Machine Learning
Compressing LLMs with MoP: Mixture of Pruners
Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Victor Zacarias et al. (+7 more)
The high computational demands of Large
Language Models (LLMs) motivate methods that reduce parameter count and accelerate inference. In response, model
pruning emerges as an effective strategy, yet current methods typically focus on a single dimension-depth or width. We introduce MoP (Mixture of Pruners), an iterative framework that unifies these dimensions. At each iteration, MoP generates two branches-
pruning in depth versus
pruning in width-and selects a candidate to advance the path. On LLaMA-2 and LLaMA-3, MoP advances the frontier of structured
pruning, exceeding the accuracy of competing methods across a broad set of compression regimes. It also consistently outperforms depth-only and width-only
pruning. Furthermore, MoP translates structural
pruning into real speedup, reducing end-to-end latency by 39% at 40% compression. Finally, extending MoP to the
vision-
language model LLaVA-1.5, we notably improve computational efficiency and demonstrate that text-only recovery fine-tuning can restore performance even on visual tasks.
Read the full abstract ▾
All authors Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Victor Zacarias, Leandro Giusti Mugnaini, Keith Ando Ogawa, Lucas Pellicer, Rosimeire Pereira Costa, Edson Bollis, Anna Helena Reali Costa, Artur Jordao
Machine Learning
Private and interpretable clinical prediction with quantum-inspired tensor train models
José Ramón Pareja Monturiol, Juliette Sinnott, Roger G. Melko et al. (+1 more)
Publicly available clinical machine learning models pose an underappreciated
privacy risk: their parameters or outputs can be exploited to recover information from patients whose data were used during training. Moreover, this risk is exacerbated by models such as logistic regression (LR), which are typically preferred in clinical settings for their transparency. To assess this empirically, we attack LORIS, a publicly available LR model for immunotherapy response prediction hosted on a U.S. government website. From evaluations through its public interface, we recover the model parameters and identify the training cohort with high confidence. More broadly, we design cohort-level membership inference attacks under three levels of
adversarial access—binary black-box, continuous black-box, and white-box—and apply them to both LR models and shallow neural networks (NNs) trained on the same task. Our results reveal that even a cohort of 35 patients can be reliably identified within training sets of hundreds to thousands, and that common practices such as cross-validation amplify rather than mitigate this risk. To address these vulnerabilities, we propose a
quantum-inspired defense based on tensorizing discretized models into tensor trains (TTs). This representation obfuscates model parameters and preserves accuracy, while offering black-box protection comparable to practical Differential
Privacy baselines. Additionally, the TT representations retain LR interpretability and extend it through efficient computation of marginal and conditional distributions, enabling this richer analysis also for black-box models such as NNs. Our results establish tensorization as a practical, post-hoc tool for private, interpretable, and effective clinical prediction.
Read the full abstract ▾
All authors José Ramón Pareja Monturiol, Juliette Sinnott, Roger G. Melko, Mohammad Kohandel
Machine Learning · Cross-listed from stat.ML
Robustness Verification of Polynomial Neural Networks
Yulia Alexandr, Hao Duan and Guido Montúfar
We study robustness verification of neural networks via metric algebraic geometry. For
polynomial neural networks, certifying a robustness radius amounts to computing the distance to the algebraic decision boundary. We use the Euclidean distance (ED) degree as an intrinsic measure of the complexity of this problem, analyze the associated ED discriminant, and introduce a parameter discriminant that detects parameter values at which the ED degree drops. We derive formulas for the ED degree for several network architectures and characterize the expected number of real critical points in the infinite-width limit. We develop symbolic elimination methods to compute these quantities and homotopy-continuation methods for exact robustness certification. Finally, experiments on lightning self-
attention modules reveal decision boundaries with strictly smaller ED degree than generic cubic hypersurfaces of the same ambient dimension.
Read the full abstract ▾
Machine Learning
Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference
Yingke Li, Anjali Parashar, Enlu Zhou et al. (+1 more)
Many engineering and scientific workflows rely on expensive black-box evaluations, requiring sequential decisions that must both improve task performance and reduce uncertainty.
Bayesian optimization (BO) and
Bayesian experimental design (BED) provide powerful but largely separate treatments of goal-directed optimization and information-seeking experimentation, leaving limited guidance for hybrid settings in which learning and optimization are intrinsically coupled. We propose Pragmatic Curiosity (PraC), a unified framework for hybrid learning and optimization via active inference. PraC evaluates candidate queries by trading information gain about a task-relevant latent symbol against an expected regret-based potential over outcomes. This formulation exposes three operational design choices: which latent quantity should be clarified, how task value is encoded as regret, and how strongly information gain should be exchanged against pragmatic value. We instantiate PraC across three regimes of increasing complexity: decision-oriented plume monitoring with fixed global symbols and known downstream losses, targeted active search with induced local symbols and evolving coverage goals, and composite
Bayesian optimization with hierarchical regret learning under unknown preferences. Across these regimes, PraC reduces downstream decision risk, improves coverage of critical outcome regions, and jointly learns predictive and preference structures without relying on task-specific staging rules.
Read the full abstract ▾
All authors Yingke Li, Anjali Parashar, Enlu Zhou, Chuchu Fan
Machine Learning
Toward Faithful and Complete Answer Construction from a Single Document
Zhaoyang Chen and Cody Fleming
Modern large
language models (LLMs) are powerful generators driven by statistical next-
token prediction. While effective at producing fluent text, this design biases models toward high-probability continuations rather than exhaustive and faithful answers grounded in source content. As a result, directly applying LLMs lacks systematic mechanisms to ensure both completeness (avoiding omissions) and faithfulness (avoiding unsupported content), which fundamentally conflicts with core AI safety principles. To address this limitation, we present EVE, a structured framework for document-grounded
reasoning. Unlike free-form prompting, EVE constrains generation to a structured, verifiable pipeline that decomposes high-rigor
reasoning into extraction, validation, and enumeration. Empirically, this design enables consistent and simultaneous improvements in recall, precision, and F1-score: recall and precision increase by up to 24% and 29%, respectively, with a corresponding 31% gain in F1-score. This effectively breaks the long-standing trade-off between coverage and accuracy typical of single-pass LLM generation, while also mitigating generation truncation caused by length limitations. At the same time, we emphasize that EVE exhibits performance saturation due to the inherent ambiguity of natural
language, reflecting fundamental limits of
language-based
reasoning.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SE
A Theoretical Analysis of Test-Driven Code Generation
Nicolas Menet, Michael Hersche, Andreas Krause et al. (+1 more)
Code assistants are increasingly utilized in test-driven software development, yet the theoretical mechanisms behind their environment-interaction strategies remain underexplored. We provide a probabilistic framework for two dominant paradigms: code selection after generation using the execution environment, and code generation conditioned on environment feedback. First, we formalize several well-established selection heuristics as environment-aware
estimators of code correctness. We theoretically prove that
estimators based on fuzzy functional similarity add an inductive bias and strictly dominate
estimators based on functional equivalence in terms of signal-to-noise ratio. Second, we frame backprompting as an in-context approximation of Thompson sampling. We derive a novel regret bound for reward functions with unobservable components, theoretically explaining why the effectiveness of backprompting is limited by the ambiguity of the informal task description (an irreducible regret). Using seven state-of-the-art open weight models, we corroborate these findings across BigCodeBenchHard, LeetCodeDataset, QiskitHumanEvalSim, and SWE-bench Verified. Our formalization also suggests how to improve task descriptions effectively, leading to an improved
benchmark for LLM-assisted
quantum programming, QiskitHumanEvalSimX.
Read the full abstract ▾
All authors Nicolas Menet, Michael Hersche, Andreas Krause, Abbas Rahimi
Machine Learning
Agentic Workflow Using RBA$_\theta$ for Event Prediction
Purbak Sengupta, Sambeet Mishra and Sonal Shreya
Wind power ramp events are difficult to forecast due to strong variability, multi-scale dynamics, and site-specific meteorological effects. This paper proposes an event-first, frequency-aware
forecasting paradigm that directly predicts ramp events and reconstructs the power trajectory thereafter, rather than inferring events from dense forecasts. The framework is built on an enhanced Ramping Behaviour Analysis (RBA$_\theta$) method's event representation and progressively integrates statistical, machine-learning, and deep-learning models. Traditional
forecasting models with post-hoc event extraction provides a strong interpretable baseline but exhibits limited generalisation across sites. Direct event prediction using Random Forests improves robustness over survival-based formulations, motivating fully event-aware modelling. To capture the multi-scale nature of wind ramps, we introduce an event-first deep architecture that integrates wavelet-based frequency decomposition, temporal excitation features, and adaptive feature selection. The resulting sequence models enable stable long-horizon event prediction, physically consistent trajectory reconstruction, and zero-shot transfer to previously unseen wind farms. Empirical analysis shows that ramp magnitude and duration are governed by distinct mid-frequency bands, allowing accurate signal reconstruction from sparse event forecasts. An agentic
forecasting layer is proposed, in which specialised workflows are selected dynamically based on operational context. Together, the framework demonstrates that event-first, frequency-aware
forecasting provides a transferable and operationally aligned alternative to trajectory-first wind-power prediction.
Read the full abstract ▾
Machine Learning
NanoNet: Parameter-Efficient Learning with Label-Scarce Supervision for Lightweight Text Mining Model
Qianren Mao, Yashuo Luo, Ziqi Qin et al. (+12 more)
The lightweight semi-supervised learning (LSL) strategy provides an effective approach of conserving labeled samples and minimizing model inference costs. Prior research has effectively applied knowledge transfer learning and co-training regularization from large to small models in LSL. However, such training strategies are computationally intensive and prone to local optima, thereby increasing the difficulty of finding the optimal solution. This has prompted us to investigate the feasibility of integrating three low-cost scenarios for text mining tasks: limited labeled supervision, lightweight fine-tuning, and rapid-inference small models. We propose NanoNet, a novel framework for lightweight text mining that implements parameter-efficient learning with limited supervision. It employs online knowledge
distillation to generate multiple small models and enhances their performance through mutual learning regularization. The entire process leverages parameter-efficient learning, reducing training costs and minimizing supervision requirements, ultimately yielding a lightweight model for downstream inference.
Read the full abstract ▾
All authors Qianren Mao, Yashuo Luo, Ziqi Qin, Junnan Liu, Weifeng Jiang, Zhijun Chen, Zhuoran Li, Likang Xiao, Chuou Xu, Qili Zhang, Hanwen Hao, Jingzheng Li, Chunghua Lin, Jianxin Li, Philip S. Yu
Machine Learning
Transformer-Based Reinforcement Learning for Autonomous Orbital Collision Avoidance in Partially Observable Environments
Thomas Georges and Adam Abdin
We introduce a
Transformer-based Reinforcement Learning framework for autonomous orbital collision avoidance that explicitly models the effects of partial observability and imperfect monitoring in space operations. The framework combines a configurable encounter simulator, a distance-dependent observation model, and a sequential state
estimator to represent uncertainty in relative motion. A central contribution of this work is the use of
transformer-based Partially Observable Markov Decision Process (POMDP) architecture, which leverage long-range temporal
attention to interpret noisy and intermittent observations more effectively than traditional architectures. This integration provides a foundation for training collision avoidance
agents that can operate more reliably under imperfect monitoring environments.
Read the full abstract ▾
Machine Learning
Shared LoRA Subspaces for almost Strict Continual Learning
Prakhar Kaushik, Ankit Vaidya, Shravan Chaudhari et al. (+2 more)
Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high cost of retraining. While parameter-efficient tuning methods like low rank adaptation (LoRA) reduce computational demands, they lack mechanisms for strict continual learning and knowledge integration, without relying on data replay, or multiple adapters. We propose Share, a novel approach to parameter efficient continual finetuning that learns and dynamically updates a single, shared low-rank subspace, enabling seamless adaptation across multiple tasks and modalities. Share constructs a foundational subspace that extracts core knowledge from past tasks and incrementally integrates new information by identifying essential subspace directions. Knowledge from each new task is incorporated into this evolving subspace, facilitating forward knowledge transfer, while minimizing catastrophic interference. This approach achieves up to 100x parameter reduction and 281x
memory savings over traditional LoRA methods, maintaining performance comparable to jointly trained models. A single Share model can replace hundreds of task-specific LoRA adapters, supporting scalable, asynchronous continual learning. Experiments across image classification, natural
language understanding, 3D pose estimation, and text-to-image generation validate its effectiveness, making Share a practical and scalable solution for lifelong learning in large-scale AI systems.
Read the full abstract ▾
All authors Prakhar Kaushik, Ankit Vaidya, Shravan Chaudhari, Rama Chellappa, Alan Yuille
Machine Learning
Pseudo-Invertible Neural Networks
Yamit Ehrlich, Nimrod Berman and Assaf Shocher
The Moore-Penrose Pseudo-inverse (PInv) serves as the fundamental solution for linear systems. In this paper, we propose a natural generalization of PInv to the nonlinear regime in general and to neural networks in particular. We introduce Surjective Pseudo-invertible Neural Networks (SPNN), a class of architectures explicitly designed to admit a tractable non-linear PInv. The proposed non-linear PInv and its implementation in SPNN satisfy fundamental
geometric properties. One such property is null-space projection or "Back-Projection", $x' = x + A^\dagger(y-Ax)$, which moves a sample $x$ to its closest consistent state $x'$ satisfying $Ax=y$. We formalize Non-Linear Back-Projection (NLBP), a method that guarantees the same consistency constraint for non-linear mappings $f(x)=y$ via our defined PInv. We leverage SPNNs to expand the scope of zero-shot inverse problems.
Diffusion-based null-space projection has revolutionized zero-shot solving for linear inverse problems by exploiting closed-form back-projection. We extend this method to non-linear degradations. Here, "degradation" is broadly generalized to include any non-linear loss of information, spanning from optical distortions to semantic abstractions like classification. This approach enables zero-shot inversion of complex degradations and allows precise semantic control over generative outputs without retraining the
diffusion prior.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
CommCP: Efficient Multi-Agent Coordination via LLM-Based Communication with Conformal Prediction
Xiaopan Zhang, Zejin Wang, Zhixu Li et al. (+2 more)
To complete assignments provided by humans in natural
language,
robots must interpret commands, generate and answer relevant questions for scene understanding, and manipulate target objects. Real-world deployments often require multiple heterogeneous
robots with different manipulation capabilities to handle different assignments cooperatively. Beyond the need for specialized manipulation skills, effective information gathering is important in completing these assignments. To address this component of the problem, we formalize the information-gathering process in a fully cooperative setting as an underexplored multi-
agent multi-task
Embodied Question Answering (MM-EQA) problem, which is a novel extension of canonical
Embodied Question Answering (EQA), where effective communication is crucial for coordinating efforts without redundancy. To address this problem, we propose CommCP, a novel LLM-based decentralized communication framework designed for MM-EQA. Our framework employs conformal prediction to calibrate the generated messages, thereby minimizing receiver distractions and enhancing communication reliability. To evaluate our framework, we introduce an MM-EQA
benchmark featuring diverse, photo-realistic household scenarios with
embodied questions. Experimental results demonstrate that CommCP significantly enhances the task success rate and exploration efficiency over baselines. The experiment
videos, code, and
dataset are available on our project website: https://comm-cp.github.io.
Read the full abstract ▾
All authors Xiaopan Zhang, Zejin Wang, Zhixu Li, Jianpeng Yao, Jiachen Li
Machine Learning
Can Vision Language Models Learn Intuitive Physics from Interaction?
Luca M. Schulze Buschoff, Konstantinos Voudouris, Can Demircan et al. (+1 more)
Pre-trained
vision language models do not have good intuitions about the physical world. Recent work has shown that supervised fine-tuning can improve model performance on simple physical tasks. However, fine-tuned models do not appear to learn robust physical rules that can generalize to new contexts. Based on research in cognitive science, we hypothesize that models need to interact with an environment to properly learn its physical dynamics. We train models that learn through interaction with a simulated environment using reinforcement learning. While learning from interaction allows models to improve their within-task performance, it fails to produce models with generalizable physical intuitions. We find that models trained on one task do not reliably generalize to related tasks, even if the tasks share visual statistics and physical principles, and regardless of whether the models are trained through interaction.
Read the full abstract ▾
All authors Luca M. Schulze Buschoff, Konstantinos Voudouris, Can Demircan, Eric Schulz
Machine Learning
AP-OOD: Attention Pooling for Out-of-Distribution Detection
Claus Hofmann, Christian Huber, Bernhard Lehner et al. (+3 more)
Out-of-distribution (OOD) detection, which maps high-dimensional data into a scalar OOD score, is critical for the reliable deployment of machine learning models. A key challenge in recent research is how to effectively leverage and aggregate
token embeddings from
language models to obtain the OOD score. In this work, we propose AP-OOD, a novel OOD detection method for natural
language that goes beyond simple average-based aggregation by exploiting
token-level information. AP-OOD is a semi-supervised approach that flexibly interpolates between unsupervised and supervised settings, enabling the use of limited auxiliary outlier data. Empirically, AP-OOD sets a new state of the art in OOD detection for text: in the unsupervised setting, it reduces the FPR95 (false positive rate at 95% true positives) from 27.84% to 4.67% on XSUM summarization, and from 77.08% to 70.37% on WMT15 En-Fr translation.
Read the full abstract ▾
All authors Claus Hofmann, Christian Huber, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter, Werner Zellinger
Machine Learning · Cross-listed from cs.MA
PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling
Kavana Venkatesh, Yinhan He, Jundong Li et al. (+1 more)
Large
language model (LLM)-based multi-
agent systems enable expressive
agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned state-transition simulation, while classical
agent-based models (ABMs) offer interpretability but struggle to integrate rich individual-level signals and non-stationary behaviors. We propose PhysicsAgentABM, which shifts inference to behaviorally coherent
agent clusters: state-specialized symbolic
agents encode mechanistic transition priors, a
multimodal neural transition model captures temporal and interaction dynamics, and uncertainty-aware epistemic fusion yields calibrated cluster-level transition distributions. Individual
agents then stochastically realize transitions under local constraints, decoupling population inference from entity-level variability. We further introduce ANCHOR, an LLM
agent-driven clustering strategy based on cross-contextual behavioral responses and a novel contrastive loss, reducing LLM calls by up to 6-8 times. Experiments across public health, finance, and social sciences show consistent gains in event-time accuracy and calibration over mechanistic, neural, and LLM baselines. By re-architecting generative ABM around population-level inference with uncertainty-aware neuro-symbolic fusion, PhysicsAgentABM establishes a new paradigm for scalable and calibrated simulation with LLMs.
Read the full abstract ▾
All authors Kavana Venkatesh, Yinhan He, Jundong Li, Jiaming Cui
Machine Learning
Curiosity is Knowledge: Self-Consistent Learning and No-Regret Optimization with Active Inference
Yingke Li, Anjali Parashar, Enlu Zhou et al. (+1 more)
Active inference (AIF) unifies exploration and exploitation by minimizing the Expected Free Energy (EFE), balancing epistemic value (information gain) and pragmatic value (task performance) through a curiosity coefficient. Yet it has been unclear when this balance yields both coherent learning and efficient decision-making: insufficient curiosity can drive myopic exploitation and prevent uncertainty resolution, while excessive curiosity can induce unnecessary exploration and regret. We establish the first theoretical guarantee for EFE-minimizing
agents, showing that a single requirement–sufficient curiosity–simultaneously ensures self-consistent learning (
Bayesian posterior consistency) and no-regret optimization (bounded cumulative regret). Our analysis characterizes how this mechanism depends on initial uncertainty, identifiability, and objective
alignment, thereby connecting AIF to classical
Bayesian experimental design and
Bayesian optimization within one theoretical framework. We further translate these theories into practical design guidelines for tuning the epistemic-pragmatic trade-off in hybrid learning-optimization problems, validated through real-world experiments.
Read the full abstract ▾
All authors Yingke Li, Anjali Parashar, Enlu Zhou, Chuchu Fan
Machine Learning · Cross-listed from cs.CL
Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
Haozhen Zhang, Haodong Yue, Tao Feng et al. (+8 more)
Memory is increasingly central to Large
Language Model (LLM)
agents operating beyond a single context window, yet most existing systems rely on offline, query-agnostic
memory construction that can be inefficient and may discard query-critical information. Although runtime
memory utilization is a natural alternative, prior work often incurs substantial overhead and offers limited explicit control over the performance-cost trade-off. In this work, we present BudgetMem, a runtime
agent memory framework for explicit, query-aware performance-cost control. BudgetMem structures
memory processing as a set of
memory modules, each offered in three budget tiers (i.e., Low/Mid/High). A lightweight router performs budget-tier routing across modules to balance task performance and
memory construction cost, which is implemented as a compact neural policy trained with reinforcement learning. Using BudgetMem as a unified testbed, we study three complementary strategies for realizing budget tiers: implementation (method complexity),
reasoning (inference behavior), and capacity (module model size). Across LoCoMo, LongMemEval, and HotpotQA, BudgetMem surpasses strong baselines when performance is prioritized (i.e., high-budget setting), and delivers better accuracy-cost frontiers under tighter budgets. Moreover, our analysis disentangles the strengths and weaknesses of different tiering strategies, clarifying when each axis delivers the most favorable trade-offs under varying budget regimes.
Read the full abstract ▾
All authors Haozhen Zhang, Haodong Yue, Tao Feng, Quanyu Long, Jianzhu Bao, Bowen Jin, Weizhi Zhang, Xiao Li, Jiaxuan You, Chengwei Qin, Wenya Wang
Machine Learning
Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering
Miranda Muqing Miao, Young-Min Cho and Lyle Ungar
Large
language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference
alignment. Modified training objectives can improve calibration, but retraining is expensive. Inference-time steering offers a lightweight alternative, yet most existing methods optimize proxies for correctness rather than correctness itself. We introduce CORAL (Correctness-Optimized Residual Activation Lens), a regularized inference-time steering method that captures distributed correctness signals from model internal activations using weight-decay MLP probes. We evaluate CORAL across three 7B-parameter models and find that it consistently improves accuracy by 10% and expected calibration error (ECE) by 50% on average. We additionally demonstrate that these gains transfer without retraining to the complete published test sets of four held-out
benchmarks (ARC-Challenge, HellaSwag, Math-MC, OpenBookQA), averaging 14% accuracy improvements and 49% ECE improvements. Our results support the hypothesis that distributed information in model internals can be extracted using regularized probes when individual
neurons are insufficient. CORAL thus provides a compute-efficient, transferable, and calibration-aware approach to improve MCQA performance during inference.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold
Ye He, Yitong Qiu and Molei Tao
We study a data-dependent notion of
diffusion-model generalization: when a model does not memorize the training set, where do its generated samples go relative to the geometry induced by the data? To answer this, we introduce a time-dependent family of log-density ridge
manifolds constructed from the smoothed empirical distribution, and use it to characterize reverse-time inference. Our main result shows that generated samples evolve by a reach-align-slide mechanism: they first enter a neighborhood of the ridge, then their distance to the ridge is controlled by the normal component of training error, and finally their motion along the ridge is controlled by the tangential component. We further connect this
geometric picture to training dynamics through directional decompositions of the learned error, and make this link explicit for random feature models, where architectural bias and optimization error can be separated quantitatively. Experiments on synthetic
multimodal data and MNIST latent
diffusion support the predicted
geometric behavior in both low and high dimensions.
Read the full abstract ▾
Machine Learning
Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
Kevin Lu, Jannik Brinkmann, Stefan Huber et al. (+4 more)
How do
protein structure prediction models fold
proteins? We investigate this question through causal interventions on the folding trunks of ESMFold, OpenFold, and Boltz-1. Across all three models, we find a shared two-stage computational structure. In the first stage, early blocks initialize pairwise biochemical signals: features like charge propagate from sequence into pairwise representations through architecture-specific pathways. In the second stage, late blocks develop pairwise spatial features: distance and contact information accumulate in the pairwise representation. We verify these mechanisms causally by showing that steering charge and distance features induces predictable structural changes. Furthermore, these representations are functionally interchangeable: pairwise states can be linearly aligned and substituted across models. Together, these results suggest that folding trunks with different architectures, inputs, and training procedures converge on a shared representational organization for mapping sequence chemistry into spatial geometry.
Read the full abstract ▾
All authors Kevin Lu, Jannik Brinkmann, Stefan Huber, Aaron Mueller, Yonatan Belinkov, David Bau, Chris Wendler
Machine Learning · Cross-listed from cs.CL
John Kirchenbauer, Abhimanyu Hans, Brian Bartoldson et al. (+3 more)
Existing techniques for accelerating
language model inference, such as speculative decoding, require training auxiliary speculator models and building and deploying complex inference pipelines. We consider a new approach for converting a pretrained autoregressive
language model from a slow single next
token prediction model into a fast standalone multi-
token prediction model using a simple online
distillation objective. The final model retains the exact same implementation as the pretrained initial checkpoint and is deployable without the addition of any auxiliary verifier or other specialized inference code. Our method produces models that decode more than $3\times$ faster at $<5\%$ drop in accuracy on GSM8K relative to the single
token decoding performance of the same checkpoint.
Read the full abstract ▾
All authors John Kirchenbauer, Abhimanyu Hans, Brian Bartoldson, Micah Goldblum, Ashwinee Panda, Tom Goldstein
Machine Learning
Optimism Stabilizes Thompson Sampling for Adaptive Inference
Shunxing Yan and Han Zhong
Thompson sampling (TS) is widely used for
stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle. Classical asymptotic theory for sample means can fail because arm-specific sample sizes are random and coupled with the rewards through the action-selection rule. We study adaptive inference for Thompson sampling with Gaussian randomized indices in $K$-armed
stochastic bandits with independent sub-Gaussian reward noises, and identify optimism as a key mechanism for restoring stability, meaning that each arm's pull count concentrates around a deterministic scale. This stability yields asymptotically valid Wald inference despite adaptive sampling. First, we prove that variance-inflated TS is stable for any $K \ge 2$, including the challenging regime where multiple arms are optimal, with asymptotically uniform allocation over optimal arms and sharp logarithmic pull-count asymptotics for suboptimal arms. This resolves the $K$-armed extension question raised by \citet{halder2025stable}, using new winner-map and Lyapunov-drift techniques to control allocation among multiple optimal arms. Second, we analyze an alternative optimistic modification that keeps the Gaussian index variance unchanged but adds an explicit mean bonus to the index center, and establish a similar stability conclusion. In summary, suitably implemented optimism stabilizes Thompson sampling and enables asymptotically valid Wald inference in multi-armed bandits, while incurring only a mild additional regret cost.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce
Xianyang Liu, Shangding Gu, Fan Xu et al. (+5 more)
Large
language model
agents are increasingly expected to negotiate and transact autonomously, yet existing
benchmarks rarely combine
multimodal product grounding, multi-issue bargaining, and competitive multi-
agent markets. We introduce AgenticPay, a unified
benchmark for evaluating
multimodal agents' ability to reach high-welfare, multidimensional agreements in realistic
markets. AgenticPay includes 160
multimodal tasks across four business scenarios (E-commerce, Food Delivery, Ride-hailing, and Apartment Rental) and eight
market topologies, from bilateral bargaining to many-to-many competition.
Agents interpret product images, infer opponents' hidden preferences, and negotiate binding contract terms such as price, lease duration, return policy, and delivery speed through multi-round natural-
language dialogue. A utility-based framework evaluates agreement quality and joint welfare. Experiments with proprietary (GPT-5.4, Claude Sonnet 4.6, Gemini 3.1 Pro Preview) and open-weight (Qwen3-VL-32B-Instruct, InternVL3-38B)
multimodal models reveal substantial limitations in value creation and
market reasoning. Even the strongest model, Gemini 3.1 Pro Preview, achieves a GlobalScore of only 42.3/100. As
markets shift from bilateral to multi-sided, average GlobalScore falls by 5.7 points, with open-weight models declining by up to 11.5 points. AgenticPay provides a testbed for evaluating
multimodal agents in realistic commerce. Code and data: https://github.com/SAIL-Research-Lab/AgenticPay.
Read the full abstract ▾
All authors Xianyang Liu, Shangding Gu, Fan Xu, Manxi Wu, Boyi Li, Jun Wang, Costas Spanos, Dawn Song
Machine Learning · Cross-listed from cs.AI
Speech Emotion Recognition Leveraging OpenAI's Whisper Representations and Attentive Pooling Methods
Ali Shendabadi, Parnia Izadirad, Mostafa Salehi et al. (+1 more)
Speech Emotion Recognition (SER) research has faced limitations due to the lack of standard and sufficiently large
datasets. Recent studies have leveraged pre-trained models to extract features for downstream tasks such as SER. This work explores the capabilities of Whisper, a pre-trained ASR system, in
speech emotion recognition by proposing two
attention-based pooling methods, Multi-head Attentive Average Pooling and QKV Pooling, designed to efficiently reduce the dimensionality of Whisper representations while preserving emotional features. We experiment on English and Persian, using the IEMOCAP and ShEMO
datasets respectively, with Whisper Tiny and Small. Our multi-head QKV architecture achieves state-of-the-art results on the ShEMO
dataset, with a 2.47% improvement in unweighted accuracy. We further compare the performance of different Whisper encoder layers and find that intermediate layers often perform better for SER on the Persian
dataset, providing a lightweight and efficient alternative to much larger models such as HuBERT X-Large. Our findings highlight the potential of Whisper as a representation extractor for SER and demonstrate the effectiveness of
attention-based pooling for dimension reduction.
Read the full abstract ▾
All authors Ali Shendabadi, Parnia Izadirad, Mostafa Salehi, Mahmoud Bijankhan
Machine Learning
On the Role of Computation in Reinforcement Learning
Raj Ghugare, Michał Bortkiewicz, Alicja Ziarko et al. (+1 more)
How does the amount of compute available to a reinforcement learning (RL) policy affect its learning? Can policies using a fixed amount of parameters, still benefit from additional compute? The standard RL framework does not provide a
language to answer these questions formally. Empirically, deep RL policies are often parameterized as neural networks with static architectures, conflating the amount of compute and the number of parameters. In this paper, we formalize compute bounded policies and prove that policies which use more compute can solve problems and generalize to longer-horizon tasks that are outside the scope of policies with less compute. Building on prior work in algorithmic learning and model-free planning, we propose a minimal architecture that can use a variable amount of compute. Our experiments complement our theory. On a set 31 different tasks spanning online and offline RL, we show that $(1)$ this architecture achieves stronger performance simply by using more compute, and $(2)$ stronger generalization on longer-horizon test tasks compared to standard feedforward networks or deep residual network using up to 5 times more parameters.
Read the full abstract ▾
All authors Raj Ghugare, Michał Bortkiewicz, Alicja Ziarko, Benjamin Eysenbach
Machine Learning · Cross-listed from stat.ML
Causal Inference on Stopped Random Walks in Online Advertising
Jia Yuan Yu
We consider a causal inference problem frequently encountered in online advertising systems, where a publisher (e.g., Instagram, TikTok) interacts repeatedly with human users and advertisers by sporadically displaying to each user an advertisement selected through an auction. Each treatment corresponds to a parameter value of the advertising mechanism (e.g., auction reserve-price), and we want to estimate through experiments the corresponding long-term treatment effect (e.g., annual advertising revenue). In our setting, the treatment affects not only the instantaneous revenue from showing an ad, but also changes each user's interaction-trajectory, and each advertiser's bidding policy – as the latter is constrained by a finite budget. In particular, each a treatment may even affect the size of the population, since users interact longer with a tolerable advertising mechanism. We drop the classical i.i.d. assumption and model the experiment measurements (e.g., advertising revenue) as a stopped random walk, and use a budget-splitting experimental design, the Anscombe
Theorem, a Wald-like equation, and a Central Limit
Theorem to construct confidence intervals for the long-term treatment effect.
Read the full abstract ▾
Machine Learning
Leo Zhang and James Martens
Softmax Self-
Attention (SSA) is a key component of
Transformer architectures. However, when utilised within skipless architectures, which aim to improve representation learning, recent work has highlighted the inherent instability of SSA due to inducing rank collapse and poorly-conditioned Jacobians. In this work, we design a novel
attention mechanism: Orthogonal Self-
Attention (OSA), which aims to bypass these issues with SSA, in order to allow for (non-causal)
Transformers without skip connections and normalisation layers to be more easily trained. In particular, OSA parametrises the
attention matrix to be orthogonal via mapping a skew-symmetric
matrix, formed from query-key values, through the
matrix exponential. We show that this can be practically implemented, by exploiting the low-rank structure of our query-key values, resulting in the computational complexity and
memory cost of OSA scaling linearly with sequence length. Furthermore, we derive an initialisation scheme for which we prove ensures that the Jacobian of OSA is well-conditioned.
Read the full abstract ▾
Machine Learning
Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps
Peter Holderrieth, Douglas Chen, Luca Eyring et al. (+7 more)
Flow and
diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward
alignment. We argue that efficient reward
alignment should be a property of the generative model itself, not an afterthought, and redesign the model for adaptability. We propose "Diamond Maps",
stochastic flow map models that enable efficient and accurate
alignment to arbitrary rewards at inference time. Diamond Maps amortize many simulation steps into a single-step sampler, like flow maps, while preserving the stochasticity required for optimal reward
alignment. This design makes search, Sequential Monte Carlo, and guidance scalable by enabling efficient and consistent estimation of the value function. Our experiments show that Diamond Maps can be learned efficiently via
distillation from GLASS Flows, achieve stronger reward
alignment performance, and scale better than existing methods. Our results point toward a practical route to generative models that can be rapidly adapted to arbitrary preferences and constraints at inference time.
Read the full abstract ▾
All authors Peter Holderrieth, Douglas Chen, Luca Eyring, Ishin Shah, Giri Anantharaman, Yutong He, Zeynep Akata, Tommi Jaakkola, Nicholas Matthew Boffi, Max Simchowitz
Machine Learning
Layer-wise LoRA fine-tuning: a similarity metric approach
Keith Ando Ogawa, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara et al. (+5 more)
Pre-training Large
Language Models (LLMs) on web-scale
datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge through fine-tuning. Parameter-efficient fine-tuning techniques, such as Low-Rank Adaptation (LoRA), aim to reduce the computational cost of this process by freezing the pre-trained model and updating a smaller number of parameters. In comparison to full fine-tuning, these methods achieve over 99% reduction in trainable parameter count, depending on the configuration. Unfortunately, such a reduction may prove insufficient as LLMs continue to grow in scale. In this work, we address the previous problem by systematically selecting only a few layers to fine-tune using LoRA or its variants. We argue that not all layers contribute equally to the model adaptation. Leveraging this, we identify the most relevant layers to fine-tune by measuring their contribution to changes in internal representations. Our method is orthogonal to and readily compatible with existing low-rank adaptation techniques. We reduce the trainable parameters in LoRA-based techniques by up to 50%, while maintaining the predictive performance across different models and tasks. Specifically, on encoder-only architectures, this reduction in trainable parameters leads to a negligible predictive performance drop on the GLUE
benchmark. On decoder-only architectures, we achieve a small drop or even improvements in the predictive performance on mathematical problem-solving capabilities and coding tasks. Finally, this effectiveness extends to
multimodal models, for which we also observe competitive results relative to fine-tuning with LoRA modules in all layers. Code is available at: https://github.com/c2d-usp/Layer-wise-LoRA-with-CKA
Read the full abstract ▾
All authors Keith Ando Ogawa, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Lucas Pellicer, Rosimeire Pereira Costa, Edson Bollis, Anna Helena Reali Costa, Artur Jordao
Machine Learning
Clifford Kolmogorov-Arnold Networks
Matthias Wolff, Francesco Alesiani, Christof Duhme et al. (+1 more)
We introduce Clifford Kolmogorov-Arnold Network (ClKAN), a flexible and efficient architecture for function approximation in arbitrary Clifford
Algebra spaces. We propose the use of Randomized Quasi-Monte Carlo grid generation as a solution to the exponential scaling associated with higher-dimensional
algebras. Our ClKAN also introduces new batch normalization strategies to deal with variable domain input. ClKAN finds application in scientific discovery and engineering, and is validated in synthetic and physics-inspired tasks.
Read the full abstract ▾
All authors Matthias Wolff, Francesco Alesiani, Christof Duhme, Xiaoyi Jiang