Machine Learning
Latent Context Compilation: Distilling Long Context into Compact Portable Memory
Zeju Li, Yizhou Zhou and Qiang Xu
Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires modifying model weights, creating stateful parameters that complicate concurrent serving. We propose Latent Context Compilation, a framework that fundamentally shifts context processing from adaptation to compilation. By utilizing a disposable LoRA module as a compiler, we distill long contexts into compact buffer
tokens – stateless, portable
memory artifacts that are plug-and-play compatible with frozen base models. Crucially, we introduce a self-aligned optimization strategy that eliminates the need for synthetic context-relevant QA pairs. By regularizing context reconstruction task with context-agnostic random queries, we force compressed
tokens to reside within the model's existing instruction-following
manifold. Experiments with Llama-3.1-8B demonstrate that Latent Context Compilation preserves fine-grained details and
reasoning capabilities where prior methods falter, effectively decoupling
memory density from model parameters even at a 16x compression ratio.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Field-Theoretic Memory for AI Agents: Continuous Dynamics for Context Preservation
Subhadip Mitra
We present a
memory system for AI
agents that treats stored information as continuous fields governed by partial differential equations rather than discrete entries in a database. The approach draws from classical field theory:
memories diffuse through semantic space, decay thermodynamically based on importance, and interact through field coupling in multi-
agent scenarios. We evaluate the system on two established long-context
benchmarks: LoCoMo (ACL 2024) with 300-turn conversations across 35 sessions, and LongMemEval (ICLR 2025) testing multi-session
reasoning over 500+ turns. On LongMemEval, the field-theoretic approach achieves significant improvements: +116% F1 on multi-session
reasoning (p<0.01, d= 3.06), +43.8% on temporal
reasoning (p<0.001, d= 9.21), and +27.8%
retrieval recall on knowledge updates (p<0.001, d= 5.00). Multi-
agent experiments show near-perfect collective intelligence (>99.8%) through field coupling. Code is available at github.com/rotalabs/rotalabs-fieldmem.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
Amin Banayeeanzade, Qingchuan Yang, Deqing Fu et al. (+6 more)
High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for downstream development, and large
language models (LLMs) have emerged as powerful engines for generating it. However, existing private text generation methods are severely inefficient: they are data-intensive, computationally slow, and often require large private corpora or batch sizes to achieve usable quality. We introduce EPSVec, a differentially-private lightweight alternative that steers LLM generation using *
dataset vectors*–directions in activation space that capture the distributional gap between private data and public priors. EPSVec extracts and sanitizes steering vectors just once and then performs standard decoding. This decouples the
privacy budget from generation, enabling arbitrarily many synthetic samples without additional
privacy cost and yielding strong fidelity even in low-data regimes. Furthermore, we enhance our method by utilizing pretrained (base) models and introducing fixed-shot prompting to boost generation diversity and fidelity. Our experiments demonstrate that EPSVec outperforms existing baselines in distributional
alignment and downstream utility, particularly in low-data regimes, while significantly reducing computational overhead.
Read the full abstract ▾
All authors Amin Banayeeanzade, Qingchuan Yang, Deqing Fu, Spencer Hong, Erin Babinsky, Alfy Samuel, Anoop Kumar, Robin Jia, Sai Praneeth Karimireddy
Machine Learning · Cross-listed from eess.SP
A Gradient Boosted Mixed-Model Machine Learning Framework for Vessel Speed in the U.S. Arctic
Mauli Pant, Linda Fernandez and Indranil Sahoo
Understanding how environmental and operational conditions influence vessel speed is crucial for characterizing navigational conditions in the Arctic. We analyzed Automatic Identification System (AIS) data from 2010-2019 to examine vessel speed over ground (SOG). Over half of the AIS records showed zero SOG, and treating zero and positive SOG as a single continuous process can obscure important patterns. We therefore applied a two-stage machine learning framework, first modeling the probability of SOG greater than zero and then modeling SOG conditional on being positive. AIS observations were integrated with sea ice concentration, course over ground, wind, bathymetric depth, distance to coast, vessel group, and navigational status. Gradient boosted decision trees with random effects captured nonlinear environmental responses while accounting for repeated observations. The positive SOG classifier achieved strong discrimination (AUC = 0.85), while the conditional speed model explained approximately 77 percent of out-of-fold variance. SHAP values quantified
covariate effects by decomposing model predictions into additive contributions from individual variables. Distance to coast and bathymetric depth were dominant determinants of both the likelihood and magnitude of vessel speed, while changes in course, vessel group, and navigational status introduced secondary variation. Wind and sea ice effects were modest. Together, these results empirically characterize Arctic vessel operating regimes relevant to speed management and corridor-level assessment.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
Jiaxi Yang, Shicheng Liu, Yuchen Yang et al. (+1 more)
With the rapid advancement of
Vision Language Models (VLMs), refusal mechanisms have become a critical component for ensuring responsible and safe model behavior. However, existing refusal strategies are largely one-size-fits-all and fail to adapt to diverse user needs and contextual constraints, leading to either under-refusal or over-refusal. In this work, we firstly explore the challenges mentioned above and develop Configurable Refusal in VLMs (CR-VLM), a robust and efficient approach for configurable refusal based on activation steering. CR-VLM consists of three integrated components: (1) extracting a configurable refusal vector via a teacher-forced mechanism to amplify the refusal signal; (2) introducing a gating mechanism that mitigates over-refusal by preserving acceptance for in-scope queries; and (3) designing a counterfactual
vision enhancement module that aligns visual representations with refusal requirements. Comprehensive experiments across multiple
datasets and various VLMs demonstrate that CR-VLM achieves effective, efficient, and robust configurable refusals, offering a scalable path toward user-adaptive safety
alignment in VLMs.
Read the full abstract ▾
All authors Jiaxi Yang, Shicheng Liu, Yuchen Yang, Dongwon Lee
Machine Learning · Cross-listed from stat.ML
Deep networks learn to parse uniform-depth context-free languages from local statistics
Jack T. Parley, Francesco Cagnetta and Matthieu Wyart
Understanding how the structure of
language can be learned from sentences alone is a central question in both cognitive science and machine learning. Studies of the internal representations of Large
Language Models (LLMs) support their ability to parse text when predicting the next word, while representing semantic notions independently of surface form. Yet, which data statistics make these feats possible, and how much data is required, remain largely unknown. Probabilistic context-free grammars (PCFGs) provide a tractable testbed for studying these questions. However, prior work has focused either on the post-hoc characterization of the parsing-like
algorithms used by trained networks; or on the learnability of PCFGs with fixed syntax, where parsing is unnecessary. Here, we (i) introduce a tunable class of PCFGs in which both the degree of ambiguity and the correlation structure across scales can be controlled; (ii) provide a learning mechanism – an inference
algorithm inspired by the structure of deep convolutional networks – that links learnability and sample complexity to specific
language statistics; and (iii) validate our predictions empirically across deep convolutional and
transformer-based architectures. Overall, we propose a unifying framework where correlations at different scales lift local ambiguities, enabling the emergence of hierarchical representations of the data.
Read the full abstract ▾
Machine Learning
A Causal Perspective for Enhancing Jailbreak Attack and Defense
Licheng Pan, Yunsheng Lu, Jiexi Liu et al. (+5 more)
Uncovering the mechanisms behind "jailbreaks" in large
language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood. Existing studies predominantly analyze jailbreak
prompts by probing latent representations, often overlooking the causal relationships between interpretable
prompt features and jailbreak occurrences. In this work, we propose Causal Analyst, a framework that integrates LLMs into data-driven causal discovery to identify the direct causes of jailbreaks and leverage them for both attack and defense. We introduce a comprehensive
dataset comprising 35k jailbreak attempts across seven LLMs, systematically constructed from 100 attack templates and 50 harmful queries, annotated with 37 meticulously designed human-readable
prompt features. By jointly training LLM-based
prompt encoding and GNN-based causal graph learning, we reconstruct causal pathways linking
prompt features to jailbreak responses. Our analysis reveals that specific features, such as "Positive Character" and "Number of Task Steps", act as direct causal drivers of jailbreaks. We demonstrate the practical utility of these insights through two applications: (1) a Jailbreaking Enhancer that targets identified causal features to significantly boost attack success rates on public
benchmarks, and (2) a Guardrail Advisor that utilizes the learned causal graph to extract true malicious intent from obfuscated queries. Extensive experiments, including baseline comparisons and causal structure validation, confirm the robustness of our causal analysis and its superiority over non-causal approaches. Our results suggest that analyzing jailbreak features from a causal perspective is an effective and interpretable approach for improving LLM reliability. Our code is available at https://github.com/Master-PLC/Causal-Analyst.
Read the full abstract ▾
All authors Licheng Pan, Yunsheng Lu, Jiexi Liu, Jialing Tao, Haozhe Feng, Hui Xue, Zhixuan Chu, Kui Ren
Machine Learning
CoCopula: Conformal Calibration and Copula Aggregation for Reliable Renewable Energy Forecasting
Alireza Moradi, Mathieu Tanneau, Reza Zandehshahvar et al. (+1 more)
The rapid growth of renewable energy penetration has intensified the need for reliable probabilistic forecasts to support grid operations at aggregated (fleet or system) levels. In practice, however, system operators often lack access to fleet-level probabilistic models and instead rely on site-level forecasts produced by heterogeneous third-party providers. Constructing coherent and calibrated fleet-level probabilistic forecasts from such inputs remains challenging due to complex cross-site dependencies and aggregation-induced miscalibration. Motivated by a real-world operational challenge identified through collaboration with an industry partner, this paper presents a probabilistic aggregation and calibration framework that directly converts site-level probabilistic forecasts into reliable fleet-level forecasts. The paper introduces \method~ (Conformal Calibration and Copula Aggregation), which integrates Copula-based dependence modeling to capture cross-site correlations followed by Context-Aware Conformal Prediction (CACP) to mitigate miscalibration at the aggregated level. This combination enables dependence-aware aggregation while improving empirical coverage and maintaining sharp prediction intervals. Experiments on large-scale
solar generation
datasets from three system operators in the United States including MISO, ERCOT, and SPP demonstrate that the proposed \method{} approach achieves near-nominal empirical coverage and consistently lower Winkler scores than competing aggregation-based baselines across different target coverage levels. Importantly, \method{} achieves performance comparable to directly calibrated system-level forecasts, demonstrating its practical value when dedicated fleet-level
forecasting models are unavailable.
Read the full abstract ▾
All authors Alireza Moradi, Mathieu Tanneau, Reza Zandehshahvar, Pascal Van Hentenryck
Machine Learning · Cross-listed from cs.AI
Uncertainty and Fairness Awareness in LLM-Based Recommendation Systems
Chandan Kumar Sah, Xiaoli Lian, Li Zhang et al. (+2 more)
Large
language models (LLMs) enable powerful zero-shot recommendations by leveraging broad contextual knowledge, yet predictive uncertainty and embedded biases threaten reliability and
fairness. This paper studies how uncertainty and
fairness evaluations affect the accuracy, consistency, and trustworthiness of LLM-generated recommendations. We introduce a
benchmark of curated metrics and a
dataset annotated for eight demographic attributes (31 categorical values) across two domains: movies and music. Through in-depth case studies, we quantify predictive uncertainty (via
entropy) and demonstrate that Google DeepMind's Gemini 1.5 Flash exhibits systematic unfairness for certain sensitive attributes; measured similarity-based gaps are SNSR at 0.1363 and SNSV at 0.0507. These disparities persist under
prompt perturbations such as typographical errors and
multilingual inputs. We further integrate personality-aware
fairness into the RecLLM evaluation pipeline to reveal personality-linked bias patterns and expose trade-offs between personalization and group
fairness. We propose a novel uncertainty-aware evaluation methodology for RecLLMs, present empirical insights from deep uncertainty case studies, and introduce a personality profile-informed
fairness benchmark that advances explainability and equity in LLM recommendations. Together, these contributions establish a foundation for safer, more interpretable RecLLMs and motivate future work on multi-model
benchmarks and adaptive calibration for trustworthy deployment.
Read the full abstract ▾
All authors Chandan Kumar Sah, Xiaoli Lian, Li Zhang, Tony Xu, Syed Shazaib Shah
Machine Learning
QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals
Nan Zhang, Eugene Kwek, Yusen Zhang et al. (+4 more)
Weight-only quantization is important for compressing Large
Language Models (LLMs). Inspired by the spirit of classical magnitude
pruning, we study whether the magnitude of weight updates during
reasoning-incentivized fine-tuning can provide valuable signals for quantizing Large
Reasoning Models (LRMs). We hypothesize that the smallest and largest weight updates during fine-tuning are more important than those of intermediate magnitude, a phenomenon we term "protecting both ends". Upon hypothesis validation, we introduce QuantLRM, which stands for weight quantization of LRMs via fine-tuning signals. We fit simple restricted quadratic functions on weight updates to protect both ends. By multiplying the average quadratic values with the count of zero weight updates of channels, we compute channel importance that is more effective than using activation or second-order information. We run QuantLRM to quantize various fine-tuned models (including supervised, direct preference optimization, and reinforcement learning fine-tuning) over four
reasoning benchmarks (AIME-120, FOLIO, temporal sequences, and GPQA-Diamond) and empirically find that QuantLRM delivers a consistent improvement for LRMs quantization, with an average improvement of 6.55% on a reinforcement learning fine-tuned model. Also supporting non-fine-tuned LRMs, QuantLRM gathers effective signals via pseudo-fine-tuning, which greatly enhances its applicability.
Read the full abstract ▾
All authors Nan Zhang, Eugene Kwek, Yusen Zhang, Muyu Pan, Suhang Wang, Prasenjit Mitra, Rui Zhang
Machine Learning · Cross-listed from stat.ML
Relaxed Triangle Inequality for Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
Shiji Xiao, Yufeng Zhang, Chubo Liu et al. (+3 more)
The Kullback-Leibler (KL) divergence is not a proper distance metric and does not satisfy the triangle inequality, posing theoretical challenges in certain practical applications. Existing work has demonstrated that KL divergence between multivariate Gaussian distributions follows a relaxed triangle inequality. Given any three multivariate Gaussian distributions $\mathcal{N}_1, \mathcal{N}_2$, and $\mathcal{N}_3$, if $KL(\mathcal{N}_1, \mathcal{N}_2)\leq \epsilon_1$ and $KL(\mathcal{N}_2, \mathcal{N}_3)\leq \epsilon_2$, then $KL(\mathcal{N}_1, \mathcal{N}_3)< 3\epsilon_1+3\epsilon_2+2\sqrt{\epsilon_1\epsilon_2}+o(\epsilon_1)+o(\epsilon_2)$. However, the supremum of $KL(\mathcal{N}_1, \mathcal{N}_3)$ is still unknown. In this paper, we investigate the relaxed triangle inequality for the KL divergence between multivariate Gaussian distributions and give the supremum of $KL(\mathcal{N}_1, \mathcal{N}_3)$ as well as the conditions when the supremum can be attained. When $\epsilon_1$ and $\epsilon_2$ are small, the supremum is $\epsilon_1+\epsilon_2+2\sqrt{\epsilon_1\epsilon_2}+o(\epsilon_1)+o(\epsilon_2)$. Finally, we demonstrate several applications of our results in out-of-distribution detection with flow-based generative models and safe reinforcement learning.
Read the full abstract ▾
All authors Shiji Xiao, Yufeng Zhang, Chubo Liu, Yan Ding, Keqin Li, Kenli Li
Machine Learning
Product Interaction: An Algebraic Formalism for Deep Learning Architectures
Haonan Dong, Chun-Wun Cheng and Angelica I. Aviles-Rivero
Modern neural architectures are largely developed as distinct empirical constructions, despite recurring principles across convolutional,
attention, state-space, and equivariant models. We introduce Product Interactions, an algebraic formalism that unifies these architectures under a common construction principle and turns their design into a systematic procedure. The core shift is representing data as algebraic elements and treating multiplication, rather than linear transformation alone, as a primitive architectural operation. Architectures are generated by composing multiplication operators, with input dependence organized by self-interaction order. Within this formalism, we derive convolutional and equivariant networks as
symmetry-constrained first-order product interactions, recover Mamba from state-space models as an increase in self-interaction order from one to three, and establish
attention as a third-order interaction from composing the same operator. Equivariance is incorporated by constraining the algebraic product via
symmetry: translation equivariance yields convolution, while SO(3)-compatibility produces the Clebsch–Gordan product and tensor-field interactions. This perspective recasts architecture design as an algebraic construction problem: the choice of
algebra defines admissible interactions,
symmetry constrains their structure, and composition generates higher-order architectures. The framework is thus generative. Following these principles, we construct a simplified-
algebra dynamical layer that improves both accuracy and throughput over Mamba on CIFAR-10. Experiments show that interaction order affects accuracy non-monotonically and
symmetry constraints boost learnability. Product Interactions provides a mathematical methodology for analyzing existing architectures and systematically designing new ones.
Read the full abstract ▾
Machine Learning
Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective
Haichuan Wang, Tao Lin, Lingkai Kong et al. (+3 more)
Existing
alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy. This practice is suboptimal for maximizing user's utility because the KL regularization may cause the LLM to inherit the bias in the base policy that conflicts with user preferences. While amplifying rewards for preferred outputs can mitigate this bias, it also increases the risk of reward hacking. This tradeoff motivates the problem of optimally designing reward models under KL regularization. We formalize this reward model optimization problem as a Stackelberg game, and show that a simple reward shaping scheme can effectively approximate the optimal reward model. We empirically evaluate our method in inference-time
alignment settings and demonstrate that it integrates seamlessly into existing
alignment methods with minimal overhead. Our method consistently improves average reward and achieves win-tie rates exceeding 66% against all baselines, averaged across evaluation settings.
Read the full abstract ▾
All authors Haichuan Wang, Tao Lin, Lingkai Kong, Ce Li, Hezi Jiang, Milind Tambe
Machine Learning
Trajectory Consistency for One-Step Generation on Euler Mean Flows
Zhiqi Li, Yuchen Sun, Duowen Chen et al. (+2 more)
We propose Euler Mean Flows (EMF), a flow-based generative framework for one-step and few-step generation that enforces long-range trajectory consistency with minimal sampling cost. The key idea of EMF is to replace the trajectory consistency constraint, which is difficult to supervise and optimize over long time scales, with a principled linear surrogate that enables direct data supervision for long-horizon flow-map compositions. We derive this approximation from the
semigroup formulation of flow-based models and show that, under mild regularity assumptions, it faithfully approximates the original consistency objective while being substantially easier to optimize. This formulation leads to a unified, JVP-free training framework that supports both $u$-prediction and $x_1$-prediction variants, avoiding explicit Jacobian computations and significantly reducing
memory and computational overhead. Experiments on image synthesis, particle-based geometry generation, and functional generation demonstrate improved optimization stability and sample quality under fixed sampling budgets, together with approximately $50\%$ reductions in training time and
memory consumption compared to existing one-step methods for image generation.
Read the full abstract ▾
All authors Zhiqi Li, Yuchen Sun, Duowen Chen, Jinjin He, Bo Zhu
Machine Learning
Mitigating Task-Order Sensitivity and Forgetting via Hierarchical Second-Order Consolidation
Protik Nag, Krishnan Raghavan and Vignesh Narayanan
We introduce $\textbf{Hierarchical Taylor Series-based Continual Learning (HTCL)}$, a framework that couples fast local adaptation with conservative, second-order global consolidation to address the high variance introduced by random task ordering. To address task-order effects, HTCL identifies the best intra-group task sequence and integrates the resulting local updates through a Hessian-regularized Taylor expansion, yielding a consolidation step with theoretical guarantees. The approach naturally extends to an $L$-level hierarchy, enabling multiscale knowledge integration in a manner not supported by conventional single-level CL systems. Across a wide range of
datasets and replay and regularization baselines, HTCL acts as a model-agnostic consolidation layer that consistently enhances performance, yielding mean accuracy gains of $7\%$ to $25\%$ while reducing the standard deviation of final accuracy by up to $68\%$ across random task permutations.
Read the full abstract ▾
Machine Learning
IceBench-S2S: A Benchmark of Deep Learning for Challenging Subseasonal-to-Seasonal Daily Arctic Sea Ice Forecasting in Deep Latent Space
Jingyi Xu, Shengnan Wang, Weidong Yang et al. (+3 more)
Arctic sea ice plays a critical role in regulating Earth's
climate system, significantly influencing polar ecological stability and human activities in coastal regions. Recent advances in artificial intelligence have facilitated the development of skillful pan-Arctic sea ice
forecasting systems, where data-driven approaches showcase tremendous potential to outperform conventional physics-based numerical models in terms of accuracy, computational efficiency and
forecasting lead times. Despite the latest progress made by deep learning (DL)
forecasting models, most of their skillful
forecasting lead times are confined to daily subseasonal scale and monthly averaged values for up to six months, which drastically hinders their deployment for real-world applications, e.g., maritime routine planning for Arctic transportation and scientific investigation. Extending daily forecasts from subseasonal to seasonal (S2S) scale is scientifically crucial for operational applications. To bridge the gap between the
forecasting lead time of current DL models and the significant daily S2S scale, we introduce IceBench-S2S, the first comprehensive
benchmark for evaluating DL approaches in mitigating the challenge of
forecasting Arctic sea ice concentration in successive 180-day periods. It proposes a generalized framework that first compresses spatial features of daily sea ice data into a deep latent space. The temporally concatenated deep features are subsequently modeled by DL-based
forecasting backbones to predict the sea ice variation at S2S scale. IceBench-S2S provides a unified training and evaluation pipeline for different backbones, along with practical guidance for model selection in polar environmental monitoring tasks.
Read the full abstract ▾
All authors Jingyi Xu, Shengnan Wang, Weidong Yang, Siwei Tu, Lei Bai, Ben Fei
Machine Learning · Cross-listed from math.ST
Improving Minimax Estimation Rates for Contaminated Mixture of Multinomial Logistic Experts via Expert Heterogeneity
Fanqi Yan, Dung Le, Trang Pham et al. (+2 more)
Contaminated mixture of experts (MoE) is motivated by transfer learning methods where a pre-trained model, acting as a frozen expert, is integrated with an adapter model, functioning as a trainable expert, in order to learn a new task. Despite recent efforts to analyze the convergence behavior of parameter estimation in this model, there are still two unresolved problems in the literature. First, the contaminated MoE model has been studied solely in regression settings, while its theoretical foundation in classification settings remains absent. Second, previous works on MoE models for classification capture pointwise convergence rates for parameter estimation without any guaranty of minimax optimality. In this work, we close these gaps by performing, for the first time, the convergence analysis of a contaminated mixture of multinomial logistic experts with homogeneous and heterogeneous structures, respectively. In each regime, we characterize uniform convergence rates for estimating parameters under challenging settings where ground-truth parameters vary with the sample size. Furthermore, we also establish corresponding minimax lower bounds to ensure that these rates are minimax optimal. Notably, our theories offer an important insight into the design of contaminated MoE, that is, expert heterogeneity yields faster parameter estimation rates and, therefore, is more sample-efficient than expert homogeneity.
Read the full abstract ▾
All authors Fanqi Yan, Dung Le, Trang Pham, Huy Nguyen, Nhat Ho
Machine Learning · Cross-listed from cs.RO
CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining
I-Chun Arthur Liu, Krzysztof Choromanski, Sandy Huang et al. (+1 more)
Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information about objects and scenes that is essential for precise manipulation. In this work, we introduce Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining (CLAMP), a novel 3D pre-training framework that utilizes point clouds and
robot actions. From the merged point cloud computed from RGB-D images and camera extrinsics, we re-render multi-view four-channel image observations with depth and 3D coordinates, including dynamic wrist views, to provide clearer views of target objects for high-precision manipulation tasks. The pre-trained encoders learn to associate the 3D
geometric and positional information of objects with
robot action patterns via contrastive learning on large-scale simulated
robot trajectories. During encoder pre-training, we pre-train a
Diffusion Policy to initialize the policy weights for fine-tuning, which is essential for improving fine-tuning sample efficiency and performance. After pre-training, we fine-tune the policy on a limited amount of task demonstrations using the learned image and action representations. We demonstrate that this pre-training and fine-tuning design substantially improves learning efficiency and policy performance on unseen tasks. Furthermore, we show that CLAMP outperforms state-of-the-art baselines across six simulated tasks and five real-world tasks. The project website and
videos can be found at https://clamp3d.github.io/CLAMP/.
Read the full abstract ▾
All authors I-Chun Arthur Liu, Krzysztof Choromanski, Sandy Huang, Connor Schenck
Machine Learning
Continuous-Utility Direct Preference Optimization
Muhammad Ahmed Mohsin, Muhammad Umer and Emily Fox
Large
language model
reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fine-grained
reasoning quality. We introduce continuous utility direct preference optimization (CU-DPO), a framework that aligns models to a portfolio of
prompt-based cognitive strategies by replacing binary labels with continuous scores that capture fine-grained
reasoning quality. We prove that learning with K strategies yields a Theta(K log K) improvement in sample complexity over binary preferences and that DPO converges to the
entropy-regularized utility-maximizing policy. To exploit this signal, we propose a two-stage pipeline: (i) strategy selection, which optimizes the model to choose the best strategy via best-vs-all comparisons, and (ii) execution refinement, which trains correct execution using margin-stratified pairs. The framework is domain-agnostic: any task admitting cognitively distinct solution strategies and a decomposable continuous utility signal can be incorporated into the portfolio. On mathematical
reasoning benchmarks, CU-DPO improves strategy selection accuracy from 35-46% to 68-78% across seven base models, yielding downstream
reasoning gains of up to +6.6 points on in-distribution
datasets with effective out-of-distribution transfer. CU-DPO demonstrates consistent gains on code generation and causal
reasoning benchmarks, confirming generalization beyond the mathematical domain.
Read the full abstract ▾
Machine Learning
Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision
Yihao Xue, Allan Zhang, Jianhao Huang et al. (+2 more)
Training LLMs to think and reason for longer has become a key ingredient in building state-of-the-art models that can solve complex problems previously out of reach. Recent efforts pursue this in different ways, such as RL fine-tuning to elicit long CoT or scaling latent
reasoning through architectural recurrence. This makes
reasoning length an important scaling knob. In this work, we identify a novel phenomenon (both theoretically and experimentally): under outcome-only supervision, out-of-distribution (OOD) performance can continue improving as training-time
reasoning length (e.g., the
token budget in RL, or the loop count in looped
Transformers) increases, even after in-distribution (ID) performance has saturated. This suggests that robustness may require a larger budget than ID validation alone would indicate. We provide theoretical explanations via two mechanisms: (i) self-iteration can induce a stronger inductive bias in the hypothesis class, reshaping ID-optimal solutions in ways that improve OOD generalization; and (ii) when shortcut solutions that work for ID samples but not for OOD samples persist in the hypothesis class, regularization can reduce the learned solution's reliance on these shortcuts as the number of self-iterations increases. We complement the theory with empirical evidence from two realizations of scaling training-time
reasoning length: increasing the number of loops in looped
Transformers on a synthetic task, and increasing
token budgets during RL fine-tuning of LLMs on mathematical
reasoning.
Read the full abstract ▾
All authors Yihao Xue, Allan Zhang, Jianhao Huang, Amit Sahai, Baharan Mirzasoleiman
Machine Learning · Cross-listed from math.OC
On the Convergence of Jacobian-Free Backpropagation for Optimal Control Problems with Implicit Hamiltonians
Eric Gelphman, Deepanshu Verma, Nicole Tianjiao Yang et al. (+2 more)
Optimal feedback control with implicit
Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence of closed-form optimal control laws. Recent work~\cite{gelphman2025end} introduced an implicit deep learning approach using Jacobian-Free Backpropagation (JFB) to address this setting, but only established sample-wise descent guarantees. In this paper, we establish convergence guarantees for JFB in the
stochastic minibatch setting, showing that the resulting updates converge to stationary points of the expected optimal control objective. We further demonstrate scalability on substantially higher-dimensional problems, including multi-
agent optimal consumption and swarm-based quadrotor and bicycle control. Together, our results provide both theoretical justification and empirical evidence for using JFB in high-dimensional optimal control with implicit
Hamiltonians.
Read the full abstract ▾
All authors Eric Gelphman, Deepanshu Verma, Nicole Tianjiao Yang, Stanley Osher, Samy Wu Fung
Machine Learning
Early Classification of Time Series in Non-Stationary Cost Regimes
Aurélien Renault, Alexis Bondu, Antoine Cornuéjols et al. (+1 more)
Early Classification of Time Series (ECTS) addresses decision-making problems in which predictions must be made as early as possible while maintaining high accuracy. Most existing ECTS methods assume that the time-dependent decision costs governing the learning objective are known, fixed, and correctly specified. In practice, however, these costs are often uncertain and may change over time, leading to mismatches between training-time and deployment-time objectives. In this paper, we study ECTS under two practically relevant forms of cost non-stationarity: drift in the balance between misclassification and decision delay costs, and
stochastic realizations of decision costs that deviate from the nominal training-time model. To address these challenges, we revisit representative ECTS approaches and adapt them to an online learning setting. Focusing on separable methods, we update only the triggering model during deployment, while keeping the classifier fixed. We propose several online adaptations and baselines, including bandit-based and RL-based approaches, and conduct controlled experiments on synthetic data to systematically evaluate robustness under cost non-stationarity. Our results demonstrate that online learning can effectively improve the robustness of ECTS methods to cost drift, with RL-based strategies exhibiting strong and stable performance across varying cost regimes.
Read the full abstract ▾
All authors Aurélien Renault, Alexis Bondu, Antoine Cornuéjols, Vincent Lemaire
Machine Learning · Cross-listed from cs.CL
Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration
Víctor Yeste and Paolo Rosso
Human value detection from single sentences is a sparse, imbalanced multi-label task. We study whether Schwartz higher-order (HO) categories help this setting on ValueEval'24 / ValuesML (74K English sentences) under a compute-frugal budget. Rather than proposing a new architecture, we compare direct supervised
transformers, hard HO$\rightarrow$values pipelines, Presence$\rightarrow$HO$\rightarrow$values cascades, compact instruction-tuned large
language models (LLMs), QLoRA, and low-cost upgrades such as threshold tuning and small ensembles. HO categories are learnable: the easiest bipolar pair, Growth vs. Self-Protection, reaches Macro-$F_1=0.58$. The most reliable gains come from calibration and ensembling: threshold tuning improves Social Focus vs. Personal Focus from $0.41$ to $0.57$ ($+0.16$),
transformer soft voting lifts Growth from $0.286$ to $0.303$, and a
Transformer+LLM hybrid reaches $0.353$ on Self-Protection. In contrast, hard hierarchical gating does not consistently improve the end task. Compact LLMs also underperform supervised encoders as stand-alone systems, although they sometimes add useful diversity in hybrid ensembles. Under this
benchmark, the HO structure is more useful as an inductive bias than as a rigid routing rule.
Read the full abstract ▾
Machine Learning
Efficient Deep Learning for Medical Imaging: Bridging the Gap Between High-Performance AI and Clinical Deployment
Cuong Manh Nguyen and Truong-Son Hy
Deep learning has revolutionized medical image analysis, playing a vital role in modern clinical applications. However, the deployment of large-scale models in real-world clinical settings remains challenging due to high computational costs, latency constraints, and patient data
privacy concerns associated with cloud-based processing. To address these bottlenecks, this review provides a comprehensive synthesis of efficient and lightweight deep learning architectures specifically tailored for the medical domain. We categorize the landscape of modern efficient models into three primary streams: Convolutional Neural Networks (CNNs), Lightweight
Transformers, and emerging Linear Complexity Models. Furthermore, we examine key model compression strategies (including
pruning, quantization, knowledge
distillation, and low-rank factorization) and evaluate their efficacy in maintaining diagnostic performance while reducing hardware requirements. By identifying current limitations and discussing the transition toward on-device intelligence, this review serves as a roadmap for researchers and practitioners aiming to bridge the gap between high-performance AI and resource-constrained clinical environments.
Read the full abstract ▾