Machine Learning
Stable-Plastic Subspace Construction for Differentially Private Continual LoRA
Jin Liu, Ning Xi, Yinbin Miao et al. (+3 more)
Continual learning (CL) adapts pretrained models to a sequence of tasks while retaining knowledge acquired from earlier tasks. When task data are sensitive, differential
privacy (DP) provides record-level protection, but maintaining both adaptation and retention under
privacy constraints remains challenging. We study this problem in continual low-rank adaptation (LoRA) and observe that: 1) private training increases forgetting primarily during subsequent adaptation rather than initial task acquisition; 2) jointly perturbing both LoRA factors introduces a non-negligible bilinear noise interaction; and 3) DP aggravates the stability-plasticity dilemma, hindering both knowledge retention and adaptation to new tasks. Based on these observations, we propose DP-SPA, which constructs a stable subspace from previously privatized updates and a plastic subspace from pretrained weights within its orthogonal complement. The method fixes these bases and privately optimizes only the LoRA factor, eliminating the bilinear noise interaction within each step. Before merging each task update, it rescales stable-direction coefficients using historical and current update energies. We establish a
privacy guarantee and show that recalibration does not increase historical overlap and tightens a conditional upper bound on old-task loss increase. Experiments across five
datasets, eight settings, and multiple
privacy budgets show that DP-SPA improves average accuracy and reduces forgetting compared with the evaluated baselines.
Read the full abstract ▾
All authors Jin Liu, Ning Xi, Yinbin Miao, Junkang Liu, Ke Cheng, Jianfeng Ma
Machine Learning
FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention
Guoxia Wang, Qianyue He, Siming Wu et al. (+6 more)
Long-context training of large
language and
multimodal models couples structured
attention masks (document, prefix-LM, share-question, sliding-window, block-sparse) with multi-node context parallelism, making the mask a dominant bottleneck. FlashMask's column-wise sparse mask compresses them from $O(n^2)$ to $O(n)$ via four query-axis boundary vectors, covering broad structured patterns. Implemented for Ampere GPUs, it neither exploits FlashAttention-3's TMA/WGMMA warp-specialized pipeline on Hopper nor supports distribution. The column-wise sparse mask is indexed by key positions but stores query-axis interval boundaries. Under any multi-chunk context-parallel assignment, it reduces per-rank mask localization to a provably zero-communication clip–shift–max on the boundary vectors, compatible with the single-GPU kernel. FlashMask-3 introduces a mask-aware Hopper kernel with three-role warp specialization atop FlashAttention-3's TMA/WGMMA pipeline, plus a mask-aware distributed extension: zero-communication mask localization, a sparsity-aware load balancer (HCC-IPO), and a mask-aware compute-communication overlap with mask-driven communication
pruning, whose forward all-gather uses
topology-aware hierarchical routing. On a single H100 across 12 masks at 4K–128K context, it improves achieved TFLOPs over FlashMask, FlexAttention, and MagiAttention by 45–141%, 34–71%, and 2–44%. At context-parallel degrees 4–32 with 8K sequence per device, it attains 31–75% compute-communication overlap efficiency and improves throughput over Megatron-Core CP ring, Megatron-Core CP all-gather, and MagiAttention by $1.80\times$–$3.71\times$, $1.71\times$–$2.92\times$, and $1.09\times$–$1.46\times$. In end-to-end training of a 118B-A14B MoE at 128K on 128 H100 GPUs, it raises throughput by 7.3–11.0% over a Dual Chunk all-gather baseline, with
attention forward+backward 24.5–44.9% faster.
Read the full abstract ▾
All authors Guoxia Wang, Qianyue He, Siming Wu, Haoyang Xie, Qiwen Bao, Jinle Zeng, Jiabin Yang, Tian Wu, Dianhai Yu
Machine Learning · Cross-listed from cs.AI
PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning
Changguo Jia, Zhiyou Xiao, Xinbei Ma et al. (+5 more)
Extended chain-of-thought
reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter
reasoning. We introduce PaceReasoner, a label-free test-time reinforcement learning framework that uses a model's LONG responses to improve its SHORT-mode accuracy. Both modes share a trainable policy, creating a need for reliable supervision, sufficient SHORT training samples, and continued LONG responses to guide learning. PaceReasoner combines all-response and LONG-only answer consensus through progressive, confidence-weighted supervision. A behavior reward gradually shifts from encouraging SHORT exploration to rewarding agreement with LONG answers, while a ratio controller regulates the balance between modes. Across three model backbones and four
benchmarks, PaceReasoner improves average SHORT accuracy over the baselines by 7.4–13.5 percentage points, with fewer than 25
reasoning tokens per response on average. Ablations support the key components, and cross-
dataset results demonstrate transfer beyond the adaptation set.
Read the full abstract ▾
All authors Changguo Jia, Zhiyou Xiao, Xinbei Ma, Geng Chen, Weiming Zhang, Yiming Xu, Tianqi Zhao, Minghui Zhou
Machine Learning
Evaluating the Causal Faithfulness of SHAP as a Candidate Attribution Method for SAE Features
Samuel Xie and Noura Al-Moubayed
Sparse autoencoders decompose
language model representations into interpretable features, but feature interpretation in this literature remains predominantly correlational. Attribution methods offer more direct estimates of feature influence, yet their faithfulness to actual causal effects has not been systematically evaluated in the SAE setting. We apply SHAP-based attribution to SAE latent features and evaluate it against direct causal intervention, using sentiment classification on SST-2 with GPT-2 Small and a 32,768-feature layer-7 SAE as a testbed. We compare SHAP to Integrated Gradients, Gradient$\times$Input, and probe-weight baselines across linear and MLP probe arms, scoring each against feature ablation and activation steering measured through the
language model's own logit difference. Most faithfulness associations we measure do not survive multiple-comparison correction, and attribution methods that agree strongly with one another ($\rho = 0.42$–$0.80$) agree poorly with measured causal effects, indicating that inter-method agreement is not evidence of causal faithfulness. Two effects hold under control. First, local per-example attribution retains a directional advantage over global averaged attribution, while its apparent importance advantage is explained by feature activity rather than superior causal ranking. Second, under known-ground-truth minimal pairs, attribution recovers inserted sentiment signal well above chance (AUROC $0.792$) but fails to localize deletions (AUROC $0.520$), suggesting that these methods detect the presence of a feature's influence more reliably than its absence. We argue that importance faithfulness and directional faithfulness are separable properties requiring separate evaluation, and that attribution agreement should not substitute for causal validation.
Read the full abstract ▾
Machine Learning
Interaction-as-a-Judge
Wayne Chi, I-Hung Hsu, Li Chen et al. (+6 more)
Coding
agents are tasked with producing sophisticated interactive applications such as websites, desktop applications, and games. While humans assess these applications interactively, current automated LLM evaluations primarily focus on code analysis and unit tests. This mismatch can cause LLM judges to miss failures that are immediately apparent to human users. We study Interaction-as-a-Judge, an evaluation paradigm where computer-use
agents (CUAs) directly interact with an application. We demonstrate that Interaction-as-a-Judge can improve both evaluation and generation of interactive applications. To this end, we collect and release two complementary
datasets: $6,858$ pairs of applications with human preferences and corresponding
agent traces, and $222$ applications with human-verified requirement labels. Relative to standard non-interactive approaches, we find that Interaction-as-a-Judge improves evaluation in terms of predicting human preferences ($65.6\% \to 69.1\%$) and requirement verification ($77.0\% \to 81.6\%$). We also observe scaling benefits: across both preference
alignment and requirement verification, higher-quality interactions improve performance. Finally, through both inference- and training-time experiments, we demonstrate that Interaction-as-a-Judge can also improve the quality of generated artifacts. At inference time, Interaction-as-a-Judge repairs $75.5\%$ of broken requirements within five attempts, compared to $55.4\%$ for code-only self-feedback. At training time, using Interaction-as-a-Judge as a reward signal improves win-rate over the base model by $6.7$pp while reducing both generated code length by $35.7\%$ and build failure rates by $7.2$pp compared to a code-only reward signal.
Read the full abstract ▾
All authors Wayne Chi, I-Hung Hsu, Li Chen, Wei-Lin Chiang, Ion Stoica, Anastasios Nikolas Angelopoulos, Ameet Talwalkar, Chris Donahue, Cho-Jui Hsieh
Machine Learning · Cross-listed from cs.AI
Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards
Keru Chen, Sen Lin, Yingbin Liang et al. (+2 more)
Effective collaboration among large
language model (LLM)
agents in multi-
agent systems requires sharing relevant evidence, requesting missing information, and incorporating teammates' contributions into decisions. Training these behaviors is challenging because final task outcomes provide limited feedback on the value of individual messages. We introduce CoSIR (Collaboration via Surprisal-based Information Rewards), a post-training approach that uses a simple, verifiable environment to teach collaboration behaviors that generalize to more complex, unseen tasks. We propose a
Bayesian evaluator that scores shared information by its reduction in team surprisal, defined as the sum of the negative log probabilities assigned to the correct option given each
agent's available evidence. Requests are scored by the potential reduction in the same quantity if the requested information were truthfully provided. Separate rewards encourage
agents to use the received information in their private choices and calculations. We post-train Qwen3-4B, Qwen3-8B, and Gemma-3-4B-it through self-play and evaluate transfer to seven unseen natural-
language collaboration tasks. CoSIR achieves the highest aggregate score, while its performance in general tasks remains competitive. Behavioral analyses show increased disclosure of private evidence and fewer judged failures to use teammates' input.
Read the full abstract ▾
All authors Keru Chen, Sen Lin, Yingbin Liang, Nathaniel D. Bastian, Shaofeng Zou
Machine Learning
Deep Mesoscopic Dynamics
Yue Zhao, Shiqi Wu, Yihang Ouyang et al. (+6 more)
Microscopic simulations resolve spatial patterns but are feasible only over small domains and short timescales, whereas bulk descriptions erase those patterns through spatial averaging. Mesoscopic fields preserve this spatial organisation, but their effective equations are known only for selected microscopic systems and scaling limits. We introduce Deep Mesoscopic Dynamics (DeepMesoD), which uses neural networks to learn an effective mesoscopic field equation from microscopic trajectories at a prescribed coarse-graining scale. For the nonconserved dissipative dynamics studied here, DeepMesoD learns the free-energy functional with a spatial interaction kernel and a state-dependent dissipation operator constrained by the fluctuation-dissipation relation. We first validate the construction in the Ising-Kac model, where the learned mesoscopic equation recovers the known hydrodynamic limit and rollouts remain stable far beyond the training horizon. We then treat two systems without closed-form mesoscopic descriptions. For a two-dimensional Heisenberg ferromagnet governed by atomistic
spin dynamics, DeepMesoD learns a mesoscopic model whose predictions match atomistic references up to 1 ns, and a rollout with an unseen initial condition remains bounded up to 25 ns. For layered CrBr$_3$, the learned kernel captures the suppression and sign reversal of interlayer coupling at a stacking fault whose location and strength are not supplied as inputs. Controlled changes to the learned interaction show how fault number and placement shape multistep
magnetic responses, complementing our magneto-photoluminescence measurements. Across the two atomistic systems, DeepMesoD achieves a three-to-four-order-of-magnitude reduction in wall-clock time compared with atomistic
spin dynamics.
Read the full abstract ▾
All authors Yue Zhao, Shiqi Wu, Yihang Ouyang, Sergey Grebenchuk, Magdalena Grzeszczyk, Xiaoxu Zhao, Kostya S. Novoselov, Maciej Koperski, Qianxiao Li
Machine Learning
Searching for What Matters: Open-Ended Discovery of Multiple Hypotheses with Agentic Data Exploration
Sanchit Kabra, Nurendra Choudhary, Jiangshu Du et al. (+3 more)
Discovering what drives an outcome from data is central to science and often requires deciding what is worth investigating before a specific hypothesis is known. Yet most existing hypothesis generation settings substantially narrow this search by providing a research question, target relationship, or curated context. We introduce open-ended multiple hypothesis discovery, where a system receives only a large tabular
dataset and an outcome and must discover multiple data-supported hypotheses without knowing in advance the relevant variables, functional forms, conditions, or number of underlying mechanisms. To study this problem, we introduce a
benchmark built from structural causal models grounded in real-world data schemas, containing 351 planted hypotheses across 15 tasks and five domains, with 53–65 variables and 1M–10M rows per task. The causal model is hidden from the discovery method and retained only by the evaluator, allowing proposed hypotheses to be tested through interventions and separating observational discovery from causal validation. We further propose HypAgent, which treats the
dataset as an interactive environment and performs iterative search by proposing candidate directions, triaging and refining promising hypotheses, and removing explained signal so that each accepted discovery redirects subsequent search. HypAgent achieves 0.47 precision, 0.51 recall, and 0.49 F1, compared with 0.35 F1 for the strongest baseline. Our analysis shows that many failures occur after a relevant variable has already been surfaced, suggesting that correctly characterizing a mechanism's functional form and conditions, rather than merely identifying relevant variables, remains a key challenge in open-ended discovery.
Read the full abstract ▾
All authors Sanchit Kabra, Nurendra Choudhary, Jiangshu Du, Eddie Huang, Danai Koutra, Chandan K Reddy
Machine Learning
RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions
Rishabh Ranjan, Vignesh Kothapalli, Harshvardhan Agarwal et al. (+5 more)
Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains. However, adapting existing models to unseen
datasets requires tens of thousands of examples. Here we introduce RT-J, an 86M-parameter relational foundation model (RFM) that makes accurate predictions even with hundreds of in-context examples or fewer. To achieve this, we first assemble the Join, a large collection of 639 web-crawled databases with 6,023 LLM-generated forecasting tasks. We pretrain with long contexts of up to 8,192 database
cells, using in-context examples from a novel lightweight random-walk retriever. Finally, we leverage context tuning and ensembling to scale up test-time compute. On in-context regression tasks from RelBench, RT-J requires 10x fewer examples on average to match strong feature engineering pipelines with LLM-
agent or RDBLearn featurizers and TabICLv2 or LightGBM predictors. Overall, our work pushes the frontier for context-efficient predictions on relational data and highlights the importance of real-world semantics, context engineering and large-scale pretraining for RFMs.
Read the full abstract ▾
All authors Rishabh Ranjan, Vignesh Kothapalli, Harshvardhan Agarwal, Charilaos Kanatsoulis, Roshan Upendra, Tom Palczewski, Carlos Guestrin, Jure Leskovec
Machine Learning
TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting
Yangze Li, Zhengyang Zhou, Qihe Huang et al. (+3 more)
Long-term time series forecasting requires temporal dependency modeling that remains stable and generalizable under temporal distribution shifts. However, real-world time series are often noisy and non-stationary, making deep learning models prone to fitting incidental temporal interactions in the training data. A key question is whether there exist temporal relationship structures that recur across different temporal positions and variables. We analyze temporal relationship
matrices on commonly used time series
datasets and find that samples from different temporal positions and different variables exhibit shared dominant temporal relationship structures. This indicates that temporal relationship structures contain patterns that recur stably across samples and variables. To learn such shared structures, we propose Temporal Structure Network (TStruct), a simple yet effective network for directly learning shared and generalizable temporal dependencies. Specifically, TStruct directly parameterizes a set of shared temporal dependency
matrices and generates normalized combination weights using dynamic sample information and static variable priors. These weights represent a soft allocation of each sample-variable pair over shared temporal dependency structures, enabling the model to generate adaptive temporal dependency
matrices under shared structural constraints, rather than fitting incidental interactions in a fully unconstrained manner. Notably, this simple structure-aware design consistently outperforms several strong baselines across all
datasets, achieving superior accuracy while maintaining high computational efficiency.
Read the full abstract ▾
All authors Yangze Li, Zhengyang Zhou, Qihe Huang, Pengkun Wang, Binwu Wang, Yang Wang
Machine Learning
MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision
Ziyang Zhang, Shenyi Li, Yilin Wang et al. (+4 more)
Time-series analysis is increasingly studied in
multimodal settings, yet most
benchmarks pair temporal signals with text or with visualizations derived from the same signal. This leaves open whether
multimodal large
language models (MLLMs) can integrate time series with real-world visual evidence. We introduce MMTA (
multimodal temporal analysis), a
benchmark of tri-modal tasks with diverse cross-modal complementarity patterns among time series, text, and
vision. MMTA spans nine domains – robotics, autonomous driving, human action, manufacturing, AR assistance, healthcare, recommendation, finance, and
climate – under
video+TS and image+TS layouts, with a 3,524-sample test split covering classification and forecasting. The
benchmark standardizes heterogeneous real-world sources into a shared schema with domain-specific
prompts, provenance documentation, and success-weighted metrics that penalize both wrong answers and failed generations. Evaluating eight open-source and proprietary MLLMs reveals a shared bottleneck: representing time series as text creates very long
token sequences and weakens fine-grained
alignment with visual evidence, especially in long-
video settings. We then introduce TimeOmni-v, a
multimodal LLM extension with a dedicated time-series encoder, temporal positional
alignment, modality-aware
token layout, and a forecasting head. TimeOmni-v improves long-
video classification and time-series inference efficiency, showing that MMTA not only exposes representation and grounding failures but also motivates targeted model design.
Read the full abstract ▾
All authors Ziyang Zhang, Shenyi Li, Yilin Wang, Ziyun Cui, Bowen Zhou, Wen Wu, Chao Zhang
Machine Learning
Persistence Positional Encoding: A Minimal Transformer Recipe for Persistence Diagrams
Eunwoo Heo, Ganghyun Kim and Jaejun Yoo
Persistence diagrams (PDs) represent multiscale topological information as multisets of birth-death pairs $(b,d)$. How best to use them with
Transformers, however, remains unclear. Connecting PDs to
Transformers requires choosing how topological information is tokenized and exposed to self-
attention. Prior methods use specialized designs for tokenization, aggregation,
Transformer blocks, or
attention, but are hard to compare since reported results rarely share PD inputs, splits, or model-selection rules. We instead confine the diagram-specific design to point representation, mapping each birth-death pair through fixed random
Fourier features while leaving the
Transformer backbone unchanged, and call this recipe Persistence Positional Encoding (PPE). In matched controls on eight TU graph
benchmarks (TU8), changing only point representation shifts macro accuracy by 5.49 to 6.47 percentage points (pp), against 0.47 to 1.45 pp from changing the downstream module, identifying point representation as the dominant design variable tested. We further reevaluate vectorizations, kernels, learned representations, and
Transformer-based models under one protocol with shared PD inputs, outer folds, and validation-only selection. Among all evaluated PD methods and downstream configurations, PPE achieves the highest mean on most
benchmarks, including TU8, ORBIT5K, and MCB-C. Finally, we prove that grid averaging leaves a reconstruction error at any resolution, whereas a
Transformer with fixed random
Fourier frequencies is almost surely universal. PPE thus offers a minimal,
Transformer-native baseline for persistence diagrams, and a common protocol for future comparison.
Read the full abstract ▾
Machine Learning
GeoNIRS: Geometry-Aware Pretraining for Heterogeneous fNIRS Representation Learning
Zongsheng Li, Shengyuan Zhu, Zimo Zhang et al. (+3 more)
Functional near-infrared spectroscopy (fNIRS) provides portable and spatially localized measurements of cortical hemodynamics, but differences in channel count, probe layout, signal distribution, and task type hinder joint pretraining across
datasets. We introduce GeoNIRS, a geometry-aware framework that uses source-detector locations as a shared spatial reference across heterogeneous probe layouts. GeoNIRS compresses variable-size channel sets into a fixed-size latent representation and employs bidirectional HbO/HbR cross-reconstruction with contiguous temporal masking. GeoNIRS-base is pretrained on eight heterogeneous
datasets, while GeoNIRS-large scales to 22
datasets. Neither downstream data nor labels are used during pretraining, enabling evaluation under a strict cross-task setting. To our knowledge, GeoNIRS is the first fNIRS framework to explicitly model physical channel geometry during joint pretraining across heterogeneous channel configurations, and the first to provide complete source code and downloadable pretrained checkpoints. We evaluate GeoNIRS on eight held-out tasks spanning clinical and auditory assessment, pain and affective processing, semantic decoding, and motor function. GeoNIRS achieves the highest task-averaged balanced accuracy among the evaluated conventional machine-learning, fNIRS-specific, general time-series, and fNIRS pretraining baselines. Compared with random initialization, pretraining improves average balanced accuracy by 4.12 percentage points under linear probing and 3.30 points under full fine-tuning, with larger benefits when labels are scarce. GeoNIRS also remains robust to missing input channels. Geometry perturbations and pretraining ablations further show that both channel geometry and cross-chromophore reconstruction contribute to the learned representations.
Read the full abstract ▾
All authors Zongsheng Li, Shengyuan Zhu, Zimo Zhang, Hanyao Li, Shengming Wang, Quanying Liu
Machine Learning · Cross-listed from cs.IR
FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion Retrieval
Tripti Shukla, Shwetha Somasundaram, Akshat Gupta et al. (+3 more)
Evaluating fashion
retrieval systems remains challenging due to the limited availability of
benchmarks that capture the fine-grained, open-ended queries encountered in real-world search and recommendation. Existing
benchmarks often rely on manual curation, predefined taxonomies, or synthetic
prompts, limiting scalability and semantic coverage. We introduce FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion
Retrieval, an automated framework that derives user-type queries and relevance sets directly from catalog structure. Our key insight is that hierarchical discrete representations learned by Residual Quantized Variational Autoencoders (RQ-VAE) organize products into semantically coherent clusters at progressively finer granularities. We leverage this structure to construct FASHION-RQBENCH, a scalable
benchmark without manual query annotation or predefined taxonomies. We propose four complementary tasks for evaluating ranking, relevance classification, fine-grained sibling discrimination, and paraphrase robustness, alongside query- and attribute-level relevance metrics. Experiments across recent
retrieval models demonstrate that FASHION-RQBENCH differentiates model capabilities across query types and attributes. A human study further shows that
benchmark queries achieve comparable naturalness and higher intent clarity than real user queries, supporting their validity for real-world evaluation. The code and FASHION-RQBENCH
dataset will be publicly released upon acceptance.
Read the full abstract ▾
All authors Tripti Shukla, Shwetha Somasundaram, Akshat Gupta, Rohit Garg, Paul Duff, Ian Anderson
Machine Learning · Cross-listed from quant-ph
A Tutorial on Quantum Amplitude Embedding with Data Re-Uploading
Hyojun Ahn and Joongheon Kim
Amplitude
embedding lets a variational
quantum model read many classical features with few
qubits, but the model output is then only a quadratic form in the normalized input. Data re-uploading, which encodes the input repeatedly between trainable blocks, can be used to enrich such a model. Because every additional upload of an amplitude
embedding repeats a costly state preparation, the gain that an upload buys has to be known before the gates are spent. This tutorial thus addresses the problem of explaining what data re-uploading adds to an amplitude-embedded model and how large the gain is. We express sequential re-uploading and parallel re-uploading with two copies in one notation and show that each upload raises the reachable
polynomial order by two. Under one trainable
circuit family and one budget of trainable parameters, simulation results show that re-uploading raises the test coefficient of determination from 0.689 to between 0.883 and 0.975 on targets of order four and from 0.337 to between 0.642 and 0.783 on targets of order six, on all ten seeds. On a quadratic target and on handwritten digits, one upload remains the best choice, and every additional upload lowers the gate error that the classifier tolerates. These results help designers match the number of uploads to the
polynomial order of the task at hand.
Read the full abstract ▾
Machine Learning
Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design
Yu Zeng, Yuchuan Chen, Ziyue Zhang et al. (+5 more)
Materials and chemical optimization must choose the next synthesis, characterization, or high-fidelity simulation from sequential observations under a limited budget. Large
language models can use task knowledge to propose adjustments, but composing surrogates, acquisition functions, and search strategies is constrained by compatibility, parameter dependencies, and evidence requirements. We present Agentic-MatriBO, a capability-compiled agentic
Bayesian optimization (BO) framework that represents BO components and selection conditions as composable capabilities. A
language policy proposes BO recipes and candidate plans; a compiler checks proposals against the registered capability catalog; and a deterministic execution layer validates and commits candidates. Oracle observations are stored in research
memory and inform later rounds. We compare Agentic-MatriBO with eight baselines on four offline finite candidate pools—COF, PCE10, Buchwald–Hartwig (BH), and Suzuki–Miyaura—using five seeds per condition; results are reported descriptively. Across the four tasks, Agentic-MatriBO has the best mean endpoint quality after orienting each objective so that higher is better. On COF, it reaches the tabulated optimum in all five seeds both in the end-to-end comparison and after shared initialization, where it also retains an advantage in cumulative quality. Its normalized area under the best-so-far quality curve during the BO stage (nAUC-BO) is substantially higher on COF, near parity with the best baseline on PCE10 and BH, and lower on Suzuki. COF ablations show that removing the capability compiler or evidence gate coincides with lower cumulative quality and fewer exact-optimum hits. The framework provides an inspectable interface for evidence-conditioned BO adaptation.
Read the full abstract ▾
All authors Yu Zeng, Yuchuan Chen, Ziyue Zhang, Zijian Wei, Yanyi Su, Guojiang Zhao, Hongshuai Wang, Zhifeng Gao
Machine Learning
Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR
Savyasachi Gupta and Aniruddha Srinivas Joshi
Reinforcement learning with verifiable rewards (RLVR) has become a principal recipe for improving the
reasoning of large
language models (LLMs). It rests on the assumption that the checker scoring each response is itself correct. In practice, rule-based checkers reject correct answers in unexpected formats, unit tests accept incorrect programs, and LLM judges can be led to approve empty or
adversarial responses. This work surveys 58 studies that measure, analyze, or mitigate such verifier errors. We ask what errors verifiers make, how they affect training, which mitigations work against which errors, and how the findings extend to self-generated, rubric- and judge-based, and verifier-free rewards. The evidence suggests that the structure of an error matters more than its rate. Random errors mostly slow learning, though under a fixed budget or KL regularization they also lower final accuracy. False positives that the policy can learn to trigger can cause plateaus or collapse, sometimes even with a low initial error rate. Whether a verifier wrongly rejects or accepts depends on what it checks and who built it, not on its family. Its errors shift as the policy improves, and most mitigations have been tested against only one kind of error. We compile the findings into comparison tables, reconcile apparent conflicts in the literature, and propose a reporting protocol to make future results comparable.
Read the full abstract ▾
Machine Learning
Follow the Perturbed Leader for Linear Bandits: $\sqrt{T}$ Regret over General Convex Sets
Chen-Yu Wei
We give the first
adversarial linear bandit
algorithm based on Follow-the-Perturbed-Leader (FTPL) that achieves $\sqrt{T}$ regret over general convex action sets. Our
algorithm attains $\widetilde{\mathcal{O}}(d^{5/4}\sqrt{T})$ regret using only linear optimization oracles, and the near-optimal $\widetilde{\mathcal{O}}(d\sqrt{T})$ regret when an optimal-design exploration distribution is further available. This improves on the $T^{2/3}$ regret of the FTPL
algorithm of Dani and Hayes (2006) for general convex sets, and generalizes the $\sqrt{T}$ regret of Lévy et al. (2026) over two special action sets (hypercube and Euclidean ball). Compared to previous oracle-efficient linear bandit
algorithms based on continuous exponential weights, the FTPL approach generally has better computational efficiency, and is much simpler to implement. The key algorithmic element is a perturbation distribution that adapts to the past reward
estimators. Its simplest form, an adaptive Gaussian perturbation, is straightforward to implement and already attains the regret bound above. We further extend it to two general constructions, random-weighting and elliptical perturbations, each covering distributions from light tails (Gaussian) to heavy tails (Student-$t_2$). On the technical side, we develop a systematic way to analyze the stability term in the FTPL regret through the Fisher information of the perturbation distribution. This builds a general framework for FTPL beyond existing ones such as the hazard rate and the FTRL-FTPL duality.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
SPARCL: Spatially Adaptive Regional Coverage for Active Learning in Chest X-ray Analysis
Juho Jung, Seongjae Kang, Mijoo Kim et al. (+4 more)
Pixel-level annotation for chest X-ray (CXR) lesion segmentation is expensive, making active learning (AL) essential. However, existing AL strategies fail to account for the spatial distribution of selected samples, resulting in inconsistent performance across focal (e.g., aortic calcification) and diffuse (e.g., nodules) pathologies. In this paper, we propose SPARCL (Spatially Adaptive Regional Coverage for Active Learning) to dynamically balance predictive uncertainty with cumulative spatial coverage. By employing a concave coverage function, SPARCL imposes diminishing returns on previously annotated regions, naturally directing the annotation budget toward under-labeled areas. Furthermore, an
entropy gate reverts the
algorithm to standard uncertainty sampling when spatial variation is absent. This coverage objective is monotone submodular, guaranteeing near-optimal greedy batch selection. To address how aggregate metrics like Dice obscure regional failures, we further introduce two metrics—Spatial Inconsistency (SI) and Performance Coverage (PC)—to quantify anatomical
fairness across AL rounds. Evaluated on an in-house calcification cohort and public CXR
benchmarks, SPARCL reaches 95% of fully supervised performance using only 24% of the data, compared to 29% for the best baseline. Ultimately, SPARCL ensures robust spatial reliability, surfacing regional gains that aggregate metrics miss.
Read the full abstract ▾
All authors Juho Jung, Seongjae Kang, Mijoo Kim, Sungduk Cho, Yunkyoung Jun, Sunghoon Joo, Yoona Hwang
Machine Learning · Cross-listed from cond-mat.mtrl-sci
Learning from fracture: Teaching language models to design through physical experience
Bo Ni
How can
language models learn to optimize physical designs through experience? We introduce FracLearn, an experience-abstraction-generalization framework evaluated through a deliberately unfamiliar, Tetris-inspired fracture game. The model first proposes architectures and examines simulated fracture responses to accumulate experience. Abstraction organizes these observations into conditional principles linking reinforcement placement, crack
evolution and load transfer, with supporting evidence and failure conditions. Generalization challenges the model to combine these principles in new architectures and surpass the earlier design record. Campaigns demonstrate progressive refinement and recovery through hypothesis revision, yielding a best composite score 11.0% above the experience-stage record. Fracture analyses connect improved performance to crack deflection and temporary trapping as toughening mechanisms, alongside greater residual load capacity. Learning occurs through external knowledge and decisions, without model-weight updates. This approach offers a route to scientific
agents that turn computational experiments into reusable physical knowledge for materials discovery and engineering design.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Beyond the End-Effector: Learning Whole-Arm Contact Manipulation from Human Demonstrations
Bo-Ruei Huang, Daniel Seita and Erdem B{\i}y{\i}k
Robot manipulation has traditionally relied on end-effector-centric interactions. In contrast, humans routinely exploit whole-arm contacts to improve efficiency, robustness, and adaptability, especially when the hands are occupied or when precise grasping is unnecessary. Enabling similar capabilities in
robots remains challenging: the
robot must select where on its arm to make contact, generate effective non-prehensile interactions, and satisfy task-specific pose or safety constraints on the end-effector. We propose Whole-Arm Contact Learning (WACL), a hierarchical framework that describes each whole-arm contact task with three
robot-agnostic representations and hands them to a quasi-static surface-contact optimizer: semantic keypoints that summarize the scene, a reference contact trajectory that specifies where and how the arm presses on the object, and safety-aware path constraints that a
vision-
language model generates from the task description to protect the end-effector's task. The
robot's kinematic chain enters only in this optimizer, which grounds these representations onto the arm by jointly searching over which link makes contact, where on that link, and the joint configuration that realizes it. This decomposition lets WACL learn the contact trajectory from 10 bare-hand human demonstrations per task collected without teleoperation, while new end-effector constraints change only the optimizer's input rather than any trained component. Real-world experiments on a 7-DoF arm across four whole-arm tasks show that WACL sustains contact under end-effector constraints where a strong link-pose baseline fails (78% vs. 33% success) and generalizes to new constraints without retraining. Website: https://wacl-
robot.github.io
Read the full abstract ▾
Machine Learning
GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation
Xu Liu, Hanshu Yan, Taha Aksu et al. (+6 more)
Contextual forecasting seeks to improve time series forecasting by incorporating forward-looking information, such as planned events, external conditions, and expert expectations. However, reliable evaluation remains difficult: existing
benchmarks often have limited domain coverage, lack standardized history-future splits, or provide text that is not guaranteed to inform the future. We introduce GIFT-Eval-CTX, a
benchmark that isolates whether forecasting methods can translate verified future information into accurate numerical trajectories. Built upon GIFT-Eval, GIFT-Eval-CTX contains 10,000 instances across 20
datasets. Each instance provides structured effects derived from the realized future: Macro effects describe horizon-wide behavior, while Micro effects specify localized changes. We construct these annotations with an agentic pipeline combining LLM-based discovery and deterministic code validation. We
benchmark TSFMs, frontier LLMs, and tool-using agentic systems. The results show that structured effects reduce aggregate relative MASE by 40.7% for GPT-5.6 Sol and 29.6% for Claude Opus 4.8 relative to history-only prompting. The evaluated MoiraiAgent system achieves the best overall result. We further analyze the contributions of structured effects and agentic systems to performance, and identify opportunities for future research.
Read the full abstract ▾
All authors Xu Liu, Hanshu Yan, Taha Aksu, Quang Pham, Zhongzheng Qiao, Jun Hao Liew, Silvio Savarese, Doyen Sahoo, Junnan Li
Machine Learning
Posterior-Averaged Bellman Flow Matching for Distributional Critics
Zeqiao Li, Yijing Wang, Haoyu Wang et al. (+2 more)
Distributional critics model the full return distribution, providing richer signals for exploration and risk-sensitive control. Recent work has shown that flow-based critics can model these distributions flexibly and provide effective supervision across flow time for temporal-difference learning. However, unlike standard flow matching with fixed data endpoints, a flow critic is trained on Bellman targets recursively generated by a learned target critic under the current policy. Existing objectives therefore either use noisy single-endpoint supervision or rely on the learned flow itself for additional guidance. Our key observation is that an intermediate bridge state may be compatible with several Bellman endpoints, so its velocity should average their directions under the corresponding posterior. We propose Posterior-Averaged Bellman Flow Matching (PA-BFM), which samples an endpoint pool, infers the closed-form posterior over the latent anchor, and regresses to the posterior-mean velocity. Uniform anchor selection makes this target an exact finite-pool Rao–Blackwellization of the single-endpoint target: for every \(K\), it preserves the population target, cannot increase conditional variance, and its conditional variance scales as \(O(K^{-1})\). The endpoint pool supports conservative updates, while the twin return flows provide critic-disagreement and unsupported-mass diagnostics. Controlled studies show that PA-BFM reduces fixed-query target mean-squared error by \(79.7\%\) and target-induced gradient variance by up to \(98.0\%\), while improving return-distribution fidelity. Across 50 OGBench tasks and four offline-to-online scenarios, PA-BFM achieves higher aggregate performance than Value Flows.
Read the full abstract ▾
All authors Zeqiao Li, Yijing Wang, Haoyu Wang, Zheng Li, Zhiqiang Zuo
Machine Learning · Cross-listed from cs.AI
Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis
Nam V. Nguyen, Hoang Van Truong, Hieu D. D. et al. (+3 more)
We study industrial fault diagnosis as a classification task that assigns sensor time-series windows to predefined health states or fault types. Scarce labels and changing operating conditions make repeated training of specialized classifiers costly. Yet structures such as periodicity, trends, and transients can remain diagnostically informative and be examined through reusable analytical tools. LLM
agents can select and interpret these tools, but fixed rules or training-derived guidance may not resolve each signal's ambiguity, while unconstrained interpretation may overstate weak or conflicting results. We introduce Agentic4PDM, a framework that separates adaptive investigation from control over evidence use. LLM
agents compare each signal with labeled references from every candidate class, identify unresolved distinctions, and propose follow-up measurements. A deterministic software controller, called the host, enforces contract-checked gated adjudication (CCGA): it checks requests, requires commitment to a complete tool batch before results are observed, and assigns evidence roles based on tool checks against labeled references. These roles distinguish corroborative support from advisory information. The Judge
Agent proposes a diagnosis, while the controller checks protocol compliance and records the investigation. Agentic4PDM supports training-free diagnosis using pretrained representations and labeled references without task-specific diagnostic models, and a standard setting that additionally investigates trained-model predictions. Experiments on selected bearing and motor diagnosis challenges and an unfiltered industrial test set supplied by our customer show gains in aggregate macro F1 over the evaluated diagnostic and agentic baselines. Ablations further support the value of the governed workflow.
Read the full abstract ▾
All authors Nam V. Nguyen, Hoang Van Truong, Hieu D. D., Duy Khuong Nguyen, Quang Pham, Tung Kieu
Machine Learning
Hybrid Parallel Bessel KAN Model: a Kolmogorov Arnold Network: integrated framework for developing a novel architecture to reconstruct the fused-basis approach via a parameter free quadratic interaction
Mintu Pathak, Meshv Patel, Mohendra Roy et al. (+1 more)
The Kolmogorov-Arnold Network (KAN) challenges traditional MLPs by placing learnable activation functions on network edges. However, scaling KANs to spatial data exposes limitations in default B-Splines. While hybrid architectures mix multiple basis families on a single edge to resolve this, monolithic superposition causes
geometric overlap, parameter explosion, and severe numerical ill-conditioning ($\kappa(G) \approx 10^{16}$).To overcome this, we propose Parallel BesselKAN, which isolates B-Spline and low-order Bessel branches into parallel processing pipelines integrated via a parameter-free quadratic interaction. This decoupled architecture acts as an efficient internal ensemble, bypassing monolithic stability bottlenecks. It compresses the parameter footprint by $35\%$ while achieving $97.99\%$ accuracy on MNIST. Although standard MLPs retain a hardware speed advantage for pure
vision tasks, Parallel BesselKAN provides a robust, parameter-efficient framework stabilizing mixed-basis networks and paving the way for scalable spatial adaptations like Convolutional KANs.
Read the full abstract ▾
All authors Mintu Pathak, Meshv Patel, Mohendra Roy, Jwngsar Brahma
Machine Learning
Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback
Shuang Wu
Gaussian process bandits exploit similarities among configurations to optimize
prompts,
retrieval systems, and
agent workflows. In these applications, however, inexpensive model-based evaluations can disagree with trusted task outcomes. We study selective verification when an action is chosen before a diagnostic is observed and trusted feedback is informative on an unknown set of diagnostic states. A finite reliability class and a finite RKHS signal dictionary describe these two sources of uncertainty. We construct a fixed audit design that combines reliability coverage with reward separation and establish a finite-time regret bound that accounts for a hard audit budget and the rounds needed to obtain informative observations. A safe adaptive extension mixes this robust design with predictable Chernoff allocations while preserving a uniform identification floor and exact expected acquisition-cost accounting. For signed-coordinate kernels, structured and diffuse reliability classes require different audit scales despite sharing the same reward geometry. Synthetic experiments distinguish these certified designs from an adaptive posterior heuristic and GP controls. Safe adaptive allocation reduces aggregate regret relative to the fixed design under the exact dictionary, but its finite-budget error certificate is numerically loose. Conditional-feedback errors can remove the heuristic's advantage and target perturbations can reverse it. Separate AI-task replays assess feedback correction and fitted-dictionary policies without establishing end-to-end validation of a learned selective-verification method.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.MA
Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
Yiqing Peng, Hehai Lin, Zixuan Wang et al. (+7 more)
Large
language model (LLM)-based multi-
agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but can create a bottleneck at a single coordination locus, whereas decentralized coordination offers local autonomy but must achieve effective collaboration through distributed decisions and experience. These trade-offs motivate a systematic study of the space between the two regimes. We introduce Degrees of Freedom (DoF), a continuous configuration framework that quantifies the size of the decision space delegated to downstream
agents. DoF controls the granularity of delegated work and the target probability that each task unit is assigned to the branches. Its endpoints recover the two coordination regimes. Across multiple task domains, DoF reveals a hierarchy of organizational effects. Delegated granularity and within-regime routing produce structured but bounded profile reallocations, whereas task domain and retained experience are associated with stronger differences between the centralized- and decentralized-branch profiles. The resulting performance landscape is task-dependent: different domains favor different DoF configurations, while atomic-target conditions are more consistent across runs. In-domain retained experience brings the two branch profiles closer together. The same controlled sweep reveals a task-dependent coordination landscape: some domains exhibit higher-performing configurations, whereas others show flatter responses and no single configuration dominates across domains. In five of the six evaluated state, an intermediate DoF configuration achieves higher mean accuracy than both endpoints, demonstrating the value of exploring the coordination space between them. Together, these findings provide empirical guidance for studying and designing intermediate coordination regimes in LLM-based MAS.
Read the full abstract ▾
All authors Yiqing Peng, Hehai Lin, Zixuan Wang, Dongyi Zhang, Zhengjie Zhu, Yi Han, Yangyang Zheng, Hao Wang, Qian Li, Chengwei Qin
Machine Learning · Cross-listed from cs.CL
Auditing Failure Attribution: Label Predictability and Judge Behavior
Tianyang Xu and Jing Gao
Failure-attribution
benchmarks ask an LLM judge which step or
agent caused a failure. A high score should mean the judge checked the faulty step against the run (a cross-step check). However, spurious signals (surface cues) that predict the annotation can produce a high score. In this paper, we propose four tests to separate checking from cue use. Input restriction asks whether partial input predicts the annotation. Cue following checks whether moved cues change answers. Residual accuracy scores judges where cue-only predictors fail. Aggregation asks whether the failure mix or metric changes rankings. Real observations motivate these tests: on three
benchmarks, simple predictors match or beat GPT-4.1. In two Who&When Pro systems, a classifier reading one step's
reasoning finds 95-100% of faulty steps, motivating input restriction. In one of them, error injection leaves no
reasoning after the faulty step; judges fine-tuned on its labels beat GPT-4.1 by 41 points. Adding task-related
reasoning after that step moves this cue: fine-tuned judges lose 31-99 points, but zero-shot judges lose at most 9, motivating cue following. On Aegis, blaming every
agent matches GPT-4.1 on micro-F1 but trails by 19 points in exact-set accuracy, motivating aggregation. We recommend reporting these tests when developing failure-attribution
benchmarks.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Geometric Structure Predicts Per-Example Neighborhood Loss Under PCA Truncation
Sriram Loganathan, Gokul Anand and Ragavan Arivazhagan
Dimensionality reduction can preserve the average performance of text
embeddings even when a substantial fraction of their dimensions is removed. Aggregate metrics, however, do not reveal whether degradation is distributed uniformly across examples. We study per-example neighborhood stability under PCA truncation across static word
embeddings and modern sentence encoders. Per-item neighbor retention varies widely and is predictable from
geometric properties of the representation and its
alignment with the retained PCA subspace. The fraction of centered-vector energy retained by the truncated subspace is strongest for CBOW and RI, with neighborhood contrast leading on SkipGram and the modern/Matryoshka settings (GTE approximately tied), while local density is associated with retention in marginal analysis but adds little unique information once energy and contrast are controlled (R-squared increments 0.001 to 0.010). Local intrinsic dimensionality accounts for more variation than density on modern sentence encoders in pairwise comparison. On SciFact, query density predicts
retrieval degradation under aggressive compression; on NFCorpus the primary 32d association does not replicate, and a direct variance-restriction test leaves that null unresolved. Average compression performance conceals systematic per-example variation that geometry makes visible.
Read the full abstract ▾
Machine Learning
HiSTOR: Structured Treatment-outcome Representation Learning for High-Dimensional Longitudinal Data
Chuanqi Lao, Junzhou Huang and Qiao Liu
Estimating potential outcomes under alternative treatment sequences is essential for personalized decision-making, but remains challenging with high-dimensional
covariates and time-varying confounding. In this study, we propose HiSTOR (High-dimensional Structured Treatment-Outcome Representation), an end-to-end framework that integrates nonlinear dimension reduction with longitudinal counterfactual prediction. The central idea is to learn structured low-dimensional representations of both current patient states and evolving histories, according to their shared and distinct relationships with treatment assignment and outcomes. This extends latent-space
covariate adjustment to longitudinal settings, jointly addressing
covariate dimensionality and historical complexity. The resulting framework supports one-step and multi-step outcome prediction under specified treatment sequences. Experiments on CVSim and CancerSim demonstrate the superiority of HiSTOR across varying
covariate dimensions, confounding strengths, and prediction horizons compared to state-of-the-art methods. To sum up, HiSTOR offers a unified approach to connecting high-dimensional
covariate adjustment with longitudinal potential-outcome prediction.
Read the full abstract ▾