Machine Learning
Path-Sampled Integrated Gradients
Firuz Kamalov, Fadi Thabtah, R. Sivaraj et al. (+1 more)
We introduce path-sampled integrated gradients (PS-IG), a framework that generalizes feature attribution by computing the expected value over baselines sampled along the linear interpolation path. We prove that PS-IG is mathematically equivalent to path-weighted integrated gradients, provided the weighting function matches the cumulative distribution function of the sampling density. This equivalence allows the
stochastic expectation to be evaluated via a deterministic Riemann sum, improving the error convergence rate from $O(m^{-1/2})$ to $O(m^{-1})$ for smooth models. Furthermore, we demonstrate analytically that PS-IG functions as a variance-reducing filter against gradient noise - strictly lowering attribution variance by a factor of 1/3 under uniform sampling - while preserving key axiomatic properties such as linearity and implementation invariance.
Read the full abstract ▾
All authors Firuz Kamalov, Fadi Thabtah, R. Sivaraj, Neda Abdelhamid
Machine Learning
When Missing Becomes Structure: Intent-Preserving Policy Completion from Financial KOL Discourse
Yuncong Liu, Yuan Wan, Zhou Jiang et al. (+1 more)
Key Opinion Leader (KOL) discourse on social media is widely consumed as investment guidance, yet turning it into executable trading strategies without injecting assumptions about unspecified execution decisions remains an open problem. We observe that the gaps in KOL statements are not random deficiencies but a structured separation: KOLs express directional intent (what to buy or sell and why) while leaving execution decisions (when, how much, how long) systematically unspecified. Building on this observation, we propose an intent-preserving policy completion framework that treats KOL discourse as a partial trading policy and uses offline reinforcement learning to complete the missing execution decisions around the KOL-expressed intent. Experiments on
multimodal KOL discourse from YouTube and X (2022-2025) show that KICL achieves the best return and Sharpe ratio on both platforms while maintaining zero unsupported entries and zero directional reversals, and ablations confirm that the full framework yields an 18.9% return improvement over the KOL-aligned baseline.
Read the full abstract ▾
All authors Yuncong Liu, Yuan Wan, Zhou Jiang, Yao Lu
Machine Learning
Thermodynamic Diffusion Inference with Minimal Digital Conditioning
Aditi De
Diffusion-model inference and overdamped Langevin dynamics are formally identical. A physical substrate that encodes the score function therefore equilibrates to the correct output by thermodynamics alone, requiring no digital arithmetic during inference and potentially achieving a $10{,}000\times$ reduction in energy relative to a GPU. Two fundamental barriers have until now prevented this equivalence from being realized at production scale: non-local skip connections, which locally coupled analog substrates cannot represent, and input conditioning, in which the coupling constants carry roughly $2{,}600\times$ too little signal to anchor the system to a specific input. We resolve both obstacles. Hierarchical bilinear coupling encodes U-Net skip connections as rank-$k$ inter-module interactions derived directly from the singular structure of the encoder and decoder Gram
matrices, requiring only $O(Dk)$ physical connections instead of $O(D^2)$. A minimal digital interface – a 4-dimensional bottleneck encoder together with a 16-unit transfer network, totalling 2,560 parameters – overcomes the conditioning barrier. When evaluated on activations drawn from a trained denoising U-Net, the complete system attains a decoder cosine similarity of 0.9906 against an oracle upper bound of 1.0000, while preserving theoretical net energy savings of approximately $10^7\times$ over GPU inference. These results constitute the first demonstration of trained-weight, production-scale thermodynamic
diffusion inference.
Read the full abstract ▾
Machine Learning
Heat and Matérn Kernels on Matchings
Dmitry Eremeev, Salem Said and Viacheslav Borovitskiy
Applying kernel methods to matchings is challenging due to their discrete, non-Euclidean nature. In this paper, we develop a principled framework for constructing
geometric kernels that respect the natural geometry of the space of matchings. To this end, we first provide a complete characterization of stationary kernels, i.e. kernels that respect the inherent
symmetries of this space. Because the class of stationary kernels is too broad, we specifically focus on the heat and Matérn kernel families, adding an appropriate inductive bias of smoothness to stationarity. While these families successfully extend widely popular Euclidean kernels to matchings, evaluating them naively incurs a prohibitive super-exponential computational cost. To overcome this difficulty, we introduce and analyze a novel, sub-exponential
algorithm leveraging zonal
polynomials for efficient kernel evaluation. Finally, motivated by the known bijective correspondence between matchings and phylogenetic trees-a crucial data modality in biology-we explore whether our framework can be seamlessly transferred to the space of trees, establishing novel negative results and identifying a significant open problem.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Doubly Outlier-Robust Online Infinite Hidden Markov Model
Horace Yiu, Leandro Sánchez-Betancourt, Álvaro Cartea et al. (+1 more)
We derive a robust update rule for the online infinite hidden Markov model (iHMM) for when the streaming data contains outliers and the model is misspecified. Leveraging recent advances in generalised
Bayesian inference, we define robustness via the posterior influence function (PIF), and provide conditions under which the online iHMM has bounded PIF. Imposing robustness inevitably induces an adaptation lag for regime switching. Our method, which is called Batched Robust iHMM (BR-iHMM), balances adaptivity and robustness with two additional tunable parameters. Across limit order book data, hourly electricity demand, and a synthetic high-dimensional linear system, BR-iHMM reduces one-step-ahead
forecasting error by up to 67% relative to competing online
Bayesian methods. Together with theoretical guarantees of bounded PIF, our results highlight the practicality of our approach for both
forecasting and interpretable online learning.
Read the full abstract ▾
All authors Horace Yiu, Leandro Sánchez-Betancourt, Álvaro Cartea, Gerardo Duran-Martin
Machine Learning · Cross-listed from stat.ME
Combining Bayesian and Frequentist Inference for Laboratory-Specific Performance Guarantees in Copy Number Variation Detection
Austin Talbot, Alex V. Kotlar and Yue Ke
Targeted amplicon panels are widely used in oncology diagnostics, but providing per-gene performance guarantees for copy number variant (CNV) detection remains challenging due to amplification artifacts, process-mismatch heterogeneity, and limited validation sample sizes. While
Bayesian CNV callers naturally quantify per-sample uncertainty, translating this into the frequentist population-level guarantees required for clinical validation, coverage rates, false-positive bounds, and minimum detectable copy-number changes, is a fundamentally different inferential problem. We show empirically that even robust
Bayesian credible intervals, including coarsened posteriors and sandwich-adjusted intervals, are severely miscalibrated on panels with small amplicon counts per gene. To address this, we propose a hybrid framework that evaluates
Bayesian posterior functionals on validation samples and models the resulting squared losses with a Gamma distribution, yielding tolerance intervals with valid frequentist coverage. Three components make the method practical under real-world constraints: (1) imputation that removes the influence of true CNV-positive samples without requiring known ground truth, (2) regularization to address small sample variability, and (3) evidence-based stratification on the log model evidence to accommodate non-exchangeable noise profiles arising from process mismatch. Evaluated on two targeted amplicon panels using leave-one-out cross-validation, the proposed method achieves single-digit mean absolute coverage error across all genes under both process-matched and unmatched conditions, whereas
Bayesian comparators exhibit mean absolute errors exceeding 60% on clinically relevant genes such as ERBB2.
Read the full abstract ▾
Machine Learning
Quantum-inspired tensor networks in machine learning models
Guillermo Valverde, Igor García-Olaizola, Giannicola Scarpa et al. (+1 more)
Tensor networks were developed in the context of many-body physics as compressed representations of multiparticle
quantum states. These representations mitigate the exponential complexity of many-body systems by capturing only the most relevant dependencies. Due to the formal similarity between
quantum entanglement and statistical correlations, tensor networks have recently been integrated in machine learning, operating both as alternative learning architectures and as decompositions of components of neural networks. The expectation is that the theoretical understanding of tensor networks developed within
quantum many-body physics leads to novel methods that offer advantages in terms of computational efficiency, explainability, or
privacy. Here we review the use of tensor networks in the context of machine learning, providing a critical assessment of the state of the art, the potential advantages, and the challenges that must be overcome.
Read the full abstract ▾
All authors Guillermo Valverde, Igor García-Olaizola, Giannicola Scarpa, Alejandro Pozas-Kerstjens
Machine Learning
Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization
Junzhe Wang, Zhiheng Xi, Yajie Yang et al. (+4 more)
Search
agents extend Large
Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for training such
agents, existing approaches face key limitations: process supervision often suffers from unstable value estimation, whereas outcome supervision struggles with credit assignment due to sparse, trajectory-level rewards. To bridge this gap, we propose Contribution-Weighted GRPO (CW-GRPO), a framework that integrates process supervision into group relative policy optimization. Instead of directly optimizing process rewards, CW-GRPO employs an LLM judge to assess the
retrieval utility and
reasoning correctness at each search round, producing per-round contribution scores. These scores are used to rescale outcome-based advantages along the trajectory, enabling fine-grained credit assignment without sacrificing optimization stability. Experiments on multiple knowledge-intensive
benchmarks show that CW-GRPO outperforms standard GRPO by 5.0% on Qwen3-8B and 6.3% on Qwen3-1.7B, leading to more effective search behaviors. Additional analysis reveals that successful trajectories exhibit concentrated contributions in specific rounds, providing empirical insight into search
agent tasks.
Read the full abstract ▾
All authors Junzhe Wang, Zhiheng Xi, Yajie Yang, Hao Luo, Shihan Dou, Tao Gui, Qi Zhang
Machine Learning
Reinforcement Learning via Value Gradient Flow
Haoran Xu, Kaiwen Hu, Somayeh Sojoudi et al. (+1 more)
We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the
dataset in offline RL or the base model in LLM RL finetuning) is essential to prevent value over-optimization caused by erroneous out-of-distribution extrapolation. Existing methods either rely on reparameterized policy gradient, which are difficult to scale to large generative models, or on reject sampling, which can be overly conservative when attempting to move beyond the behavior support. In this paper, we propose Value Gradient Flow (VGF), a scalable new paradigm for behavior-regularized RL. VGF casts behavior-regularized RL as an optimal transport problem that maps the reference distribution to the value-induced optimal policy distribution. We solve this transport problem via discrete gradient flow, where value gradients guide particles initialized from the reference distribution. Our analysis shows that VGF imposes regularization implicitly by controlling the transport budget. VGF eliminates explicit policy parameterization while remaining expressive and flexible, this enables adaptive test-time scaling by adjusting the transport budget. Extensive experiments demonstrate that VGF significantly outperforms prior methods, achieving state-of-the-art results on offline RL
benchmarks (D4RL, OGBench) and LLM RL tasks. Code and runs can be found at https://ryanxhr.github.io/vgf.
Read the full abstract ▾
All authors Haoran Xu, Kaiwen Hu, Somayeh Sojoudi, Amy Zhang
Machine Learning · Cross-listed from q-bio.TO
A deep learning framework for glomeruli segmentation with boundary attention
Behnaz Elhaminia, Catherine King, Jiaqi Lv et al. (+5 more)
Accurate detection and
segmentation of glomeruli in kidney tissue are essential for diagnostic applications. Traditional deep learning methods primarily rely on semantic
segmentation, which often fails to precisely delineate adjacent glomeruli. To address this challenge, we propose a novel glomerulus detection and
segmentation model that emphasises boundary separation. Leveraging pathology foundation models, the proposed U-Net-based architecture incorporates a specialised
attention decoder designed to highlight critical regions and improve instancelevel
segmentation. Experimental evaluations demonstrate that our approach surpasses state-of-the-art methods in both Dice score and Intersection over Union, indicating superior performance in glomerular delineation.
Read the full abstract ▾
All authors Behnaz Elhaminia, Catherine King, Jiaqi Lv, Lorraine Harper, Paul Moss, Owen Cain, Dimitrios Chanouzas, Shan E Ahmed Raza
Machine Learning
GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models
Yangyue Wang, Harshvardhan Sikka, Yash Mathur et al. (+3 more)
GUI grounding models report over 85% accuracy on standard
benchmarks, yet drop 27-56 percentage points when instructions require spatial
reasoning rather than direct element naming. Current
benchmarks miss this because they evaluate each screenshot once with a single fixed instruction. We introduce GUI-Perturbed, a controlled perturbation framework that independently varies visual scenes and instructions to measure grounding robustness. Evaluating three 7B models from the same architecture lineage, we find that relational instructions cause systematic accuracy collapse across all models, a 70% browser zoom produces statistically significant degradation, and rank-8 LoRA fine-tuning with augmented data degrades performance rather than improving it. By perturbing along independent axes, GUI-Perturbed isolates which specific capability axes are affected-spatial
reasoning, visual robustness,
reasoning calibration-providing diagnostic signal that aggregate
benchmarks cannot. We release the
dataset, augmentation pipeline, and a fine-tuned model.
Read the full abstract ▾
All authors Yangyue Wang, Harshvardhan Sikka, Yash Mathur, Tony Zhou, Jinu Nyachhyon, Pranav Guruprasad
Machine Learning · Cross-listed from q-bio.TO
Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replay
Qianyu Chen and Shujian Yu
Functional
magnetic resonance imaging (fMRI) is widely used for studying and diagnosing
brain disorders, with functional connectivity (FC)
matrices providing powerful representations of large-scale neural interactions. However, existing diagnostic models are trained either on a single site or under full multi-site access, making them unsuitable for real-world scenarios where clinical data arrive sequentially from different institutions. This results in limited generalization and severe catastrophic forgetting. This paper presents the first continual learning framework specifically designed for fMRI-based diagnosis across heterogeneous clinical sites. Our framework introduces a structure-aware variational autoencoder that synthesizes realistic FC
matrices for both patient and control groups. Built on this generative backbone, we develop a multi-level knowledge
distillation strategy that aligns predictions and graph representations between new-site data and replayed samples. To further enhance efficiency, we incorporate a hierarchical contextual bandit scheme for adaptive replay sampling. Experiments on multi-site
datasets for major depressive disorder (MDD), schizophrenia (SZ), and autism spectrum disorder (ASD) show that the proposed generative model enhances data augmentation quality, and the overall continual learning framework substantially outperforms existing methods in mitigating catastrophic forgetting. Our code is available at https://github.com/4me808/FORGE.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Wangjie Gan, Miao Pan, Linbo Xi et al. (+4 more)
Large
language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we provide a training-dynamics analysis showing that SFT can be interpreted as a special case of policy gradient optimization with an extremely sparse implicit reward and unstable inverse-probability weighting, which together lead to single-path dependency,
entropy collapse, and gradient explosion. Motivated by this diagnosis, we propose Group Fine-Tuning (GFT), a unified post-training framework that addresses these intrinsic limitations through two mechanisms: Group Advantage Learning, which constructs diverse response groups and derives normalized contrastive supervision to alleviate reward sparsity, and Dynamic Coefficient Rectification, which adaptively bounds inverse-probability weights to stabilize optimization while preserving efficient knowledge injection. Experiments demonstrate that GFT consistently surpasses SFT-based methods and yields policies that integrate more smoothly with subsequent RL training.
Read the full abstract ▾
All authors Wangjie Gan, Miao Pan, Linbo Xi, Wenqi Zhang, Jintao Chen, Jianwei Yin, Xuhong Zhang
Machine Learning
Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades
Edoardo Pona, Milad Kazemi, Mehran Hosseini et al. (+4 more)
Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalated to a more expensive expert. Existing cascades delegate based on probe uncertainty, but uncertainty is a poor proxy for the utility of an expert call, as it ignores whether the expert would actually improve the prediction. To address this problem, we introduce Calibrate-Then-Delegate (CTD), a model-cascade approach that provides probabilistic guarantees on either computation cost or safety performance while enabling instance-level (streaming) decisions. CTD builds on a novel delegation value (DV) probe, a lightweight model operating on the same internal representations as the safety probe that predicts the benefit of replacing the probe score with the expert score after an expert call. CTD calibrates a threshold on the DV signal using held-out data and multiple hypothesis testing, yielding finite-sample guarantees while optimising the complementary objective. Evaluated on four safety
datasets using learned-
attention probes, CTD improves over uncertainty-based delegation over much of the budget range, avoids unnecessary expert calls, and extracts positive-value subsets even from groups where the expert score is worse than the probe score on average. Ablations across four probe architectures show that these findings are not specific to any particular architecture.
Read the full abstract ▾
All authors Edoardo Pona, Milad Kazemi, Mehran Hosseini, Yali Du, David Watson, Osvaldo Simeone, Nicola Paoletti
Machine Learning
Metric-Aware Principal Component Analysis (MAPCA):A Unified Framework for Scale-Invariant Representation Learning
Michael Leznik
We introduce Metric-Aware Principal Component Analysis (MAPCA), a unified framework for scale-invariant representation learning based on the generalised eigenproblem max Tr(W^T Sigma W) subject to W^T M W = I, where M is a symmetric positive definite metric
matrix. The choice of M determines the representation geometry. The canonical beta-family M(beta) = Sigma^beta, beta in [0,1], provides continuous spectral bias control between standard PCA (beta=0) and output whitening (beta=1), with condition number kappa(beta) = (lambda_1/lambda_p)^(1-beta) decreasing monotonically to isotropy. The diagonal metric M = D = diag(Sigma) recovers Invariant PCA (IPCA), a method rooted in Frisch (1928) diagonal regression, as a distinct member of the broader framework. We prove that scale invariance holds if and only if the metric transforms as M_tilde = CMC under rescaling C, a condition satisfied exactly by IPCA but not by the general beta-family at intermediate values. Beyond its classical interpretation, MAPCA provides a
geometric language that unifies several self-supervised learning objectives. Barlow Twins and ZCA whitening correspond to beta=1 (output whitening); VICReg's variance term corresponds to the diagonal metric. A key finding is that W-MSE, despite being described as a whitening-based method, corresponds to M = Sigma^{-1} (beta = -1), outside the spectral compression range entirely and in the opposite spectral direction to Barlow Twins. This distinction between input and output whitening is invisible at the level of loss functions and becomes precise only within the MAPCA framework.
Read the full abstract ▾
Machine Learning
Awakening Dormant Experts:Counterfactual Routing to Mitigate MoE Hallucinations
Wentao Hu, Yanbo Zhai, Xiaohui Hu et al. (+6 more)
Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to
hallucinations, particularly when processing long-tail knowledge. We identify that this fragility stems from static Top-$k$ routing: routers tend to favor high-frequency patterns over rare factual associations. Consequently, “specialist experts” possessing critical long-tail knowledge are often assigned low gating scores and remain “dormant” – under-prioritized for specific
tokens despite their proven causal importance on other inputs. To address this, we propose Counterfactual Routing (CoR), a training-free inference framework designed to awaken these dormant experts. CoR integrates layer-wise perturbation analysis with the Counterfactual Expert Impact (CEI) metric to dynamically shift computational resources from syntax-dominant to knowledge-intensive layers while maintaining a constant total activation count, effectively retrieving causally decisive experts via virtual ablation. Extensive experiments on TruthfulQA, FACTOR, and TriviaQA demonstrate that CoR improves factual accuracy by 3.1% on average without increasing the inference budget, establishing a superior Pareto frontier compared to static scaling strategies.
Read the full abstract ▾
All authors Wentao Hu, Yanbo Zhai, Xiaohui Hu, Mingkuan Zhao, Shanhong yu, Xue Liu, Kaidong Yu, Shuangyong Song, Xuelong Li
Machine Learning
Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees
Sourav Ganguly, Kartik Pandit and Arnob Ghosh
Real-world decision-making systems operate in environments where state transitions depend not only on the
agent's actions, but also on exogenous factors outside its control–competing
agents, environmental disturbances, or strategic adversaries–formally, $s_{h+1} = f(s_h, a_h, \bar{a}_h)+\omega_h$ where $\bar{a}_h$ is the adversary/external action, $a_h$ is the
agent's action, and $\omega_h$ is an additive noise. Ignoring such factors can yield policies that are optimal in isolation but fail catastrophically in deployment, particularly when safety constraints must be satisfied. Standard Constrained MDP formulations assume the
agent is the sole driver of state
evolution, an assumption that breaks down in safety-critical settings. Existing robust RL approaches address this via distributional robustness over transition kernels, but do not explicitly model the strategic interaction between
agent and exogenous factor, and rely on strong assumptions about divergence from a known nominal model. We model the exogenous factor as an
adversarial policy $\bar{\pi}$ that co-determines state transitions, and ask how an
agent can remain both optimal and safe against such an adversary. To the best of our knowledge, this is the first work to study safety-constrained RL under explicit
adversarial dynamics. We propose Robust Hallucinated Constrained Upper-Confidence RL (RHC-UCRL), a model-based
algorithm that maintains optimism over both
agent and adversary policies, explicitly separating epistemic from aleatoric uncertainty. RHC-UCRL achieves sub-linear regret and constraint violation guarantees.
Read the full abstract ▾
Machine Learning · Cross-listed from q-bio.BM
Polyformer: a generative framework for thermodynamic modeling of polymeric molecules
Alessio Valentini, David Pekker, Chungwen Liang et al. (+2 more)
The classic paradigm of structural biology is that the sequence of a biomolecule (
protein, nucleic acid, lipid, etc) determines its conformation (shape) which determines its biological function.
Protein folding programs like AlphaFold address this paradigm by predicting the single best conformation given a sequence that defines the molecule. However, biomolecules are not static structures, and their conformational ensemble determines their function. We present the Polyformer – a generative framework for thermodynamic modeling of polymeric molecules. Given the sequence and temperature (or another thermodynamic variable), the Polyformer generates conformations faithful to the molecule's thermodynamic conformational ensemble. It is the first generative model that solves three problems simultaneously: how does a molecule fold, what is its conformational ensemble, and how does the conformational ensemble change as we change physical temperature. As a concrete test case, we apply Polyformer to
protein domains with 50-111 residues and report good agreement of model predictions to Molecular Dynamics (MD) trajectories.
Read the full abstract ▾
All authors Alessio Valentini, David Pekker, Chungwen Liang, Todd Martinez, Swagatam Mukhopadhyay
Machine Learning · Cross-listed from cs.AI
Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making
Pramudita Satria Palar, Paul Saves, Muhammad Daffa Robani et al. (+6 more)
The simulation of complex systems increasingly relies on sophisticated but fundamentally opaque computational black-box simulators. Surrogate models play a central role in reducing the computational cost of complex systems simulations across a wide range of scientific and engineering domains. Notwithstanding, they inevitably inherit and often exacerbate this black-box nature, obscuring how input variables drive physical responses. Conversely, Explainable Artificial Intelligence (XAI) offers powerful tools to unpack these models. Yet, XAI methods struggle with engineering-specific constraints, such as highly correlated inputs, dynamical systems, and rigorous reliability requirements. Consequently, surrogate modeling and XAI have largely evolved as distinct fields of research, despite their strong complementarity. To reconnect these approaches, this state-of-the-art survey provides a structured perspective that maps existing XAI techniques onto the various stages of surrogate modeling workflows for design and exploration. To ground this synthesis, we draw upon illustrative applications across both equation-based simulations and
agent-based modeling. We survey a broad spectrum of techniques, highlighting their strengths for revealing interactions and supporting human comprehension. Finally, we identify pressing open challenges, including the explainability of dynamical systems and the handling of mixed-variable systems, and propose a research agenda to make explainability a core, embedded element of simulation-driven workflows from model construction through decision-making. By transforming opaque emulators into explainable tools, this agenda empowers practitioners to move beyond accelerating simulations to extracting actionable insights from complex system behaviors.
Read the full abstract ▾
All authors Pramudita Satria Palar, Paul Saves, Muhammad Daffa Robani, Nicolas Verstaevel, Moncef Garouani, Julien Aligon, Koji Shimoyama, Joseph Morlier, Benoit Gaudou
Machine Learning
TOPCELL: Topology Optimization of Standard Cell via LLMs
Zhan Song, Yu-Tung Liu, Chen Chen et al. (+6 more)
Transistor
topology optimization is a critical step in standard
cell design, directly dictating
diffusion sharing efficiency and downstream routability. However, identifying optimal
topologies remains a persistent bottleneck, as conventional exhaustive search methods become computationally intractable with increasing
circuit complexity in advanced nodes. This paper introduces TOPCELL, a novel and scalable framework that reformulates high-dimensional
topology exploration as a generative task using Large
Language Models (LLMs). We employ Group Relative Policy Optimization (GRPO) to fine-tune the model, aligning its
topology optimization strategy with logical (
circuit) and spatial (layout) constraints. Experimental results within an industrial flow targeting an advanced 2nm technology node demonstrate that TOPCELL significantly outperforms foundation models in discovering routable, physically-aware
topologies. When integrated into a state-of-the-art (SOTA) automation flow for a 7nm library generation task, TOPCELL exhibits robust zero-shot generalization and matches the layout quality of exhaustive solvers while achieving an 85.91x speedup.
Read the full abstract ▾
All authors Zhan Song, Yu-Tung Liu, Chen Chen, Guoheng Sun, Jiaqi Yin, Chia-tung Ho, Ang Li, Haoxing Ren, Cunxi Yu
Machine Learning
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
Yuqiao Tan, Minzheng Wang, Bo Liu et al. (+5 more)
While reinforcement learning with verifiable rewards (RLVR) significantly enhances LLM
reasoning by optimizing the conditional distribution P(y|x), its potential is fundamentally bounded by the base model's existing output distribution. Optimizing the marginal distribution P(y) in the Pre-train Space addresses this bottleneck by encoding
reasoning ability and preserving broad exploration capacity. Yet, conventional pre-training relies on static corpora for passive learning, leading to a distribution shift that hinders targeted
reasoning enhancement. In this paper, we introduce PreRL (Pre-train Space RL), which applies reward-driven online updates directly to P(y). We theoretically and empirically validate the strong gradient
alignment between log P(y) and log P(y|x), establishing PreRL as a viable surrogate for standard RL. Furthermore, we uncover a critical mechanism: Negative Sample Reinforcement (NSR) within PreRL serves as an exceptionally effective driver for
reasoning. NSR-PreRL rapidly prunes incorrect
reasoning spaces while stimulating endogenous reflective behaviors, increasing transition and reflection thoughts by 14.89x and 6.54x, respectively. Leveraging these insights, we propose Dual Space RL (DSRL), a Policy Reincarnation strategy that initializes models with NSR-PreRL to expand the
reasoning horizon before transitioning to standard RL for fine-grained optimization. Extensive experiments demonstrate that DSRL consistently outperforms strong baselines, proving that pre-train space
pruning effectively steers the policy toward a refined correct
reasoning subspace.
Read the full abstract ▾
All authors Yuqiao Tan, Minzheng Wang, Bo Liu, Zichen Liu, Tian Liang, Shizhu He, Jun Zhao, Kang Liu
Machine Learning
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
Sumeet Ramesh Motwani, Daniel Nichols, Charles London et al. (+17 more)
As
language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this ability is planning and managing a long, complex chain-of-thought (CoT). We introduce LongCoT, a scalable
benchmark of 2,500 expert-designed problems spanning chemistry, mathematics, computer science, chess, and logic to isolate and directly measure the long-horizon CoT
reasoning capabilities of frontier models. Problems consist of a short input with a verifiable answer; solving them requires navigating a graph of interdependent steps that span tens to hundreds of thousands of
reasoning tokens. Each local step is individually tractable for frontier models, so failures reflect long-horizon
reasoning limitations. At release, the best models achieve <10% accuracy (GPT 5.2: 9.8%; Gemini 3 Pro: 6.1%) on LongCoT, revealing a substantial gap in current capabilities. Overall, LongCoT provides a rigorous measure of long-horizon
reasoning, tracking the ability of frontier models to reason reliably over extended periods.
Read the full abstract ▾
All authors Sumeet Ramesh Motwani, Daniel Nichols, Charles London, Peggy Li, Fabio Pizzati, Acer Blake, Hasan Hammoud, Tavish McDonald, Akshat Naik, Alesia Ivanova, Vignesh Baskaran, Ivan Laptev, Ruben Glatt, Tal Ben-Nun, Philip Torr, Natasha Jaques, Ameya Prabhu, Brian Bartoldson, Bhavya Kailkhura, Christian Schroeder de Witt
Machine Learning · Cross-listed from cs.CL
From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs
Itay Itzhak, Eliya Habba, Gabriel Stanovsky et al. (+1 more)
Evaluating LLMs is challenging, as
benchmark scores often fail to capture models' real-world usefulness. Instead, users often rely on “vibe-testing”: informal experience-based evaluation, such as comparing models on coding tasks related to their own workflow. While prevalent, vibe-testing is often too ad hoc and unstructured to analyze or reproduce at scale. In this work, we study how vibe-testing works in practice and then formalize it to support systematic analysis. We first analyze two empirical resources: (1) a survey of user evaluation practices, and (2) a collection of in-the-wild model comparison reports from blogs and social media. Based on these resources, we formalize vibe-testing as a two-part process: users personalize both what they test and how they judge responses. We then introduce a proof-of-concept evaluation pipeline that follows this formulation by generating personalized
prompts and comparing model outputs using user-aware subjective criteria. In experiments on coding
benchmarks, we find that combining personalized
prompts and user-aware evaluation can change which model is preferred, reflecting the role of vibe-testing in practice. These findings suggest that formalized vibe-testing can serve as a useful approach for bridging
benchmark scores and real-world experience.
Read the full abstract ▾
All authors Itay Itzhak, Eliya Habba, Gabriel Stanovsky, Yonatan Belinkov
Machine Learning · Cross-listed from cs.CL
Rhetorical Questions in LLM Representations: A Linear Probing Study
Louie Hong Yao, Vishesh Anand, Yuan Zhuang et al. (+1 more)
Rhetorical questions are asked not to seek information but to persuade or signal stance. How large
language models internally represent them remains unclear. We analyze rhetorical questions in LLM representations using linear probes on two social-media
datasets with different discourse contexts, and find that rhetorical signals emerge early and are most stably captured by last-
token representations. Rhetorical questions are linearly separable from information-seeking questions within
datasets, and remain detectable under cross-
dataset transfer, reaching AUROC around 0.7-0.8. However, we demonstrate that transferability does not simply imply a shared representation. Probes trained on different
datasets produce different rankings when applied to the same target corpus, with overlap among the top-ranked instances often below 0.2. Qualitative analysis shows that these divergences correspond to distinct rhetorical phenomena: some probes capture discourse-level rhetorical stance embedded in extended argumentation, while others emphasize localized, syntax-driven interrogative acts. Together, these findings suggest that rhetorical questions in LLM representations are encoded by multiple linear directions emphasizing different cues, rather than a single shared direction.
Read the full abstract ▾
All authors Louie Hong Yao, Vishesh Anand, Yuan Zhuang, Tianyu Jiang
Machine Learning
Complex Interpolation of Matrices with an application to Multi-Manifold Learning
Adi Arbel, Stefan Steinerberger and Ronen Talmon
Given two symmetric positive-definite
matrices $A, B \in \mathbb{R}^{n \times n}$, we study the spectral properties of the interpolation $A^{1-x} B^x$ for $0 \leq x \leq 1$. The presence of `common structures' in $A$ and $B$, eigenvectors pointing in a similar direction, can be investigated using this interpolation perspective. Generically, exact log-linearity of the operator norm $\|A^{1-x} B^x\|$ is equivalent to the existence of a shared eigenvector in the original
matrices; stability bounds show that approximate log-linearity forces principal singular vectors to align with leading eigenvectors of both
matrices. These results give rise to and provide theoretical justification for a multi-
manifold learning framework that identifies common and distinct latent structures in multiview data.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.IR
ID and Graph View Contrastive Learning with Multi-View Attention Fusion for Sequential Recommendation
Xiaofan Zhou and Kyumin Lee
Sequential recommendation has become increasingly prominent in both academia and industry, particularly in e-commerce. The primary goal is to extract user preferences from historical interaction sequences and predict items a user is likely to engage with next. Recent advances have leveraged contrastive learning and graph neural networks to learn more expressive representations from interaction histories – graphs capture relational structure between nodes, while ID-based representations encode item-specific information. However, few studies have explored multi-view contrastive learning between ID and graph perspectives to jointly improve user and item representations, especially in settings where only interaction data is available without auxiliary information. To address this gap, we propose Multi-View Contrastive learning for sequential recommendation (MVCrec), a framework that integrates complementary signals from both sequential (ID-based) and graph-based views. MVCrec incorporates three contrastive objectives: within the sequential view, within the graph view, and across views. To effectively fuse the learned representations, we introduce a multi-view
attention fusion module that combines global and local
attention mechanisms to estimate the likelihood of a target user purchasing a target item. Comprehensive experiments on five real-world
benchmark datasets demonstrate that MVCrec consistently outperforms 11 state-of-the-art baselines, achieving improvements of up to 14.44% in NDCG@10 and 9.22% in HitRatio@10 over the strongest baseline. Our code and
datasets are available at https://github.com/sword-Lz/MMCrec.
Read the full abstract ▾
Machine Learning
Momentum Further Constrains Sharpness at the Edge of Stochastic Stability
Arseniy Andreyev, Advikar Ananthkumar, Marc Walden et al. (+2 more)
Recent work suggests that (
stochastic) gradient descent self-organizes near an instability boundary, shaping both optimization and the solutions found. Momentum and mini-batch gradients are widely used in practical deep learning optimization, but it remains unclear whether they operate in a comparable regime of instability. We demonstrate that SGD with momentum exhibits an Edge of
Stochastic Stability (EoSS)-like regime with batch-size-dependent behavior that cannot be explained by a single momentum-adjusted stability threshold. Batch Sharpness (the expected directional mini-batch
curvature) stabilizes in two distinct regimes: at small batch sizes it converges to a lower plateau $2(1-\beta)/\eta$, reflecting amplification of
stochastic fluctuations by momentum and favoring flatter regions than vanilla SGD; at large batch sizes it converges to a higher plateau $2(1+\beta)/\eta$, where momentum recovers its classical stabilizing effect and favors sharper regions consistent with full-batch dynamics. We further show that this aligns with linear stability thresholds and discuss the implications for hyperparameter tuning and coupling.
Read the full abstract ▾
All authors Arseniy Andreyev, Advikar Ananthkumar, Marc Walden, Tomaso Poggio, Pierfrancesco Beneventano
Machine Learning
Yuanda Xu, Hejian Sang, Zhengze Zhou et al. (+3 more)
On-policy knowledge
distillation (OPD) trains a student on its own rollouts under
token-level supervision from a teacher. Not all
token positions matter equally, but existing views of
token importance are incomplete. We ask a direct question: which
tokens carry the most useful learning signal in OPD? Our answer is that informative
tokens come from two regions: positions with high student
entropy, and positions with low student
entropy plus high teacher–student divergence, where the student is overconfident and wrong. Empirically, student
entropy is a strong first-order proxy: retaining $50\%$ of
tokens with
entropy-based sampling matches or exceeds all-
token training while reducing peak
memory by up to $47\%$. But
entropy alone misses a second important region. When we isolate low-
entropy, high-divergence
tokens, training on fewer than $10\%$ of all
tokens nearly matches full-
token baselines, showing that overconfident
tokens carry dense corrective signal despite being nearly invisible to
entropy-only rules. We organize these findings with TIP (
Token Importance in on-Policy
distillation), a two-axis taxonomy over student
entropy and teacher–student divergence, and give a theoretical explanation for why
entropy is useful yet structurally incomplete. This view motivates type-aware
token selection rules that combine uncertainty and disagreement. We validate this picture across three teacher–student pairs spanning Qwen3, Llama, and Qwen2.5 on MATH-500 and AIME 2024/2025, and on the DeepPlanning
benchmark for long-horizon agentic planning, where Q3-only training on $<$$20\%$ of
tokens surpasses full-
token OPD. Our experiments are implemented by extending the OPD repository https://github.com/HJSang/OPSD_OnPolicyDistillation, which supports
memory-efficient
distillation of larger models under limited GPU budgets.
Read the full abstract ▾
All authors Yuanda Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang, Alborz Geramifard
Machine Learning · Cross-listed from math.OC
Multistage Conditional Compositional Optimization
Buse Şen, Yifan Hu and Daniel Kuhn
We introduce Multistage Conditional Compositional Optimization (MCCO) as a new paradigm for decision-making under uncertainty that combines aspects of multistage
stochastic programming and conditional
stochastic optimization. MCCO minimizes a nest of conditional expectations and nonlinear cost functions. It has numerous applications and arises, for example, in optimal stopping, linear-quadratic regulator problems, distributionally robust contextual bandits, as well as in problems involving dynamic risk measures. The naïve nested sampling approach for MCCO suffers from the curse of dimensionality familiar from scenario tree-based multistage
stochastic programming, that is, its scenario complexity grows exponentially with the number of nests. We develop new multilevel Monte Carlo techniques for MCCO whose scenario complexity grows only polynomially with the desired accuracy.
Read the full abstract ▾
Machine Learning
Neural architectures for resolving references in program code
Gergő Szalay, Gergely Zsolt Kovács, Sándor Teleki et al. (+2 more)
Resolving and rewriting references is fundamental in programming
languages. Motivated by a real-world decompilation task, we abstract reference rewriting into the problems of direct and indirect indexing by permutation. We create synthetic
benchmarks for these tasks and show that well-known sequence-to-sequence machine learning architectures are struggling on these
benchmarks. We introduce new sequence-to-sequence architectures for both problems. Our measurements show that our architectures outperform the baselines in both robustness and scalability: our models can handle examples that are ten times longer compared to the best baseline. We measure the impact of our architecture in the real-world task of decompiling switch statements, which has an indexing subtask. According to our measurements, the extended model decreases the error rate by 42%. Multiple ablation studies show that all components of our architectures are essential.
Read the full abstract ▾
All authors Gergő Szalay, Gergely Zsolt Kovács, Sándor Teleki, Balázs Pintér, Tibor Gregorics