant validation examples; learned nonnegative weights combine their losses into an objective. A single backward pass through the merged proxy supplies gradients for all shares, avoiding an additional mixture-response regression model. Selecting 100K instructions from an 8M pool, CLIVO attains 97.2% of the full-data four-target average score with only 1.25% of the data. It improves on the strongest evaluated selection baseline by 1.16 points using random within-cluster sampling; combining learned…
PDF
arXiv cs.CLOct 12
SpecGuardBench: Can Coding Agents Construct Reliable Validation Harnesses from Natural Language Specifications?
Zhiqing Zhong, Mingyu Chen, Aoyang Fang, Yuzhong Zhang, Haoye Tian +3
As coding agents become more capable, tests remain the primary evidence for judging whether their code is correct. Yet passing available tests does not establish that an implementation satisfies its natural language specification. Reliable validation requires checks that faithfully capture the specification and scenarios that thoroughly exercise the code, but current benchmarks provide limited insight into whether agents can construct such evidence themselves. We introduce SpecGuardBench, a benchmark of 291 tasks from 13 real-world repositories, covering 8 types of verification logic such as functional postconditions and interaction protocols. Given a natural language specification, repository context, and a reference implementation, an agent constructs a validation harness comprising executable checks and test scenarios. The checks should reject implementations that violate the specification while accepting those that satisfy it, and the scenarios should thoroughly exercise the code. Across four proprietary and open-weight coding agents, none constructs a harness scored as faithful on the benchmark's implementations for more than 63% of the tasks. The bottleneck lies less in…
PDF
arXiv cs.LGOct 12
From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon
Tom Jacobs, Rebekka Burkholz
Simplicity bias, which can arise from sequential feature learning during training, has been proposed as a general explanation for the success of deep learning. An important driver of this phenomenon is saddle-to-saddle behavior, in which the gradient flow trajectory remains close to a sequence of saddle manifolds while learning one feature at a time. However, Muon, a state-of-the-art optimizer based on spectral descent, does not exhibit such dynamics in the full-batch setting and instead learns features in parallel. How is it then that Muon is so successful in deep learning settings? We show that stochastic gradient noise fundamentally changes this behavior: small-batch noise restores sequential feature learning, providing a mechanism for simplicity bias that is absent from full-batch Muon. We explain this transition through stochastic smoothing of the spectral descent operator underlying Muon. When gradients are small relative to the noise scale, the expected spectral update becomes approximately proportional to the actual gradient, which restores gradient-flow-like dynamics. We formalize this mechanism for deep linear models by deriving the effective continuous dynamics of…
PDF
arXiv cs.LGOct 12
Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments
Xiaoyang Yuan, Ji Zhao, Xingyu Hu, Wenhan Wang, Yutao Hu +5
Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were achieved. Scaling either trajectory coverage or verification alone is insufficient as new environments introduce distinct states, rules, and dependencies that must also be reflected in the success criteria. To address this challenge, we introduce Davinci-Tool, a 30B tool-use model, and Davinci-ToolData, an execution-grounded dataset designed to scale environment coverage and outcome verification together. Davinci-ToolData preserves restorable states, execution traces, outcomes, and verifiers as a unified substrate for supervision. Two complementary pipelines populate this substrate: Execution-Grounded Task Synthesis (EGTS) derives verified demonstrations from independently authored systems, and Executable Environment Synthesis (EES) synthesizes auditable environments, state-grounded tasks, and executable verifiers across single and coordinated domains. These pipelines yield 30,395 verified trajectories spanning 2,260 invoked tool names. We first train on these demonstrations with supervised fine-tuning, then reuse EES states and…
PDF
arXiv cs.LGOct 12
Efficient Resource-Shiftable RL Post-training with Generative Rewards
Yanfeng Zhao, Haoyang Li, Sheng Lin, Yuming Zhou, Jiawei Jiang +2
Reinforcement learning (RL) post-training with generative reward models (GenRM) has become a central recipe for improving large language models (LLMs), and it is also increasingly resource-intensive: policy rollout, GenRM-based reward evaluation, and policy training all compete for GPU resources. However, existing colocated and disaggregated systems rely on static resource allocation for these roles. Such allocation cannot adapt as each role's workload changes during RL and therefore leaves a role's resources underutilized. We present PivotRL, an RL post-training system that dynamically shifts resources among different roles according to their runtime demands. PivotRL introduces a resource-shiftable runtime built on a Global Parameter Storage, together with a unified mechanism that efficiently shifts role-specific context. A shift-aware scheduler enables sequence migration upon a shift, while a planner considers the aggregate throughput benefit and the shift overhead to determine when and how to shift. We evaluate PivotRL on a 128-GPU cluster using four model groups spanning dense and mixture-of-experts models. PivotRL enables resource shifting within seconds and improves…
PDF
arXiv cs.HCOct 12
Better together? A performance theory of human-machine skill policies under generalization difficulty
Riccardo Zanardelli
Organizations pairing a human and a machine on a task decide, often by default, which executes each instance and what happens when both do. We account for what this attains under the squared rule, with performance distributed over instances to capture generalization difficulty. A gross stake lies between the skills' mean and best per instance. It splits at the best single skill into a systematic part, known from separate assessments and secured by commitment, and a residual, the expected value of perfect information on which skill each instance favors, known only from paired observation and split further by classes. Skills set the stake; workflows decide the take, via two channels. Routing directs work, weighting or selecting responses; with binary truth it is capped by the best skill per instance. Reading responses as joint evidence is not routing; what they jointly reveal caps it. Synergy lets skills interact before responding; bounded by no skill either way, its lift over independent responses must clear a break-even and can fall below one. As algorithms, arrangements form a ladder stating what each reads, holds and records, and a procedure whose checks keep earlier gains when…
PDF
arXiv cs.CVOct 12
From Volpiano to Pixels: 30,000 Lines of OMR Ground Truth for Medieval Chant
Robert Klugseder
Optical music recognition (OMR) for medieval chant lacks training data linking manuscript images to musical symbols across notational families. Using existing Volpiano transcriptions from the Cantus Database, we created 30,567 image-target pairs from ten sources in eleven exports, including 339 verse fragments. Their target sequences contain 1,952,143 tokens. The pipeline locates staff systems, infers clefs and maps known pitches to staff positions. Six detector families handle the different layouts and notations. Where heuristics failed, two small U-Nets learned staff lines and clef letters from manual annotations. Reviews of sampled export lines found zero to four pitch or clef errors, but used different error definitions and do not provide a uniform audit of the corpus. A CRNN trained from scratch achieved a symbol error rate of 9.6 % on 3,086 test lines. The earlier model, trained mainly on Austrian sources of the 15th and 16th centuries, scored 45.3 %. In three separate training runs, each excluding one manuscript, error rates on the excluded manuscript were 21.5-31.0 %. Model-assisted alignment recovered a further 2,686 lines.
PDF
arXiv cs.LGOct 12
GpFlash: Maximizing Speed and Minimizing Memory for Gaussian Process Training and Prediction
Andre Marchildon
This paper presents GpFlash, a Gaussian process library that is focused on fast training and posterior evaluations, minimal memory usage, and scalability to high-dimensional problems. GpFlash was compared to the popular GP libraries scikit-learn, GPy, GPflow, GPyTorch, and SMT on a MacBook Pro and the supercomputer Trillium. GpFlash was found to use less memory and to be faster for training and posterior evaluations relative to the other GP libraries for all cases considered. For example, when using $\nx = 10^4$ training points in a 10-dimensional space GpFlash required 9.6 to 35 times less memory and was 2.6 to 54 times faster than the other GP libraries for the evaluation of the marginal log likelihood and its gradient. The memory reduction was achieved by only using one matrix of size $\nx \times \nx$ to store different symmetric matrices in its lower and upper triangular entries. The computational speedup was the result of designing algorithms to access memory efficiently, using BLAS and LAPACK methods extensively, and factoring kernel equations so that expensive exponential calculations could be reused. GpFlash was more than 440 times faster than all of the other GP…
PDF
arXiv cs.CVOct 12
Vision Models Capture Complementary Representations in Children That Converge in Adults
Domenic Bersch, Timothy Schaumlöffel, Michela Proietti, Antonia Franaszek-Traczewska, Hannah Elisabeth Zwad +9
How the relationship between image-text aligned and vision-only models changes across development remains unknown. We applied time-resolved representational similarity analysis to EEG data from 8-year-olds, 12-year-olds, and adults. CLIP showed significant model-brain alignment already in children, whereas vision-only models aligned more strongly later in development. Residual analyses revealed complementary structure, with CLIP retaining alignment beyond an architecture-matched vision-only model from age 8. Much of the model-brain alignment reflected semantic structure, with EEG representations of category and animacy strengthening toward adulthood, while alignment with low-level image properties remained weak across age. Together, these findings suggest that image-text aligned and vision-only models capture complementary aspects of developing visual representations and may provide useful constraints for AI systems that aim to learn and adapt over time.
PDF
arXiv cs.CLOct 12
ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding
Wenqiang Zhu, Xinping Lei, Zhiyi Lai, Zhengshuo Gong, Tianzhuang He +15
For repository-grounded coding agents, a functionally correct patch is not necessarily an acceptable one: developers also constrain how the task must be carried out-modification scope, workflow order, validation, tool use, and reporting. This capability, which we call engineering constraint following, remains largely invisible to current evaluations. We introduce ANCHOR (Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding), a benchmark built on naturalistic, multilingual repository tasks spanning eight language groups. ANCHOR combines (i) a hierarchical taxonomy of 10 categories and 78 leaf types distilled from real developer interactions, (ii) an automated pipeline that instantiates task-grounded atomic constraints and composes them into typed AND/THEN/PRIORITY relations, and (iii) a trajectory-grounded evaluation framework that checks both the code diff and the execution trajectory with rule-based and LLM judges. Across 19 agent configurations spanning 2 scaffolds and 10 foundation models on 358 tasks, the strongest measured system, Claude Opus 4.8 under Cline, reaches 70.1% atomic compliance and 63.7% relation compliance, while…
PDF
arXiv cs.CVOct 12
Towards Cost-Efficient Video Dataset Construction with Large Language Models
Mohammed Shabot, Jonathan Adams, Jan Van den Stock, Joost Vennekens
Research on video classification models has witnessed significant growth recently, accompanied by a significant increase in the demand for datasets to train such models. Existing video dataset curation approaches share a common bottleneck: candidate videos must be downloaded before any relevance judgment is made, which results in storage, time and annotation costs. In this work, we present a filtering step, using Large Language Models (LLMs) to pre-screen videos based on their metadata, before actually downloading these videos, thereby saving on these costs. We evaluate the LLMs against a strict human majority vote derived from four independent annotators and validate the reliability of the annotations through inter-annotator agreement analysis (Gwet's AC1). We compare the LLM pre-filter against two no-LLM baselines, namely two keyword heuristics. Via a Leave-One-Rater-Out (LOO) mechanism and an Add-One-Rater-In (AORI), we evaluate the performance of the LLMs as virtual annotators. Finally, we report cost comparisons relative to existing approaches. To ensure reproducability, we made our implementation available on github.
PDF
arXiv cs.LGOct 12
Radial Tail Repair: Post-Training Correction for Diffusion and Flow Models
Hamza Cherkaoui, Hélène Halconruy, Antonio Ocello
Diffusion and flow-matching models may struggle to accurately represent distributional tails, especially for heavy-tailed data. Existing approaches often use heavy-tailed noise or modify the generative dynamics, requiring dedicated retraining and more difficult estimation. We take a simpler approach: rather than relearning the full distribution, we correct only the model's behavior in the extreme regime. Our method builds on the radial-angular decomposition of multivariate heavy tails, where radius and direction become asymptotically independent. This allows us to preserve the directional structure learned by the pretrained model and correct only its radial tail. We estimate the tail onset from reference and generated samples, then rescale generated extremes so that their radial survival matches the target distribution. The resulting method is a lightweight post-training correction applied to a frozen diffusion or flow-matching model, requiring neither retraining nor changes to its sampling dynamics. Experiments on challenging synthetic heavy-tailed distributions and real weather and wildfire datasets show that this simple correction substantially improves extreme-tail coverage…
PDF
arXiv cs.CVOct 12
A Multi-Task Deep Learning Framework for Pose-Invariant Face Recognition and Facial Landmark Localization
Ali Ashkeyev, Zukhra Abdiakhmetova
Face recognition systems often experience performance degradation under large pose variations due to changes in facial appearance and visibility of discriminative features. This study presents a multi-task deep learning framework that jointly addresses pose-invariant face recognition and facial landmark localization within a unified architecture. To enable simultaneous optimization of identity recognition and facial structure learning, the original Cross-Pose Labeled Faces in the Wild (CPLFW) dataset was adapted into a multi-task learning dataset by associating facial images with identity labels and five-point landmark annotations. The proposed framework consists of two task-specific branches operating on a common facial input: a ResNet50-based branch for identity recognition and an EfficientNetV2B0-based branch with spatial attention for facial landmark localization. The two objectives are jointly optimized using a weighted multi-task loss, allowing the model to learn complementary semantic and spatial facial representations. The proposed framework was evaluated on the prepared CPLFW-based multi-task dataset. Unlike the original CPLFW benchmark, which focuses primarily on…
PDF
arXiv stat.MLOct 12
Feature Normalization under Finite Training Budgets
Johan Larsson
Standardizing a rare feature can help stochastic gradient descent learn its effect within a finite budget, but it also changes the noise cost of learning. We characterize the lowest rare-subgroup risks attainable by standardized and unscaled training when each chooses a nonnegative constant learning rate and a deterministic stopping time under the same observation cap. For two independent binary features, we derive both optimized risks as prevalence vanishes while the expected number of rare observations remains finite. Uniform control over rates and stopping times reduces each limiting oracle to a scalar minimization. With positive noise, the preferred scaling changes exactly once as we move signal to the rare feature while the limiting risk at initialization stays fixed and positive. The formulas also explain how noise and budget affect the comparison. Separate finite-prevalence bounds favor standardization on a rare-dominant signal family and unscaled training on a common-dominant family. The results concern final iterates with population preprocessing and fresh observations. Exact-moment searches assess the approximation at finite prevalence. In a controlled study, both…
PDF
arXiv cs.LGOct 12
Few-for-Many Best-Arm Identification in Multi-Objective Bandits
Bo Xue, Yilu Liu, Haodong Jing, Hongzong Li, Xi Lin +1
Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback. Modeling each option as an arm in a multi-objective bandit, we introduce \emph{few-for-many best-arm identification}, which seeks a small set of arms minimizing the worst weighted degradation from the objective-wise optima, rather than the best arm for every objective. We consider both known objective groups and latent groups specified only by a representative budget, and propose \textsc{GFM-Elim} and \textsc{AFM-Elim} with instance-dependent sample-complexity guarantees. For Gaussian rewards, we further derive a lower bound for the latent-group setting and show that it is asymptotically attainable with high probability by an oracle-based Track-and-Stop procedure. Our results show that sharing observations across objectives and ignoring irrelevant objective-wise distinctions can substantially reduce the sampling cost, as confirmed by experiments on synthetic and real-world tasks.
PDF
arXiv cs.CLOct 12
Label Collapse in Diffusion Language Model In-Context Learning
Ziye Guo, Ye Yuan
In-context learning (ICL) applies large language models to new tasks by prepending a few labeled demonstrations to a query. Prior work has studied how demonstration ordering affects ICL, but the interaction between label arrangement patterns and model biases has not been systematically examined. We define label collapse as the failure mode in which the model generates query-independent labels, and show that it is architecturally universal at the tested 8-9B scale: five models spanning autoregressive (Llama-3, Qwen3.5) and discrete diffusion (LLaDA, iLLaDA, LLaDA-Instruct) families all exhibit label collapse even under the class-balanced alternating arrangement, with some label word pairs collapsing in virtually every tested condition and others flipping their collapse direction with arrangement. Critically, accuracy alone cannot detect this collapse: models can achieve near-chance accuracy while generating query-independent labels, a score indistinguishable from balanced performance, so the failure can persist undetected in deployment. We measure separation, the log-odds of the two label words at the query position (the quantity that label-bias calibration operates on), as a…
PDF
arXiv cs.AIOct 12
Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization
Huihao Jing, Shaojin Chen, Wenbin Hu, Yuxuan Liu, Haochen Shi +3
As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central safety problem. Guardrails are often placed in front of these actions, yet few evaluations ask whether their decisions follow authorization: blocking unauthorized actions while still allowing the same actions under valid permission. We introduce \bench{}, a benchmark that contrasts authorization evidence for the same operation in its language track. It combines expert-annotated natural-language scenarios with executed and verified operations, plus externally sourced native-policy requests. \bench{} checks each decision for correctness, usability and resulting effect, and tracks each request across guardrail changes. Our experiments show that many blocked operations stem from failed reviews, not correct denials. Repairing the output format restores usable decisions but changes which authorized requests are honored, and adding a second reviewer removes some errors while rejecting valid authorization. Guardrails should therefore be evaluated on both the unauthorized actions they stop and the authorized actions they let through.
PDF
arXiv cs.CLOct 12
A Scaled-Up Empirical Study of Syntactic Language Models
Pengcheng Wang, Zhexuan Zhang, Chao Lou, Kewei Tu
Syntactic language models (SLMs) that generate sentences along with their syntactic tree structures have shown promise in both syntactic generalization and downstream tasks. Prior studies, however, have mostly evaluated smaller models trained on less pretraining data and tested on narrower task suites. In addition, the design space of tree linearization and attention masks remains underexplored. We conduct a large-scale empirical study of 12 controlled configurations---one terminal baseline and 11 SLM variants spanning different linearizations and masks---at scales up to 1B parameters and 100B training tokens, evaluated across 11 downstream tasks and two syntactic benchmarks. The experimental results show that SLMs with standard causal attention match or exceed structural-mask variants across downstream and syntactic benchmarks. They require no architectural modifications and remain compatible with FlashAttention. We also observe that when scaling up to the 1B-parameter scale, the top-performing SLM variant no longer shows a clear advantage over a compute-matched non-structural baseline, suggesting that SLMs may become less competitive with scale. Our code is available at…
PDF
arXiv cs.CROct 12
Beyond User-Side Defenses: Image Protection in Open-Weight Diffusion Models
Jihye Kang, Jiwon Park, Namhyuk Ahn
Model providers can support image protection, but open-weight deployment introduces practical constraints. We propose four requirements: protection effectiveness, clean fidelity, compatibility, and tamper resistance. We incorporate long-horizon attack simulations to strengthen resistance to protection removal. Experiments with a single protection tool show improved resistance to re-alignment at a cost to clean fidelity, motivating further research toward practical model-side protection.
PDF