Machine Learning · Cross-listed from cs.CL
Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion
Zhen Tan, Chengshuai Zhao, Song Wang et al. (+3 more)
Distilling robust
reasoning capabilities from large
language models (LLMs) into smaller, computationally efficient student models remains an unresolved challenge. Despite recent advances, distilled models frequently suffer from superficial pattern memorization and subpar generalization. To overcome these limitations, we introduce a novel
distillation framework that moves beyond simple mimicry to instill a deeper conceptual understanding. Our framework features two key innovations. \underline{First}, to address pattern memorization, Explanatory Inversion (EI) generates targeted “explanatory probes” that compel the student to articulate the underlying logic behind an answer, rather than just memorizing it. \underline{Second}, to improve generalization, Explanatory GRPO (EXGRPO) uses a reinforcement learning
algorithm with a novel Dialogue Structure Utility Bonus, which explicitly rewards the student for maintaining a coherent
reasoning process across these probes. Extensive evaluations on 12
datasets demonstrate significant improvements. Using Gemma-7b as the student model, our method yields an average 20.39% increase over zero-shot performance and a 6.02% improvement over the state-of-the-art
distillation baselines. Moreover, models distilled with our method show remarkable training efficiency (e.g., surpassing vanilla fine-tuning with 10-25% training data) and strong generalization to out-of-distribution tasks. Implementation is released at https://github.com/Zhen-Tan-dmml/ExGRPO.git.
Read the full abstract ▾
All authors Zhen Tan, Chengshuai Zhao, Song Wang, Jundong Li, Tianlong Chen, Huan Liu
Machine Learning · Cross-listed from cs.CL
Significance-Gain Pair Encoding for LLMs: A Statistical Alternative to Frequency-Based Subword Merging
Azam Nouri
Subword tokenization is a key design choice for modern
language models, including large
language models (LLMs), with byte- and character-level BPE serving as a widely used baseline. Standard BPE selects merges by raw pair frequency, which favors compression but can conflate true adjacency cohesion with pairs that are frequent due to high marginal counts. This paper introduces Significance-Gain BPE, a drop-in alternative merge criterion that measures cohesion via a z-statistic under an independence null model and combines it with an explicit compression-aware gain term. Significance-Gain BPE is evaluated on WikiText-103 (raw) character slices using a small causal
Transformer language model, reporting both
token-dependent perplexity and the tokenizer-invariant metric bits per character (BPC). At a representative operating point, Significance-Gain BPE reduces validation and test perplexity by 13% and 12%, respectively, and improves validation and test BPC by about 0.9 to 1.0%. A vocabulary-size sweep further shows lower BPC in most closest-compression comparisons, suggesting that statistically grounded merge selection can improve predictive efficiency per unit of raw text across a range of compression regimes.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
MAPLE: Metadata Augmented Private Language Evolution
Eli Chien, Yuzheng Hu, Ryan McKenna et al. (+3 more)
Differentially private (DP) fine-tuning of large
language models (LLMs) requires massive compute and full model access, which rules out state-of-the-art proprietary APIs for general users. Generating DP synthetic data offers a practical workaround. This approach also allows for transparent exploratory data analysis and arbitrary reuse across downstream tasks, sidestepping the rigid constraints of a model's parameter space. Private
Evolution (PE) provides a promising API-based framework for generating this data, but its success relies heavily on initialization. If the private data distribution falls too far outside the foundation model's pre-training priors – a common issue in highly specialized domain – PE struggles to align with the target data. This misalignment causes poor convergence, degraded utility, and wasted API calls. To solve this initialization bottleneck, we introduce Metadata Augmented Private
Language Evolution (MAPLE). MAPLE extracts DP tabular metadata and uses in-context learning to firmly ground the initial synthetic distribution in the target domain. Our evaluations on domain-specific text generation tasks show that MAPLE yields a strictly better
privacy-utility trade-off, converges significantly faster, and sharply reduces API costs compared to baseline PE methods.
Read the full abstract ▾
All authors Eli Chien, Yuzheng Hu, Ryan McKenna, Shanshan Wu, Zheng Xu, Peter Kairouz
Machine Learning · Cross-listed from cs.AI
NextMem: Towards Latent Factual Memory for LLM-based Agents
Zeyu Zhang, Rui Li, Xiaoyan Zhao et al. (+4 more)
Memory is critical for LLM-based
agents to preserve past observations for future decision-making, where factual
memory serves as its foundational part. However, existing approaches to constructing factual
memory face several limitations. Textual methods impose heavy context and indexing burdens, while parametric methods suffer from catastrophic forgetting and high costs. To address these challenges, we introduce NextMem, a latent factual
memory framework that utilizes an autoregressive autoencoder to efficiently construct latent
memory while ensuring accurate reconstruction. For better optimization, we propose a two-stage training process, including autoregressive reconstruction
alignment and progressive latent substitution. We also incorporate quantization to reduce storage overhead. Extensive experiments demonstrate that NextMem achieves superior performance, and excels in
retrieval, robustness, and extensibility properties. We release our code and model checkpoints at https://github.com/nuster1128/NextMem.
Read the full abstract ▾
All authors Zeyu Zhang, Rui Li, Xiaoyan Zhao, Yang Zhang, Wenjie Wang, Xu Chen, Tat-Seng Chua
Machine Learning · Cross-listed from cs.AR
The AetherFloat Family: Block-Scale-Free Quad-Radix Floating-Point Architectures for AI Accelerators
Keita Morisaki
The IEEE 754 floating-point standard is the bedrock of modern computing, but its structural requirements – a hidden leading bit, Base-2 bit-level normalization, and Sign-Magnitude encoding – impose significant silicon area and power overhead in massively parallel Neural Processing Units (NPUs). Furthermore, the industry's recent shift to 8-bit formats (e.g., FP8 E4M3, OCP MX formats) has introduced a new hardware penalty: the strict necessity of Block-Scaling (AMAX) logic to prevent out-of-bound Large
Language Model (LLM) activations from overflowing and degrading accuracy. The AetherFloat Family is a parameterizable architectural replacement designed from first principles for Hardware/Software Co-Design in AI acceleration. By synthesizing Lexicographic One's Complement Unpacking, Quad-Radix (Base-4) Scaling, and an Explicit Mantissa, AetherFloat achieves zero-cycle native integer comparability, branchless subnormal handling, and a verified 33.17% area, 21.99% total power, and 11.73% critical path delay reduction across the multiply-accumulate (MAC) unit. Instantiated as AetherFloat-8 (AF8), the architecture relies on a purely explicit 3-bit mantissa. Combined with Base-4 scaling, AF8 delivers a substantially wider dynamic range, acting as a “Block-Scale-Free” format for inference that circumvents dynamic scaling microarchitecture. Finally, a novel Vector-Shared 32-bit Galois
Stochastic Rounding
topology bounds precision variance while neutralizing the vanishing gradients that plague legacy formats. While AF16 serves as a near-lossless bfloat16 replacement via post-training quantization, AF8 is designed as a QAT-first inference format: its Block-Scale-Free property eliminates dynamic AMAX hardware at the cost of requiring quantization-aware fine-tuning for deployment.
Read the full abstract ▾
Machine Learning · Cross-listed from quant-ph
Quantum Deep Learning: A Comprehensive Review
Yanjun Ji, Zhao-Yun Chen, Marco Roth et al. (+10 more)
Quantum deep learning (QDL) explores the use of both
quantum and
quantum-inspired resources to determine when deep learning's core capabilities, such as expressivity, generalization, and scalability, can be enhanced based on specific resource constraints. Distinct from broader
quantum machine learning, QDL emphasizes compositional depth at the pipeline level and the integration of
quantum or
quantum-inspired components within end-to-end workflows. This review provides an operational definition of QDL and introduces a taxonomy comprising four primary paradigms: hybrid
quantum-classical models,
quantum deep neural networks,
quantum algorithms for deep learning primitives, and
quantum-inspired classical
algorithms. Theoretical principles are connected to advanced architectures, software toolchains, and experimental demonstrations across superconducting, trapped-ion, photonic,
semiconductor spin, and neutral-atom systems, as well as
quantum annealers. Claims of
quantum advantage are critically assessed by distinguishing provable complexity-theoretic separations from empirical observations. The analysis characterizes trade-offs between model expressivity, trainability, and classical simulability, while systematically detailing the bottlenecks imposed by optimization landscapes, input-output access models, and hardware constraints. Applications are surveyed in domains encompassing image classification, natural
language processing, scientific discovery,
quantum data processing, and
quantum optimal control, underscoring fair benchmarking against optimized classical counterparts and a comprehensive assessment of resource requirements. This review serves as a tutorial entry point for graduate students while guiding readers to specialized literature. It concludes with a verification-aware roadmap to transition QDL from near-term demonstrations to scalable and fault-tolerant implementations.
Read the full abstract ▾
All authors Yanjun Ji, Zhao-Yun Chen, Marco Roth, David A. Kreplin, Christian Schiffer, Martin King, Oliver Anton, M. Sahnawaz Alam, Markus Krutzik, Dennis Willsch, Ludwig Mathey, Frank K. Wilhelm, Guo-Ping Guo
Machine Learning
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training
Swamynathan V P
Test-Time Training (TTT)
language models replace the KV-cache with fast weights updated during inference, achieving O(1)
memory but suffering catastrophic failure on exact-recall tasks. Version 1 of this work proposed SR-TTT, which routes high-surprisal
tokens to a sparse exact-
attention Residual Cache, and reported large Needle-in-a-Haystack gains. We show those gains were evaluation artifacts: the loss and metric read logits at the answer positions rather than one position earlier, training both models to copy an answer already visible in their input (a model trained on
retrieval-impossible data reaches 100% accuracy under the flawed metric); additionally, the cache attended non-causally over future
tokens, including the answer itself. We release a corrected implementation with startup causality self-tests, then ask whether the SR-TTT hypothesis survives correction. It does not, and the failure decomposes into two independent, separately measured bottlenecks. Storage: surprisal gating is systematically position-biased - the TTT reconstruction loss requires burn-in before a needle becomes relatively surprising, so early-context needles are stored at near-zero rates (0-1% containment at depth 0.1) exactly where long-context
memory matters most. Addressing: with storage solved by an oracle and with new trainable read-time projections, per-slot
attention supervision raises addressing mass 2.5x (0.06 -> 0.15) yet
token accuracy is statistically unchanged, and
retrieval extracts only approx. 0.06 nats of the 2.30-nat needle; position-free content addressing cannot resolve ordered slots whose contents are near-interchangeable. Exact match remains 0% in all 2,250 paired trials across all corrected conditions. We retract the claims of v1 and offer the corrected codebase, diagnostic protocol, and negative results as a cautionary reference for surprise-gated
memory architectures.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.LO
MPBMC: Multi-Property Bounded Model Checking with GNN-guided Clustering
Soumik Guha Roy, Sumana Ghosh, Ansuman Banerjee et al. (+2 more)
Formal verification of designs with multiple properties has been a long-standing challenge for the verification research community. The task of coming up with an effective strategy that can efficiently cluster properties to be solved together has inspired a number of proposals, ranging from structural clustering based on the property cone of influence (COI) to leverage runtime design and verification statistics. In this paper, we present an attempt towards functional clustering of properties utilizing graph neural network (GNN)
embeddings for creating effective property clusters. We propose a hybrid approach that can exploit neural functional representations of hardware
circuits and runtime design statistics to speed up the performance of Bounded Model Checking (BMC) in the context of multi-property verification (MPV). Our method intelligently groups properties based on their functional
embedding and design statistics, resulting in speedup in verification results. Experimental results on the HWMCC
benchmarks show the efficacy of our proposal with respect to the state-of-the-art.
Read the full abstract ▾
All authors Soumik Guha Roy, Sumana Ghosh, Ansuman Banerjee, Raj Kumar Gajavelly, Sudhakar Surendran
Machine Learning
An Explainable Ensemble Framework for Alzheimer's Disease Prediction Using Structured Clinical and Cognitive Data
Nishan Mitra
Early and accurate detection of Alzheimer's disease (AD) remains a major challenge in medical diagnosis due to its subtle onset and progressive nature. This research introduces an explainable ensemble learning Framework designed to classify individuals as Alzheimer's or Non-Alzheimer's using structured clinical, lifestyle, metabolic, and lifestyle features. The workflow incorporates rigorous preprocessing, advanced feature engineering, SMOTE-Tomek hybrid class balancing, and optimized modeling using five ensemble
algorithms-Random Forest, XGBoost, LightGBM, CatBoost, and Extra Trees-alongside a deep artificial neural network. Model selection was performed using stratified validation to prevent leakage, and the best-performing model was evaluated on a fully unseen test set. Ensemble methods achieved superior performance over deep learning, with XGBoost, Random Forest, and Soft Voting showing the strongest accuracy, sensitivity, and F1-score profiles. Explainability techniques, including SHAP and feature importance analysis, highlighted MMSE, Functional Assessment Age, and several engineered interaction features as the most influential determinants. The results demonstrate that the proposed framework provides a reliable and transparent approach to Alzheimer's disease prediction, offering strong potential for clinical decision support applications.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu et al. (+47 more)
Current AI
agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation,
agents frequently “reinvent the wheel”, rediscovering solutions in isolated contexts without leveraging prior strategies. To address this challenge, we introduce SkillNet, an open infrastructure for creating, evaluating, and organizing AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 600,000 skills, an interactive platform, and a versatile Python toolkit. Experiments on ALFWorld, WebShop, and ScienceWorld show 40% higher average rewards and 30% fewer execution steps across multiple backbone models. Furthermore, SkillNet-Gym
benchmarks skill
retrieval, utilization, and composition, while SkillNet-Fabric enables task-specific skill routing through lightweight Wikis. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for
agents to move from transient experience to durable mastery.
Read the full abstract ▾
All authors Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Yida Xue, Xin Xu, Tongtong Wu, Kun Wang, Yang Liu, Zhen Bi, Jungang Lou, Yuchen Eleanor Jiang, Hangcheng Zhu, Gang Yu, Haiwen Hong, Longtao Huang, Hui Xue, Chenxi Wang, Yijun Wang, Zifei Shan, Xi Chen, Zhaopeng Tu, Feiyu Xiong, Xin Xie, Peng Zhang, Zhengke Gui, Lei Liang, Jun Zhou, Chiyu Wu, Jin Shang, Yu Gong, Junyu Lin, Changliang Xu, Hongjie Deng, Wen Zhang, Keyan Ding, Qiang Zhang, Fei Huang, Ningyu Zhang, Jeff Z. Pan, Guilin Qi, Haofen Wang, Huajun Chen
Machine Learning · Cross-listed from q-bio.QM
Automated Measurement of Geniohyoid Muscle Thickness During Speech Using Deep Learning and Ultrasound
Alisher Myrgyyassov, Bruce Xiao Wang, Yu Sun et al. (+4 more)
Manual measurement of muscle morphology from ultrasound during
speech is time-consuming and limits large-scale studies. We present SMMA, a fully automated framework that combines deep-learning
segmentation with skeleton-based thickness quantification to analyze geniohyoid (GH) muscle dynamics. Validation demonstrates near-human-level accuracy (Dice = 0.9037, MAE = 0.53 mm, r = 0.901). Application to Cantonese vowel production (N = 11) reveals systematic patterns: /a:/ shows significantly greater GH thickness (7.29 mm) than /i:/ (5.95 mm, p < 0.001, Cohen's d > 1.3), suggesting greater GH activation during production of /a:/ than /i:/, consistent with its role in mandibular depression. Sex differences (5-8% greater in males) reflect anatomical scaling. SMMA achieves expert-validated accuracy while eliminating the need for manual annotation, enabling scalable investigations of
speech motor control and objective assessment of
speech and swallowing disorders.
Read the full abstract ▾
All authors Alisher Myrgyyassov, Bruce Xiao Wang, Yu Sun, Shuming Huang, Zhen Song, Min Ney Wong, Yongping Zheng
Machine Learning · Cross-listed from cs.CR
RLShield: Practical Multi-Agent RL for Financial Cyber Defense with Attack-Surface MDPs and Real-Time Response Orchestration
Srikumar Nayak
Financial systems run nonstop and must stay reliable even during cyber incidents. Modern attacks move across many services (apps, APIs, identity, payment rails), so defenders must make a sequence of actions under time pressure. Most security tools still use fixed rules or static playbooks, which can be slow to adapt when the attacker changes behavior. Reinforcement learning (RL) is a good fit for sequential decisions, but much of the RL-in-finance literature targets trading and does not model real cyber response limits such as action cost, service disruption, and defender coordination across many assets. This paper proposes RLShield, a practical multi-
agent RL pipeline for financial cyber defense. We model the enterprise attack surface as a Markov decision process (MDP) where states summarize alerts, asset exposure, and service health, and actions represent real response steps (e.g., isolate a host, rotate credentials, ratelimit an API, block an account, or trigger recovery). RLShield learns coordinated policies across multiple
agents (assets or service groups) and optimizes a risk-sensitive objective that balances containment speed, business disruption, and response cost. We also include a game-aware evaluation that tests policies against adaptive attackers and reports operational outcomes, not only reward. Experiments show that RLShield reduces time-to-containment and residual exposure while keeping disruption within a fixed response budget, outperforming static rule baselines and single-
agent RL under the same constraints. These results suggest that multi-
agent, cost-aware RL can provide a deployable layer for automated response in financial security operations.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Kei Suzuki, Jing Liu, Ye Wang et al. (+4 more)
Cross-
robot policy learning – training a single policy to perform well across multiple embodiments – remains a central challenge in
robot learning.
Transformer-based policies, such as
vision-
language-action (VLA) models, are typically embodiment-agnostic and must infer kinematic structure purely from observations, which can reduce robustness across embodiments and even limit performance within a single embodiment. We propose an embodiment-aware
transformer policy that injects morphology via three mechanisms: (1) kinematic
tokens that factorize actions across joints and compress time through per-joint temporal chunking; (2) a
topology-aware
attention bias that encodes kinematic
topology as an inductive bias in self-
attention, encouraging message passing along kinematic edges; and (3) joint-attribute conditioning that augments
topology with per-joint descriptors to capture semantics beyond connectivity. Across a range of embodiments, this structured integration consistently improves performance over a vanilla pi0.5 VLA baseline, indicating improved robustness both within an embodiment and across embodiments.
Read the full abstract ▾
All authors Kei Suzuki, Jing Liu, Ye Wang, Chiori Hori, Matthew Brand, Diego Romeres, Toshiaki Koike-Akino
Machine Learning
Engineering FAIR Privacy-preserving Applications that Learn Histories of Disease
Ines N. Duarte, Praphulla M. S. Bhawsar, Lee K. Mason et al. (+4 more)
A recent report on "Learning the natural history of human disease with generative
transformers" created an opportunity to assess the engineering challenge of delivering user-facing Generative AI applications in
privacy-sensitive domains. The application of these models, particularly for personalized healthcare tasks like predicting individual morbidity risk, is typically constrained by data
privacy concerns. This project was accordingly designed as an in-browser model deployment exercise (an "App") testing the architectural boundaries of client-side inference generation (no downloads or installations). We relied exclusively on the documentation provided in the reference report to develop the model, specifically testing the "R" component of the FAIR data principles: Findability, Accessibility, Interoperability, and Reusability. The successful model deployment, leveraging ONNX and a custom JavaScript SDK, establishes a secure, high-performance architectural blueprint for the future of private generative AI in medicine.
Read the full abstract ▾
All authors Ines N. Duarte, Praphulla M. S. Bhawsar, Lee K. Mason, Jeya Balaji Balasubramanian, Daniel E. Russ, Arlindo L. Oliveira, Jonas S. Almeida
Machine Learning
NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
Jiwoo Kim, Swarajh Mehta, Hao-Lun Hsu et al. (+3 more)
Generative modeling of neural network parameters is often tied to architectures because standard parameter representations rely on known weight-
matrix dimensions. Generation is further complicated by permutation
symmetries that allow networks to model similar input-output functions while having widely different, unaligned parameterizations. In this work, we introduce Neural Network
Diffusion Transformers (NNiTs), which generate weights in a width-agnostic manner by tokenizing weight
matrices into patches and modeling them as locally structured fields. We establish that Graph HyperNetworks (GHNs) with a convolutional neural network (CNN) decoder structurally align the weight space, creating the local correlation necessary for patch-based processing. Focusing on Multilayer Perceptrons (MLPs), where permutation
symmetry is especially apparent, NNiTs generate fully functional networks across a range of architectures. Our approach jointly models discrete architecture
tokens and continuous weight patches within a single sequence model. On ManiSkill3 robotics tasks, NNiT achieves $>85\%$ success on architecture
topologies unseen during training, while baseline approaches fail to generalize; the same pipeline also generalizes to MNIST classification beyond the robotic control setting.
Read the full abstract ▾
All authors Jiwoo Kim, Swarajh Mehta, Hao-Lun Hsu, Hyunwoo Ryu, Yudong Liu, Miroslav Pajic
Machine Learning · Cross-listed from cs.CR
Detecting Cognitive Signatures in Typing Behavior for Non-Intrusive Authorship Verification
David Condrey
The proliferation of AI-generated text has intensified the need for reliable authorship verification, yet current output-based methods are increasingly unreliable. We observe that the ordinary typing interface captures rich cognitive signatures, measurable patterns in keystroke timing that reflect the planning, translating, and revising stages of genuine composition. Drawing on large-scale keystroke
datasets comprising over 136 million events, we define the Cognitive Load Correlation (CLC) and show it distinguishes genuine composition from mechanical transcription. We present a non-intrusive verification framework that operates within existing writing interfaces, collecting only timing metadata to preserve
privacy. Our analytical evaluation estimates 85 to 95 percent discrimination accuracy under stated assumptions, while limiting biometric leakage via evidence quantization. We analyze the
adversarial robustness of cognitive signatures, showing they resist timing-forgery attacks that defeat motor-level authentication because the cognitive channel is entangled with semantic content. We conclude that reframing authorship verification as a human-computer interaction problem provides a
privacy-preserving alternative to invasive surveillance.
Read the full abstract ▾
Machine Learning
Bridging Policy and Real-World Dynamics: LLM-Augmented Rebalancing for Shared Micromobility Systems
Heng Tan, Hua Yan and Yu Yang
Shared micromobility services such as e-scooters and bikes have become an integral part of urban transportation, yet their efficiency critically depends on effective vehicle rebalancing. Existing methods either optimize for average demand patterns or employ robust optimization and reinforcement learning to handle predefined uncertainties. However, these approaches overlook emergent events (e.g., demand surges, vehicle outages, regulatory interventions) or sacrifice performance in normal conditions. We introduce AMPLIFY, an LLM-augmented policy adaptation framework for shared micromobility rebalancing. The framework combines a baseline rebalancing module with an LLM-based adaptation module that adjusts strategies in real time under emergent scenarios. The adaptation module ingests system context, demand predictions, and baseline strategies, and refines adjustments through self-reflection. Evaluations on real-world e-scooter data from Chicago show that our approach improves demand satisfaction and system revenue compared to baseline policies, highlighting the potential of LLM-driven adaptation as a flexible solution for managing uncertainty in micromobility systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Summer-22B: A Systematic Approach to Dataset Engineering and Training at Scale for Video Foundation Model
Simo Ryu and Chunghwan Han
We describe our experience training Summer-22B, a
video foundation model developed from scratch. This report documents the engineering challenges, design decisions, and lessons learned while scaling from raw footage collection to a functional model trained on approximately 50 million clips. We outline our approach combining metadata-driven
dataset curation, multi-stage filtering, $\mu$P parameterization, and hypersphere-constrained optimization. We developed the Lavender Data system for
dataset management and adopted inference-aware architectural choices. We share observations on what worked in our setting:
dataset engineering consumed the majority of effort, architectural variants showed smaller differences than we expected, and $\mu$P hyperparameter transfer appeared effective even under
geometric constraints. We hope this account proves useful to others undertaking similar projects.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
A Boundary-Metric Evaluation Protocol for Whiteboard Stroke Segmentation Under Extreme Imbalance
Nicholas Korcynski
The binary
segmentation of whiteboard strokes is hindered by extreme class imbalance, caused by stroke pixels that constitute only $1.79%$ of the image on average, and in addition, the thin-stroke subset averages $1.14% \pm 0.41%$ in the foreground. Standard region metrics (F1, IoU) can mask thin-stroke failures because the vast majority of the background dominates the score. In contrast, adding boundary-aware metrics and a thin-subset equity analysis changes how loss functions rank and exposes hidden trade-offs. We contribute an evaluation protocol that jointly examines region metrics, boundary metrics (BF1, B-IoU), a core/thin-subset equity analysis, and per-image robustness statistics (median, IQR, worst-case) under seeded, multi-run training with non-parametric significance testing. Five losses – cross-
entropy, focal, Dice, Dice+focal, and Tversky – are trained three times each on a DeepLabV3-MobileNetV3 model and evaluated on 12 held-out images split into core and thin subsets. Overlap-based losses improve F1 by more than 20 points over cross-
entropy ($0.663$ vs $0.438$, $p < 0.001$). In addition, the boundary metrics confirm that the gain extends to the precision of the contour. Adaptive thresholding and Sauvola binarization at native resolution achieve a higher mean F1 ($0.787$ for Sauvola) but with substantially worse worst-case performance (F1 $= 0.452$ vs $0.565$ for Tversky), exposing a consistency-accuracy trade-off: classical baselines lead on mean F1 while the learned model delivers higher worst-case reliability. Doubling training resolution further increases F1 by 12.7 points.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
SKINOPATHY AI: Smartphone-Based Ophthalmic Screening and Longitudinal Tracking Using Lightweight Computer Vision
S. Kalaycioglu, C. Hong, M. Zhu et al. (+1 more)
Early ophthalmic screening in low-resource and remote settings is constrained by access to specialized equipment and trained practitioners. We present SKINOPATHY AI, a smartphone-first web application that delivers five complementary, explainable screening modules entirely through commodity mobile hardware: (1) redness quantification via LAB a* color-space normalization; (2) blink-rate estimation using MediaPipe FaceMesh Eye Aspect Ratio (EAR) with adaptive thresholding; (3) pupil light reflex characterization through Pupil-to-Iris Ratio (PIR) time-series analysis; (4) scleral color indexing foricterus and anemia proxies via LAB/HSV statistics; and (5) iris-landmark-calibrated lesion encroachment measurement with millimeter-scale estimates and longitudinal trend tracking. The system is implemented as a React/FastAPI stack with OpenCV and MediaPipe, MongoDB-backed session persistence, and PDF report generation. All
algorithms are fully deterministic,
privacy-preserving, and designed for non-diagnostic consumer triage. We detail system architecture,
algorithm design, evaluation methodology, clinical context, and ethical boundaries of the platform. SKINOPATHY AI demonstrates that multi-signal ophthalmic screening is feasible on unmodified smartphones without cloud-based AI inference, providing a foundation for future clinically validated mobile ophthalmoscopy tools.
Read the full abstract ▾
All authors S. Kalaycioglu, C. Hong, M. Zhu, H. Xie
Machine Learning
Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents
Aishwarya Sarkar, Sayan Ghosh, Nathan Tallent et al. (+3 more)
Large-scale Graph Neural Networks (GNNs) are typically trained by sampling a vertex's neighbors to a fixed distance. Because large input graphs are distributed, training requires frequent irregular communication that stalls forward progress. Moreover, fetched data changes with graph, graph distribution, sample and batch parameters, and caching polices. Consequently, any static prefetching method will miss crucial opportunities to adapt to different dynamic conditions. In this paper, we introduce Rudder, a software module embedded in the state-of-the-art AWS DistDGL framework, to autonomously prefetch remote nodes and minimize communication. Rudder's adaptation contrasts with both standard heuristics and traditional ML classifiers. We observe that the generative AI found in contemporary Large
Language Models (LLMs) exhibits emergent properties like In-Context Learning (ICL) for zero-shot tasks, with logical multi-step
reasoning. We find this behavior well-suited for adaptive control even with substantial undertraining. Evaluations using standard
datasets and unseen configurations on the NERSC Perlmutter supercomputer show up to 91% improvement in end-to-end training performance over baseline DistDGL (no prefetching), and an 82% improvement over static prefetching, reducing communication by over 50%. Our code is available at https://github.com/aishwaryyasarkar/rudder-llm-
agent.
Read the full abstract ▾
All authors Aishwarya Sarkar, Sayan Ghosh, Nathan Tallent, Aman Chadha, Tanya Roosta, Ali Jannesari
Machine Learning · Cross-listed from cs.AI
Causal Identification from Counterfactual Data: Completeness and Bounding Results
Arvind Raghavan and Elias Bareinboim
Previous work establishing completeness results for counterfactual identification has been circumscribed to the setting where the input data belongs to observational or interventional distributions (Layers 1 and 2 of Pearl's Causal Hierarchy), since it was generally presumed impossible to obtain data from counterfactual distributions, which belong to Layer 3. However, recent work (Raghavan & Bareinboim, 2025) has formally characterized a family of counterfactual distributions which can be directly estimated via experimental methods - a notion they call counterfactual realizability. This leaves open the question of what additional counterfactual quantities now become identifiable, given this new access to (some) Layer 3 data. To answer this question, we develop the CTFIDU+
algorithm for identifying counterfactual queries from an arbitrary set of Layer 3 distributions, and prove that it is complete for this task. Building on this, we establish the theoretical limit of which counterfactuals can be identified from physically realizable distributions, thus implying the fundamental limit to exact causal inference in the non-parametric setting. Finally, given the impossibility of identifying certain critical types of counterfactuals, we derive novel analytic bounds for such quantities using realizable counterfactual data, and corroborate using simulations that counterfactual data helps tighten the bounds for non-identifiable quantities in practice.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.ET
Component Centric Placement Using Deep Reinforcement Learning
Kart Leong Lim
Automated placement of components on printed
circuit boards (PCBs) is a critical stage in placement layout design. While reinforcement learning (RL) has been successfully applied to system-on-chip IP block placement and chiplet arrangement in complex packages, PCB component placement presents unique challenges due to several factors: variation in component sizes, single- and double-sided boards, wirelength constraints, board constraints, and non-overlapping placement requirements. In this work, we adopt a component-centric layout for automating PCB component placement using RL: first, the main component is fixed at the center, while passive components are placed in proximity to the pins of the main component. Free space around the main component is discretized, drastically reducing the search space while still covering all feasible placement; second, we leverage prior knowledge that each passive's position has to be near to its corresponding voltage source. This allows us to design the reward function which avoids wasted exploration of infeasible or irrelevant search space. Using the component centric layout, we implemented different methods including Deep Q-Network, Actor-Critic
algorithm and Simulated Annealing. Evaluation on over nine real-world PCBs of varying complexity shows that our best proposed method approaches near human-like placements in terms of wirelength and feasibility.
Read the full abstract ▾