Machine Learning
Speculative Rollback Correction for Quality-Diverse Web Agent Imitation
Longkun Hao, Hongyu Lin, Hao Li et al. (+11 more)
Training interactive web
agents through imitation learning from expert trajectories has emerged as a highly effective approach. However, determining the optimal timing for expert intervention presents a critical challenge in this context. Delayed intervention often leads to the accumulation of early-stage errors, pushing the page state into an irrecoverable regime. Conversely, premature or excessive intervention causes the
agent to become overly reliant on expert policies, trapping the model in local optima characterized by a single, rigid trajectory. We propose Speculative Rollback Correction (SRC), a branch-level imitation framework for resettable
agent environments. Instead of requesting teacher labels at every visited state or correcting only after a completed trajectory, SRC uses fixed-horizon branch review: the student executes a short speculative segment before teacher review, and the teacher localizes the first harmful deviation only when local progress breaks. Rollback preserves useful prefixes, while successful rollouts are filtered by a hard verifier and retained in a lightweight quality-diversity archive. The resulting data supports next-action supervised fine-tuning on both localized corrections and verifier-passing trajectories. On WebArena-Infinity, SRC collects 977 verifier-passing trajectories and 9,183 next-action examples; fixed-horizon review improves the recovery-versus-query tradeoff over step-level review while retaining verifier-passing solution variants. Code is available at https://github.com/LongkunHao/SRC_gui_
agent.
Read the full abstract ▾
All authors Longkun Hao, Hongyu Lin, Hao Li, Zhuowen Liu, Zhichao Yang, Haojie Hao, Dongshuo Huang, Haitao Yang, Hongyu Ge, Ming jie Xie, Yanjun Wu, Zi Hao Yin, Yan Bai, Yihang Lou
Machine Learning
Scalable anomaly detection via a univariate Christoffel function
Florian Grivet, Didier Henrion, Jean-Bernard Lasserre et al. (+1 more)
Anomaly detection plays a critical role in identifying unusual patterns across domains such as fraud detection, network intrusion, and system fault diagnosis. Recently, Christoffel function-based methods, rooted in
polynomial optimization, have emerged as promising alternatives to deep learning due to their strong mathematical foundations and computational frugality. However, their practical applicability is hindered by the need to invert a
matrix whose size grows exponentially with the data dimension, rendering the method intractable even for moderate-dimensional
datasets. This paper addresses the dimensionality limitations of Christoffel function-based anomaly detection while preserving its key theoretical properties, i.e., the on-off support dichotomy behavior and the accurate support shape capture. We introduce UCF, a univariate Christoffel function which is based on the squared distance between the query point and the support points. Extensive experiments on the ADBench
benchmark demonstrate that UCF consistently outperforms 14 state-of-the-art baselines in terms of Average Precision. By resolving the scalability bottleneck of the Christoffel Function, this work expands the toolkit of anomaly detection methods with a robust, theoretically grounded, and universally applicable approach.
Read the full abstract ▾
All authors Florian Grivet, Didier Henrion, Jean-Bernard Lasserre, Louise Travé-Massuyès
Machine Learning
Representing Time Series as Structured Programs for LLM Reasoning
Jaeho Kim, Changhun Oh, Seokhyun Lee et al. (+2 more)
Large
language models (LLMs) have demonstrated strong
reasoning and instruction-following capabilities, making them potentially powerful tools for time-series analysis. However, time series lie outside their native textual modality, raising a fundamental question: how should time series be represented so that LLMs can reason about them effectively? Existing work typically serializes raw numerical sequences or fine-tunes pre-trained LLMs on time-series data. These approaches place the burden of extracting temporal structure directly on the LLM, creating a modality mismatch that often degrades performance on long sequences and introduces substantial computational overhead. In this work, we introduce Time-Series-to-Structured-Program representation (T2SP), a deterministic, training-free method that represents a time series as a structured symbolic program. T2SP decomposes time series into trends, periods, and salient events, expressing them in a program-friendly format aligned with the textual and code-like modalities on which LLMs are natively trained. By shifting temporal-structure extraction from the model to the representation itself, T2SP enables off-the-shelf LLMs to leverage their existing
reasoning capabilities for time-series understanding. We evaluate T2SP on three
reasoning tasks – editing, captioning, and question answering – where it consistently improves performance, reduces
reasoning time, and lowers failure rates compared with raw-string representations. Our results demonstrate that T2SP provides an effective interface between time series and LLMs.
Read the full abstract ▾
All authors Jaeho Kim, Changhun Oh, Seokhyun Lee, Irina Rish, Changhee Lee
Machine Learning
ReCal: Reward Calibration for RL-based LLM Routing
Qihang Yu, Hanwen Tong, Zhengqi Zhang et al. (+5 more)
Large
language model (LLM) routing has emerged as an effective paradigm for leveraging the complementary strengths of multiple LLMs through dynamic model and
reasoning-strategy selection. Recent reinforcement learning (RL)-based routing methods further improve routing quality by optimizing routing policies from interaction feedback. However, they still struggle to provide informative and comparable learning signals under heterogeneous tasks with varying difficulty. In practice, multiple objectives (e.g., correctness, format behavior) are aggregated into a single scalar reward, leading to ambiguous credit assignment and conflicting optimization signals. Moreover, reward signals exhibit significant variability across instances, where some instances produce higher or more variable rewards, introducing optimization bias that favors trivial samples over informative ones. To address these issues, we propose ReCal, a \textbf{\underline{Re}}ward \textbf{\underline{Cal}}ibration framework for RL-based LLM routing. We first introduce a hierarchical reward decomposition mechanism with component-wise advantage estimation. We further propose a distribution-aware optimization strategy that calibrates optimization variability through variance-aware reweighting and per-
dataset normalization. Experiments on seven
datasets demonstrate that ReCal consistently improves routing performance, and training stability over baselines. Code is available at https://anonymous.4open.science/r/ReCal.
Read the full abstract ▾
All authors Qihang Yu, Hanwen Tong, Zhengqi Zhang, Bo Zheng, Feng Wei, Shengyu Zhang, Zemin Liu, Fei Wu
Machine Learning
Boltzmann Attention: Learnable Ising Couplings for Cooperative Attention
Gilhan Kim and Daniel K. Park
Attention mechanisms are central to modern sequence models, yet standard
attention computes relevance primarily through individual query–key similarities. Although softmax normalization introduces competition among positions, a standard
attention layer does not explicitly parameterize learnable interactions between
attention decisions. This limits its ability to directly model cooperative or antagonistic co-
attention structure within the
attention mechanism itself. We propose Boltzmann
attention, an energy-based generalization in which
attention patterns are governed by an interacting Ising model. The method augments the usual data-dependent local fields with learnable pairwise couplings, allowing the model to represent inter-position correlations beyond those captured by softmax or sigmoid
attention. Experiments on character-level
language modeling and synthetic bracket matching show that Boltzmann
attention consistently improves over standard softmax
attention within a standard
Transformer architecture, with the advantage becoming more pronounced as sequence length increases. A four-way ablation confirms that the improvement arises from the learnable pairwise couplings. These results suggest that explicit inter-position interactions provide a principled enhancement for
attention-based sequence modeling. Moreover, the Ising formulation opens a natural path toward
quantum-computing-based sampling strategies: we demonstrate that diabatic
quantum annealing provides a practical training method while maintaining competitive performance with exact Boltzmann computation.
Read the full abstract ▾
Machine Learning
Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics
Igor Itkin
Token-level
hallucination detectors are evaluated as classifiers, by AUC over all
tokens, yet a streaming monitor is judged by its reaction time: the number of
tokens that pass between the onset of a
hallucination and the alarm. We formulate
hallucination onset detection as a quickest change detection problem. A first-order Markov model of the latent faithful/hallucinated state, validated on RAGTruth, places the task inside classical change-point theory and yields Lorden's lower bound on detection delay: about 1.3
tokens at a false-alarm rate of 0.01. We then show that a causal recurrent labeler acts as a CUSUM with a learned increment. Among the onsets it catches it detects in 11-13
tokens, against 31 for a linear per-
token baseline, though at this false-alarm budget every detector catches under a third of onsets and the recall-honest delay is 56-66
tokens: low-false-alarm onset detection is hard. A controlled decomposition attributes the speed advantage mostly to a better per-
token score rather than to temporal accumulation. An information-rate optimality
theorem of Donsker-Varadhan type explains the remaining order-of-magnitude gap: the learned score realizes only 1/4.5 of the divergence the features carry, a deficit that recalibration cannot remove, with the remainder a finite-horizon effect. Classification metrics conceal this delay structure; sequential analysis makes it measurable.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Context-Driven Incremental Compression for Multi-Turn Dialogue Generation
Yeongseo Jung, Jaehyeok Kim, Eunseo Jung et al. (+5 more)
Modern conversational
agents condition on an ever-growing dialogue history at each turn, incurring redundant
attention and encoding costs that grow with conversation length. Naive truncation or summarization degrades fidelity, while existing context compressors lack cross-turn
memory sharing or revision, causing information loss and compounding errors in long dialogues. We revisit the context compression under conversational dynamics and empirically present its fragility. To improve both efficiency and robustness, we introduce Context-Driven Incremental Compression (C-DIC), which treats a conversation as interleaved contextual threads and stores revisable per-thread compression states in a single, compact dialogue
memory. At each turn, a lightweight retrieve, revise, and write-back loop shares information across turns and updates stale
memories, stabilizing long-horizon behavior. In addition, we adapt truncated backpropagation-through-time (TBPTT) to our multi-turn setting, learning cross-turn dependencies without full-history backpropagation. Extensive experiments on long-form dialogue
benchmarks demonstrate superior performance and efficiency of C-DIC; notably, C-DIC shows stable inference latency and perplexity over hundreds of dialogue turns, supporting a scalable path to high-quality dialogue modeling.
Read the full abstract ▾
All authors Yeongseo Jung, Jaehyeok Kim, Eunseo Jung, Jiachuan Wang, Yongqi Zhang, Ka Chun Cheung, Simon See, Lei Chen
Machine Learning · Cross-listed from cs.RO
FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning
Steven Oh, Jason Jingzhou Liu, Tony Tao et al. (+5 more)
Contact-rich manipulation requires force sensitivity, but many
robot arms lack dedicated force sensors due to their high cost. We present Neural External Torque Estimation (NEXT), a data-driven method that estimates external joint torques without needing any dedicated force sensors. NEXT trains in 1 minute from only 10 minutes of free-motion data, yet achieves estimates comparable to dedicated joint-torque sensors. NEXT enables force-feedback teleoperation on low-cost arms and improves policy learning through Force-Informed Re-Sampling Training (FIRST), which up-samples pre-contact and contact segments during behavior cloning. Across five long-horizon tasks, FIRST outperforms prior force-aware policies by over 17% in task progress. Together, NEXT and FIRST bring force-aware teleoperation and policy learning to off-the-shelf
robots without additional sensing hardware.
Video results and code are available at https://jasonjzliu.com/factr2
Read the full abstract ▾
All authors Steven Oh, Jason Jingzhou Liu, Tony Tao, Philip Han, Kenneth Shaw, Satoshi Funabashi, Ruslan Salakhutdinov, Deepak Pathak
Machine Learning
Redesign Mixture-of-Experts Routers with Manifold Power Iteration
Songhao Wu, Ang Lv, Ruobing Xie et al. (+1 more)
Router is the cornerstone component to the Mixture-of-Experts models. Serving as expert proxies, the rows of the router
matrix compute their similarity to the MoE inputs to determine which subset of experts is activated. Ideally, each router row is designed to encode the expert
matrix into this representative vector, such that its dot-product with
token can better reflect
token-expert affinity. However, there exists no design principles to enforce this condensation. In this paper, we propose to align each router row with the principal singular direction of the associated expert, as this direction provides the most expressive mathematical description of a
matrix. Based on this principle, we propose a router redesign with
Manifold Power Iteration (MPI). Specifically, it introduces a "Power-then-Retract" paradigm, where a power iteration step is performed on the router weights, followed by a retraction to impose a norm constraint to ensure both efficiency and stability. Theoretically, we show that MPI drives router rows to converge toward the principal singular directions of associated experts. Empirically, we pretrain MoE model across scales from 1B to 11B parameters to confirm that this
alignment facilitates more effective MoE models.
Read the full abstract ▾
All authors Songhao Wu, Ang Lv, Ruobing Xie, Yankai Lin
Machine Learning
ATLAS: Active Theory Learning for Automated Science
Noémi Éltető, Nathaniel D. Daw, Kimberly L. Stachenfeld et al. (+1 more)
Advancing scientific understanding through mechanistic modeling requires posing the right experimental questions to yield maximally informative data. To automate this pursuit within cognitive science, we introduce ATLAS (Active Theory Learning for Automated Science), an active learning framework for the data-driven discovery of interpretable behavioral models. ATLAS iterates between generating mechanistic hypotheses–instantiated as a diverse ensemble of sparse neural networks (Disentangled RNNs)–and designing experiments that optimally distinguish between them. We test this approach on the problem of recovering reinforcement learning
agents from their behavior in bandit tasks. ATLAS designs varied sequences of qualitatively novel experiments with temporal structure tailored to underlying
agent characteristics. The models trained on these experiments are evaluated against a comprehensive set of metrics for mechanistic modeling that capture behavioral, structural, and computational similarity. ATLAS achieves a 5-10x improvement in sample efficiency across all metrics compared to random experimentation, and its performance is further validated against expert-designed experiments derived from literature. These in silico results showcase ATLAS's potential to accelerate human-interpretable insights in cognitive science and other domains where scientific inquiry relies on discovering mechanistic models.
Read the full abstract ▾
All authors Noémi Éltető, Nathaniel D. Daw, Kimberly L. Stachenfeld, Kevin J. Miller
Machine Learning
APPO: Agentic Procedural Policy Optimization
Xucong Wang, Ziyu Ma, Yong Wang et al. (+5 more)
Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large
language model
agents. However, most existing methods assign credit over coarse heuristic units, such as tool-call boundaries or fixed workflows, making it difficult to identify which intermediate decisions influence downstream outcomes. In this work, we study agentic RL from two perspectives: where to branch and how to assign credit after branching. Our pilot analysis shows that influential decision points are broadly distributed throughout the generated sequence rather than concentrated at tool calls, while
token entropy alone does not reliably reflect their impact on final outcomes. Motivated by these observations, we propose Agentic Procedural Policy Optimization (APPO), which shifts branching and credit assignment from coarse interaction units to fine-grained decision points in the sequence. APPO selects branching locations using a Branching Score that combines
token uncertainty with policy-induced likelihood gains of subsequent continuations, enabling more targeted exploration while filtering out spurious high-
entropy positions. It further introduces procedure-level advantage scaling to better distribute credit across branched rollouts. Experiments on 13
benchmarks show that APPO consistently improves strong agentic RL baselines by nearly 4 points, while keeping efficient tool-calls and maintaining behavior interpretability.
Read the full abstract ▾
All authors Xucong Wang, Ziyu Ma, Yong Wang, Yuxiang Ji, Shidong Yang, Guanhua Chen, Pengkun Wang, Xiangxiang Chu
Machine Learning · Cross-listed from cs.RO
UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning
Haoyuan Deng, Yitong Gao, Yudong Lin et al. (+3 more)
Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance. However, current HiL-RL frameworks remain intervention-intensive, relying on frequent human corrections to redirect the policy out of unproductive exploration, which incurs high labor cost and limits real-world scalability. To address this, we propose UniIntervene, an agentic intervention model that detects unproductive exploration and autonomously recovers the policy toward high-value states, taking over the bulk of interventions from human operators. Specifically, UniIntervene first performs future-conditioned action-value estimation, predicting the latent consequence of the current action and evaluating its induced value, which provides a more stable progress signal. Building on this, a temporal value-risk critic aggregates recent value dynamics and triggers intervention when the estimated value exhibits sustained stagnation or degradation. When intervention is required, UniIntervene retrieves a high-value recovery target from a
memory of past intervention episodes and produces executable corrective actions through a goal-conditioned recovery policy. In this way, UniIntervene turns intervention from passive human correction into a value-aware recovery process for efficient real-world RL. Extensive experiments on diverse real-world manipulation tasks demonstrate that UniIntervene improves the average success rate by 8.6% while reducing human interventions by 57% relative to state-of-the-art HiL-RL baselines.
Read the full abstract ▾
All authors Haoyuan Deng, Yitong Gao, Yudong Lin, Haichao Liu, Zhenyu Wu, Ziwei Wang
Machine Learning
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Yucheng Li, Huiqiang Jiang, Yang Xu et al. (+14 more)
Reinforcement learning (RL) has become a key component in modern large
language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-
Token Prediction (MTP) offers a natural solution to accelerate rollouts through speculative decoding, many studies have observed that MTP acceptance rates degrade significantly during RL training, leading to limited speedup performance. To address this bottleneck, we present Bebop, a systematic study of MTP in LLM post-training, and offer practical recipes to integrate MTP into large-scale RL pipelines. First, we reveal that the MTP acceptance rate is fundamentally bounded by the fluctuation of model
entropy, which demonstrates a clear negative linear relationship with the rise of
entropy in the RL stage. Second, we show that probabilistic rejection sampling largely alleviates the disturbance introduced by
entropy in RL compared to greedy draft sampling. We further identify that the conventional MTP training objectives (cross-
entropy or KL) are suboptimal in such settings, and therefore we propose a novel end-to-end TV loss that directly optimizes multi-step rejection sampling acceptance rate, yielding ~10% acceptance rate improvements, achieving up to 95% acceptance rates and up to 25% extra inference throughput gains across mathematical
reasoning, code generation, and agentic tasks. Third, we test various online MTP training strategies during RL and show that pre-RL MTP training with e2e TV loss and rejection sampling achieves a consistent acceptance rate and speedup throughout the entire RL, eliminating the need for costly online MTP updating. We provide extensive experiments and analysis that validate our findings. Experimental results show our method achieves up to 1.8x end-to-end acceleration in async RL training of Qwen3.5, Qwen3.6, and Qwen3.7 models.
Read the full abstract ▾
All authors Yucheng Li, Huiqiang Jiang, Yang Xu, Jianxin Yang, Yi Zhang, Yizhong Cao, Yuhao Shen, Fan Zhou, Rui Men, Jianwei Zhang, An Yang, Bowen Yu, Bo Zheng, Fei Huang, Junyang Lin, Dayiheng Liu, Jingren Zhou
Machine Learning
On Subquadratic Architectures: From Applications to Principles
Anamaria-Roberta Hartl, Levente Zólyomi, David Stap et al. (+6 more)
Transformers dominate modern sequence modeling, but their quadratic
attention incurs substantial computational cost. Subquadratic architectures offer a scalable alternative. However, it remains unclear which designs yield the most effective sequence models. We compare three leading approaches: xLSTM, Mamba-2, and Gated DeltaNet. We evaluate these models on tasks with complex dependencies: (1) code-model pre-training, (2)
distillation of code models from large
language models, and (3) pre-training of time-series foundation models. Across these settings, xLSTM delivers the strongest overall performance. To explain xLSTM's advantage, we present a unified formulation and analyze the underlying architectural mechanisms, focusing on state tracking and
memory dynamics. Our results show that xLSTM enables more flexible and stable
memory correction via its gating scheme. We corroborate these findings on controlled synthetic length-generalization tasks. Overall, our findings indicate that xLSTM's gains on complex tasks stem from robust state tracking and accumulation.
Read the full abstract ▾
All authors Anamaria-Roberta Hartl, Levente Zólyomi, David Stap, Pieter-Jan Hoedt, Niklas Schmidinger, Lukas Hauzenberger, Sebastian Böck, Günter Klambauer, Sepp Hochreiter
Machine Learning
Latent World Recovery for Multimodal Learning with Missing Modalities
Hui Wang, Tianyu Ren, Joseph Butler et al. (+3 more)
We study
multimodal learning under missing modalities, with particular motivation from bioscience applications in which heterogeneous modalities are often only partially available when decisions need to be made. We propose Latent World Recovery (LWR), a framework built on two key ideas: (i) modality-specific
embeddings from different modalities are aligned in a shared latent space, and (ii) a unified representation is constructed by fusing only the
embeddings of the modalities that are actually available at both training and inference time. Rather than imputing missing modalities or requiring a fixed modality set, LWR treats each modality as a partial perception of an underlying latent state and performs availability-aware representation learning directly from the observed modalities. This combination of neighbor-based latent
alignment and availability-aware modality fusion enables robust
multimodal prediction under partial observation, while avoiding error propagation from explicit reconstruction of missing modalities. We evaluate the proposed framework on real-world incomplete multi-omics
benchmarks and demonstrate that it provides an effective approach to downstream tasks such as cancer phenotype classification and survival prediction.
Read the full abstract ▾
All authors Hui Wang, Tianyu Ren, Joseph Butler, Christopher Baker, Karen Rafferty, Simon McDade
Machine Learning
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
Leon Bergen, Usha Bhalla, Sidharth Baskaran et al. (+14 more)
Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. This abstraction gives practitioners little visibility into what their data actually teaches models, allowing spurious correlations to be learned by a model and inducing undesirable behaviors such as over-stylization and sycophancy. To address this problem, we ask: can we inspect a preference
dataset before optimization and decide, at the level of concepts, which behaviors a model should be allowed to learn? Motivated by this, we introduce a data-centric post-training pipeline that uses interpretability protocols to develop statistical hypotheses for the latent concepts separating preferred from dispreferred generations, making them explicit for fine-grained user feedback. Building on this view, we unify several interpretability-based training protocols as ways of shaping rewards via feature or data interventions. Empirically, we show that our pipeline diagnoses undesirable signals in existing preference data, mitigates off-target learning, and can also help amplify or shape desired properties such as safeguards and model personality. More broadly, our results suggest that interpretability can turn post-training from optimizing opaque proxy rewards into a process of
auditing and sculpting the learning signal itself.
Read the full abstract ▾
All authors Leon Bergen, Usha Bhalla, Sidharth Baskaran, Max Loeffler, Raphael Sarfati, Dhruvil Gala, Ryan Panwar, Santiago Aranguri, Thomas Fel, Atticus Geiger, Matthew Kowal, Siddharth Boppana, Daniel Balsam, Owen Lewis, Jack Merullo, Thomas McGrath, Ekdeep Singh Lubana
Machine Learning · Cross-listed from cs.CV
Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy
Kai Standvoss, Miriam Hägele, Rosemarie Krupar et al. (+25 more)
Hematoxylin and eosin (H&E) staining is the cornerstone of histopathology, yet scalable, quantitative analysis of H&E whole-slide images (WSIs) remains a central challenge in computational pathology. We present Atlas H&E-TME, an AI-based system built on the Atlas family of pathology foundation models that predicts tissue quality, tissue region, and
cell type labels across multiple cancer types, yielding over 4,500 quantitative readouts per slide at
cell-level resolution. A key challenge to validating such systems is overcoming morphological ambiguity inherent to H&E-only ground truth and the limited scalability of more informed references drawing on modalities such as immunohistochemistry (IHC). We address this with a dual validation framework combining biologically grounded depth with technical and morphological breadth. For depth, we propose an IHC-informed multi-pathologist consensus protocol that substantially improves inter-rater agreement over conventional H&E-only annotation. This yields a molecularly grounded reference against which we compare Atlas H&E-TME and pathologists working from H&E alone. For breadth, we
benchmark Atlas H&E-TME on over 200,000 high-confidence H&E-only pathologist annotations across 1,500+ cases spanning eight cancer types and their most common metastatic sites, with subtypes covering >90% of clinical cases per cancer type, drawn from 25+ sources and 8+ scanner models. Benchmarked against the IHC-informed consensus, Atlas H&E-TME matches or exceeds pathologist H&E-only performance and generalizes consistently and robustly across this broad morphological and technical scope. In doing so, Atlas H&E-TME turns the H&E slide – the most ubiquitous data in pathology – into a scalable, quantitative window into the tumor and its microenvironment, laying a foundation for the next generation of tissue-based biomarkers in translational and clinical research.
Read the full abstract ▾
All authors Kai Standvoss, Miriam Hägele, Rosemarie Krupar, Julika Ribbat-Idel, Jennifer Altschüler, Gerrit Erdmann, Hans Pinckaers, Evelyn Ramberger, Madleen Drinkwitz, Ádám Nárai, Alexander Möllers, Katja Lingelbach, Sebastian Kons, Lukas Hönig, Recepcan Adigüzel, Joana Baião, Alberto Megina Gonzalo, Marius Teodorescu, Marie-Lisa Eich, Paolo Chetta, Shakil Merchant, Verena Aumiller, Simon Schallenberg, Andrew Norgan, Klaus-Robert Müller, Lukas Ruff, Maximilian Alber, Frederick Klauschen
Machine Learning
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Mengyu Zheng, Kai Han, Boxun Li et al. (+13 more)
The software engineering capabilities of general-purpose
agent harnesses remain underexplored, and existing
benchmarks offer limited support for comparing these harnesses under consistent conditions. To address this gap, we introduce Claw-SWE-Bench, a unified
benchmark that enables researchers to systematically assess the capabilities and efficiency of general-purpose harnesses on software engineering tasks. The
benchmark contains 350 real-world GitHub issue-resolution instances across eight programming
languages and 43 repositories and provides a shared adapter protocol to align task inputs, outputs, and execution environments across harnesses. Experiments show that general-purpose harnesses can effectively resolve real-world software issues and that their success rates and resource consumption vary substantially even when the underlying model is held fixed. To lower evaluation costs and support faster debugging and iteration, we also provide Claw-SWE-Bench Lite, an 80-instance subset designed to preserve the key evaluation properties of the full
benchmark. We hope this
benchmark will help researchers better evaluate and understand the performance of general-purpose harnesses on software engineering tasks and guide the development of more capable and efficient harnesses. The data is available at https://github.com/opensquilla/claw-swe-bench and https://huggingface.co/
datasets/TokenRhythm/Claw-SWE-Bench.
Read the full abstract ▾
All authors Mengyu Zheng, Kai Han, Boxun Li, Haiyang Xu, Yuchuan Tian, Wei He, Hang Zhou, Jianyuan Guo, Hailin Hu, Lin Ma, Chao Xu, Guohao Dai, Lixue Xia, Yunchao Wei, Yunhe Wang, Yu Wang
Machine Learning · Cross-listed from cs.CL
ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing
Chirag Chawla, Pratinav Seth and Vinay Kumar Sankarapu
Domain fine-tuning degrades the safety of large
language models: fine-tuned specialists readily comply with harmful
prompts framed in domain
language. Existing inference-time defenses that mix logits from a safe anchor model require both models to share a vocabulary, which rules them out for the cross-family specialists where safety is most degraded. We present ALIGNBEAM, a training-free method that lifts this restriction by translating anchor logits into the target model's vocabulary
token-by-
token at each decoding step; a small LLM judge then selects the safest among K candidate continuations. No weights are changed, and the safety-utility trade-off can be tuned at deployment without retraining. Across both cross-vocabulary and same-vocabulary evaluation pairs, ALIGNBEAM substantially raises refusal on
adversarial benchmarks while keeping task accuracy and inference overhead within practical bounds. The results show that safety
alignment can be transferred between model families at inference time, without touching either model's weights.
Read the full abstract ▾
Machine Learning · Cross-listed from math.NA
Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems
Zhen Zhang, Alessandro Alla and George Em Karniadakis
Inverse problems governed by partial differential equations (PDEs) are central to computational mechanics and are commonly solved by adjoint-based optimization, while physics-informed neural networks (PINNs) have emerged as a flexible alternative. Their relative performance remains difficult to assess because the two approaches are often compared under different formulations, parameterizations, optimizers, and regularization choices. We present a controlled comparison of adjoint optimization and PINNs for PDE-constrained inverse problems. From a common abstract formulation, we instantiate both methods on identical domains, governing equations, observation models, and regularization terms, while matching the optimizer, unknown parameterization, and arithmetic precision wherever applicable. The
benchmarks include unsteady Burgers, noisy Darcy permeability inversion, three-dimensional Allen-Cahn reaction identification, and unsteady Navier-Stokes viscosity identification. The results show that the representation of the unknown largely determines the preferred method: grid-based fields favor the discrete adjoint, whereas neural representations are native to PINNs and relevant for closure and constitutive modeling. For time-dependent problems, adjoint inversion can be dominated by trajectory storage and differentiation, while PINNs provide satisfactory reconstructions at lower cost. A PINN-warm-started adjoint strategy then recovers adjoint-level accuracy at about half the cost.
Read the full abstract ▾
Machine Learning
Fourier Features Let Agents Learn High Precision Policies with Imitation Learning
Balázs Gyenes, Emiliyan Gospodinov, Jan Frieling et al. (+5 more)
High-precision robotic manipulation requires fine-grained spatial
reasoning that is often difficult to achieve with RGB-only policies due to depth ambiguity and perspective scale issues. Policies that leverage 3D information directly, such as those based on point clouds, offer a stronger
geometric prior over purely image-based ones, yet their performance remains highly task-dependent. We hypothesize that this discrepancy may be due to the spectral bias of neural networks towards learning low frequency functions, which especially affects architectures conditioned on slow-moving Cartesian features. We thus propose to map point clouds from Cartesian space into high-dimensional
Fourier space, effectively equipping the point cloud encoder with direct access to high-frequency features. We experimentally validate the use of
Fourier features on challenging manipulation tasks from the RoboCasa and ManiSkill3
benchmarks and on a real
robot setup. Despite their simplicity, we find that
Fourier features provide significant benefits across diverse encoder architectures and
benchmarks and are robust across hyperparameters. Our results indicate that
Fourier features let policies leverage
geometric details more effectively than Cartesian features, showing their potential as a general-purpose tool for point cloud-based imitation learning. We provide source code and
videos on our project page: https://
fourier-il.github.io/
fourier-il
Read the full abstract ▾
All authors Balázs Gyenes, Emiliyan Gospodinov, Jan Frieling, Enrico Krohmer, Nicolas Schreiber, Xiaogang Jia, Niklas Freymuth, Gerhard Neumann
Machine Learning · Cross-listed from cs.CL
Measuring Semantic Progress in Multi-turn Dialogue via Information Gain
Paul He, Shiva Kasiviswanathan and Dominik Janzing
Evaluating multi-turn dialogue is challenging because quality emerges across turns rather than within individual responses. We focus on a key dimension of information-seeking dialogue: semantic progress, defined as the accumulation of new, question-relevant, and non-redundant information over the course of a conversation. We formalize semantic progress as question-conditioned uncertainty reduction and introduce an information-theoretic metric that approximates it in
embedding space. Our main
estimator uses a tractable Gaussian formulation with closed-form updates, while a complementary maximum-
entropy argument shows why log-determinant structure arises more broadly when only second-order
embedding information is retained. This formulation yields desirable theoretical properties, including monotonicity, additive decomposition of total information gain across turns, and diminishing returns for redundant evidence. Unlike LLM-as-a-judge approaches, our metric requires no autoregressive inference at evaluation time and is fully reproducible for a fixed
embedding model. Experiments on MT-Bench, Chatbot Arena, and UltraFeedback show that the proposed metric achieves competitive agreement with human judgments despite targeting only semantic progress, with improved
alignment on MT-Bench and UltraFeedback compared to several LLM-based judges. Notably, the method remains effective with lightweight
embedding models under CPU-only execution, indicating that semantic progress can be captured without reliance on large model capacity.
Read the full abstract ▾
Machine Learning
Chain of Operators: An Inference-Time Harness for In-Context Operator Learning
Minghui Yang, Chenghan Wu, Ling Guo et al. (+1 more)
While scientific foundation models show immense promise in accelerating physical simulations and numerical
forecasting, they remain notoriously brittle when encountering out-of-distribution (OOD) scenarios. Adapting these generalist models to complex OOD tasks typically requires expensive parameter fine-tuning. In linguistic AI, this bottleneck is bypassed using "harnesses", which serve as external scaffolding such as
reasoning chains and tool use to adapt frozen weights to complex tasks, yet designing an equivalent harness for physical domains remains an open frontier. To bridge this gap, we introduce Chain of Operators (CHOP), a framework that guides a frozen foundation model through complex OOD tasks without updating a single weight. By exploiting the in-context learning capability of In-Context Operator Networks (ICON), CHOP systematically decomposes unfamiliar problems into a sequence of explicit, closed-form mathematical operations and multiple model calls, translating OOD queries back into the model's learned operating regime. Across diverse
benchmarks, including canonical PDE problems and real-world air-quality
forecasting, CHOP consistently and substantially reduces inference errors compared to direct model evaluation. Crucially, these modular operator chains remain fully interpretable and can generalize across entirely distinct families of physical equations. Ultimately, this work demonstrates how frozen scientific models can adapt through programmable inference, establishing a modular, potential paradigm for agentic scientific computing.
Read the full abstract ▾
All authors Minghui Yang, Chenghan Wu, Ling Guo, Liu Yang
Machine Learning · Cross-listed from cs.RO
Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering
Hyun Joe Jeong, Gokul Swamy and Andrea Bajcsy
Vision-
Language-Action (VLA) models provide a natural
language interface to
robot control, but the mapping from
language to behavior is often brittle and unintuitive: semantically similar instructions can induce drastically different behaviors, while some capabilities may not be elicitable through prompting alone. As a result, both human instructions and zero-shot
language models can fail to reliably steer VLAs toward successful task execution. In this work, we propose a framework that interactively searches for
language sequences that improve closed-loop VLA task performance, distills these sequences into a test-time
language feedback policy (LFP), and learns an improvement head that predicts when
language steering will improve performance. We conformalize this improvement head to prevent harmful steering interventions, where the LFP decreases task performance relative to the original instruction on out-of-distribution scenarios. Crucially, our approach operates on arbitrary frozen pre-trained VLAs, requiring neither access to the original training distribution nor fine-tuning of the underlying model. On seen environments, our conformalized LFP improves base VLA performance by 24.7% in simulation and 65.0% in hardware. On visual and semantic perturbations with calibration samples, our conformalized LFP has strong harmlessness guarantees, and produces recovery behaviors not observed with open-loop prompting.
Read the full abstract ▾
Machine Learning
The Standard Interpretable Model: Design interpretable machine learning methods from elementary symmetries
Pietro Barbiero, Giovanni De Felice, Mateo Espinosa Zarlenga et al. (+5 more)
As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations. However, interpretability lacks general theories to deductively design interpretable methods. This gap between theories and methods results in a fragmented literature and inconsistent evaluation protocols. To fill this gap, we introduce the Standard Interpretable Model (SIM), a general theory that enables the deductive design of interpretable methods from first principles. Specifically, the SIM summarises, in a set of premises, what interpretability is for a target entity. From these premises, the SIM systematically derives interpretability
symmetries and corresponding constraints. One can then build interpretable models by either introducing constraints in the optimisation problem or by compiling constraints into an interpretable architecture. The most important finding, both theoretical and empirical, is that full expressivity and interpretability
symmetries can coexist in the same model, showing that the trade-off between accuracy and interpretability is an artefact of model design. We demonstrate this on
language models (LMs), where SIM-based LMs match the performance of equivalent opaque LMs without making any compromise on interpretability. Beyond this, the SIM shows how to improve the interpretability of existing pre-trained models, highlights underexplored research directions, and unifies a discipline that has long been fragmented, offering pedagogical grounding for interpretability curricula.
Read the full abstract ▾
All authors Pietro Barbiero, Giovanni De Felice, Mateo Espinosa Zarlenga, Francesco Giannini, Filippo Bonchi, Mateja Jamnik, Giuseppe Marra, Ruggero Noris
Machine Learning · Cross-listed from cs.SD
PianoKontext: Expressive Performance Rendering from Deadpan Context
Dmitrii Gavrilev
Expressive performance rendering (EPR) aims to generate realistic performances constrained on sequences of notes. However, flow matching audio editing models manipulate only synchronized music samples of the same duration, limiting their understanding of expressive timing. We introduce PianoKontext, a flow matching rendering model for classical piano music that generates variable-length performances in the latent space of a pretrained Music2Latent model. We synthesize MIDI scores into deadpan audio and employ Dynamic Time Warping (DTW) in the latent space to construct paired data for training. The aligned
embeddings are concatenated in DiT blocks, allowing for a simple and effective learning of the dependencies between the score and performances. Audio samples are available at our demo page: https://realfolkcode.github.io/pianokontext_demo/.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.MA
CCKS: Consensus-based Communication and Knowledge Sharing
Jinyuan Zu, Xiaowei Lv, Yongcai Wang et al. (+5 more)
In Decentralized Training and Decentralized Execution (DTDE) for cooperative Multi-
Agent Reinforcement Learning (MARL), action-advising-based knowledge sharing promotes interpretable and scalable cooperation among
agents. However, current action advising approaches often adhere too much to the teacher's guidance without evaluating teacher-student compatibility, which causes excessive advising, suboptimal stability, and degraded performance. To overcome these challenges, this paper presents a Consensus-based Communication and Knowledge Sharing (CCKS) framework, which allows
agents to adopt recommendations based on consensus-derived constraints and to follow the teacher's instructions more smartly. This mechanism enables
agents to balance exploration and learning from experienced teachers, improving overall performance. The key is the consensus model construction, for which we propose to employ contrastive learning to construct consensus models based on local observations in the
agents' training phase. In action selection,
agents score and choose actions based on consensus and shared knowledge. Designed as a plug-and-play solution, CCKS integrates seamlessly with existing DTDE
algorithms. Experiments conducted in the Google Research Football environment and the complex StarCraft II Multi-
Agent Challenge demonstrate that the integration with CCKS significantly improves cooperation efficiency, learning speed, and overall performance compared with current DTDE baselines. The code is available at https://github.com/yuanxpy/CCKS.
Read the full abstract ▾
All authors Jinyuan Zu, Xiaowei Lv, Yongcai Wang, Deying Li, Yunjun Han, Wenping Chen, Fengyi Zhang, Naiqi Wu
Machine Learning
Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs
Deep Gandhi, Ali Asaria and Tony Salomone
We study post-training quantization (PTQ) of Ideogram 4.0, a 9.3B flow-matching
diffusion transformer (DiT) that realizes classifier-free guidance with two separate-weight copies of a single-stream backbone and is conditioned by a Qwen3-VL text encoder, targeting Ampere RTX~3090 GPUs, which lack FP8 tensor cores. Because Ideogram~4.0 is trained on structured JSON captions, we evaluate every variant under schema-valid JSON
prompts produced by an LLM expander built to Ideogram's published caption specification, and score them with a battery spanning human-preference (HPSv2), CLIP, and PickScore for standalone quality; PP-OCR exact-match and edit distance for text; and PSNR/SSIM/LPIPS for fidelity to the FP8 reference (the highest-precision public checkpoint) output. On a 300-
prompt benchmark with paired bootstrap confidence intervals, an INT8 W8A8 recipe (per-channel weights, per-
token dynamic activations, SmoothQuant, and bf16 protection of a small high-fragility layer set) is statistically indistinguishable from FP8 on CLIP and PickScore (paired CIs include zero) and within ~0.004 HPSv2, and, at its 8-bit size, is the most faithful reproduction of the FP8 output (LPIPS 0.243 vs 0.277/0.306 for the half-size 4-bit baselines; the INT8-Q4_K gap excludes zero). A GGUF Q4_K quantization reaches the same standalone quality as the published NF4 baseline at the same on-disk size, making it the Pareto choice on the quality-
memory frontier. We further show that under JSON
prompts all four variants reach parity on standalone quality, the variants separate on fidelity and text rendering, not on aggregate image-quality scores, and that text legibility, near-zero when the model is prompted with raw strings, reaches 55% OCR exact-match under the JSON captions it expects. We release the INT8 W8A8 and GGUF Q4_K quantized weights on Hugging Face under a gated, non-commercial license.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.NE
Genetic Algorithms with Optimization Guided Operators
Anna Brandenberger, Ilan Doron-Arad and Elchanan Mossel
Recent work in ML applies genetic
algorithms at inference time to iteratively improve solutions to optimization problems. The basic mutation and recombination operators involved are qualitatively different from those studied classically. Mutations are no longer random; an ML
algorithm mutates a solution with the goal of improving an objective. Similarly, recombination is not based on random collages of parent solutions. Instead, it is an ML optimization-based operator whose goal is to synthesize improved solutions from its inputs. Thus, these mutation and recombination operators are more likely to improve the objective, but their computational cost is much higher. We introduce a general model of genetic
algorithms and formulate optimization in this model as a query complexity problem, using the
language of reinforcement learning. We demonstrate three fundamental phenomena. First, we show that diversity of the solution pool can be necessary: for parity learning, viewed in our framework, we show that with pool size $w$ and vectors of length $n$, the optimal query complexity is $\Theta(w+2^{n-w})$. We further show that this phenomenon persists under general
memory constraints: $\Theta(n^2)$ bits of
memory are necessary for efficient success. Second, we show that generation, mutation, and recombination can all be simultaneously necessary to reach a nearly optimal solution. Finally, we give a phase transition for Gaussian distributions, showing that a positive drift of the operators yields exponential speedup.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning
Romana Qureshi, Hafida Benhidour, Said Kerrache et al. (+1 more)
Neural network
pruning reduces model size by removing less important parameters while aiming to preserve predictive performance. Although the Lottery Ticket Hypothesis (LTH) shows that sparse subnetworks can match dense networks when trained from suitable initializations, its iterative
pruning procedure requires multiple complete training cycles. This work evaluates progressive magnitude-based
pruning as a single-cycle alternative. The method gradually increases sparsity during training using a linear schedule and updates
pruning masks based on active weight magnitudes. We conduct systematic experiments on CIFAR-10 and MNIST across ResNet, VGG-style, and LeNet architectures, comparing the proposed method with representative iterative and initialization-based
pruning baselines, including LTH, SNIP, and GraSP. On CIFAR-10, the method achieves 95.12% accuracy on ResNet-18 at 72.9% sparsity, compared with 90.5% reported for LTH. At extreme sparsity, it achieves 93.13% accuracy on a VGG-like architecture at 97% sparsity, compared with approximately 92.0% for SNIP, and 93.44% accuracy on VGG-19 at 97.97% sparsity, compared with 92.19% for GraSP at 98% sparsity. A sparsity-accuracy analysis on ResNet-18 further shows that accuracy remains within 0.1 percentage points of the dense baseline across 70–85% sparsity. These results indicate that progressive magnitude-based
pruning provides an effective single-cycle approach for neural network sparsification under the evaluated settings.
Read the full abstract ▾
All authors Romana Qureshi, Hafida Benhidour, Said Kerrache, Nahlah Aljeraisy