Papers

Some limits on what language models know are not gaps in data coverage but structural properties of learning from text. We introduce the information shadow: the region of phenomena that a text-trained learner cannot acquire regardless of scale, comprising (I) structures language cannot express, (II) functions that are statistically non-identifiable from the training distribution, and (III) functions that are representable but unreachable by gradient-based training. We give each type a probe that is decisive because the premise of the shadow is, in that setting, provable. For Type I, Language Compression Residuals compare a text learner, which sees only a lossy text-like encoding of the signal, against a full-signal learner, which sees the underlying signal directly. The text learner sits at a computable expressibility ceiling while the full-signal learner pulls away by a gap that stays flat across 300x more data, so the deficit is a property of the channel, not of training. For Type II, the Counterfactual Distinction Test trains models on data exactly consistent with two incompatible rules. Across a provable string task and a language-like agreement task, behavior on counterfactuals is set by the model's inductive bias, while 5% disambiguating data steers the learned rule bidirectionally to either target (r = +/-1.0, p < 1e-10). For Type III, Basin Escape Mapping exhibits a function that is representable at 100% (by hand construction) yet reached 0% of the time by standard training and instantly from a nearby initialization, with width scaling providing no help (p = 1.6 x 10^-14). Each effect is isolated by a control that rules out a capacity or modality artifact. We release the probe suite and discuss implications for benchmark design, capability auditing, and shadow-aware uncertainty.

The sycophancy of large language models can increase the safety risk in intervention dialogue for autistic children. Supervised fine-tuning can somewhat reduce sycophancy, but relying solely on positive examples is often insufficient to identify and correct failure patterns. We observe that sycophancy behaviors can often be localized to a limited span within the model response. In this regime, sequence-level preference optimization can over-update preference-irrelevant tokens and degrade intervention ability. To address this, we propose the Minimal Edit Data Augmentation (MEDA) strategy to construct controlled, stable, minimal edit preference pairs and Token-level Difference Direct Preference Optimization (TD-DPO), which upweights difference tokens between chosen and rejected responses while downweighting shared tokens to suppress background drift. Extensive experiments across multiple backbones and evaluators show that TD-DPO achieves a better trade-off between sycophancy mitigation and intervention ability retention in our offline settings, highlighting its potential as a practical alignment approach for autism intervention.

Identifying which string produces a given pitch in monophonic electric guitar audio is a classification challenge: a single pitch can often be produced on multiple strings, with timbral differences largely imperceptible to untrained humans. We present Fretiq, a preliminary single-instrument, single-player browser-based string classification system using a 26-dimensional feature representation of frequency band energies, spectral statistics, and 13 Mel-Frequency Cepstral Coefficients. Across five seeds, a shuffled frame-level validation split yields 97.25 +/- 0.32 percent accuracy, with an ablation study identifying MFCCs as the primary accuracy driver (92.09 +/- 0.50 percent without MFCCs). We introduce Comparison Training, a data collection method recording same-pitch pairs on adjacent strings in deliberate alternation. An initial shuffled-split comparison found no net benefit but was confounded by non-comparable validation sets across conditions. A corrected matched evaluation, using an identical recording session held out from training and model selection, shows including comparison-session data improves accuracy by 25.78 +/- 1.46 percentage points; a size-matched control shows this is not explained by training-set size alone. A recording-session-held-out evaluation yields 86.53 +/- 1.23 percent accuracy, closely matching an independently collected free-play evaluation (87.8 percent), both well below the shuffled-split figure, showing shuffled validation substantially overestimates real generalization here. We describe the feature extraction pipeline in Python and TypeScript for training-inference parity and document two implementation failure modes. The system runs entirely in-browser with no specialized hardware required.

Autoregressive language models are least accurate at the beginning of a sequence, where little context forces reliance on a generic pretraining prior. We show that this cold-start penalty is domain dependent and reduce it with a domain-conditional position offset: a single learned vector added to the embedding activation at the first sequence positions while all model weights remain frozen. The offset trains in minutes on roughly one hundred documents, switches between domains without added sequence state, and has no measurable latency overhead. Across eight Mamba, GPT-NeoX, and Llama models spanning 410M to 8B parameters, it reduces held-out in-domain perplexity by up to 27%; the effect persists at 70B, and one position captures most of the benefit. A matched, converged direct logit-bias correction reaches at most only 7.9% and leaves later-token loss unchanged, showing that the offset propagates through model state rather than merely recalibrating the output prior. A tuned LoRA reaches lower perplexity but uses two to three orders of magnitude more parameters and an active low-rank weight path, while soft prompts add sequence positions. With wrong-domain controls, offsets improve retrieval reranking and domain classification when decisions depend on early in-domain tokens, For the few-shot reasoning whose signal occurs later, the results maintains unchanged. Position-aware prefill application also help generation tasks, whereas naive application at every cached decoding step causes repetition. The offset is therefore not the strongest adapter, but a lightweight, hot switchable tool for short in-domain scoring and calibration.

In multi-task learning (MTL) negative transfer is often considered as an optimization artifact, but it can also be viewed as a consequence of limited shared capacity and weak task redundancy. We investigate this effect through a Capacity–Redundancy (CR) identity that decomposes the sum of per-task predictive informations into joint predictive information that includes label redundancy defined via total correlation (TC), and a residual coupling term that quantifies interference left unresolved by the shared representation. Additionally, we show two key results: (i) a clustering-gap decomposition that gives a necessary and sufficient condition for clustered sharing to outperform global sharing, and (ii) a gradient–TC bridge in a Gaussian multi-task model that formally justifies gradient cosine similarity as a proxy for redundancy ordering. Empirically, we estimate the residual coupling $\Delta$ from validation residual correlations, showing that clustered LoRA substantially reduces $\widehat{\Delta}$, outperforms size-matched random partitions, and results in statistically significant gains with multi-seed confidence intervals.

Protein fold classification can be approached via sequence-based representations or structural descriptors, but direct comparisons between lightweight handcrafted descriptors and pretrained protein language model embeddings remain limited. We investigate discrete Ricci curvature on Calpha contact graphs as a lightweight structural descriptor for fold classification. Each protein domain is represented by a 22-dimensional fixed-length feature derived from summary statistics and quantiles of Ollivier-Ricci and Forman-Ricci edge curvature distributions. We evaluate on CATH top-10 Topology classification and on the ASTRAL 40%-identity SCOPe top-10 Fold benchmark, comparing against geometry, contact-graph statistics, persistent homology, and mean-pooled ESM-2 (150M) baselines. On both datasets, lightweight structural descriptors substantially outperform mean-pooled ESM-2 embeddings, with a larger performance gap on the ASTRAL 40% SCOPe benchmark. Ricci alone uses 22 dimensions, or 3.4% of the ESM-2 baseline dimensionality, and already outperforms mean-pooled ESM-2 on both datasets. Combining Ricci with persistent homology yields the strongest performance, achieving macro-F1 of 0.71 on CATH and 0.68 on SCOPe with a 112-dimensional feature vector. These results identify a regime where lightweight interpretable graph descriptors offer a practical alternative to pretrained protein language model embeddings.

Reinforcement learning (RL) has achieved strong results in control, yet learned policies remain brittle to changes in dynamics, action spaces, observation spaces, or goals, a critical limitation for real-world deployment. Existing benchmarks offer limited diversity and complexity, making it difficult to rigorously study transfer, multi-task learning, and meta-learning in RL. We introduce Building2Building (B2B), a large-scale suite of realistic Heating, Ventilation, and Air Conditioning (HVAC) control environments built on EnergyPlus, a state-of-the-art building simulator. B2B is fully compatible with the Gymnasium interface and features a parametric building generator, enabling the systematic generation of diverse building configurations with heterogeneous observation and action spaces. Based on this suite, we define benchmark tasks targeting key open challenges in RL, including goal adaptation, dynamics adaptation, action-space shifts, and cross-domain transfer. By providing a large-scale, diverse, and physically grounded testbed with standardized evaluation protocols, B2B enables systematic investigation of generalization and transfer in continuous control. Beyond advancing research on generalization in RL, this new benchmark also carries significant societal implications by enabling improved HVAC control at scale, one of the most energy-intensive systems in buildings.

We study hierarchical domain generalization as a problem of extrapolation from finite observed regions to an entire instance space, replacing i.i.d. sampling with arbitrary domain hierarchies. We show that the central obstruction is not only the complexity of the hypothesis class, but the train/test domain partition through which evidence is revealed. In particular, no matter how small the class or how large the training size, some partition makes generalization fail for some target. These results suggest that modern generalization theory must treat domain structure as a first-class object.

Cooperative multi-agent RL systems routinely use team-averaged rewards, a feedback-attribution choice that gives each agent the team outcome regardless of its individual contribution. We ask whether this leaves a measurable signature, geometric or behavioral, on learned representations. We propose EffRank/$n$ (effective rank normalized by agent count) and $D_\text{act}$ (mean pairwise KL divergence between agents' action distributions) as low-overhead diagnostics for reward-attribution effects, then test them on competent MAPPO agents in SMACv2 protoss\_5\_vs\_5, where unit type is encoded in the observation. In an observation $\times$ reward-attribution comparison (unit type observed vs.\ masked; individual damage-contribution reward vs.\ shared team reward), geometry follows observation rather than reward. With unit type observed, shared and individual rewards have similar EffRank/$n$ ($0.31{\pm}0.03$ vs.\ $0.29{\pm}0.02$) and probe accuracy ($0.75{\pm}0.05$ vs.\ $0.73{\pm}0.05$, both $\gg 1/3$ chance), while $D_\text{act}$ leans higher under individual rewards ($1.23{\pm}0.06$ vs.\ $1.07{\pm}0.20$). Masking unit type cuts the above-chance probe signal by more than half, to $0.49$ in both reward arms. In short: individually rewarded agents are competent and separable by role, but on SMACv2 the observation explains the geometry and reward attribution shows up mainly in behavior. Thus geometric diagnostics must control for observed role information and test persistent roles that are not directly observed. EffRank/$n$ and $D_\text{act}$ add $<$5% overhead.

Vision-Language-Action (VLA) policies offer strong general-purpose manipulation priors, but often fail on tight-tolerance, contact-rich assembly due to long-horizon credit assignment and subtask coupling: a state that is geometrically successful for the current skill can be brittle for downstream skills. We show this failure mode in residual reinforcement learning (RL) over a frozen VLA base policy: constant sparse success rewards improve each subtask in isolation yet yield little or no gain when skills are chained, because terminal state quality is uncontrolled. We propose Foresight Residual RL, which optimizes handoff quality by augmenting each subtask's sparse success reward with an offline-estimated foresight value – the probability of future subtask success conditioned on the terminal state of the current subtask. Concretely, we (i) train a visual foresight predictor from images of terminal states of the base policy, labeled using downstream rollout statistics, and (ii) train residual policies via backward foresight induction, using the predictor output as a reward multiplier. On a three-phase wrench-based nut-tightening assembly task in Isaac Gym (grasp, move-insert, rotate), our method achieves 85.6% full-task success, outperforming standard subtask residual RL (54.5%) and VLA baselines, while leaving per-subtask success unchanged. These results highlight that improving long-horizon performance requires shaping which successful states are produced at each sub-task, not only whether success occurs.

Multi-task deep learning models that jointly perform fault classification and remaining useful life (RUL) regression are increasingly used in predictive maintenance, yet reported performance can be strongly affected by how sliding-window sequences are split into training and test sets. We investigate this issue using AMTLNet, an attention-enhanced multi-task architecture, on three public benchmarks: NASA C-MAPSS, NASA IMS, and the UCI Hydraulic System dataset. We show that naive splitting can inflate classification accuracy from a genuine 20-60 percent to 99.9 percent, or reduce it to 0 percent through degenerate class representation. To address this, we introduce a chunk-based, leakage-audited splitting protocol and evaluate all models using five seeds, one-way ANOVA, and Tukey HSD tests. On C-MAPSS, with 19,976 leakage-free training windows, AMTLNet matches a single-task CNN-LSTM baseline in classification, achieving 84.12 +/- 0.96 percent accuracy with Tukey p = 1.0, and reaches an R2 of 0.86 +/- 0.01 while significantly outperforming a naive multi-task baseline. On the smaller Bearing and Hydraulic datasets, multi-task training is unstable, but the failure mode differs: classification degrades for Bearing, whereas regression degrades for Hydraulic. We relate this asymmetry to label provenance and propose a practical framework for deciding when joint training is appropriate under data scarcity. Ablation results show that the multi-head attention branch is the main contributor to regression stability. Removing it reduces R2 from 0.861 to 0.766 and more than doubles classification variance, whereas the convolutional branch contributes little to regression despite using about one-third of the parameters. This study contributes a reusable leakage-audit protocol, seed-transparent evaluation, and evidence that task-specific stability depends more on label provenance than on task type.

Oversampling is widely used to address class imbalance in tabular classification, but existing methods can distort the feature importance ranking underlying model explanations. Although recent studies have quantified this distortion by comparing real and synthetic data, none have actively sought to prevent it. In this paper, we introduce Kendall-constrained Importance-Preserving Oversampling (K-IPO), a generator-agnostic, "generate-then-select" framework that preserves the original data's feature importance ranking during augmentation. K-IPO iteratively generates minority-class candidates and accepts them only if their inclusion maintains a user-defined minimum Kendall's tau ({\tau}) correlation with the reference ranking. Optionally, stricter constraints can be applied to the highest-ranked features. We evaluated K-IPO on 20 imbalanced binary classification datasets using three classifiers and multiple explanation methods. In most cases, K-IPO achieved the best or tied-best results in feature importance preservation, explanation consistency, and class separability. It also generally improved predictive performance while maintaining competitive computational overhead.

Over the past decades, the frequency of global wildfires has been increasing steadily. Therefore, if the fire can be detected and precisely located at an early stage, the potential hazards caused by it can be minimized to the greatest extent. The machine learning methods based on satellite images, due to their ability to automatically monitor extremely remote and vast areas, have shown great potential for application in the field of wildfire detection. To address this challenge, we proposed a new model named spectral-morphological attention U-Net(SMA-UNet), which includes a spectral attention module, a residual attention UNet backbone, a channel-spatial modulator, and a pair of differentiable morphological gates. We trained and evaluated this model with two datasets. These modules, excluding the backbone, are used to detect active fire events for the first time, especially the pair of differentiable morphological gates, which is innovatively developed. The proposed model achieved the highest scores in both datasets (e.g., intersection over union 75.16% in TS-SatFire, 22.50% in Sen2Fire). By conducting ablation studies of each module, we compared their independent contributions and tested their combinations. Ultimately, the integration of these modules yields a highly robust framework that significantly improves segmentation consistency across diverse and complex environmental conditions. Future work will focus on validating the proposed architecture across large-scale, multi-regional datasets from different satellite sensors to establish its broader generalizability for global wildfire detection.

The increasing use of first-person-view drones in modern conflicts has created a demand for compact and reliable detection systems capable of operating in complex electromagnetic environments. These drones continuously transmit video signals through onboard video transmitters, generating radio-frequency emissions that can be exploited for early detection. This study investigates the use of lightweight convolutional neural networks for automated detection of drone signals captured by a software-defined radio-based electronic warfare framework. Samples are converted into rasterized time-domain images, providing a computationally efficient input representation suitable for embedded systems. Several custom model architectures were designed and benchmarked in terms of accuracy, model size, and inference performance using a dataset containing approximately 40,000 labeled images. In addition to offline testing, the models were integrated into a GNU Radio signal processing chain for real-time evaluation. The results show that compact models can achieve high detection accuracy while maintaining low computational requirements, making them suitable for embedded radio-frequency monitoring applications. Compared with existing spectrogram-based RF detection methods, the proposed approach eliminates frequency-domain preprocessing and achieves comparable accuracy with significantly reduced computational cost.

Accurate path loss prediction is a critical component of wireless network planning. Current path loss prediction methods typically struggle to balance the trade-off between accuracy and computational efficiency. This paper proposes the Efficient Attention Radio Map Estimation Network (EA-RMENet) which is an image data-driven, deep learning (DL) model designed for radio map estimation (RME). EA-RMENet uses a U-Net framework with an EfficientNetB5 encoder, Attention Gated (AG) skip connections, and Atrous Spatial Pyramid Pooling (ASPP). The EfficientNet encoder uses compound scaling to balance accuracy and efficiency. AG skip connections suppress irrelevant features, and the ASPP captures a multi-scale context. The model has a test prediction RMSE of 0.0334 on the RadioMapSeer3D dataset with an inference time of 0.022 seconds/sample. In the ICASSP 2023 Radio Map Prediction Challenge, the model ranks third with a competitive RMSE of 0.0406 this highlights the models potential for real-world RME.

Interpretability methods for neural network activations span a wide cost spectrum, from cheap, training-free techniques (such as linear probes, PCA, SVD) to more expensive training-based ones (such as SAEs and activation oracles). Training-based methods are typically more powerful, in part because they leverage large activation datasets during training. This raises a natural question - do they actually surface insights that go beyond what is recoverable from the training dataset itself? To address this, we equip an LLM agent with a vector database of activations paired with their textual contexts, along with tools for manipulating activations - projecting out directions in latent space, computing activation differences and averages. The agent iteratively queries the database, forms hypotheses from the retrieved samples, and validates them by constructing linear probes. We call this method HARP, for Hypothesis-driven Agentic Retrieval and Probing. Despite not involving any training, HARP outperforms both activation oracles and SAE-based agents on concept discovery, concept detection, model steering, and secret elicitation. The training-free design also makes HARP substantially cheaper and more flexible: new datasets can be indexed on demand whenever existing ones prove insufficient. More broadly, our results suggest that current training-based methods do not yet extract insights beyond their training data, and motivate benchmarks that explicitly require interpretability methods to demonstrate such insights. We release our code at https://github.com/SriramB-98/HARP

For a second time, the android robot Andrea was set up at a public museum in Germany for six consecutive days to have conversations with visitors, fully autonomously. Building on previously gathered qualitative results, the robot was now capable of engaging in multi-lingual conversation with the visitors about the museum context. The robot was prepared with context information about the museum in general and its surrounding exhibits this time. The robot featured a slightly artificial sounding voice that was previously evaluated as congruent with its gender-ambiguous but very humanlike design. Three experimental conditions were implemented, in which either (1) the robot simulated no emotions, (2) the robots emotions were determined by ChatGPT 4.1, or (3) the WASABI emotion simulation architecture simulated the robot's emotion dynamics. An extended version of the TAM2 questionnaire was employed to let 73 visitors report on several factors of their opinion about the android robot Andrea after having experienced it. In result, the statistical analysis suggests that these first two approaches to implementing emotions into the chat architecture of our android robot Andrea did not yield any positive effects on the subjective evaluations by the visitors and were not detectable on a conscious level.

Unified Multimodal Large Language Models (MLLMs) offer a promising paradigm for unifying visual understanding and generation, yet they still struggle to follow complex spatial instructions and logical constraints in controllable image generation. To address this gap, we present ATLAS, a unified framework that equips MLLMs with a human-like "Think, Plan, and Paint" paradigm. We adopt layout as the shared representation that connects the three stages, enabling the model to reason about spatial requirements, plan explicit object arrangements, and render the final image. We further improve plan-to-image fidelity with reinforcement-learning-based layout alignment. We instantiate ATLAS at 7B and 80B scales, achieving state-of-the-art performance among MLLMs on image generation benchmarks and an average 65.31% improvement over existing layout-based unified MLLMs. On spatially related tasks, ATLAS obtains an average 23.06% gain over the base models. Through the same layout interface, ATLAS also supports instruction-guided editing and multimodal grounding. We further introduce ATLAS-Reasoning, a benchmark for evaluating generation under complex spatial instructions.

For stochastic gradient descent (SGD) with a constant stepsize $\alpha$, the invariant law of the iterates, centered at a minimizer, describes the behavior of the algorithm over long time horizons. In the strongly convex case, this invariant law has the familiar $\sqrt{\alpha}$ scaling and a Gaussian limit as $\alpha\downarrow 0$. We show that this behavior changes fundamentally for convex objectives $H$ with flat minima and (sub)quadratic tails. More specifically, we study SGD with Markovian noise generated by a contractive driving chain. For every sufficiently small constant stepsize $\alpha$, we prove existence, uniqueness, and geometric convergence to an augmented invariant law in a Wasserstein distance induced by an $\alpha$-dependent metric. When the minimizer $x_\star$ has local flatness exponent $m\ge2$, meaning that $\nabla^2 H(x)\asymp \lVert x-x_\star\rVert^{m-2} I_d$ as $x\to x_\star$, we obtain a contraction bound with factor $1-c\alpha^{m-1}$, where $c>0$ is a constant. This recovers the factor $1-c\alpha$ in the quadratic case $m=2$. We then analyze the small-stepsize scaling limit. We show that the invariant law concentrates on the scale $\alpha^{1/m}$ and that the rescaled iterates converge weakly to the stationary distribution of the stochastic differential equation $$ dY_t=-h_0(Y_t)\,dt+\Sigma^{1/2}\,dB_t , $$ where $h_0$ is the limiting drift at the minimizer and $\Sigma$ denotes the asymptotic covariance. This recovers the Gaussian limit when $m=2$ and gives generally non-Gaussian stationary limits in the flat case $m>2$. Finally, we give corresponding results for coordinate-separable objectives with unequal flatness exponents.

Estimating the apparent age of individuals from facial images is challenging due to the subjective nature of perception and the inherent variability of the data. We investigate the role of uncertainty estimation, attributing uncertainty jointly to a lack of knowledge (epistemic) or inherent noise/chance (aleatoric). Leveraging the APPA-REAL dataset, we train Bayesian Neural Networks on datasets of varying sizes using three BNN approximations: MC-DropConnect, Flipout, and Deep Ensembles using supervision on human aleatoric uncertainty available in the APPA-REAL dataset. Each model outputs both the predicted apparent age and the amount of aleatoric and epistemic uncertainty. Our results confirm the hypothesis that the inherent aleatoric uncertainty remains stable across dataset sizes, while epistemic uncertainty increases as training data decreases. These findings demonstrate that different sources of uncertainty can be quantified in face age estimation.

Interactive theorem proving (ITP) underpins program verification and formalized mathematics, but its manual effort limits scalability. LLM-based proof agents promise to ease this effort, but their heavy token consumption and API cost remain a major obstacle. We trace this cost to a shared root: current agents operate on serialized concrete syntax, emitting proofs as source text and recovering proof states through separate, line-number-based queries, so every edit shifts later lines and forces repeated relocation of errors and states. This same dependence on concrete syntax also blocks adoption of Minilang, a recent proof language that reaches SOTA on LLM-based proving but is too new for LLMs' training corpora. We address both problems by lifting the agent off source text and onto the abstract syntax tree (AST): the model supplies proofs as JSON representations of Minilang's AST – native to tool-calling LLMs – and drives the prover through a tree-edit model that fuses proof operations and states into one proof tree, so each operation carries its own subgoal's state, readable directly off the tree. We realize this design in Agent over AST (AoA). Against Amazon's Isabelle Agent on miniF2F and NTP4VC-Pearl common success sets, AoA cuts API cost by 2.3–4.7x (normalized input-cache accounting), uses 2.9–6.9x fewer tokens and 3.9–8.9x fewer tool calls, and finishes 1.4–2.0x faster – while also solving far more problems on the harder verification benchmark.

A large body of Semi-supervised Learning~(SSL) algorithms encounter the threshold $\tau$ to select pseudo-labels. The value of $\tau$ across different SSL algorithms can vary depending on the learning perspective, yet they may achieve similar performance. It motivates us to establish a unified theoretical framework to explain the role of $\tau$ in SSL. We statistically explained that the unsupervised loss is affected independently by correct and incorrect pseudo-labels, while $\tau$ adjusts their numbers to balance the corresponding error term. This inherent trade-off indicates that SSL can reach the same loss with varying $\tau$, precise optimal values of $\tau$ during training may be unnecessary. With this, we treat $\tau$ as an updatable parameter and optimize it via differentiation; the new policy is named Meta-Thresholding Semi-Supervised Learning (MTSSL). Extensive experiments demonstrate the superior performance of MTSSL. We observe that the accuracy curves of SSL algorithms can overlap completely even when the values of $\tau$ differ significantly, which supports our theoretical framework and indicates that the selection of $\tau$ can be relaxed in the future design of SSL algorithms.

Retail demand forecasting remains difficult when demand shifts faster than static forecasting models can be retrained, especially in early demand cycles where newly observed labels are sparse. To address this, this study aims to improve adaptive retail forecasting by proposing a predict-then-correct (PtC) framework that retains a first-stage machine learning (ML) forecast and applies a few-shot continuous contextual bandit correction policy with similar-SKUs augmentation and top-p masked updating. Across Walmart retail data and an exclusive beverage dataset, PtC delivers statistically significant reductions in MAPE, MAE, and RMSE across stable & high volume, stable & low volume, and erratic & intermittent demand patterns, improves average RMSE by 9.52% over the ML-only baseline in the ablation study, and yields lower inventory costs than base-stock, proximal policy optimization, and soft actor-critic policies under the tested lead-time settings. These findings show that online forecast correction can bridge offline demand learning and real-time retail decision-making by adapting to sparse feedback without fully retraining the base forecasting model.

Sensor-based human activity recognition (HAR) has achieved significant progressed in fully supervised learning settings. However, these supervised learning models rely on large amount of labeled data, which require labor-intensive collection and meticulous annotation. To address these challenges, this paper proposes a Joint Embedding Predictive Architecture framework tailored for sensor-based HAR, designed to learn robust and generalizable representations from unlabeled datasets. The proposed framework features an encoder designed to explicitly model both the fine-grained local temporal representations within individual window and the long-term temporal sequence of adjacent windows. Furthermore, we introduce an improved Variance-Invariance-Covariance Regularization (VICReg) objective function that incorporates computationally lightweight norm term to stabilize the JEPA pre-training phase. This term balances variance, invariance and covariance constraints to prevent representation collapse. The proposed HAR-JEPA framework is evaluated using two benchmark continuously performed activity datasets. The results show that high-quality representations are successfully learned by the proposed framework. Furthermore, the representations learned by HAR-JEPA demonstrates superior generalization on minority, high variance transitional activities such as sit-to-stand and sit-to-lie where supervised learning tend to overfit due to limited support.

Machine learning-based intrusion detection systems (IDSs) often suffer from class imbalance and vulnerability to adversarial attacks, leading to degraded detection performance and reduced robustness. This study proposes a TabTransformer framework augmented by the Boundary-Seeking Generative Adversarial Network (BGAN) for flow-based intrusion detection using the CICIDS2017 dataset. BGAN serves a dual purpose by generating synthetic minority-class samples to mitigate data imbalance and producing adversarial samples to evaluate model robustness. Experimental results demonstrate that BGAN augmentation improves TabTransformer's Macro-F1 score from 82.96% to 86.50%, with the largest class-wise improvement observed for Web_Attack (F1 score: 0.29 to 0.61). Robustness evaluation shows that all non-augmented models experienced a 100% Performance Drop Rate (PDR) under adversarial testing, whereas all BGAN-augmented models achieved negative PDR values, indicating improved resilience. Furthermore, the augmented TabTransformer maintained stable and low False Triggered Rate (FTR) values (1.51%-2.92%) across all noise levels, compared with the BGAN-augmented Decision Tree, which reached 49.09% under benign perturbations. These findings demonstrate that BGAN consistently enhances both class balance and adversarial robustness, while the proposed BGAN-TabTransformer framework provides an effective and adaptive intrusion detection solution for adversarial network environments.

Mixture-of-Experts (MoE) is a popular class of large language models (LLMs), offering high efficiency and accuracy. However, in KV-cache-intensive serving scenarios, MoEs often exhibit a tension between the GPU memory requirements of the model weights and the growing KV cache. We propose PagedWeight, a novel management method for MoE LLM serving that dynamically quantizes MoE model's weights at runtime and balances expert-weight precision with the KV cache sizes. PagedWeight exposes and effectively navigates the complex tradeoff between the model's task accuracy, memory consumption, and throughput/latency. Across several memory-sensitive MoE serving scenarios, PagedWeight improves the quality-memory tradeoff over several existing quantization baselines. PagedWeight achieves FP16-equivalent accuracy with up to 72.0% GPU memory savings and 1.94$\times$ throughput improvement, and improves quality over quantization methods by up to 39.3% at a similar memory budget with at most 4.1% throughput loss.

To help address the escalating energy and latency demands of machine-learning workloads, we introduce a blueprint for an energy-efficient and fast thermodynamic computing stack that leverages stochastic analog processes in physical hardware. In this work, we focus on energy-based thermodynamic computing where the stochastic process is well described by Langevin dynamics with tunable energy potentials. The implementation of such potentials in physical hardware enables us to generate and sample from basic parameterized energy-based models. We demonstrate how to construct and train popular classes of machine learning models based on these hardware-native energy-based models, using the framework of probabilistic graphical models. We analyze the runtime and energy consumption of different models in this thermodynamic paradigm based on theoretical considerations and numerical studies. As a preliminary experimental realization of such hardware, we present our stochastic analog superconducting circuits driven by thermal noise. Together, these results outline a path toward energy-efficient thermodynamic hardware for probabilistic machine learning.

In many applications of matching, the point clouds to be matched are not merely unstructured sets of points but rather samples from distributions with an intrinsic cluster structure. In such cases, as individual points are often interchangeable within a coherent region, finding a robust region-to-region alignment is more desirable than establishing a precise point-to-point correspondence. To this end, we propose a novel approach for cluster-aware matching based on Laplacian Optimal Transport (LapOT). The key idea is to regularize the optimal transport problem with quadratic Laplacian terms constructed from similarity graphs of the point clouds, which encourages the optimal coupling to respect the cluster structure of both point sets. We also introduce Refined Simultaneous Clustering (RSC), a method that leverages the cluster-aware coupling obtained from LapOT to produce consistent partitions across the point sets, which can overcome the limitations of independent clustering and yield more stable and interpretable results. We demonstrate the effectiveness of our approach through theoretical analysis and empirical experiments, showing that LapOT indeed produces cluster-aware matching that leads to more consistent and meaningful alignments between point clouds.

Reinforcement learning (RL) has recently emerged as a promising feedback control strategy for nonlinear and complex dynamical systems. However, RL algorithms are sample inefficient and require a large number of interaction with the environment to synthesize optimal control strategies. Consequently, applications of RL are typically limited to sparse sensors and actuators due to the curse of dimensionality entailed by the exploration-exploitation dilemma in high-dimensional spaces. In this work, we bridge RL and traditional optimal control for dynamical system with a novel Physics-EnhAnced Reinforcement Learning (PEARL) paradigm tailored to the control of high-dimensional and parametric dynamical systems, exploiting the differentibility of their dynamics. Specifically, PEARL employs an actor-adjoint algorithm that leverages automatic differentiation to compute policy gradients over short horizons and adjoint-based sensitivities of future returns approximated via neural networks, significantly reducing the number of environment interactions, while mitigating long-term gradient instabilities. Through two challenging parametric navigation problems in unsteady flows, we show that PEARL (i) effectively exploits differentiable environments to outperform state-of-the-art RL algorithms, (ii) is sample efficient, thanks to the physics-guided policy learning, (iii) generalizes across multiple scenarios, which is crucial when dealing with parametric systems, and (iv) enables scaling RL to high-dimensional state and action spaces, without requiring low-dimensional state representations or multi-agent strategies.

Muon is competitive with AdamW in large-scale pre-training, but its operating regime in reinforcement-learning post-training remains unclear. We map this regime on ALFWorld, a sparse-reward agentic benchmark, using three group-based objectives and Qwen2.5 models from 0.5B to 3B. Under a shared KL and clipping recipe, matched optimizer comparisons and AdamW rate controls trace the usable step-size range. AdamW responds non-monotonically to rate, whereas fan-in Muon remains stable at a more aggressive effective step: at $3 \times 10^{-5}$ it improves late success over an AdamW $10^{-6}$ baseline after correction across rate-metric tests. Its normalized-AUC effect is directionally positive but less uniform; the heuristic-matched lower-rate effect is less consistent, and tuned AdamW nearly matches high-rate Muon at 3B GraphGPO. High-rate Muon applies $3.53 \times$ AdamW's hidden-matrix update RMS; a full-budget RMS-matched control removes the late-success gain. Together, these results identify a recipe-level operating regime in which fan-in Muon supports a more aggressive stable effective step under shared KL and clipping: the margin is largest when optimization headroom remains and contracts near saturation, after AdamW tuning, or under magnitude matching. The scale-matched control ties this spectral effect to Muon's scale convention rather than establishing a universal optimizer ranking. Code is available at https://github.com/x66ccff/verl-muon.