Machine Learning · Cross-listed from eess.SP
ReFLEX: Length-Generalizable CSI Denoising for MIMO-OFDM via Relative-Frequency Bias
Zhibin Zhang, Robert Potekhin, Ziwei Wan et al. (+2 more)
This letter studies CSI denoising for
MIMO–OFDM with variable NR resource block (RB) allocations. ReFLEX is a length-generalizable
Transformer whose frequency
attention uses a relative-frequency position bias (RFPB) generated from subcarrier offsets. A single checkpoint handles unseen RB lengths and can be applied to sparse DM-RS observations in the tested RB5/RB10 PUSCH setup without retraining. In a 3GPP~TR~38.901 UMa NLOS channel, ReFLEX achieves about $-9.6$~dB NMSE on unseen RB lengths. In NR PUSCH/UL-SCH simulations, ReFLEX denoising followed by time-frequency interpolation reduces the 10% BLER threshold by about 2–3~dB.
Read the full abstract ▾
All authors Zhibin Zhang, Robert Potekhin, Ziwei Wan, Vladimir Lyashev, Zhen Gao
Machine Learning
When Softmax Fails at the Top: Extreme Value Corrections for InfoNCE
Melihcan Erol, Suat Evren, Oktay Ozel et al. (+3 more)
InfoNCE is the standard contrastive learning objective, but its softmax form is not only a computational convenience: it also encodes a statistical assumption about how the top-scoring example is selected. Using extreme value theory, we show that this assumption is often misaligned with the normalized
embedding setting used in modern contrastive learning. Motivated by this mismatch, we propose WEINCE, a simple modification of InfoNCE that uses anchor-wise online batch statistics to blend the usual softmax logits with an endpoint shortfall correction, adding no trainable parameters. Across five
vision benchmarks, WEINCE yields consistent improvements in frozen-feature evaluation. These results show that a more faithful statistical treatment of hard negatives can improve contrastive objectives.
Read the full abstract ▾
All authors Melihcan Erol, Suat Evren, Oktay Ozel, Alexander Morgan, Jongha Jon Ryu, Lizhong Zheng
Machine Learning · Cross-listed from cs.CV
LastAct: Trajectory-Guided Latest-Activity Localization for Real-Time Smart-Home Activity Recognition
Zishuai Liu, Ruili Fang, Jin Lu et al. (+1 more)
Human Activity Recognition (HAR) from ambient sensors enables smart-home applications such as health monitoring and assisted living. In realistic deployments, however, sensor events arrive as a continuous stream and activity boundaries are unknown. Sliding-window inference therefore produces many windows that straddle transitions and contain mixed activities, creating boundary contamination that violates the pre-segmented instance assumption used by most
benchmarks and models. Moreover, many pipelines under-use spatial context by treating sensor IDs as independent
tokens. We present LastAct, a trajectory-centric framework for streaming smart-home HAR that targets the most recent activity under mixed windows while explicitly modeling spatial structure. LastAct projects sensor events onto the home floorplan to form a layout-aligned trajectory image sequence that preserves spatial continuity. A lightweight gate identifies contaminated windows, and a boundary localizer estimates the last transition to enable boundary-guided masking that emphasizes post-boundary evidence and suppresses stale context. For efficiency, we reuse a precomputed layout-aligned template cache to avoid repeated rendering. Empirically, across four public smart-home
datasets under near-realistic mixed-activity protocols, LastAct achieves competitive or superior performance on pure windows and yields substantial Macro-F1 gains on cross/mixed windows, demonstrating improved robustness under near-realistic sliding-window regimes.
Read the full abstract ▾
All authors Zishuai Liu, Ruili Fang, Jin Lu, Fei Dou
Machine Learning
ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate
Rodney Lafuente-Mercado
Token-level credit assignment for
language-model reinforcement learning is usually formulated as if the policy were fully trainable, while practical LLM-RL pipelines often rely on parameter-efficient fine-tuning, especially LoRA. We argue that this separation hides a structural failure mode. Under LoRA, the policy is restricted to a low-rank neighborhood of the reference model, so the per-
token output-distribution differences used by common intrinsic credit signals, surprisal,
entropy reduction, and policy divergence, can become degenerate after within-trajectory normalization, either approaching uniform weights or concentrating on a small set of task-agnostic positions. We formalize this behavior and propose measuring it directly with concentration diagnostics such as weight Gini and effective-
token ratio. We then introduce Adapter-Residual Credit Assignment (ARCA), a lightweight alternative that derives
token salience from the adapter's own hidden-state residual, $\|h^{\text{adapted}}_t - h^{\text{base}}_t\|_2$. ARCA asks where the adapter actually changes the model, rather than where the output distribution appears uncertain or shifted, and requires no learned reward model, value head, or tree construction. In a compact MATH/Qwen3-1.7B GRPO sweep, ARCA exhibits the predicted non-degenerate middle-regime credit distribution under matched rollout budgets and remains competitive with rank-matched baselines.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation
Pau Montagut Bofi, Mario García Blasco, Tessa Pulli et al. (+1 more)
Fine-tuning
Vision-
Language-Action (VLA) models for mobile manipulators with heterogeneous joint spaces can produce a counterintuitive result: the checkpoint with the lowest aggregate MSE is not the one that performs best on the real
robot. We argue this is a predictable consequence of collapsing heterogeneous joint groups (arm, gripper, head, wheeled base) into a single metric, where easy-to-predict joints can mask joints that still fail. We fine-tune SmolVLA (450M, action-expert only) on the 11-DoF Toyota HSR and compare it against $\pi_{0.5}$ (3.3B), a stronger pretrained baseline. Per-group analysis exposes two patterns: in SmolVLA, the mobile base converges slowest and limits overall performance. In expert-only fine-tuning of $\pi_{0.5}$ (training only the action head, backbone frozen), total MSE drops below the baseline but arm accuracy degrades. On 60 real-
robot trials (20 per model), $\pi_{0.5}$ 80k (4.0/4) significantly outperforms both fine-tuned variants (expert-only 3k: 3.75/4; HSR-SmolVLA: 3.5/4; Mann-Whitney $p \leq 0.010$), despite expert-only 3k having the lowest total MSE. This separation is most consistent with the offline arm-group error, not total MSE or base-group error. We conclude that per-group error is a more reliable signal than total MSE for checkpoint selection on
robots with heterogeneous action spaces. Code: https://github.com/paumontagut/per-group-mse-vla
Read the full abstract ▾
All authors Pau Montagut Bofi, Mario García Blasco, Tessa Pulli, Markus Vincze
Machine Learning · Cross-listed from cs.RO
HOIST: Humanoid Optimization with Imitation and Sample-efficient Tuning for Manipulating Suspended Loads
Songyang Liu, Shunyu Yao, Dingyuan Huang et al. (+1 more)
Manipulating suspended payloads with
humanoid robots is challenging because the
robot can only influence an underactuated, oscillatory load through whole-body motion and intermittent contact. Imitation learning provides safe initial behavior but does not directly optimize final placement, while reinforcement learning from scratch is unsafe and sample-inefficient on real
humanoids. We present HOIST-
Humanoid Optimized with Imitation and Sample-efficient Tuning for manipulating suspended loads. HOIST first finetunes a high-level
vision-
language-action (VLA) policy from virtual-reality (VR) teleoperation demonstrations and executes its commands through a whole-body controller. It then uses VLA rollouts and iterative batched RL to improve placement accuracy and stopping behavior. Experiments in simulation and on a real
humanoid show that HOIST improves over imitation-only and additional-demonstration baselines; compared with pure VLA rollouts, HOIST reduces translational placement error by 19.9 cm and raw angular error by 3.56 degrees, demonstrating the potential of
humanoids for underactuated material-handling tasks.
Read the full abstract ▾
All authors Songyang Liu, Shunyu Yao, Dingyuan Huang, Shuai Li
Machine Learning
InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate
Zhengyang Hu, Yanzhi Chen, Hanxiang Ren et al. (+5 more)
Measuring statistical dependency between high-dimensional random variables is a fundamental task in data science and machine learning. Neural mutual information (MI)
estimators offer a promising avenue, but they typically require costly iterative optimization for each new
dataset, making them impractical for real-time applications. We present InfoAtlas, a foundation model-like architecture that eliminates this bottleneck by directly inferring MI in a single forward pass. Pretrained on large-scale synthetic data with rich dependence patterns, InfoAtlas learns to identify diverse dependence structures and predict MI directly from the
dataset. Comprehensive experiments demonstrate that InfoAtlas matches state-of-the-art neural
estimators in accuracy while achieving $100\times$ speedup, can flexibly handle varying dimensions and sample sizes through a single unified model, and generalizes effectively to complex, real-world scenarios. By reformulating MI estimation as an inference task, InfoAtlas establishes a foundation for real-time dependency analysis.
Read the full abstract ▾
All authors Zhengyang Hu, Yanzhi Chen, Hanxiang Ren, Qunsong Zeng, Youyi Zheng, Adrian Weller, Kaibin Huang, Yanchao Yang
Machine Learning · Cross-listed from cs.AI
Self-Correction Can Amplify Hallucinations: Fact-Level Repair with Graph-Based Evidence Routing in Multimodal Generation
Kaixiang Zhao, Tianrun Yu, Shawn Huang et al. (+3 more)
We study fact-level repair for
multimodal generation, where a fluent output may contain specific facts that are not supported by the input. Existing inference-time repair methods often generate feedback by jointly conditioning on the input and the current output. This design has two limitations: hallucinated claims in the output can bias the model's interpretation of the input, and free-form feedback cannot be ranked or scheduled at the fact level. We present TIGER, an inference-time framework that redesigns feedback for localized repair. TIGER independently extracts an observation graph from the input and a claim graph from the current output, then assigns each claim a graph-conditioned risk score based on support and conflict. The model repairs selected high-risk claims while keeping the backbone frozen. We provide a convergence analysis showing that the expected total risk decreases geometrically to an explicit asymptotic bound under mild assumptions. Experiments across four cross-modal paths, including image-to-text, image+text-to-text, audio-to-text, and
video-to-text, show that TIGER reduces unsupported content while preserving task quality. The gains hold across multiple backbones, and a CrisisFACTS case study suggests that the same repair mechanism can improve grounding in multi-source settings.
Read the full abstract ▾
All authors Kaixiang Zhao, Tianrun Yu, Shawn Huang, Porter Jenkins, Yushun Dong, Amanda Hughes
Machine Learning
A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization
Sherin Muckatira, Namrata Shivagunde, Vijeta Deshpande et al. (+1 more)
Grokking, the phenomenon in which neural networks generalize long after fitting their training data, has been studied in supervised settings on many epochs. LLM pre-training instead involves next-
token prediction over an unlabeled corpus, with limited data repetition and no explicit train/validation split. To address this, we propose an exposure-based framework that enables the study of grokking-like dynamics during LLM pre-training. We ground our evaluation in BLiMP minimal pairs, which provide controlled grammatical contrasts. For every BLiMP minimal pair, we identify a critical phrase, the smallest continuous span that captures the grammatical contrast and the phenomenon-relevant context. Examples whose critical phrase appears in the pre-training window are assigned to the proxy-train split; the remaining examples are assigned to the proxy-validation split. Across five grammatical phenomena, we observe delayed generalization. Analyzing pre-training checkpoints before and after generalization shows that grammatical concept vectors become more predictive of grammatical acceptability and occupy a higher-dimensional subspace after generalization. We also find that
attention from the critical
token to the relevant context
token is concentrated in a small number of heads.
Read the full abstract ▾
All authors Sherin Muckatira, Namrata Shivagunde, Vijeta Deshpande, Anna Rumshisky
Machine Learning · Cross-listed from cs.RO
Yueh-Hua Wu, Tatsuya Matsushima and Kei Ota
Natural
language is a powerful
reasoning medium for
language and
vision-
language models, but it is mismatched to the granularity of continuous control. Text and explicit subgoals operate at task-level granularity, whereas
vision-
language-action (VLA) policies must choose actions at a much finer temporal scale; a single
reasoning step can therefore span many action chunks while remaining only weakly coupled to the action needed now. This suggests a different question for VLA: what should play the role of
language? We argue that a useful VLA
reasoning medium must be shareable across model instances, verifiable through downstream action improvement, and aligned with temporally extended control structure. Based on this view, we propose Continuous
Reasoning for
Vision-
Language-Action. Our model first predicts continuous
reasoning in the form of a structured set of continuous thoughts, then reuses them as shared context for chunk-structured action generation. Better action prediction alone does not certify good
reasoning: if the same internal medium cannot be shared across model instances and independently verified through improved downstream control, the added latent may simply become a model-private shortcut that helps on seen behaviors without supporting generalizable control. We therefore instantiate continuous
reasoning as a shared Gaussian latent interface and train it with a self-verification objective in which an exponential-moving-average teacher must successfully consume the student's
reasoning when predicting target actions. Empirically, Continuous
Reasoning improves LIBERO-PRO robustness and performs strongly on real
robots, raising mean subtask success over {\pi}0.5 by 40.4% on TX-G2, an AgiBot G2-compatible variant, and 26.3% on HSR. This suggests that
reasoning in VLA is less about extra
tokens than about a shareable, verifiable internal
language for action.
Read the full abstract ▾
Machine Learning
LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
Yao Lai, Xuyuan Xiong, Zeyue Xue et al. (+7 more)
In
semiconductor manufacturing, lithography projects
circuit layouts onto silicon wafers through an optical mask. As
circuit features shrink below the wavelength of light, optical diffraction causes the printed patterns to deviate from their intended layouts. Inverse Lithography Technology (ILT) addresses this challenge by generating optimized masks that enhance the fidelity of pattern transfer onto wafers. While ILT resembles an image synthesis task, its reliance on explicit physical metrics for mask evaluation limits the applicability of existing generative models. We introduce LithoGRPO, an ILT framework that integrates the flow-matching paradigm with GRPO-based reinforcement learning (RL) fine-tuning, enabling efficient exploration of diverse masks for a given target layout. Unlike purely generative or optimization-based approaches, RL in LithoGRPO exploits the explicitly defined, physics-based reward function of ILT, enabling optimization under complex, process-aware constraints. To the best of our knowledge, this is the first framework that unifies flow matching and RL for mask optimization. To improve RL sampling efficiency, we propose a fast shot-counting
algorithm for manufacturability evaluation, achieving over 130x speedup while preserving the mask ranking of the traditional shot-count metric. Extensive experiments demonstrate that LithoGRPO achieves state-of-the-art performance over both optimization-based and learning-based methods, while maintaining efficient mask generation.
Read the full abstract ▾
All authors Yao Lai, Xuyuan Xiong, Zeyue Xue, Guojin Chen, Jing Wang, Xihui Liu, Rui Zhang, Robert Mullins, Bei Yu, Ping Luo
Machine Learning · Cross-listed from astro-ph.CO
21cmEMUv3: a hybrid diffusion-LSTM emulator of 21cmFAST summary observables
Daniela Breitman, Andrei Mesinger, Steven G. Murray et al. (+2 more)
We are witnessing a surge in observations of the
cosmic dawn (CD) and epoch of reionisation (EoR), driving an increasing demand for fast and robust theoretical interpretation frameworks. In response, machine learning (ML), and emulation in particular, has emerged as a powerful approach to accelerate and enhance inference pipelines. In this work, we present 21cmEMUv3, an emulator trained on 21cmFASTv3 simulations that model both atomically and molecularly cooling
galaxies. 21cmEMUv3 is conditioned on $\sigma_8$ and ten astrophysical parameters to produce seven summary observables: (i) the cylindrical 21cm power spectrum (PS), emulated for the first time at such high resolution and accuracy across a wide
redshift range of $z \sim$ 6–30; (ii) the spherically-averaged 21cm PS; (iii) the mean neutral fraction of the intergalactic medium (IGM); (iv) the mean 21cm
spin temperature; (v) the global 21cm signal; (vi) the ultraviolet (UV) luminosity functions (LFs); and (vii) the Thomson scattering optical depth. Notably, the cylindrical 21cm PS is emulated via score-based
diffusion, while the remaining six summaries are emulated via long-short term
memory (LSTM) networks, all achieving sub-percent median accuracy. We use the emulator to reinterpret current 21cm PS upper limits from HERA, for the first time using state-of-the-art hydrodynamical simulations to inform priors on
star formation inside molecularly cooling
galaxies. We find that our inferred soft-band X-ray luminosity per unit
star formation rate is consistent with extrapolations of high-mass X-ray binaries to the low-
metallicity regimes expected in the first
galaxies, excluding values below $10^{39.2}$ erg s$^{-1}M^{-1}_\odot \rm{yr}$ at $95\%$ confidence. Finally, we produce forecasts for the detection of the
cosmic 21cm PS with the Square Kilometre Array for different array configurations. The 21cmEMU package is publicly available.
Read the full abstract ▾
All authors Daniela Breitman, Andrei Mesinger, Steven G. Murray, Ivan Nikolic, Roberto Trotta
Machine Learning
Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
Sanae Lotfi, Polina Kirichenko, Steven Li et al. (+1 more)
Post-training quantization (PTQ) is widely used to deploy large
language models efficiently, but its effect on
reasoning models is not well understood. Across math, coding, and science QA, we find that aggressive PTQ reduces accuracy while increasing chain-of-thought (CoT) length. Surprisingly, we show that in up to 52% of the quantized models' failures, models reach the right answer in intermediate
reasoning steps but do not output it as a final answer. To understand why quantization leads to this increase in overthinking errors, we measure the
token-level KL divergence between quantized and full-precision output distributions. Positions with high KL divergence correlate strongly with high next-
token entropy, and at these positions quantized models disproportionately sample overthinking markers such as "wait", "but", and "alternatively". We show that simply introducing a training-free logit penalty on a curated set of overthinking markers can reduce CoT length by 12–23% while preserving or improving accuracy across 5 models (1.5B-32B parameters), 3 quantization methods, and 5
benchmarks, yielding a favorable Pareto frontier of accuracy against
reasoning cost compared to penalizing other
token sets. Overthinking errors produced by quantized models are particularly reduced by up to 58%.
Read the full abstract ▾
All authors Sanae Lotfi, Polina Kirichenko, Steven Li, Zechun Liu
Machine Learning
From Rashomon Theory to PRAXIS: Efficient Decision Tree Rashomon Sets
Zakk Heile, Hayden McTavish, Varun Babbar et al. (+2 more)
Standard machine learning pipelines often admit many near-optimal models. These "Rashomon sets" pose a range of challenges and opportunities for uncertainty-aware, robust decision making. They allow users to incorporate domain knowledge and preferences that would otherwise be difficult to specify directly in an objective, and they quantify diversity among valid models for a given training
dataset and objective function. However, computation of Rashomon sets, even for simple, interpretable model classes such as sparse decision trees, continues to require immense
memory and runtime resources. We present PRAXIS, an
algorithm to approximate this Rashomon set with orders of magnitude improvement in runtime and
memory usage. We validate that PRAXIS regularly recovers almost all of the full Rashomon set. PRAXIS allows researchers and practitioners to scalably model the Rashomon set for real-world
datasets. Code for PRAXIS is available at https://github.com/zakk-h/PRAXIS
Read the full abstract ▾
All authors Zakk Heile, Hayden McTavish, Varun Babbar, Margo Seltzer, Cynthia Rudin
Machine Learning
BAGEN: Are LLM Agents Budget-Aware?
Yuxiang Lin, Zihan Wang, Mengyang Liu et al. (+9 more)
While
agents are increasingly spending more resources, today
agent cost is mostly measured only after execution. A Budget-Aware
Agent (BAGEN) should treat budget as an active control signal, rather than a passive cost metric. We first systematically define budget estimation as internal budgets (from
agent computation) and external budgets (from
agent actions). We then formalize budget-awareness as progressive interval estimation: at each step of a plan, an
agent should predict an upper and lower bound on remaining budget, and alert when completion is unlikely. Scoring with a rollout-replay protocol, we find consistent failure patterns on four environments and five frontier
agents: (1) strong
agents do not necessarily have strong budget-awareness, with correlation r=0.35. (2) frontier models are consistently over-optimistic, continue spending on tasks that are unlikely to succeed, instead of alerting the user early. (3) budget-aware signal is actionable and trainable. Early stop saves 28-64%
tokens on failed trajectories, and SFT+RL strengthens early stop and alert behavior. (4) precise interval calibration remains challenging, with interval coverage capping at 47% after SFT+RL. Project page: https://ragen-ai.github.io/bagen/
Read the full abstract ▾
All authors Yuxiang Lin, Zihan Wang, Mengyang Liu, Yuxuan Shan, Longju Bai, Junyao Zhang, Xing Jin, Boshan Chen, Jinyan Su, Xingyao Wang, Jiaxin Pei, Manling Li
Machine Learning
Learning to Construct Practical Agentic Systems
Aditya Kumar, Zhihan Lei, Jerry Yan et al. (+6 more)
Automated design and optimization of agentic LLM-based systems leads to sophisticated systems that substantially improve result quality over off-the-shelf agentic patterns. However, studies of fielded agentic systems show that production systems focus much more on issues such as simplicity, controllability, and predictability of inference costs. In this paper we propose principled approaches to designing and optimizing practical agentic systems. We describe an
agent framework that enables designers to enforce modularity in agentic systems, by defining "pseudo-tools" that call LLMs recursively on a restricted context. Using this framework we hand-engineer
agents for a diverse set of tasks, and show that relative to dynamically-planned workflows, hand-constructed fixed workflows are generally cheaper and more accurate. We then propose novel learning methods for the agentic components required by this framework, namely pseudo-tools and fixed workflows. These learning methods generally outperform hand-engineered
agents. We also exploit the modularity of the framework to apply multi-objective optimization methods to jointly optimize cost and response quality and blend the results of multiple learning systems.
Read the full abstract ▾
All authors Aditya Kumar, Zhihan Lei, Jerry Yan, Joshua W. Momo, Lauhitya Reddy, Rafael Enrique Cabrera Jimenez, Cassandra A. Cohen, Arthur Kajiyama, William W. Cohen
Machine Learning · Cross-listed from cs.GR
PaintBench: Deterministic Evaluation of Precise Visual Editing
Kai Xu, Ellis Brown, Shrikar Madhu et al. (+3 more)
While current
multimodal models are proficient at open-ended visual editing, executing precise single-answer edits remains an important obstacle. To probe this challenge, we introduce PaintBench, a dynamically scalable
benchmark targeting 20 fundamental precise visual editing operations across four categories:
geometric transformation, structural manipulation, color change, and symbolic
reasoning. Procedural generation with configurable complexity enables an effectively infinite, contamination-resistant evaluation suite, and deterministic pixel-level evaluation eliminates reliance on bias-prone judge models. Across 11 image editing models, we find overall low performance, with the current highest-performing industry leader scoring only 17.1% (mIoU). Task decomposition reveals especially challenging operation types (
geometric transformation, most structural manipulation, formula-based color change) and model-specific specializations. Fine-grained
benchmark diagnostics further show performance degradations induced by scene variations in object count, background complexity, color scheme, and edit-region size. To test generalization of PaintBench scores to applied task performance, we create a procedural, deterministic evaluation for data visualization editing (TinyGrafixBench) and find strong linear correlation with PaintBench scores ($R^2 = 0.91$, $p < 0.001$). Altogether, PaintBench provides a rigorous foundation for measuring and driving progress in precise
multimodal visual editing.
Read the full abstract ▾
All authors Kai Xu, Ellis Brown, Shrikar Madhu, Rob Fergus, He He, Saining Xie
Machine Learning
AI-Guided Design and Optimization of Graphite-Based Anodes via Iterative Experimental Feedback
Qian Du, Mark M. Sullivan, James E. Saal et al. (+1 more)
This study presents an iterative AI-guided workflow that accelerates graphite-based anode development by improving both formulation feasibility and process robustness. Sequential learning via AI/ML-guided multiobjective inverse design for anode optimization was implemented using the Citrine Platform. Starting from a noisy, incomplete
dataset, the Citrine Platform was used to generate early surrogate models, which despite low predictive certainty highlighted missing process constraints. By iteratively adding feasibility labels and boundary condition failures, the workflow rapidly converged toward manufacturable, higher-performing formulations. Fabrication reliability improved from frequent process failures to 100% successful
cell production, while the fraction of
cells delivering $\geq$ 350 mAh g$^{-1}$ increased from 28.4% to 84.8%, with capacity retention rising from 42.1% to 97.3%. These results demonstrate that structured, feedback-driven AI workflows can transform imperfect industrial data into actionable guidance, enabling faster, more reproducible optimization of battery electrode manufacturing.
Read the full abstract ▾
All authors Qian Du, Mark M. Sullivan, James E. Saal, Florian Huber
Machine Learning
Agentic Transformers Provably Learn to Search via Reinforcement Learning
Tong Yang, Yu Huang, Yingbin Liang et al. (+1 more)
Tree search is a central abstraction behind many
language-
agent reasoning and decision-making tasks:
agents must explore actions, remember failures, and backtrack toward promising alternatives. Yet, we lack a theoretical understanding of how
transformer-based policies acquire such search capabilities from the training dynamics of reinforcement learning (RL). We study this question in a
stochastic $k$-ary tree environment, where an agentic
transformer observes only its trajectory history through interaction and receives a terminal reward for reaching a hidden leaf goal node. We first construct a two-head
transformer that implements randomized depth-first search (DFS): one head tracks previous actions, while the other detects failure outcomes and triggers backtracking. We then analyze the training dynamics of policy gradient under a depth-wise curriculum, showing that this same DFS mechanism emerges in stages from sparse reinforcement feedback without expert demonstrations. The resulting policy exhibits depth generalization: after training only on depth-$1$ and depth-$2$ trees, it succeeds on deeper full trees. We further show that, under imbalanced goal distributions, discounting the return leads to a ranked DFS policy that prioritizes higher-probability branches. Overall, our results identify a mechanistic normal form for
transformer-based search, in which
attention heads specialize and cooperate to extract decision-relevant traces from context and convert them into agentic action selection via RL training.
Read the full abstract ▾
All authors Tong Yang, Yu Huang, Yingbin Liang, Yuejie Chi
Machine Learning
Beyond Augmentation: Score-Guided Pathological Prior for EEG-based Depression Detection
Xiaojing Chen, Jingqi Cheng, Xu Zhao et al. (+2 more)
Deep learning-based Major Depressive Disorder (MDD) detection using Electroencephalography (
EEG) is fundamentally constrained by the "small-sample dilemma." Prevailing generative data augmentation methods not only incur heavy computational overhead but also risk introducing synthetic noise, thereby blurring classification boundaries. To challenge the traditional "data quantity first" convention, we propose a novel framework "Beyond Augmentation": Score-Guided Classification (SGC). SGC does not synthesize pseudo-samples; instead, it utilizes an unsupervised generative network architecture to model the structural and statistical anomaly degrees of samples, serving as the core "Pathological Prior". This prior, after robust normalization, is explicitly fused with deep feature representations, thereby precisely guiding the classifier's decision boundary. Furthermore, to dynamically adapt to varying channel configurations, we propose a Cross-Channel Spatial Adaptation module, utilizing a spatial mapping mechanism to effectively resolve the hardware heterogeneity of mismatched channels in multi-center
datasets. Extensive experiments on the Mumtaz2016 and high-density MODMA
datasets demonstrate the effectiveness and exceptional generalizability of our method under the challenging "zero data augmentation" setting and at "zero sample synthesis cost". Keywords: Electroencephalography (
EEG), Depression Detection, Anomaly Score,
Diffusion Models, Few-Shot Learning
Read the full abstract ▾
All authors Xiaojing Chen, Jingqi Cheng, Xu Zhao, Wan Jiang, Jingjing Wu
Machine Learning
ChurnNet: A Optimized Modern AI for Churn Prediction
Syed Saad Saif, Giulio Maggiore, Paolo Russo et al. (+1 more)
Increased competition and the growing similarity of products and services offered by retailers have lowered the barriers for customers to switch to competitors. Accurate churn prediction can be a valuable tool for driving effective personalized marketing campaigns and helping to reduce customer attrition. This study evaluates the performance of traditional machine learning techniques, namely, Random Forests, XGBoost, and Support Vector Machines, and compares them with the Unified Multi-Task Time Series Model for churn prediction, a binary time-series classification task. Despite the strong capacity of the latter to model complex temporal dynamics and inter-variable relationships, our results indicate that for churn prediction, conventional methods can still outperform it in terms of predictive performance, data efficiency, and computational resource requirements for training and deployment. These findings are consistent across multiple
datasets and various churn labeling techniques.
Read the full abstract ▾
All authors Syed Saad Saif, Giulio Maggiore, Paolo Russo, Damiano Distante
Machine Learning · Cross-listed from cs.RO
Modeling Robotics Dataset Construction as an Artifact-Based Build Process
Leon Pohl, Lukas Beer, George Sebastian et al. (+1 more)
Robotic systems generate large volumes of
multimodal sensor data, but converting ROS bag recordings into machine learning
datasets is often handled by ad hoc sequential scripts, creating engineering overhead and slow iteration cycles. We model
dataset construction as an artifact-based build process over a dependency graph and implement this approach in Bagzel, an open-source Bazel extension for reproducible, incremental
dataset generation (including nuScenes-format export). We compare Bagzel and Bagzel-xattr (server-side digest management) against a sequential rosbag2nuscenes baseline. Bagzel reduces runtime in all evaluated execution modes, with the largest gains in iterative workflows (up to 386.26x in warm builds and 7.21x in incremental builds on a 20.4 GB
dataset). Across
dataset sizes from 5.1 to 20.4 GB, Bagzel variants show markedly better scaling behavior than the baseline, especially in warm and incremental modes. Bagzel-xattr provides additional gains, with a mean runtime reduction of 5.9% compared to Bagzel in the input granularity study. Overall, modeling robotics
dataset construction as an artifact-based build process substantially reduces
dataset update latency while maintaining a deterministic build design that supports reproducibility.
Read the full abstract ▾
All authors Leon Pohl, Lukas Beer, George Sebastian, Mirko Maehlisch
Machine Learning · Cross-listed from cs.CR
Improving IoT Intrusion Detection Through SMOTE-Based Oversampling and Extended Multi-Model Evaluation on Side-Channel Power Data
Muhammad Khuram Shahzad, Haseeb Khan, Muhammad Masood Khan et al. (+1 more)
The detection of intrusions in IoT-based networks poses challenges that cannot be overcome using traditional machine learning methods. Perhaps the biggest of them is related to the presence of a class imbalance in the side-channel
dataset, where the number of samples in the normal class compared to the attacks can reach a ratio of 75,964 to 1. Such an aspect is addressed by Dominguez et al. through the proof of concept of power-based intrusion detection. Unfortunately, neither the authors attempt to cope with the problem of imbalance nor do they assess the classifier performance using a balanced training set. In the current paper, both aspects will be handled at once. First, a Synthetic Minority Oversampling Technique (SMOTE) was performed on all nine possible
datasets extracted from the initial one, providing an exact imbalance ratio of 1.1 for each. Then, eight
algorithms i.e. Random Forest, HistGradientBoosting, LightGBM, Extra Trees, XGBoost, k-Nearest Neighbors, Multi-Layer Perceptron, and Decision Tree were trained under identical conditions for the SMOTE balanced 6-hour
dataset. Random Forest reached a micro-averaged F1 score of 0.9989 and macro F1 of 0.9794, thus outperforming the previously best micro-F1 result obtained by Time Series Forest
algorithm from the base paper of 0.9983. Extra Trees provided the same performance as well, but at 10 times faster. The introduction of a macro-F1 metric explicitly in contrast to the base paper assessment reveals important class-level information missed with aggregate performance metrics. Recall rates per-class calculated with confusion
matrices, F1 heatmaps, and ROC curves show that minority attack classes, especially those with combined M+L infections, are detected reliably only when using SMOTE balance. Feature importance analysis indicates the latest time steps as the most important predictor signals out of 60 steps in a power window.
Read the full abstract ▾
All authors Muhammad Khuram Shahzad, Haseeb Khan, Muhammad Masood Khan, Mubashra Bibi
Machine Learning · Cross-listed from stat.ML
Interpreting FCDNNs via RG on Exponential Family
Fuzhou Gong and Zigeng Xia
We consider establishing the interpretability theory of deep learning through constructing a corresponding relationship between the renormalization group (RG) method in statistical physics and the training process of deep neural networks (DNNs). We have proved the constructed relationship using the one-dimensional Ising model as the input data. In this paper we generalize our results to the case of continuous input data, which is a necessary preparation for applying the corresponding framework to real-world data. To be representative, we consider a class of data distribution in the exponential family. We prove that when the parameters of fully connected (FC) DNNs achieve their optimal value after training, the characteristic parameters of the feature layer output of DNNs are equal to the fixed points of the characteristic parameters of input data under RG method for continuous fields. This conclusion shows that the training process of DNNs is equivalent to RG calculation on this kind of data and therefore the network can extract main features from the input data just like RG. Also, the equivalence further validates the correspondence framework we have established, providing an explanation for the outstanding performance of DNNs on real-world data.
Read the full abstract ▾
Machine Learning
Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
Soichiro Nishimori, Paavo Parmas, Sotetsu Koyamada et al. (+4 more)
In reinforcement learning (RL),
agents benefit from exploration only because they repeatedly encounter similar states: trying different actions can improve performance or reduce uncertainty; without such retries, a greedy policy is optimal. We formalize this intuition with ReMax, an objective that evaluates a policy by the expected maximum return over $M$ samples, where $M$ is a positive integer, while accounting for return uncertainty. Optimizing this objective induces
stochastic exploration as an emergent property, without explicit bonus terms. For efficient policy optimization, we derive a new policy-gradient formulation for ReMax and introduce ReMax PPO (RePPO), a PPO variant that optimizes ReMax while generalizing the discrete retry count $M$ to a continuous parameter $m > 0$, enabling fine-grained control of exploration. Empirically, RePPO promotes exploration, without any explicit exploration bonuses, on the MinAtar and Craftax
benchmarks. The code is available at https://github.com/nissymori/remax-rl .
Read the full abstract ▾
All authors Soichiro Nishimori, Paavo Parmas, Sotetsu Koyamada, Tadashi Kozuno, Toshinori Kitamura, Shin Ishii, Yutaka Matsuo
Machine Learning
RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting
Yuduo Li, Xiaofeng Shi, Qian Kou et al. (+2 more)
Domain-specific supervised fine-tuning (SFT) often improves in-domain performance at the cost of degrading a model's general capabilities. We view this degradation through two practical gaps in domain SFT: a supervision-compatibility gap, where domain targets differ in style and
reasoning format from the original model's natural responses, and a trajectory-preservation gap, where teacher-forced SFT optimizes fixed target
tokens without constraining the model's behavior on its own generated prefixes. This process fails to preserve the model's original behavior. We propose RAFT (Data Refinement and Adaptive
Distillation for Domain Fine-Tuning with Alleviated Forgetting), a two-stage framework that addresses both factors. First, RAFT constructs model-compatible supervision through self-conditioned rewriting, semantic filtering, and answer fusion. Second, RAFT performs Answer-Conditioned On-Policy
Distillation, where the original instruction-tuned model provides soft targets on student-generated trajectories while being conditioned on the fused answer as helpful context. We further introduce top-K temperature
distillation and EMA-based adaptive loss balancing to stabilize the domain-general trade-off. Across three instruction-tuned backbones and five domains, RAFT improves average domain accuracy by 23.2% over standard SFT, while recovering part of the SFT-induced degradation on MS-Bench and IFEval, with relative improvements of 18.2% and 10.2%, respectively. These results show that coupling data refinement with trajectory-level preservation provides an effective recipe for domain fine-tuning with alleviated forgetting.
Read the full abstract ▾
All authors Yuduo Li, Xiaofeng Shi, Qian Kou, Longbin Yu, Hua Zhou
Machine Learning
BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding
Liang He, Jingbo Wen, Qishi Zhan et al. (+4 more)
Speculative decoding speeds up autoregressive decoding by using a drafter to propose multiple
tokens that a verifier validates in parallel. In resource-constrained deployments, the drafter uses a sparse KV cache to limit peak GPU
memory and end-to-end latency under a fixed KV budget, while the verifier keeps a full KV cache. Mid-to-long context inference (4K–16K context length) is common in real applications. However, naive sparse/full speculative decoding suffers from the sparse/full mismatch as context length grows, causing the acceptance rate to drop quickly. We propose BudgetDraft, a multi-view sparse training method for sparse drafting in mid-to-long inference. The drafter is exposed to multiple sampled KV budgets during training and learns to align each sparse view with one shared full-cache teacher target. BudgetDraft combines an acceptance-aware loss on a full-cache branch with a multi-view loss on a sparse-cache branch, producing a single budget-robust drafter that recovers acceptance across sparsity levels without extra inference-time components. Experimental results on PG-19, LongBench, and LWM show that BudgetDraft achieves up to 6.55x, 4.46x, and 2.10x end-to-end speedup vs AR at 4K, 8K, and 16K context lengths, while keeping the inference pipeline
memory-friendly.
Read the full abstract ▾
All authors Liang He, Jingbo Wen, Qishi Zhan, Yixiong Chen, Kangning Cui, Qizhen Lan, Xilu Wang
Machine Learning
Adaptive data selection improves wearable prediction under low baseline performance
Ali Kargarandehkordi
Adaptive sensing strategies that selectively sample data are increasingly used in wearable health systems to improve prediction performance under limited data budgets, yet their benefits across individuals remain poorly understood. Here, we evaluate adaptive selection of time windows for model training under fixed measurement budgets across multiple sensing modalities, including heart rate, activity, and ecological momentary assessment (EMA), in a longitudinal wearable
dataset. We quantify performance gains relative to random sampling using both area under the receiver operating characteristic curve (AUROC) and F1 score. Adaptive strategies yield substantial improvements in AUROC for participants with low baseline performance (with gains up to 0.7), while offering limited or negative gains for participants with strong baselines. Across modalities, adaptive gain is strongly inversely correlated with baseline performance (Pearson r = -0.67; Spearman p = -0.62). At the participant level, most individuals benefit in AUROC (60-80% across modalities), although improvements in F1 are smaller and less consistent. These findings show that adaptive sensing is not uniformly beneficial, but instead provides the greatest value in underperforming settings. Our results support selective deployment strategies that tailor adaptive sensing based on baseline performance to improve efficiency in wearable health monitoring.
Read the full abstract ▾
Machine Learning
GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
Jonas Henry Grebe, Tobias Braun, Anna Rohrbach et al. (+1 more)
While the rapid adoption of
multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and copyright infringements. To address these challenges, concept erasure has emerged as a prospective safeguard. However, as the field gradually transitions from U-Net-based
diffusion models to Rectified Flow
Transformers, erasure research has struggled to keep pace. In this work, we introduce GEM, a simple but highly effective erasure framework for Rectified Flow models. As part of our contribution, we establish a principled bridge between trajectory-based unlearning grounded in Generative Flow Networks and classic teacher-guided erasure: we translate trajectory-based signals into a teacher-guided flow-matching setup that unifies the strengths of both paradigms. Concretely, a teacher provides complementary attraction and repulsion signals that we combine into a single
geometric guidance objective, yielding targeted suppression of unwanted concepts while preserving benign generation. Our code is available at https://github.com/
multimodal-ai-lab/GEM.
Read the full abstract ▾
All authors Jonas Henry Grebe, Tobias Braun, Anna Rohrbach, Marcus Rohrbach
Machine Learning · Cross-listed from cs.CV
KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems
Alireza Kheirandish, Jihoon Hong and Sara Fridovich-Keil
Diffusion models have shown promising performance as data-driven priors for computational imaging, as well as some capacity to detect out-of-distribution (OOD) images. However, existing approaches to OOD detection often require some knowledge of the shifted distribution, fail to detect subtle or localized distribution shifts, and operate on full images, rather than the indirect measurements available in inverse problems. We propose an OOD detection metric based on the Kullback-Leibler divergence between the
diffusion prior and the posterior distribution, that (i) does not require any calibration data or knowledge of the shifted distribution, and (ii) can detect whole images as OOD as well as localize OOD patches within an image. Experimentally, we show that this metric can detect subtle yet semantically meaningful distribution shifts, such as the shift from healthy liver CT scans to those with tumors, and generalizes across different types of
diffusion models,
datasets, and inverse problems. Our code can be found at https://github.com/voilalab/KLIP.
Read the full abstract ▾