Machine Learning
Multi-Label Topic Assignment via LLM Distillation: A Comparative Analysis of Generative vs. Discriminative Student Models
Sourabh Kasliwal and Shubhranshu Singh
Multi-label topic assignment for user-generated content (UGC) – including product reviews and buyer-seller conversations – poses unique scalability challenges in large-scale e-commerce due to informal
language, extreme label sparsity, and rapidly evolving taxonomies. While utilizing Large
Language Models (LLMs) as labeling oracles to distill ground-truth data has emerged as an industry standard to bypass prohibitive manual annotation costs, determining the optimal, low-latency architecture for the resulting student models remains an open challenge. To address this, we conduct a comprehensive evaluation across Small
Language Model (SLM) parameter scales (1B, 4B, and 8B) and architectural paradigms (causal generative versus bidirectional discriminative). Comparing generative text-to-label classifiers against discriminative baselines (DeBERTa-V3 and ModernBERT), our analysis reveals a crucial data-dependent trade-off: while discriminative models outperform ultra-lightweight generative models on structured product reviews, even the smallest 1B generative model surpasses discriminative baselines on complex, multi-turn conversational data. Furthermore, generative models maintain robust performance under massive label-set expansion (up to 112 topics) and severe long-tail distributions, whereas discriminative baselines suffer a 35% drop in Macro-F1 at scale. Finally, we detail the successful production deployment of these optimized models across both product review and conversational domains, demonstrating strict latency compliance and tangible business impact at a global marketplace scale.
Read the full abstract ▾
Machine Learning
EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks
Sai Karthik Navuluru, Siddhartha Shankar Das, Franck Dernoncourt et al. (+7 more)
Sparse GNN training reduces computation, but deciding which edges to keep can be costly. Reusing one sparse graph is cheap, but locks training to a fixed
topology, while varying it across epochs can require repeated sampling or recomputation. We introduce EDiS (Edge-Disjoint Subgraph sparsification framework), which separates one-time structural extraction from per-epoch graph composition. EDiS decomposes the graph once into cacheable edge-disjoint subgraphs, then recombines them into graphs with edge-budget constraints across epochs and retention ratios without re-extracting structure. Our default construction uses feature-based scores and successive maximum score covering forests, while the same composition mechanism also supports alternative edge selection rules. We provide a combinatorial analysis of the per-epoch sampler, the composition step that draws a training graph from the cached decomposition. We show that, under the default covering-forest selector, the stored decomposition deterministically preserves high-score cut edges, and we derive a selector-agnostic conditional bound on high-score cut survival in composed training graphs. Across 19 homophilic, heterophilic, and large-scale node classification
benchmarks against 17 baselines under the same edge budget, EDiS achieves the highest mean
benchmark score (accuracy/ROC-AUC) and the lowest average rank and gap-to-best among ranked methods. Ablations show the clearest benefits of structural decomposition and epoch variation at tight edge budgets.
Read the full abstract ▾
All authors Sai Karthik Navuluru, Siddhartha Shankar Das, Franck Dernoncourt, S M Ferdous, Ryan A. Rossi, Nesreen K. Ahmed, Baris Coskunuzer, Alex Pothen, Lakshman Tamil, Mahantesh M Halappanavar
Machine Learning
Learning Cross-Model Activation Alignments with Explicit Many-to-Many Layer Maps
Alina Sudakov, Guy Bar-Shalom, Fabrizio Frasca et al. (+1 more)
LLMs are released at a rapid pace, raising a natural question: how do two independently trained models relate, both in which layers correspond and in how features transform between them? We study this by learning an activation
alignment, a map from a source model's layerwise activations to a target's. Our method, MATCHA, factors this map into a layer map, whose output is an explicit target-by-source
matrix that can be extracted and inspected, and a layer-shared feature map between hidden spaces. Most of prior work fixes the layer correspondence in advance, pairing layers at roughly the same relative depth; in contrast, we learn both factors jointly from
prompts. Across 42 pairs of seven models spanning three different families, MATCHA reconstructs the target's activations more faithfully and improves
retrieval-based metrics substantially, w.r.t. previous approaches. The recovered maps are broadly monotone in depth but, in contrast with most previous approaches, are consistently many-to-many: each target layer draws on a band of source layers. Our
alignments also enable transfer of activation-space interventions, allowing steering vectors and probes developed for one model to transfer to another.
Read the full abstract ▾
All authors Alina Sudakov, Guy Bar-Shalom, Fabrizio Frasca, Haggai Maron
Machine Learning
A Geometry-Based Capacity Theory for Finite-Feature Associative Memory
Jianhai Zhang, Donghao Zhang, Pattarawut Charatpangoon et al. (+4 more)
We develop a geometry-based capacity theory for exact-key
retrieval in compressed finite-feature Hebbian associative
memory. For random or approximately isotropic values,
retrieval interference separates into finite-feature noise, which decreases with feature dimension, and structural interference, which is determined by squared kernel overlap among stored keys and persists in the infinite-feature limit. This yields a fit-free prediction of
retrieval quality, reveals a geometry-dependent capacity ceiling, and predicts the feature budget required for a target
retrieval quality. When stored values are correlated, we show that
retrieval depends jointly on the key kernel and value Gram
matrix, and derive finite-feature approximations that account for this interaction. We validate the theory on synthetic, visual, and medical-image representations. Overall, the framework links representation geometry directly to
memory capacity and distinguishes when performance can be improved by increasing the feature budget and when the representation itself must be changed. Across these settings, the predicted
retrieval curves closely match empirical behavior and correctly identify changes in the preferred
memory design.
Read the full abstract ▾
All authors Jianhai Zhang, Donghao Zhang, Pattarawut Charatpangoon, Bijoy Menon, M. Ethan MacDonald, Wu Qiu, Aravind Ganesh
Machine Learning
BeatFlow-ECG: Rectified Flow for ECG Reconstruction from Indirect Wearable Signals
Mohamed Kamel, Sahar Selim, Walaa Medhat et al. (+1 more)
Continuous cardiac monitoring outside clinical settings requires signals that are both informative and practical to collect during daily life. Electrocardiography (ECG) provides rich information about cardiac rhythm and waveform morphology, while wearable photoplethysmography (PPG) is easier to acquire continuously but is only an indirect cardiovascular measurement and is highly sensitive to motion. We present BeatFlow-ECG, a conditional rectified-flow model for reconstructing single-channel ECG from synchronized PPG and inertial measurements. BeatFlow-ECG models reconstruction as conditional transport from noise to ECG using a convolutional encoder-decoder with a
transformer bottleneck and explicit flow-time conditioning. Motion information is incorporated through IMU-derived conditioning features, motion-dependent loss weighting, and an easy-to-hard training curriculum. We evaluate the model under leave-one-subject-out protocols on PPG-DaLiA and WESAD. BeatFlow-ECG achieves the best results among the evaluated deterministic,
adversarial, and
diffusion-based baselines across all reported waveform and beat-timing metrics, with Pearson correlations of 0.983 and 0.986 and R-peak F1 scores of 0.946 and 0.955, respectively. Compared with Conditional DDPM-1D, L1 error decreases from 0.085 to 0.062 on PPG-DaLiA and from 0.074 to 0.055 on WESAD. Additional analyses on PPG-DaLiA show higher correlation in fixed R-peak-relative waveform regions and lower reconstruction error across low-, medium-, and high-motion subsets.
Read the full abstract ▾
All authors Mohamed Kamel, Sahar Selim, Walaa Medhat, Tamer Nadeem
Machine Learning
Davis Wertheimer, Haochen Shen, Ahan Gupta et al. (+6 more)
The large KV-cache size of modern LLMs creates a barrier to efficient deployment. Recent work has explored replacing
attention layers' RoPE positional
embeddings with alternative decay-based mechanisms, which can then be used to prune KV-cache during inference. However, these decay functions have limited expressivity, and in practice devolve into sliding-window-like eviction patterns. In this work, we propose a unifying framework for complementary and novel decay mechanisms, capturing complex key statistics and interactions while preserving expressive RoPE
embeddings and Softmax
attention. The resulting Universal
Attention is a highly expressive and end-to-end trainable architecture, whose composite decay mechanism acts as a natural, $\textit{adaptive}$
pruning criterion, removing
tokens that contribute least to
attention computation. Experimentally, Universal
Attention achieves state-of-the-art $10\times$ compression on natural
language and synthetic task data, while $\textit{improving}$ downstream performance compared to both state-of-the-art baselines and unpruned oracles. It further demonstrates superior long-context generalization with unprecedented $25\times$ compression at length 16k.
Read the full abstract ▾
All authors Davis Wertheimer, Haochen Shen, Ahan Gupta, Derrick Liu, Yu Chin Fabian Lim, Mudhakar Srivatsa, Raghu K. Ganti, Minjia Zhang, Naigang Wang
Machine Learning
Towards Financial World Modeling
Humzah Merchant, Alec Guthrie, Simon Mahns et al. (+2 more)
Building a world model requires a state representation useful for planning and decision-making—potentially over tasks unknown at training time. In the context of financial
markets, planning and decision-making may require a model to reason about
market-wide conditions, asset-specific expected returns, liquidity,
volatility, and cross-asset relationships. Yet financial representation learning has largely been evaluated on individual predictive tasks, oftentimes on a single time period using comparatively narrow
datasets. We address this through three primary contributions. First, we introduce
Market-1T, a
dataset containing nearly one trillion observations across U.S. equities from 2008 to 2025 at 1 Hz resolution. Second, we develop and implement a rigorous evaluation protocol. Third, we conduct a systematic large-scale study of financial representation learning, comparing 18 encoder-training strategies across nearly two decades of
market regimes. We evaluate learned representations both by their predictive utility on common finance tasks and through probes of latent structure. We find that encoders with similar predictive performance can organize
market state very differently. Collectively, we establish a foundation for training and evaluating financial
market representations in support of world models such as DINO-WM, V-JEPA 2, and LeWM.
Read the full abstract ▾
All authors Humzah Merchant, Alec Guthrie, Simon Mahns, Randall Balestriero, Bradford Levy
Machine Learning · Cross-listed from stat.ML
Learning Transition Kernels of Jump-Diffusion Processes with Conditional Diffusion Models
Yuzhen Zhao, Yating Liu and Quentin Guibert
We study the problem of learning transition kernels for time-homogeneous jump-
diffusion processes using conditional
diffusion models, with the goal of generating new sample paths from training data consisting of N independent trajectories observed on a high-frequency discrete time grid. On the theoretical side, we establish non-asymptotic bounds for the conditional score estimation error and for the KL divergence between the laws of the true and generated discretely observed paths. On the numerical side, we first evaluate our method on synthetic data to assess the theoretical findings and
benchmark its performance against the approach of Gao et al. (2025). We then apply our method to real-world data and investigate its performance on a probabilistic forecasting task.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Quadratic Weak-to-Strong Generalization in Random Feature Networks via Random Matrix Theory
Deborah Oliveira and Elliot Paquette
Weak-to-strong generalization is the phenomenon where a strong student model trained with labels produced by a weak teacher model is able to generalize better than the teacher. In this paper, we study this phenomenon in two-layer random feature networks where the model strength is determined by its width. Using tools from random
matrix theory, we derive deterministic equivalents for the population errors of an optimally trained teacher and a student trained with gradient flow. For ReLU activation and a pure spherical harmonic target, we obtain sharp asymptotics under a Gaussian universality assumption, showing a quadratic improvement: the student error scales as the square of the teacher error. These results attain the general lower bound of Medvedev at al (2025). We also analyze how the student behaves under more general stopping times and targets supported on multiple harmonic degrees, characterizing the regimes in which weak-to-strong generalization occurs and identifying the transition between quadratic, non-quadratic, and no improvement.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Careful Judge: Safe and Efficient Human-AI Collaborative Decision Making
Chenyu Zhang, Rachel Luo, Boyi Li et al. (+3 more)
In human-AI collaborative decision making, human review can prevent unsafe AI decisions, but each human judgment is costly. Treating human intervention after AI abstention as a one-off fallback misses the opportunity to improve future AI decisions for greater automation, yet AI adaptively learning from selectively queried human feedback breaks safety guardrails calibrated for old models. We approach this challenge with CARE—calibrated adaptive rectification and escalation—an end-to-end pipeline that combines AI models and human reviewers to guarantee safe, human-aligned decisions, while continuously learning from human feedback to achieve greater automation with fewer human queries. CARE is principled, general, modular, and works with any black-box AI model. Our novel adaptive calibration module guarantees risk control at every time step for any rectification module. We further show how CARE improves query efficiency when the AI model is well trained and the human-AI misalignment has a clear structure. Experiments on four safety-critical real-world
datasets spanning driving,
language, and robotics demonstrate that CARE achieves human-aligned decisions while reducing human queries by 25-81% relative to baselines.
Read the full abstract ▾
All authors Chenyu Zhang, Rachel Luo, Boyi Li, Anjali Parashar, Marco Pavone, Apoorva Sharma
Machine Learning
ORACLE: Optimizer-Relative Alignment for Constrained LEarning
Utkarsh Grover, Wyatt Mackey, Kaixun Hua et al. (+2 more)
Constraint handling methods typically intervene before the optimizer acts, by modifying the objective or the gradient. Yet momentum, adaptive scaling, and structured preconditioning can substantially reshape that signal before it becomes a parameter update. We formulate optimizer relative constrained learning, where constraint compatibility is assessed on the post optimizer update. Building on this view, we introduce ORACLE, which evaluates the native optimizer's realized step through a joint endpoint linearization of heterogeneous constraint families, constructs the resulting
alignment in the optimizer's own geometry, bounds its authority, and commits it only after validation. We evaluate ORACLE across eight Partial Differential Equation
benchmarks and four optimizers spanning Euclidean, diagonal adaptive, and structured preconditioned geometries, where it improves or matches native optimizer in 94% of configurations. Cross model analysis shows the same behavior in 92% of configurations, while matched comparisons show improvements over alternative constraint-handling methods acting at the objective, gradient, and post-optimizer levels.
Read the full abstract ▾
All authors Utkarsh Grover, Wyatt Mackey, Kaixun Hua, J. Morris Chang, Xiaomin Lin
Machine Learning · Cross-listed from cs.AI
Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network
Brandon Ho, Nikola Rogers and Seung-Kyum Choi
Multi-
agent path planning (MAPP) in continuous environments often relies on roadmaps to balance safety and search efficiency. However, traditional roadmap generation methods, such as
lattice grids or standard sampling-based approaches, frequently face a trade-off between graph density and the likelihood of finding feasible, high-quality solutions. In this paper, we propose a scalable heterogeneous Graph Neural Network (GNN) framework for the automated generation and evaluation of shared multi-
agent roadmaps. Our model covers the representation of waypoints,
agent locations, and task locations as distinct nodes in a heterogeneous graph, allowing it to reason over global connectivity and inter-
agent interactions. By training on occupation density maps aggregated and collected from expert solver trajectories, the GNN learns to identify critical points of interest and prune redundant nodes and edges. This process produces a compact, coordination-aware roadmap that is invariant to task permutations and is reusable for multi-
agent pick and delivery tasks. Experimental results demonstrate that our framework can reduce planning effort and can potentially find better solutions, reaching at least 40% reduction in runtime and in graph size for dense roadmaps.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs
Pavan Maddula
Standard safety evaluations of large
language models assess harmful requests written in canonical plain text, while models in real-world deployment routinely receive inputs containing emojis, altered spellings, encoded strings, and character-level variations. This work introduces the
Adversarial Surface-Form Robustness
Dataset (ASRD), comprising 2,100
prompts across seven distinct surface-form families. Five open-weight
language models are evaluated across these
prompts, producing 10,500 responses. The Quad-State Evaluation Rubric classifies each response into one of four outcomes: harmful compliance, safe response, comprehension failure, or indeterminate. Emoji and invisible Unicode variations cause almost no comprehension failure, with pooled harmful compliance of 20.27% and 17.20% against a 22.87% baseline that is driven mainly by Mistral 7B, whereas leetspeak, encoded wrappers, and hybrid transformations score 2.40%, 0.13%, and 2.40% while comprehension failure rises to 36.47%, 65.60%, and 34.47%. Inspection of raw model outputs reveals three response behaviors: hallucinated benignity, structural collapse, and
language drift. Project page: www.pavanmaddula.com/quadstate
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention
Samrajya Thapa, Daniel J. Quest, Timothy L. Kline et al. (+3 more)
Medical imaging models often operate as black boxes, limiting interpretability and systematic debugging. We introduce an easy-to-use, plug-and-play framework for concept-based interpretation and model refinement. By aligning a single-modality encoder to BioMedCLIP, we construct a Concept Bottleneck Model (CBM) that enables concept-level interventions. These interventions allow us to isolate causal versus spuriously correlated concepts, validate insights with domain experts, and generate counterfactual samples for targeted fine-tuning. We evaluate our framework on a Mayo Clinic ultrasound
dataset and the CheXpert 5x200 chest X-ray
dataset. Results demonstrate that concept intervention enables reliable model diagnosis while maintaining, and occasionally improving predictive performance via guided fine-tuning. Our findings highlight the practical value of this framework for controlled, interpretable refinement of clinical deep learning models.
Read the full abstract ▾
All authors Samrajya Thapa, Daniel J. Quest, Timothy L. Kline, Carrie L. Langstraat, Emanuel C. Trabuco, Wei Le
Machine Learning
SPIN: Shadow Predictive Indexer for Sparse Attention
Yao Fu, Jiahan Chang, Ritchie Zhao et al. (+11 more)
Indexer-based sparse
attention reduces the cost of core
attention by passing only a fixed, small number of important
tokens to it. However, the indexer must still score the entire KV cache at every decoding step. This scoring overhead becomes a major bottleneck as the context length grows. We propose
SPIN (Shadow Predictive Indexer) to reduce this indexer overhead.
SPIN uses lightweight, history-based prediction to identify important KV blocks, avoiding the need to score the full KV cache at every decoding step.
SPIN treats KV blocks and speculative decoding as first-class design and implementation considerations. Across extensive evaluations on long-context and agentic
benchmarks,
SPIN achieves 30-40% sparsity while preserving task quality. In end-to-end vLLM serving,
SPIN improves output throughput by up to 14.9% and reduces median inter-
token latency by up to 13.2%.
Read the full abstract ▾
All authors Yao Fu, Jiahan Chang, Ritchie Zhao, Bryce Long, Yueying Li, Mahdi Kamani, Samkit Jain, Rahul Raman, Tara Safavi, Shreya Gupta, Parsa Ashrafi Fashi, Minseok Lee, Julien Demouth, Bita Darvish Rouhani
Machine Learning
Neighborhood Smoothing for Calibration
Idan Horowitz and Avigdor Gal
Modern neural networks are often miscalibrated, with a tendency to overconfidence. Existing train-time calibration methods largely modify task losses or calibration penalties, leaving neighborhood structure in learned representations underexploited. We introduce graph smoothing as a general principle for train-time calibration, which encourages similar predictive distributions across neighboring samples in representation space. We analyze the effects of graph smoothing, deriving bounds that connect predictive divergence between neighboring samples to local confidence variation and to the propagation of pointwise calibration error, and characterize the conditions under which smoothing can or cannot improve calibration. In light of this analysis, we propose \modelNoSpace, a graph-based train-time regularizer that penalizes the Jensen–Shannon divergence between predictive distributions of neighboring samples. We present a thorough empirical analysis, showing that across standard calibration
benchmarks, \model improves predictive quality, and the improvement is complementary to post-hoc calibration: after temperature scaling, \model attains the lowest NLL of all evaluated train-time methods in seven of the eight image and tabular settings. These findings demonstrate the value of graph smoothing over learned representations for neural network calibration.
Read the full abstract ▾
Machine Learning
Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models
Domenic Rosati, Alessa Carbo, Ali Dadsetan et al. (+5 more)
Does removing harmful information make open-weight models resistant to fine-tuning attacks? We show that mutual information at release alone cannot universally certify slow recovery. Function-preserving reparameterizations leave information unchanged while altering gradient-descent geometry, so an invariant certificate is bounded by the fastest reachable parameterization. We apply this principle to weight–data mutual information under training-data filtering and label–representation mutual information under capability removal. Training order can change recovery time at fixed weight–data information, while exact representation-level independence can preserve the entire parameter Jacobian. An explicit construction has both information quantities equal to zero and recovers in one gradient step. Controlled experiments illustrate order-dependent recovery and parameterization-dependent attack speed. These results identify the missing requirement for certification: constraints on attack dynamics beyond mutual information at release.
Read the full abstract ▾
All authors Domenic Rosati, Alessa Carbo, Ali Dadsetan, Hong Huang, Matthew Young, Subhabrata Majumdar, Frank Rudzicz, Hassan Sajjad
Machine Learning
Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers
Sourabh Kasliwal
Autoregressive Large
Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and long division. In this paper, we investigate the mechanics of multi-step arithmetic in compact "Tiny"
Transformers (~10.6M non-
embedding parameters, 49.3M total) trained on synthetic data across four basic operations (+, -, *, /) unrolled as step-by-step scratchpads. First, we establish the necessary training foundations: (1) dataloader sequence padding creates an 83% gradient starvation artifact that collapses accuracy from 40% to 1%, remediated via continuous sequence packing; (2) linguistic pretraining is an essential prerequisite (<= 2.0% without it); and (3) modern architectural primitives (RoPE, RMSNorm, SwiGLU) and Sparse Mixture of Experts (MoE) substantially improve additive
reasoning over baseline GPT-2. Second, we demonstrate that algorithmic scratchpad formulation directly dictates success. Introducing a deterministic Digit-by-Digit Long Division scratchpad within a 4-stage Hierarchical Developmental Curriculum dramatically elevates single-digit division from 4.0% to 86.7% accuracy on a 4,000-problem held-out
benchmark. In contrast, multi-digit multiplication remained challenging: detailed error analysis revealed that while the model correctly computed single-digit sub-products and place-value zeros, our FOIL scratchpad failed because it forced a simultaneous summation of up to nine multi-digit terms in a single step without pairwise intermediate accumulation. Finally, we identify two key boundaries: performance collapses to 0.00% on unseen 4-digit operands, and unbuffered training induces catastrophic forgetting, collapsing division accuracy from 86.7% down to 0.00%.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis
Muhammad Zeeshan Karamat and Christiana Chamon Garcia
As small
language models (SLMs) are increasingly deployed on resource-constrained and on-device platforms, including as components of agentic systems, the integrity of locally stored model parameters becomes an important safety concern. We investigate whether safety-sensitive behavior in LLaMA-2-7B-Chat is concentrated within a sparse subset of parameters, creating a reduced fault surface for targeted analysis. We study two complementary localization methods: low-rank safety-associated subspace analysis and parameter-level safety–utility importance filtering. Both approaches reveal highly non-uniform safety sensitivity across the network, with the MLP down_proj consistently emerging as a prominent safety-sensitive component and o_proj providing a smaller contribution. Using parameter-level localization, modifying only 0.19% of model weights in down_proj yields 53% Basic ASR and 56% GCG ASR, while tinyBenchmarks accuracy remains at 51.6% compared with a 52.2% unmodified baseline. These results motivate targeted fault analysis and selective integrity protection for
language models deployed in resource-constrained, on-device, and agentic settings.
Read the full abstract ▾
Machine Learning
REFIT: Recognize, Fix, and Test Wearable Sensor Placement Shifts without Labels
Bangxun Tang
We present REFIT, an input calibration for frozen activity-recognition models whose inertial sensors are worn differently at deployment than in training. When users move a watch to the other wrist or put a strap sensor back on turned, the model sees the same motion on changed axes. REFIT undoes such shifts without labels or retraining. It describes them by families of axis transforms, such as reflections and rotations, and fits each family to the user's data so that simple statistics match those of the training data. The family that removes most of the mismatch names the shift. REFIT fixes the shift by applying the best member of that family before the frozen model and re-estimating its normalization statistics. It tests the fixed model with a label-free accuracy estimate and asks the user to re-wear the sensor when it is low. Experiments on real left/right sensor pairs and on real and simulated re-attachment show that REFIT outperforms label-free test-time adaptation methods on every
dataset and restores most of the accuracy lost to re-attachment. It names injected shifts far more reliably than a confidence-based selector. After a correction over all signed permutations of the axes, the estimate separates successful from failed corrections.
Read the full abstract ▾
Machine Learning
LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL
Songyuan Zhang, Oswin So, Eric Yang Yu et al. (+3 more)
While offline reinforcement learning (RL) enables policy optimization from static
datasets without costly online interaction, it remains bottlenecked by the risk of executing out-of-distribution (OOD) actions. Recent approaches mitigate this by learning a behavior-cloning policy through flow matching and then performing RL within its constrained latent space. However, naively optimizing the latent policy can easily cause the policy to collapse into a brittle mode or exploit sharp artifacts of the learned critic. In this work, we find that
entropy regularization is essential in latent-space RL for addressing these challenges. We introduce
LASER, a novel offline RL
algorithm that applies latent-space adjoint matching to achieve
entropy-regularized latent-space RL with expressive flow policies while avoiding backpropagation through time. Through comprehensive experiments on 40 challenging OGBench tasks with varying
dataset qualities, we show that
LASER achieves state-of-the-art performance. Notably,
LASER uses fixed method-specific hyperparameters across all tasks and outperforms the evaluated baselines, including those with task- and
dataset-specific tuning, which highlights the robust applicability of
LASER. Project website: https://mit-realm.github.io/
laser/.
Read the full abstract ▾
All authors Songyuan Zhang, Oswin So, Eric Yang Yu, Matthew Cleaveland, Peter Crowley-Dolen, Chuchu Fan
Machine Learning · Cross-listed from astro-ph.IM
A method for multimodal analysis of TAIGA experiment data using essential features
Alexander Kryukov, Julia Dubenskaya, Elena Fedotova et al. (+6 more)
The aim of processing and analyzing experimental data from physical experiments is to obtain physically significant information about the phenomenon under study. This goal is achieved by multi-stage processing of experimental data, during which noise associated with measurements is suppressed and the dimensionality of the input data is reduced. In this paper, we propose a new method based on the use of neural networks such as autoencoders to extract essential features. The special value of the proposed approach lies in the possibility of its application to the analysis of
multimodal data received simultaneously from several installations. We will apply this approach to a
multimodal data (MMD) of the experiment TAIGA. Currently, the analysis of the MMD is carried out independently for each installation separately. Therefore, the development of methods for the joint analysis of MMD from TAIGA-type installations is an urgent task in
cosmic ray physics and gamma-ray astronomy. Based on Monte Carlo simulation, it is shown that the proposed method allows for effective MMD analysis. It can also be used for MMD analysis at other experimental complexes.
Read the full abstract ▾
All authors Alexander Kryukov, Julia Dubenskaya, Elena Fedotova, Elizaveta Gres, Stanislav Polyakov, Eugene Postnikov, Alexander Razumov, Pavel Volchugov, Dmitry Zhurov
Machine Learning
SNR-Gated LSTM-Conditioned Diffusion Model for MIMO Channel Estimation
Jixing Zhou and Xinming Huang
Accurate and low latency channel estimation is critical for modern
MIMO systems, particularly under mobility, where channels exhibit structured sparsity and strong temporal correlation. This paper proposes a time-series conditioned
diffusion framework for channel estimation that performs denoising in the angular domain. Starting from least squares (LS) observations, we train a
diffusion denoiser whose conditioning information is encoded by a long short-term
memory (LSTM) network over a short observation sequence, enabling the model to exploit temporal dynamics beyond per-snapshot estimation. To robustly balance observation fidelity and learned generative priors across a wide signal-to-noise ratio (SNR) range, we introduce a learnable SNR-gated late-fusion shortcut that injects the network input into the final decoding stage through a sigmoid gate with trainable center and scale. To reduce inference latency, we adopt deterministic denoising
diffusion implicit model (DDIM) style reverse updates with SNR-adaptive truncation and step allocation, which significantly reduces the number of reverse
diffusion steps at high SNR while maintaining strong performance in low SNR regimes. Simulations on time-evolving standardized channel models demonstrate that the proposed method achieves consistent performance gains over existing
diffusion-based channel estimation baselines, while retaining low latency through SNR-adaptive inference.
Read the full abstract ▾
Machine Learning
The Best Optimizer Depends on Batch Size
Xingyu Dang, Kaiyue Wen and Sadhika Malladi
A plethora of new adaptive optimizers are designed to efficiently estimate and use minibatch gradient statistics to shape parameter updates, but they are typically benchmarked at a single batch size. Hyperparameter scaling rules promise to preserve performance as batch size and gradient noise change, suggesting that the best optimizer at one batch size should remain the best at another. We challenge this approach to developing and evaluating optimizers by showing: (1) no principled scaling rule for
Muon works consistently across training settings, and (2) the best optimizer for
language model pretraining changes with batch size even after extensive hyperparameter tuning. To understand these failures, we analyze a noisy quadratic model and show that the batch-size scaling rule that preserves performance is direction-dependent, shifting from square-root to linear as a direction's
curvature-to-noise ratio rises. We further prove that gradient noise drives a bias-variance tradeoff in preconditioning that can reverse optimizer rankings across batch sizes, even under optimal learning rate and momentum tuning. Consistent with this, when we increase the batch size $16\times$ partway through
language model pretraining, keeping small-batch updates in only the sharpest $0.001\%$ of directions removes up to $59.5\%$ of the resulting loss gap over the next $8\%$ of training, while a random subspace of the same size barely helps. Taken together, our results show that principled optimizer design must account for batch size and empirical benchmarking should be performed across batch sizes.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
HULK: Learning Whole-Body Forceful Loco-Manipulation for Humanoids
An Dang, Arturo Flores Alvarez, Yu-Ming Chen et al. (+5 more)
Humanoid loco-manipulation of large, heavy objects demands forceful interaction across the entire body. However, such payloads shift a humanoid's center of mass and impose sustained loads across the upper body, challenging balance and command tracking. We present HULK, a whole-body control framework for forceful loco-manipulation. Using model predictive control (MPC) to guide reinforcement learning with predictions of the loaded dynamics, we train two teachers: one tracks arm motions under wrist forces, and the other locomotes while holding large objects against the body. A capture-point control barrier function augments the wrist-force teacher during training to improve balance under load. We distill both teachers into a single policy. Evaluation spans simulation and the Unitree G1. In simulation, the teacher with the barrier function achieves the lowest forward and lateral velocity tracking errors at 10 kg per arm among evaluated controllers and reduces aggregate divergent component of motion (DCM) excursion magnitude by 35.7% relative to MPC-guided reinforcement learning alone. Our wrist-force teacher withstands torso push disturbances of up to 130 N.
Read the full abstract ▾
All authors An Dang, Arturo Flores Alvarez, Yu-Ming Chen, Conor Mc Gartoll, Helen Sun, Aaron Ames, Nima Fazeli, Manikantan Nambi
Machine Learning
Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization
Gustavo Sutter, Alejandro Comas-Leon, David Holzmüller et al. (+4 more)
Black-box optimization problems are ubiquitous across science and engineering, often dealing with expensive objective functions. This objective latency has two consequences during optimization: (i) the objective evaluation dominates execution time, and (ii) sample-efficient
algorithms are crucial to accelerate development and avoid wasting resources.
Bayesian optimization (BO) methods are the de facto choice of planners for suggesting the next point to try. Standard BO fits the surrogate model's hyperparameters with a point estimate. Alternatively, a fully
Bayesian approach uses model averaging to account for uncertainty over the hyperparameters, leading to better uncertainty estimates—useful in the low-data regime that is pervasive in BO. However, it is often prohibitively expensive and thus rarely used. In this work, we propose ELF-BO, an
algorithm that uses the objective evaluation latency to headstart the computation of the next suggestion, allowing for fully
Bayesian optimization without incurring substantial decision-time costs. This is done by sampling from the hyperparameter posterior while the objective is being evaluated, only requiring reweighting of the samples once the objective value is observed. Across synthetic functions and real-world applications, we show that ELF-BO matches the performance of fully
Bayesian methods while only incurring decision latency on par with or better than standard BO. Thus, ELF-BO makes fully
Bayesian optimization practical in real-world use cases.
Read the full abstract ▾
All authors Gustavo Sutter, Alejandro Comas-Leon, David Holzmüller, Hao Wang, Luis Ricardez-Sandoval, Pascal Poupart, Agustinus Kristiadi
Machine Learning
On KL-Regularized Policy Optimization
Yifan Zhang
Asynchronous reinforcement learning (RL) for large
language model (LLM)
agents trains one policy on trajectories generated by another: rollouts come from stale checkpoints, and the inference engine's probabilities differ from the trainer's even at identical parameters. Standard remedies either clip importance ratios, which biases the update, or, as in GRPO, sample a group of responses per
prompt, which is costly when episodes are long. We propose KL-Regularized Policy Optimization (KLPO), a framework that anchors the KL regularizer at the sampler. The regularized improvement step then has a closed-form Gibbs solution, and KLPO fits its log-ratio optimality condition by least squares on the sampler's own trajectories, so the sampler probability enters through a log-ratio and no importance weights are needed. Profiling out the regression intercept replaces the intractable log-partition function with the signal's sampler mean plus a sampler-to-trainer KL divergence. For
token-level policy mirror descent targets, we show that the resulting gradient can be computed from terminal returns without a critic, via sampler-centered scores or a single trajectory residual, even under
stochastic tool outputs. We further prove that independent Monte Carlo estimates of the KL term keep these gradients unbiased, derive the exact KL gap of cheaper top-$K$ and binary approximations, and show that SPPO, GPO, REBEL, and BPO arise as special cases of KLPO. The result is a critic-free update that uses one rollout per
prompt and requires neither a learned normalizer nor a group of responses.
Read the full abstract ▾
Machine Learning
Directed Temporal Representations for Offline Visual Control
Chenyang Yuan, Haoyu Wang, Zhuo Sun et al. (+1 more)
Predictive world models provide compact visual representations for control. Control requires a latent geometry aligned with temporal reachability rather than predictive similarity alone. We introduce Directed Temporal Representations for Control (DTRC), which learns such a geometry from offline visual trajectories on top of frozen LeWorldModel (LeWM) features. DTRC constructs a directed temporal quasimetric over the learned control representation. Short-range temporal offsets calibrate the distance scale. Bootstrapped targets extend temporal reachability across longer horizons. Action-conditioned consistency aligns the representation with local transition dynamics. The resulting distance estimates temporal reaching cost, and its change across a transition defines goal-relative temporal progress. We use this progress signal as a temporal critic for direct goal-conditioned policy learning. Model-assisted targets provide an additional training-time refinement under behavior-support and dynamics-agreement constraints. Across ten visual control tasks, DTRC achieves strong goal-conditioned control performance relative to planning and direct-policy baselines. Held-out diagnostics on the four LeWM tasks show consistent short-range temporal calibration, task-dependent long-range and directional structure, and positive transition-level progress. Temporal supervision improves the same flow-policy parameterization across all four LeWM tasks, while the resulting policy acts directly without iterative trajectory search at test time.
Read the full abstract ▾
All authors Chenyang Yuan, Haoyu Wang, Zhuo Sun, Xiaoyuan Cheng
Machine Learning
GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents
Bohan Lin, Liyi Chen, Zhuoning Guo et al. (+5 more)
On-policy
distillation post-trains large
language model
agents by supplying dense, step-level guidance from a teacher policy when the reinforcement-learning reward is sparse and arrives only once per trajectory. Existing instantiations allocate this guidance by the size of the teacher-student divergence at each step, on the single-turn intuition that a large disagreement marks a mistake worth correcting. Once decisions chain over many turns, that rule misfires, since an early drift enters every later context both policies condition on, leaving the teacher consistent with the drifted trajectory instead of flagging its cause, while interchangeable steps register large but outcome-irrelevant divergences. We demonstrate this on an agentic
benchmark, where distilling the highest-divergence steps brings no consistent benefit over random selection. To this end, we introduce GraphOPD, the first method to bring graph-based structural augmentation into on-policy
distillation for
agent capabilities. It reads which steps enabled which later ones from the environment's own record of state changes, immune to the drift that corrupts the teacher-student gap, organizes them into a dependency graph, scores each step by a random-walk stationary distribution over it, and fuses that structural credit with the divergence signal into a trajectory-relative mask concentrating supervision on each rollout's highest-aptitude steps. Across three model scales and eleven baselines on ALFWorld, WebShop, and SearchQA, GraphOPD shows competitive performance throughout, improving over the strongest baseline by up to +5.8 pp. An executed-replay audit further shows that this structural credit score tracks true causal impact far above chance, that both fused signals are independently necessary, and that the same signal transfers to out-of-domain tool-integrated
reasoning.
Read the full abstract ▾
All authors Bohan Lin, Liyi Chen, Zhuoning Guo, Muyang Li, Qimeng Wang, Yan Gao, Yao Hu, Yudong Zhang
Machine Learning · Cross-listed from cs.CL
CARE: Certifying Acceleration for Vision-Language-Action Inference
Rui Liu, Tong Zheng, Jindong Gu et al. (+1 more)
While
vision-
language-action (VLA) models have advanced rapidly, running them at every control step remains expensive. Prior work accelerates VLA inference using techniques like action chunking and visual-
token pruning, typically evaluating based on latency and average task success. However, acceleration may discard information and break tasks the original policy would solve, a risk hidden by average metrics. Measuring these failures is challenging because action deviations compound over closed-loop trajectories, meaning task failure is only observable across full episodes. We therefore define an acceleration-induced failure via paired rollouts from identical initial conditions, tracking when the reference succeeds but the accelerated policy fails. To manage this, we introduce CARE, an approach for certified accelerator selection. CARE uses paired rollouts on a calibration set to provide finite-sample guarantees that acceleration-induced failure risk stays below a user-specified budget. It deploys the fastest certified candidate, falling back to the reference if none qualify. By relying only on terminal outcomes and measured compute, CARE applies unchanged across diverse acceleration mechanisms, while sequential testing and failure-triggered reference rollouts keep certification affordable. On four LIBERO suites with OpenVLA-OFT, CARE certifies $9.0$–$10.8\times$ speedups while guaranteeing (at $95\%$ confidence) that at least $85.8\%$ of reference-solved episodes are preserved. Under tight budgets, selectors without guarantees exceed the budget in up to $75\%$ of trials, whereas CARE stays within budget and its sequential form uses $78.9\%$ fewer rollouts than exhaustive evaluation. CARE further generalizes to flow-step reduction for $\pi_{0.5}$, and to Qwen3.5-9B and Llama-3.1-8B
agents in Crafter.
Read the full abstract ▾
All authors Rui Liu, Tong Zheng, Jindong Gu, Zhipeng Wang