Computation and Language
Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation
Riya Ahuja, Tim Kacprowski and Roya Shiasi Sardoabi
BioMedRAG introduced
retrieval-augmented generation with a learned chunk scorer for biomedical information extraction. However, it relies on fixed-size chunking which can fragment semantic evidence. We propose a configurable semantic chunking framework that addresses this limitation by combining entity-preserving windows, trigger-centered chunking, proposition-first extraction, tiered trigger prioritization, and hierarchical relation resolution. The framework integrates with BioMedRAG by replacing only the chunk construction stage while preserving the
embedding model, learned chunk scorer, generator, and evaluation protocol. We evaluate the framework on biomedical relation extraction
benchmarks (GM-CIHT, DDI, ChemProt) and adverse event classification (ADE). On GM-CIHT, the full hybrid configuration achieves 82.6% F1, improving over the fixed-size baseline (74.2% F1) by 8.4 points under our experimental setup. Cross-
dataset analysis shows that semantic chunking improves extraction
datasets with explicit relation cues, such as GM-CIHT and DDI, while fixed chunking remains competitive or stronger for dense biochemical extraction and binary classification settings such as ChemProt and ADE. By externalizing chunking logic into configuration files, the framework provides an interpretable and adaptable alternative to rigid fixed-size chunking for biomedical RAG pipelines.
Read the full abstract ▾
Artificial Intelligence
OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques
Hamed Babaei Giglou, Sören Auer, Peio Popov et al. (+2 more)
Ontology
alignment (OA) has evolved through several methodological paradigms, ranging from lexical and structural aligners to knowledge graph
embedding (KGE) models and, more recently, Large
Language Model (LLM)-based approaches. Although modern OA frameworks provide unified ecosystems for deploying these heterogeneous aligners, mechanisms for systematically reconciling their complementary and sometimes conflicting predictions remain relatively underexplored. We present OntoAligner-Ensemble, a modular and aligner-agnostic framework that combines candidate correspondences through a configurable two-stage process comprising voting-based fusion strategies followed by post-fusion selection policies. The framework supports any aligner implemented within OntoAligner that produces candidate correspondences, enabling diverse
alignment paradigms to be integrated through a unified decision process. To demonstrate its effectiveness, we instantiate the framework using representative lightweight string-aligner, KGE-based, and
Retrieval-Augmented Generation aligners powered by both open-weight and API-based LLMs. We evaluate individual aligners and ensemble configurations across eight
benchmark tasks from five OAEI tracks spanning biomedical to beyond-equivalence. The results show that ensemble fusion consistently improves the balance between precision and recall and frequently outperforms standalone aligners across diverse domains. Furthermore, our analysis reveals that ensemble composition directly affects the precision-recall trade-off: heterogeneous cross-paradigm ensembles generally improve precision, whereas homogeneous LLM ensembles more often achieve higher overall F1-scores. These findings demonstrate that systematic ensemble learning offers a robust and reproducible strategy for OA while providing practical guidance for selecting ensemble compositions under different
alignment scenarios.
Read the full abstract ▾
All authors Hamed Babaei Giglou, Sören Auer, Peio Popov, Mahsa Sanaei, Jennifer D'Souza
Machine Learning · Cross-listed from stat.ML
Implementing neural network mixed-effects models in Template Model Builder (TMB)
Nan Zheng, Hoi Yiu Cheung, Vibhu Sharma et al. (+2 more)
Neural network mixed-effects models (NMMs) have gained traction by combining the strong representation and predictive power of artificial neural networks with the capacity of mixed-effects modeling to capture complex correlation structures. However, existing estimation approaches rely heavily on manual derivations of objective functions and gradients, which inherently forces simplifying approximations and severely constrains the complexity and accuracy of NMMs. In this work, we introduce a general framework for implementing NMMs using Template Model Builder (TMB). By leveraging automatic differentiation and Laplace approximation, TMB requires users to specify only the negative joint log-likelihood and any regularization terms. The framework automatically integrates out random effects and evaluates the marginal objective function alongside its exact gradients, eliminating the need for manual derivations or ad hoc approximations. We demonstrate the efficiency, flexibility, and statistical performance of TMB-based NMMs across two numerical examples, including an application to monotonic NMMs. Reproducible code is provided to facilitate broader adoption.
Read the full abstract ▾
All authors Nan Zheng, Hoi Yiu Cheung, Vibhu Sharma, James T. Thorson, Noel G. Cadigan
Computation and Language
DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening
Yung Wei Shueh, Zhi-Jie Chen, Chia-Hsuan Hsu et al. (+9 more)
Large
language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and citation errors. We present DIASENTINEL, a fully on-premise multi-
agent system for one-year type 2 diabetes mellitus (T2DM) risk screening and guideline-grounded report generation from electronic health records (EHRs). The system integrates calibrated risk prediction, deterministic clinical signal extraction, Reciprocal Rank Fusion over American Diabetes Association (ADA) guidelines, and a hybrid verification layer combining rule-based checks with LLM entailment. The demonstration provides a real-time batch-screening dashboard and an interactive patient report interface with cited recommendations, verification results, and raw EHR comparison. DIASENTINEL demonstrates a practical framework for reliable, auditable, and
privacy-preserving LLM-based clinical decision support.
Read the full abstract ▾
All authors Yung Wei Shueh, Zhi-Jie Chen, Chia-Hsuan Hsu, Hsin-Ling Hsu, Donghua Zhang, Chenwei Wu, Jun-En Ding, Tongze Zhang, Shihao Yang, Pengfei Hu, Fang-Ming Hung, Feng Liu
Game Theory
Constrained Fair Allocations via Partition Matroid Reductions
Benjamin Cookson and Nisarg Shah
We study fair allocation of indivisible goods under additive valuations and matroid constraints. A challenging open question is whether a complete and feasible envy-free up to one good (EF1) allocation exists under every matroid that admits a complete and feasible allocation. The state-of-the-art result by Biswas and Barman [2018] positively resolves this question for partition matroids. Our first result positively resolves it for laminar matroids, which generalize partition matroids, when there are three
agents. Our technique reduces this general existence question to finding an EF1 allocation satisfying a mild additional condition under a single finite-sized key laminar matroid, and we establish the required allocation by case analysis. We show that our technique somewhat extends to four
agents, reducing the analogous problem to finding EF1 allocations under two finite-sized laminar matroids, although we are unable to establish their existence. We also use recent matroid decomposition results to establish EF1 existence under broader classes of matroids. Specifically, we show that EF1 allocations always exist under transversal matroids whenever a complete allocation is feasible, and obtain existence results for graphic matroids and gammoids under stronger assumptions.
Read the full abstract ▾
Machine Learning
On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions
Guy Emerson
The motivation for this paper is the investigation of the trade-offs implicit in probabilistic models used in machine learning. Models are often used to make predictions in the form of conditional probabilities. However, a pair of conditional distributions p(x|y) and p(y|x) may not be compatible with any joint distribution p(x,y). Given two such conditionals, determining if there exists a compatible joint is known as the compatibility problem. For discrete random variables, when the conditionals are encoded as probability tables, the compatibility problem has a known solution, which is computationally tractable. In this paper, we formalise and study a succinct version of the problem, encoding conditional distributions as arithmetic
circuits. This is applicable to practical applications of probabilistic modelling in high-dimensional settings, including neural network models. We show that, for succinct
circuit representations of conditionals, the compatibility problem is intractable. In the case that all probabilities are non-zero, the problem is co-NP-complete. In the case that probabilities can be zero, we give examples to demonstrate that several notions of compatibility can be distinguished, and we prove that multiple versions of the problem are PSPACE-complete. Furthermore, we show that, assuming the
polynomial hierarchy does not collapse, there exist compatible succinct conditionals whose joint cannot be expressed succinctly. Implications of these results for probabilistic modelling and machine learning are discussed.
Read the full abstract ▾
Computation and Language
PaperGym: Rubric-Centered Evolution for Research-Plan Generation
Yuhan Wang, Zhengxi Lu, Yuchen Yan et al. (+6 more)
Research planning is the decisive capability of AI scientists. Yet a research plan admits no verifiable answer, so reinforcement learning lacks the environment it requires: tasks paired with a critic. Rubrics extracted from scientific papers can supply the critic. Existing pipelines, however, draw the question and the criteria from the same content, so the reward can be earned by paraphrase. The rubric is further compressed into a single scalar per rollout. We introduce PaperGym, a unified framework that turns each research paper into a complete training environment. PaperGym exploits the structure of a paper: the question is synthesized from the research goal and background, while the criteria are derived from the method and experiments. The criteria span methodological innovation and experimental design, and criterion leakage falls to 3.7%, versus 11.90% to 34.10% in existing
datasets. Training uses the rubric twice: first as privileged context for OPSD's self-teacher, then as the reward for GRPO. Across Qwen3-1.7B/4B/8B, this schedule outperforms supervised fine-tuning, either stage alone, and the reverse ordering, improving five-
benchmark averages by +5.6, +5.0, and +4.8 points. With the recipe held fixed, models trained on PaperGym-20k win 58.1% of three-way comparisons, against 28.2% for RubricHub Science. The trained Qwen3-8B reaches 73.48 on ResearchQA, above the far larger Kimi K2.6. We release the pipeline, the 20,000-instance corpus PaperGym-20k, and the
benchmarks PaperGym-Innov and PaperGym-Design.
Read the full abstract ▾
All authors Yuhan Wang, Zhengxi Lu, Yuchen Yan, Kaitao Song, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
Artificial Intelligence
When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning
Hamed Babaei Giglou, Sören Auer and Jennifer D'Souza
The effect of Large
Language Model (LLM) scale on ontology learning (OL) performance remains insufficiently characterized. We present a controlled evaluation of 13 models spanning dense and Mixture-of-Experts variants from the Qwen3.5 and Qwen3.6 lineages, together with proprietary GPT release variants, using the OntoLearner
retrieval-augmented generation pipeline. All models are evaluated with the same
embedding model,
retrieval configuration,
prompt templates, decoding settings,
datasets, and metrics on term typing, taxonomy discovery, and non-taxonomic relationship extraction across four biomedical and materials science and engineering ontologies. Within the dense Qwen3.5 lineage, increasing parameter count primarily improves precision rather than recall, with the largest gains occurring between 9B and 27B parameters. However, the effect of scale is neither monotonic nor uniform across tasks and domains. Dense 27B models outperform substantially larger sparse models on term typing, whereas larger Mixture-of-Experts models achieve the strongest open-weight results on taxonomy discovery. Non-taxonomic relationship extraction remains difficult across model scales, particularly for the Materials Data Science ontology. Performance differences across matched Qwen variants and proprietary GPT releases further indicate that architecture and model lineage can outweigh nominal parameter count. These findings show that model size alone is an insufficient selection criterion for OL and provide empirical guidance for reproducible LLM-assisted ontology engineering.
Read the full abstract ▾
Machine Learning · Cross-listed from quant-ph
"Train classical, deploy quantum" requires rethinking generalization
Snehal Raj, Natansh Mathur and Alejandro Perdomo-Ortiz
Generative models have become central across science and industry, from image and text synthesis to the design of molecules and materials.
Quantum generative models are considered one of the most promising applications for
quantum computers, since a
quantum circuit naturally produces samples from the distribution it encodes, and for suitable
circuits that distribution is believed to be hard for any classical computer to reproduce. A leading strategy trains these models on a classical computer and reserves the
quantum device for generating samples at deployment. This is possible when the training loss can be evaluated on a classical computer. A
prime example is the maximum mean discrepancy (MMD$^2$), a moment-matching loss that compares the model and the data through their Pauli-$Z$ correlations. Research so far has asked whether such models can be trained and whether their sampling is hard; whether minimizing such an objective yields a model that generalizes, rather than one that merely reproduces the training statistics, remains poorly understood. We
benchmark thirteen
quantum and classical generative models by direct sampling on two application-inspired
datasets: first a cardinality-constrained
dataset at up to $30$
qubits and second a
dataset of genomic single-nucleotide variants, whose valid set is the observed data. Models that converge the loss to the same value differ widely in how much of the unseen valid set they cover. These results indicate that a converged moment-matching loss is not a reliable measure of generalization, and that a train-classical, deploy-
quantum workflow has to measure generalization by sampling the trained model, a step that at the sizes of interest is believed to require the
quantum device.
Read the full abstract ▾
Human-Computer Interaction
InsightToast: Proactive Information Retrieval & Glanceable Visualization in the Side Channel of Data-Rich Meetings
Mohammad Abolnejadian and Matthew Brehmer
Missing institutional context during meetings can impede effective participation. Retrieving relevant information, often scattered across heterogeneous internal and external sources, requires costly task-switching that disrupts both individual focus and collective conversational flow, particularly detrimental during cognitively demanding tasks such as decision-making. We introduce InsightToast, a mixed-initiative application that monitors verbal discourse in real time, identifies topics and informational needs as they emerge, and proactively retrieves relevant information through a multi-
agent large
language model (LLM)-based pipeline integrating
retrieval-augmented generation (RAG) to produce source-grounded insights as succinct text and glanceable interactive charts, delivered through a peripheral interface as ephemeral toasts in the conversation's side channel. To demonstrate the potential for yielding serendipitous insights, we showcase a usage scenario involving a knowledge base of legislative documents as the meeting's context. We then report on a comparative study (N=16), in which participants arrived at informed policy decisions while maintaining natural conversation flow.
Read the full abstract ▾
Computer Vision
BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives
Pradyumn Goyal, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu et al. (+6 more)
We introduce BLARM, a feed-forward method for
video-driven 3D mesh animation. Given a
monocular video and a static object mesh, BLARM predicts a temporally coherent animated mesh whose motion follows the
video. Rather than relying on explicit rigs or directly regressing high-dimensional vertex motion, we represent animation using a compact set of learned, time-varying rigid motion components and time-invariant vertex-to-component skinning weights. This yields a low-dimensional deformation space without requiring skeletons, cages, skinning weights, or rig annotations. Our architecture conditions geometry-derived deformation latents on
video features through factorized spatial-temporal
attention, then decodes rigid transformations blended by predicted skinning weights. Trained with trajectory reconstruction,
entropy regularization, and motion-aware contrastive learning, BLARM produces accurate and temporally stable animations while recovering compact, interpretable motion structure from
monocular video.
Read the full abstract ▾
All authors Pradyumn Goyal, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu, Haomiao Jiang, Snehasish Mukherjee, Kyle Spence, Mark Stauber, Evangelos Kalogerakis, Yunze Zeng
Cryptography and Security · Cross-listed from quant-ph
Unconditional Certified Randomness without Structure
Andrea Coladangelo, Dakshita Khurana, Saachi Mutreja et al. (+3 more)
We obtain a certified randomness protocol in the
quantum random oracle model. The protocol is non-interactive and publicly verifiable with a classical verifier, and is based on Yamakawa and Zhandry's proof of quantumness [JACM'24]. We prove unconditional security of this protocol against adversaries making subexponentially-many adaptive
quantum queries to the random oracle. Prior work on certified randomness relative to a random oracle additionally assumed the Aaronson–Ambainis
conjecture or proved security only against low query-depth adversaries.
Read the full abstract ▾
All authors Andrea Coladangelo, Dakshita Khurana, Saachi Mutreja, Bhaskar Roberts, Joseph Slote, Avishay Tal
Computation and Language
Aspire: Can Models Self-Evolve from Vague Goals?
Yuhao Wu, Jingyuan Zhang, Jiajun Shi et al. (+18 more)
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether they have actually improved. In contrast, existing work on LLM self-
evolution typically begins with tasks and evaluation metrics specified by humans, reducing self-
evolution to optimizing an explicit objective rather than deciding what and how to learn. We introduce ASPIRE, a
benchmark for vague-goal-driven self-
evolution. ASPIRE provides only a natural-
language capability goal while downstream evaluation tasks remain hidden. The
agent must operationalize the goal by choosing data and update methods, constructing training and validation signals, and deciding when to evaluate. ASPIRE supports both model-weight and
agent-harness
evolution in a unified interactive environment and evaluates the resulting systems on a hidden, expert-authored set of 520 items spanning six goals. Our experiments show that vague goals redirect search effort toward goal interpretation. Current
agents routinely complete training and harness-editing loops, but weight-level gains remain sparse and unstable, and the strongest evolved harness remains below the engineered Qwen-
Agent reference.
Agents often train on mismatched data and trust narrow self-evaluations, so local gains fail to transfer to hidden evaluation and continued search and training can erase earlier improvements.
Read the full abstract ▾
All authors Yuhao Wu, Jingyuan Zhang, Jiajun Shi, Yuxuan Zhang, Xinping Lei, Junting Zhou, Zexuan Wang, Yuchen Wu, Huan Zhou, Duo Wang, Yinzhu Piao, Yongchang Peng, Yunfeng Shi, Jin Chen, Zuo Wang, Jinkai Liu, Jiaheng Liu, Wenxuan Zhang, Shen Yan, Wenhao Huang, Ge Zhang
Machine Learning
Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions
Ahmed El Kady, Aravind Narayanan, Rehana Riaz et al. (+2 more)
Efficient evaluation changes the protocol used to support claims about model behavior, yet it is rarely tested whether those claims remain stable after the evaluation itself is made cheaper. We stress-test conclusion robustness in responsible-AI benchmarking by evaluating three dense and mixture-of-experts models on BBQ and BBQ-V under seven conditions spanning batching, quantization,
benchmark reduction, and their combinations. Rather than treating preserved aggregate accuracy as sufficient, we compare accuracy, bias severity and prevalence,
reasoning quality, subgroup behavior, subset-membership stability, runtime, and measured GPU energy against a full-
benchmark BF16 baseline. Larger batching keeps accuracy within 0.35 percentage points of baseline and produces comparatively small subgroup changes, while reducing energy in five of six model–
dataset settings. INT8 largely preserves quality but uses 1.79–4.26$\times$ baseline energy. INT4 causes larger, model- and context-dependent changes. Reduced
benchmarks provide the most consistent savings, but very small subsets are substantially more sensitive to which items are retained. Efficient evaluation should therefore be treated as a measurement intervention whose validity must be checked across the conclusions the
benchmark is intended to support. Our project website is https://vectorinstitute.github.io/sustainable-rai-evaluation/ and the code is available at https://github.com/VectorInstitute/sustainable-rai-evaluation.
Read the full abstract ▾
All authors Ahmed El Kady, Aravind Narayanan, Rehana Riaz, Yani Ioannou, Shaina Raza
Computer Vision
VeriCam: A Verification Baseline for the Classification of Unknown Data
Lucas Wojcik, Gabriel E. Lima, Sergio M. Silva Jr. et al. (+2 more)
The advent of foundation models have enabled a new era in zero-shot classification. Yet, key challenges persist. Despite their impressive generalization power that leverages the immense pre-training knowledge, both foundation models for image and text as well as
vision-text hybrids lack the representational power needed for fine-grained, minutiae-based class separation that some real-world tasks require. To address the current gaps in the literature, we propose VeriCam, a pipeline designed to learn highly specialized features that enable classification of unknown classes in unseen data. VeriCam works by leveraging the representation power of image models trained for the verification task, where the model develops an intricate feature space that incorporates fine-grained details. By training a model to discriminate between pairs of images from the same and different classes, a relational graph is constructed, representing the class relationships between data points. We then present two approaches for graph clustering: a naive
algorithm and a specific setup for the Leiden graph clustering
algorithm. The pipeline is validated on the LPLCv2
dataset, which comprises real-world traffic surveillance images. We show that the
dataset carries an inherent capture device bias that is posed as a generalization challenge for downstream License Plate recognition tasks such as OCR. As such, we dynamically identify capture devices with a label-agnostic approach, enabling the construction of a fair and unbiased
benchmark. In the cross-device scenario, our pipeline reaches an F1-Score of 93.45 in the verification baseline and a V-Measure score of 80.13 in the clustering step. All code is publicly available at https://github.com/lmlwojcik/VeriCam
Read the full abstract ▾
All authors Lucas Wojcik, Gabriel E. Lima, Sergio M. Silva Jr., Eduil Nascimento Jr., David Menotti
Computer Vision
DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
Jiashu Zhu, Yanhao Zheng, Ruitian Tian et al. (+7 more)
Recent
video generators often omit audio or synthesize it in a separate stage, limiting reciprocal modeling of visual dynamics and acoustic events. We present DreamX-Creator 1.0, a compact native joint audio-
video generation system centered on a 7B generator. Conditioned on a first frame and a text
prompt, the generator jointly denoises modality-specialized audio and
video streams. The streams are processed independently in the first half of the network and coupled in the latter half through Gated Cross-Modal
Attention, whose
token- and head-wise output gates modulate each active cross-modal
attention-head output. A unified Audio-
Video Data System constructs and filters temporally coherent clips, produces structured
multimodal annotations, and organizes clips into capability-oriented data pools. Progressive Joint Training comprises two audio-
video pre-training stages followed by High-Quality Finetuning. Audio-
Video Reinforcement Learning further post-trains the generator with Modality-Aware
Multimodal Feedback that routes
video-, audio-, and cross-modal feedback to the corresponding streams. For high-resolution output, our Autoregressive 1-Step 2K Refinement pipeline adapts a bidirectional multi-step teacher into an autoregressive multi-step refiner and distills it into a student requiring one denoising evaluation per temporal chunk. Overall, DreamX-Creator 1.0 achieves native, synchronized audio-
video generation with performance competitive with state-of-the-art open-source systems. By releasing our compact 7B generator and 2K Refiner, we seek to democratize native audio-
video generation and provide an accessible foundation for future research in unified audio-
video generative modeling.
Read the full abstract ▾
All authors Jiashu Zhu, Yanhao Zheng, Ruitian Tian, Rujing Dang, Shen Zhang, Bingze Song, Jiachen Lei, Ruimin Lin, Jiahong Wu, Xiangxiang Chu
Artificial Intelligence
BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
Adrians Skapars and Edoardo Manino
Users of a deployed
language model routinely encounter behaviours that have never been observed during testing, since deployment puts the model through orders of magnitude more interactions than any evaluation can simulate. Automated auditors can mitigate this issue as they are flexible enough to discover almost any specified behaviour, yet their random sampling approach makes them inefficient. To address this shortcoming, we introduce BLOOM-WILT, a full
auditing pipeline that elicits natural multi-turn instances of rare behaviours, without training cost or access beyond the target's next-
token distribution. On the user input side, WILT revises its conversational strategy across rounds, learning from previous scored interactions. On the model output side, WILT generates behaviour-relevant continuations by feeding the model with an elicitation
prompt and mixing its next-
token distribution with the unprompted model. We evaluate WILT across 4 target models and 8 behaviours, and show that it improves over the baseline in 30 of the 32 settings, thus revealing that a larger number of models exhibit harmful behaviours than previously suggested. Furthermore, WILT is the only method that can raise the mean presence of self-harm encouragement from 51% to 100% in Qwen3.5-4B, without decreasing the output probability of the generated text. Our code is available at https://github.com/AdrSkapars/bloom-wilt.
Read the full abstract ▾
Software Engineering
LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering
Gopi Krishnan Rajbahadur, Amir M. Ebrahimi, Boyuan Chen et al. (+1 more)
Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing the rest. The maintained artifact is increasingly dataware: behavior governed by a curated post-training mixture, updated via bounded mixture patches rather than clean-slate retraining. From an industrial code-generation improvement effort, we offer a maintainer's perspective on why this work is hard in practice, distilling three recurring challenges, zero-sum mixture design, yield as the binding metric, and end-to-end integration under uncertainty, and arguing that progress depends less on one-off recipes than on an engineering discipline for programming dataware. In our case study, interventions that raised the conversion of teacher
distillation into usable training data increased accepted supervision by 2.84 times while using the same solution teacher and four solution attempts per candidate problem. In our primary evaluation, the yield-engineered patch improved CodeForces pass@1 by +2.59 points (+3.11 pass@3) and held-out LiveCodeBench v6 pass@1 by +6.11 (+8.05 pass@3), all statistically significant across 16
stochastic evaluations of each
benchmark from one fixed checkpoint per condition, with internal AIME and MATH regression suites within tolerance.
Read the full abstract ▾
All authors Gopi Krishnan Rajbahadur, Amir M. Ebrahimi, Boyuan Chen, Ahmed E. Hassan
Computation and Language
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Jiajun Shi, Siyuan Tao, Yuhao Wu et al. (+18 more)
Large
language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing
agent benchmarks largely evaluate them as fixed policies. It therefore remains unclear whether an
agent can actively test its behavior, judge the resulting experience, and use that experience to improve future decisions. We introduce \textbf{S\textsuperscript{3}Gym}, an interactive
benchmark for evaluating LLM self-improvement through three coupled capabilities: Self-Testing, Self-Judging, and Self-Improvement. S$^3$Gym separates permissive exploration from strict held-out evaluation and instantiates this protocol in seven text-based games with executable environment verifiers. We evaluate three pathways for incorporating interaction experience: direct History ICL, score-conditioned Summary
Memory, and parameter Training. Our experiments reveal that self-improvement is neither automatic nor uniform. Context-level experience improves performance for several model–game pairs, but the most effective pathway depends strongly on the task structure: summaries are beneficial when experience can be compressed into reusable strategic rules, yet often underperform raw history when success depends on precise, state-contingent information. Parameter training produces substantial gains on some tasks, but also exhibits unstable improvement and severe negative transfer on others. These findings show that recognizing successful actions is insufficient;
agents must also transform feedback into executable and transferable policies. S$^3$Gym provides a unified framework for diagnosing this process and identifying the bottlenecks that prevent
agents from translating interaction experience into reliable self-improvement.
Read the full abstract ▾
All authors Jiajun Shi, Siyuan Tao, Yuhao Wu, Zexuan Wang, Jingyuan Zhang, Jiaheng Liu, Xinping Lei, Xinrong Zhang, Siyuan Fang, Zhewen Tan, Tianle Cai, Junhao Fang, Jiameng Huang, Yueyang Wang, Jinkai Liu, Yuxuan Zhang, Jian Yang, Zhoujun Li, Shen Yan, Wenhao Huang, Ge Zhang
Artificial Intelligence
Cross-Regional Grapevine Cold Hardiness Prediction via Learned Multimodal Latent Representations
William Solow, Paola Pesantez-Cabrera, Markus Keller et al. (+3 more)
Accurate daily predictions of cold hardiness in woody plants are critical in regions where freezing temperatures can damage dormant buds and reduce seasonal yield. Existing biophysical, hybrid, and deep learning models have shown high predictive accuracy when trained on local data but remain largely site-specific. The limited availability of cold hardiness data, coupled with the lack of principled methods for transferring cold hardiness predictions to new regions and cultivars, has limited the broader adoption and practical utility of these approaches, particularly in data-scarce regions. To address these limitations, we propose a cold hardiness prediction framework that learns a transferable latent representation by capturing region-specific variation through learned
embeddings. To enable prediction in previously unseen regions, we infer
embeddings from (1) text descriptions of the cultivar and growing region, and (2) limited historical observations, supporting both zero-shot and few-shot transfer. Experiments on
datasets from six regions across North America demonstrate that our approach consistently outperforms state-of-the-art cold hardiness prediction methods, yielding more accurate predictions and substantially improving transfer to data-scarce regions.
Read the full abstract ▾
All authors William Solow, Paola Pesantez-Cabrera, Markus Keller, Lav Khot, Sandhya Saisubramanian, Alan Fern
Computer Vision
One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning
Yunxiang Fu, Meng Lou and Yizhou Yu
Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while preserving the ability to recognize all seen classes. Recently, pretrained-model-based approaches have become prevalent by adapting a frozen backbone with additional lightweight trainable modules. Existing methods, however, exhibit limitations: task-specific adapters learn explicit per-task representations but are parameter- and computation-inefficient, while LoRA-based merging methods combine per-task LoRA parameters into a single model whose static aggregated weights cause representation interference during inference. To address these problems, we present FACET: task-conditioned FeAture transformation with ConditionEd feature consisTency, achieving excellent parameter efficiency while producing highly discriminative features during inference. When continually trained on a task sequence, FACET learns a single shared adapter that employs a dynamic task-conditioned feature transformation, shaping the overall feature distribution of the adapter into a mixture of overlap-reduced task-specific components. On the other hand, we propose an efficient replay-free task-conditioned feature consistency loss, aiming to mitigate catastrophic forgetting of the learned mixture distribution in the adapter's feature space. Even when maintaining only a single adapter, FACET demonstrates robust scalability. On both very long task sequences (e.g., 200 tasks) and standard short task sequences (e.g., 20 tasks), our method achieves superior performance while using significantly fewer trainable parameters and GFLOPs. The code will be made open source upon acceptance.
Read the full abstract ▾
Computer Vision
Robust retinal biometrics for patient identity verification and retrieval across age and imaging devices
Jose D. Vargas-Quiros, Dennis Bontempi, Jeroen Vermeulen et al. (+3 more)
Patient identity errors can compromise longitudinal medical records, research databases, and downstream clinical decisions. We present a retinal biometric system for verifying claimed identities and retrieving the correct identity from color fundus images. We trained a 512-dimensional metric-learning encoder combining a ConvNeXtV2 backbone with ArcFace and triplet losses on 227,004 images from 21,851 patient-eye identities in the Rotterdam Study, spanning multiple imaging devices and up to 32.6 years of follow-up. The system was evaluated on held-out Rotterdam Study data and externally on the UK Biobank and Age-Related Eye Disease Study (AREDS). Before evaluation, we used the model to screen for identity inconsistencies and manually adjudicated flagged images, identifying incorrect assignments in 0.588% of Rotterdam Study images, 0.259% of UK Biobank images, and 0.164% of AREDS images. In retrospective-only verification after removing near-duplicate images, the system achieved AUROCs of 0.9998, 0.9997, and 0.9998 in the Rotterdam Study, UK Biobank, and AREDS, respectively. For identity
retrieval using only previously acquired images, Recall@1 was 99.7%, 97.2%, and 97.6%, respectively, from galleries averaging 4436-8510 identities; the correct identity appeared among the top five results in at least 98.6% of cases. Performance remained robust across imaging devices and long follow-up intervals, while lower image quality and inconsistent retinal fields accounted for most failures. These findings establish retinal anatomy as a durable biometric signal, useful for safeguarding the integrity of longitudinal imaging records.
Read the full abstract ▾
All authors Jose D. Vargas-Quiros, Dennis Bontempi, Jeroen Vermeulen, Bart Liefers, Sven Bergmann, Caroline C.W. Klaver
Systems and Control · Cross-listed from math.OC
Interpolation Conditions for Instant Data Consistency with Port-Hamiltonian Structure
Martina Vanelli, Nima Monshizadeh and Julien M. Hendrickx
We develop a data-driven framework for nonlinear port-
Hamiltonian (pH) systems based on interpolation conditions to characterize consistency between observed data and structured dynamical models. Specifically, we derive necessary and sufficient conditions for the existence of a pH system with a smooth (convex)
Hamiltonian instantly consistent with a given
dataset, without requiring explicit parametrization. We further provide a semidefinite programming formulation to verify consistency with non-degenerate interconnection and dissipation structures. Our results provide a principled approach to assess instant data consistency with physical structure and pave the way for control design directly from data.
Read the full abstract ▾
Information Theory
Minimax bounds for watermarked and masked recursive discrete distribution estimation
Millen Kanabar and Michael Gastpar
Watermarking has been proposed as a way to identify synthetic samples in estimation settings where no metadata is available to distinguish them from real samples, but its precise effects remain unexplored. In the absence of a distinguishing mechanism, it has been shown that adding synthetic samples significantly reduces the marginal efficacy of new real samples. In this work, we study the minimax loss of such recursive discrete distribution estimation in the presence of watermarks in contrast to the unassisted and oracle-assisted losses. When the fraction of real samples vanishes asymptotically, we provide a lower bound that shows that it is impossible to improve performance by adding watermarks unless the false negative rate of detection also vanishes. Additionally, we show that in most regimes, the worst-case losses of a sequence of simple deterministic
estimators match the corresponding lower bounds up to constants. Finally, we propose masking, a randomization procedure that narrows the gap in the remaining regimes to a Jensen gap. We
conjecture that a tighter lower bound argument can close this gap.
Read the full abstract ▾
Computation and Language
Verbalizing Multi-Token Concepts in LLMs
Xijie Gong, Zimeng Huang and Tonghan Wang
Lens methods inspect model computation by mapping intermediate activations to vocabulary
tokens. Yet the concepts humans need to read out often span multiple
tokens—entities, phrases, intermediate objects—making
token-level readouts incomplete. Reliable multi-
token readout with little model-specific preparation remains challenging. We introduce Concept Lens:
token-level lens clues guide candidate concept search, then the model derives a representation for each candidate and scores it against the original activation. Across 2,400 multi-hop clozes on five LLMs (8B–70B), Concept Lens instantiated with J-lens and R-lens achieves average Rank@10 scores of 36.6% and 54.5%, respectively, compared with 21.7% for Template Lens. Concept-swap interventions on derived concept representations shift model answers toward those associated with the replacement concepts. Further experiments show that Concept Lens can also reveal what a model recognizes along the way, beyond what appears in its final answer. Our code is available at https://github.com/XijieGo/c-lens
Read the full abstract ▾
Artificial Intelligence
Agentic Context Cracking: Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data
Milad Rezaei Hajidehi, Qitong Wang and Stratos Idreos
Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI is deploying LLM
agents that reason over this data to answer complex questions for every knowledge worker.
Agents can do this today, but at prohibitive cost. Each question repeatedly opens large documents to recover scattered evidence, consuming up to a million
tokens. However, if the data were already structured, the same question would reduce to a cheap database lookup. For example, on FanOutQA
benchmark,
reasoning over an ideal pre-structured store is 28X cheaper, and the gap grows to orders of magnitude as questions fan out over more documents. Yet structuring everything in advance is not viable: documents hold vastly more possible structure than any workload will use, and the useful structure and documents are unknown until queries arrive. We propose agentic data cracking, a method that structures unstructured data adaptively and speculatively as a byproduct of
reasoning itself. Structuring is adaptive because observed queries decide when it happens and what matters, and speculative because it goes beyond the current question. Whenever the
agent opens a document to answer, a cracking sub-
agent forks from the already-loaded context at marginal cost and extracts grounded structure likely to serve related future queries. Over time, an increasing share of queries is fully covered by structured data and answered without opening a document, keeping agentic accuracy at close to RAG cost. On FanOutQA, extended with merely one related question per test question, cracking cuts cost by 53% while preserving accuracy. Agentic data cracking is a first step toward next-generation data infrastructure for agentic
reasoning over unstructured data: a shared substrate beneath the model where knowledge that
reasoning already paid to uncover accumulates.
Read the full abstract ▾
Machine Learning
Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization
Camila Blank, Zhuofan Ying, Christopher Potts et al. (+2 more)
Sycophantic agreement refers to a behavior in which
language models excessively affirm the user, often at the cost of factual accuracy. Although sycophantic agreement is a well-known failure of model
alignment, there is limited understanding of how it emerges from model training. In this work, we demonstrate that sycophantic agreement can emerge as an unintended consequence of widely used contrastive preference optimization objectives. Using the OLMo 3 post-training pipeline, we show that, for various pairs of teacher models across three families, there is a strong correlation between the log-ratio of the teacher model sycophantic agreement rates and the resulting student model sycophantic agreement rate. We further demonstrate that this unintended transfer is not limited to DPO but also occurs across 6 other preference optimization objectives. To understand whether this effect can be attributed to particular training examples, we analyze the preference data and find that the sycophancy signal is diffused across the entire
dataset rather than concentrated in a sparse set of examples: each example appears neutral, i.e., there are no explicit instances of sycophantic agreement, and filtering based on probe-based data attribution or logit-linear selection fails to mitigate sycophancy without removing a large portion of the
dataset. Overall, our findings suggest that the teacher models used to generate preference data can interact with
alignment training objectives in unexpected ways, generalizing to undesirable and potentially harmful behaviors like sycophantic agreement.
Read the full abstract ▾
All authors Camila Blank, Zhuofan Ying, Christopher Potts, Peter Hase, Jing Huang
Artificial Intelligence
Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization
Jingxiao Yang, Wangjie Gan, Yingxuan Zhuang et al. (+3 more)
Outcome-based reinforcement learning provides verified feedback for
language-model
agents, but assigns trajectory-level advantage uniformly to all decisions, yielding coarse credit over long-horizon interactions. On-policy self-
distillation offers finer supervision by re-evaluating sampled behavior with privileged information (PI) available only during training. However, fine-grained supervision is not necessarily fine-grained credit: PI-induced likelihood changes describe how additional information alters policy preference, but do not directly determine how an executable action should inherit the verified task outcome. This creates a supervision-credit gap. Privileged signals may be irrelevant to the current interaction state, operate at a
token granularity misaligned with executable decisions, and lack the outcome semantics required for reinforcement. We introduce TASPO, which converts privileged supervision into outcome-grounded action credit. TASPO constructs decision-applicable PI from verified successful experience, aggregates PI-induced likelihood shifts at the executable-action level, and converts relative action support into positive, bounded, mean-preserving weights on the original trajectory advantage. Thus, the verified outcome determines the update direction and average scale, while PI only redistributes credit across actions. Across three agentic
benchmarks, TASPO improves over GRPO by 10.6% and generalizes better to unseen tasks. Further analysis indicates that TASPO reduces supervision mismatch and that action-level assignment stabilizes the policy optimization process. These findings offer the community another interesting perspective.
Read the full abstract ▾
All authors Jingxiao Yang, Wangjie Gan, Yingxuan Zhuang, Wenqi Zhang, Jintao Chen, Xuhong Zhang
Computation and Language
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
Xuehai Wang, Haowei Qin, Tongxin Liu et al. (+6 more)
Autonomous scientific research
agents are increasingly applied to end-to-end scientific workflows, including literature review, data analysis, experimentation, and report generation. However, open-ended research tasks often do not clearly specify the analyses, methods, and success criteria required to complete the task. As a result,
agents may miss important analyses, use inappropriate methods, or draw conclusions that are insufficiently supported by evidence. To address the problem, we present AutoSciRub, an evaluation-first framework that induces a task-specific executable rubric before research execution, and uses it to guide execution, criterion-level verification as well as iterative revision. AutoSciRub decomposes an underspecified instruction into atomic scientific goals, grounds them in relevant literature and task-visible data, and synthesizes specific, actionable, and verifiable criteria. The resulting rubric makes implicit experimental and evidential requirements explicit, providing guidance for experiments and analyses. During revision, rubric-guided verification identifies unmet criteria and enables targeted refinement of the research report and its supporting artifacts. On ResearchClawBench, AutoSciRub consistently improves all tested configurations, with an average gain of 2.08 points across three backbone LLMs under the fixed Codex harness and 2.95 points across three
agent harnesses using a fixed DeepSeek-V4-Flash backbone. On a randomly sampled 20-task subset of AstaBench E2E Discovery, AutoSciRub further achieves an average improvement of 16.8 points across three
agent harnesses, while maintaining or increasing the number of successfully completed tasks. These results demonstrate that evaluation-first guidance provides an effective and generalizable control mechanism for autonomous scientific research (Code: https://github.com/zjunlp/AutoSciRub).
Read the full abstract ▾
All authors Xuehai Wang, Haowei Qin, Tongxin Liu, Junkai Li, Buqiang Xu, Jintian Zhang, Yijun Chen, Zirui Xue, Shumin Deng
Artificial Intelligence
Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence
Zhiqin Yang, Jingwen Fu, Yuhan Liu et al. (+16 more)
Recent advances in large
reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve
reasoning in mathematics and code, where outcomes can be checked automatically. Extending this progress to open-ended and agentic tasks remains difficult because reliable rewards are harder to obtain and direct human supervision cannot keep pace with the scale and complexity of model-generated experience. This paper studies how LRMs can continue to improve as human supervision gradually recedes from the learning loop. We examine two connected dimensions of this problem. The reward axis traces the development from per-instance human judgments to reusable verifiers and rewards that operate even without human feedback. The experience axis examines how learning can progress from human-curated tasks and environments toward self-generated curricula, constructed environments, and autonomous co-
evolution. We connect these dimensions through a five-level ladder from L0 to L4 that identifies which parts of the learning process remain under continued human control. Our analysis further highlights the risks introduced by increasingly autonomous rewards and experience generation, including reward hacking, feedback drift, curriculum collapse, and environment errors. Consequently, we also provide the evaluation around three complementary objects: policy capability, feedback fidelity, and experience quality. This analysis provides a structured account of current approaches to scaling LRMs beyond human supervision and the open problems involved in developing self-sustaining learning systems toward superintelligence. Furthermore, we maintain a continuously updated \href{https://github.com/visitworld123/Awesome-Scaling-LRM-Beyond-Human-Supervision}{GitHub repository} to track the latest advances.
Read the full abstract ▾
All authors Zhiqin Yang, Jingwen Fu, Yuhan Liu, Hengyu Liu, Yonggang Zhang, Kainan Cao, Zizhuo Zhang, Chenxin Li, Ruibin Yuan, Jiahao Pan, Jiankai Sun, Zhenyuan Zhang, Yibo Li, Yunlong Lin, Jing Xiong, Sida Lin, Bo Han, Wei Xue, Yike Guo