# Research Papers — 2026-06 · bundle page 87 of 260 > Full-text markdown of papers #4301–4350 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/87 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/86.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/88.md) ### Analysis of Public Schools Educational Performance Based on Causal Models and Hierarchical Clustering Authors: Anderson L. de Paula, Pedro C. dos Santos, Renato A. Krohling Published: 2026-06-19 Categories: stat.AP, cs.LG arXiv: https://arxiv.org/abs/2607.14124v1 The increasing availability of large-scale educational datasets has expanded the use of quantitative methods for investigating school performance. However, institutional heterogeneity among schools and the structural complexity of educational data pose substantial challenges to traditional statistical modeling approaches. This study investigates the existence of school typologies based on structural, pedagogical, and demographic characteristics, and examines how these typologies relate to performance in the Brazilian Basic Education Assessment System (Saeb). Using data from the Brazilian School Census and Saeb, data preprocessing and normalization procedures are applied followed by hierarchical clustering to identify groups of schools with similar structural profiles. After the identification of these typologies, causal analysis techniques are employed to investigate potential causal relationships between school characteristics and educational outcomes. The results reveal the presence of distinct school profiles and statistically significant differences in average performance among them. The causal analysis provides insights into the structural and contextual factors that may influence educational performance, contributing to a better understanding of the mechanisms associated with school effectiveness. --- ### Targeted Recovery of Weight-Space Mechanisms From Neural Networks Authors: Antoine Vigouroux, Lee Sharkey Published: 2026-06-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.13047v1 Parameter decomposition (PD) decomposes neural networks into interpretable computational components that faithfully reflect the original network's operations. However, scaling PD to large models requires vast compute, making it a costly and risky endeavor. Here we propose targeted PD (tPD), which identifies only the components that process specific inputs of interest -- from isolated prompts to large subtasks -- by introducing a high-rank catch-all component that handles all non-target data. We validate tPD on toy models and on transformer language models trained on The Pile, where it recovers reproducible, mechanistically faithful circuits. We extract a CSS-only submodel of a 4-block transformer using 7% of the FLOPs of its published decomposition, and in a 12-block transformer we surgically ablate and rewire memorized sequences, with negligible side effects on other inputs. --- ### Low-Rank Attention Residuals Authors: Jonathan Su Published: 2026-06-19 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.09694v2 Attention Residuals (AttnRes) replace the fixed residual sum with depth-wise attention over previous sub-layer outputs in Large Language Models (LLMs), but use each output as both a full-dimensional key and value. This couples routing with representation and makes the cost of computing depth-routing scores scale with hidden width $d$. We propose Low-Rank Attention Residuals (LR-AttnRes), which keep full-dimensional residual values while using $r$-dimensional keys, with $r < d$, for routing. LR-AttnRes uses the last $r$ dimensions of each value as the routing key, reducing total residual-side FLOPs while still improving performance. Comprehensive sweeps across the number of blocks ($N$) and $r$ show that depth-wise routing can be effective with far fewer dimensions than the model width. At both $1$B and $4$B parameters with $r = d/4$, LR-AttnRes achieves lower final validation loss, higher average downstream accuracy, and higher measured training-step throughput than standard AttnRes. We also provide a fused kernel supporting standard and low-rank routing. We release all code, the kernel, and all trained models to facilitate future research. --- ### Low-Rank Attention Residuals Authors: Jonathan Su Published: 2026-06-19 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.09694v1 Attention Residuals replace the fixed residual sum with depthwise attention over previous sub-layer outputs in large language models (LLMs), but use each output as both a full-dimensional key and value. This couples routing with representation and makes depth-routing scores scale with the hidden width $d$. We propose Low-Rank Attention Residuals (LR-AttnRes), which keep full-dimensional residual values while using $r$-dimensional keys, with $r \ll d$, for routing. Projected LR-AttnRes emits learned low-rank keys from existing output projections, decoupling routing from residual content and achieving the best validation loss among the variants tested. Sliced LR-AttnRes uses the last $r$ dimensions of each value as the routing key, removing the auxiliary key-projection path and reducing residual-side FLOPs while still improving performance. Comprehensive sweeps show that depthwise routing can be effective with far fewer dimensions than the model width. We release code and models to facilitate future research. --- ### Depth-Entropy Guided Sampling for Training-Free LLM Reasoning Authors: Zibin Meng, Peng Xie, Kani Chen Published: 2026-06-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.09693v1 Reinforcement learning (RL) has become the dominant paradigm for improving the reasoning capabilities of large language models, but it requires expensive training, curated data, and reward signals. Recent work shows that sampling from sharpened base-model distributions at test time recovers much of the RL gain, yet existing methods rely solely on output-layer likelihoods and ignore the transformer's internal forward-pass dynamics. We introduce Depth-Entropy Guided Sampling (DEGS), a training-free, test-time method that exploits layer-wise entropy collapse as an intrinsic quality signal. We observe that stronger reasoners -- including RL-posttrained variants -- exhibit a distinctive "late collapse": logit-lens decoded entropy stays elevated until deeper layers before converging. We define a per-sequence collapse depth $D(\mathbf{x})$ and a joint objective $π(\mathbf{x}) \propto p(\mathbf{x})^α\exp(βD(\mathbf{x}))$ that combines sequence likelihood with this depth-entropy structure, instantiated inside an MCMC power-sampling framework (DEGS-MCMC). Across three open-weight models and four reasoning benchmarks, this near-chance per-candidate signal compounds over the sampling trajectory into state-of-the-art training-free accuracy, with gains largest out of domain and on the harder splits -- exactly where likelihood alone falls short -- at single-digit-percent wall-clock overhead. DEGS narrowly trails an in-house GRPO reference on the math splits GRPO was trained for, yet surpasses it out of domain on GPQA for all three models, without any training, reward model, or labeled data. --- ### Reference-Based Distillation Detection in LLMs Authors: Rajat Rawat, Sizhe Chen, Akshay Anand, Michael Duan, Bob Rotsted, Sewon Min Published: 2026-06-19 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.09692v1 Model distillation -- training on outputs from stronger third-party models -- is widely used to boost performance, but raises concerns about unfair advantages and policy violations. This motivates a fundamental question: can we detect whether a model was distilled from another? We show that, while identifying a teacher model from a student in isolation is highly challenging, it becomes tractable in a reference-based setting: given a model and an earlier-generation checkpoint from the same lineage, we can identify the teacher model used to train the later checkpoint. We introduce a distillation detection method based on reference-based membership inference. By comparing how strongly a student model preferentially aligns with outputs from different candidate teachers relative to a reference checkpoint, our method identifies the most likely teacher and detects evidence of distillation. To handle unknown distillation pipelines such as hidden prompts, we infer proxy prompt templates directly from model outputs. We additionally identify a distinctive glyph-level signal specific to o1/o3 models. Evaluating distillation detection is challenging because modern model lineages are already heavily entangled. To address this, we develop a hybrid evaluation spanning both controlled distillation experiments and real-world models. Across both settings, our approach recovers the true teacher with near-perfect accuracy in single-teacher distillation scenarios, even when the underlying distillation pipeline is largely unknown. We further introduce statistical tests for both teacher attribution and distillation detection, and extend our framework to open-world settings where no teacher is guaranteed to be present among the candidates. Applying our method to contemporary models yields new evidence regarding potential distillation relationships involving QwQ, DeepSeek-R1, and GPT-OSS. --- ### What Context Does a Coding Agent Actually Need to Act? Authors: Brian Sam-Bodden Published: 2026-06-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.09691v1 A modern coding agent can hold an entire repository in its context window. Most of its reading is wasted -- and the interesting question is not how much context an agent can use, but what it actually \emph{needs}. We study that question at the moment it matters most: when the agent must \emph{edit} code. Separating \emph{finding} the work site from \emph{acting} on it, we hold localization fixed with an oracle, vary only how the code is represented, and score context against real issue resolution on SWE-bench Verified. The answer is starkly minimal. The signal lives in the code being edited itself: natural-language summaries of it answer almost none of the behavioral questions that the source answers ($4/45$ vs.\ $27/45$, held-out repositories, independent judge), and the gap belongs to the representation, not the summarizer -- a frontier model's summaries score exactly as poorly as a 3B model's. The surrounding context hardly matters either: across every multi-file instance in Verified, under a protocol frozen before any data, rendering a file's remainder as UML skeletons and signatures resolves no more issues than deleting that remainder outright ($N{=}70$, exact McNemar $p{=}0.75$). That was our registered hypothesis, and it failed. Compressed context, meanwhile, matches whole files at a third of the tokens: a resolved issue costs $19$K context tokens, not $94$K. The instrument also yielded a finding the field should keep: temperature-0 API inference flips ${\sim}9\%$ of per-instance outcomes between byte-identical runs. That is a noise floor under every small effect reported on this benchmark, including ours. We release the instrument -- gold-validated environments, per-instance proof that every reference edit is expressible from every arm's context, deterministic patch construction, and pre-registered hypotheses whose nulls we publish. --- ### Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders Authors: Wonseok Shin, Songkuk Kim Published: 2026-06-19 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2607.00023v1 Dense sentence embeddings are fundamental to modern Retrieval-Augmented Generation (RAG) systems but suffer from a lack of interpretability due to feature superposition. This opacity hinders the alignment of retrieval processes with human intent, as the entangled representations are difficult to analyze or control. In this work, we propose a method to disentangle the dense representations of sentence transformers (e.g., E5) into human-interpretable concepts using Top-k Sparse Autoencoders (SAEs). We demonstrate that these disentangled features align with specific semantic, syntactic, and pragmatic categories. Furthermore, we introduce an activation steering mechanism that allows for precise intervention in the retrieval process. By clamping specific latent features, we show that it is possible to re-rank search results to better align with user constraints without retraining the backbone model. Our findings suggest that SAE-based decomposition offers a viable path toward transparent and steerable neural information retrieval. --- ### LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval Authors: Mike Hang Wang, Utkarsh Garg, Reza Davari, Huitian Jiao, Hao Cheng, Baolin Peng, Tao Ge, Si-Qing Chen Published: 2026-06-19 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.28379v1 We introduce LEDGER to tackle the novel context engineering challenge of agentic document editing, where localized edits to long, structured documents must be applied efficiently without breaking cross-references or semantic consistency. LEDGER constructs a lightweight dependency graph that explicitly models document structure, including hierarchical organization, explicit references, implicit dependencies, and semantic relationships. For each edit, graph-guided retrieval selects only the necessary context, avoiding full-document processing while preserving consistency. We evaluate LEDGER on a curated benchmark of 1.9k test cases with various document types and lengths, spanning six state-of-the-art models: LEDGER improves consistency from 56% to 76% across all six models and test scenarios while reducing token usage. Notably, LEDGER with low reasoning effort matches baseline performance at high reasoning effort using fewer tokens, showing that explicit dependency representations can partially substitute for expensive internal reasoning in agentic document editing. --- ### Memory-Augmented LSTM Autoencoder for Unsupervised Activity Recognition with IMU Sensor Fusion Authors: Saeid Arabzadeh, Farshad Almasganj, Mohammad Mahdi Ahmadi Published: 2026-06-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.28377v1 HAR using Inertial Measurement Unit (IMU) sensors is vital for healthcare monitoring and rehabilitation. Despite deep learning advancements, major challenges remain: reliance on labeled data, multi-sensor fusion complexity, and the limited ability of unsupervised methods to capture spatiotemporal dependencies. These issues are pronounced in real-world scenarios with noisy data, overlapping activities, and missing labels. We propose a fully unsupervised spatiotemporal feature fusion framework using a memory-augmented autoencoder. It enhances activity representations via short temporal windows of multi-sensor IMU data, enabling real-time applications. Our framework extracts hierarchical static features via a Stacked Autoencoder, fusing them within and across sensors. A sequence-to-sequence LSTM Autoencoder then temporally refines these features, incorporating historical motion patterns without labels. We analyze key hyperparameters to identify configurations that maximize feature separability under short-window constraints. Evaluated on DaLiAc and PAMAP2 using realistic inter-class window segmentation, our method achieves 96.6% and 98.4% accuracy, respectively, surpassing supervised baselines and unsupervised approaches. Our method improves feature separability by up to 9% despite shorter temporal windows. While our realistic inter-class segmentation reduces accuracy by ~7%, it was intentionally adopted to better reflect real-world activity transitions and practical relevance. --- ### When Does Overlap Help? OSU-Mem and a Cell-Conditional Analysis of Trajectory Memory for LLM Agents Authors: Mellow Baixuan Chen, Xiangguo Sun Published: 2026-06-19 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2606.28376v1 Long-horizon large language model (LLM) agents accumulate interaction trajectories that quickly exceed any practical prompt budget, and existing memory methods either truncate aggressively and lose non-local evidence or retain boilerplate that degrades decision quality. We ask a mechanism question rather than claiming a better general-purpose memory system: when does organizing trajectory memory into overlapping semantic units (OSUs) -- groups of related steps in which one step may belong to several units -- help retrieval over flat or disjoint alternatives? We instantiate this in OSU-Mem, which retrieves from an overlapping OSU pool via budgeted coarse-to-fine expansion, and show its benefit is conditional: overlapping memory helps when the evidence steps a query needs share tool calls or entities, but hurts when those steps are fully heterogeneous and share neither. On a synthetic benchmark where evidence carries such shared structure by construction, OSU-Mem improves over the strongest baseline as the theory predicts; yet on a concatenated, constructed unaugmented $τ$-bench setting its aggregate advantage over flat retrieval vanishes. Splitting queries by whether their evidence shares tools and entities shows this near-tie to be an artifact of mixing query types rather than a property of either method, and ToolBench, a controlled probe built to carry shared structure by design, corroborates the same mechanism via an overlap-vs.-disjoint construction contrast (under a coverage-guided variant), isolating the construction principle rather than validating the full default system. Because the relevant sharing is cheaply estimable from metadata, the analysis yields a metadata-based heuristic for predicting when overlap is likely to improve retrieval. We deliberately isolate the retrieval layer, assessed by retrieval quality and an LLM-mediated evidence-selection stage. --- ### Multiscale Exit-Join Dynamics: Tactical Consensus and Strategic Coalition Formation Authors: Quanyan Zhu Published: 2026-06-19 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2606.26139v1 This paper develops a multiscale model of coalition formation in which strategic exit-and-join decisions are coupled with tactical consensus dynamics inside coalitions. Coalition value is generated endogenously from within-coalition information aggregation, while Aumann-Dreze payoffs, switching frictions, and acceptance rules govern strategic reconfiguration. The framework introduces a fast-slow architecture in which transferable coalition value emerges from DeGroot-style consensus processes, while coalition structures evolve through incentive-driven exit-and-join dynamics. The analysis characterizes joint tactical-strategic equilibria, conditions for tactical and strategic unanimity, segregation, polarization, and cognitive barriers that sustain stable coalition structures. A fixed-point characterization and existence results are established for the coupled dynamics. Numerical experiments reveal an instability-consensus paradox: low or negative switching barriers may prevent strategic convergence while simultaneously promoting temporal mixing sufficient to achieve global tactical consensus. The results provide a unified perspective on coalition formation, consensus dynamics, information aggregation, and strategic stability in multi-agent systems. --- ### Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction Authors: Mohammad Aref Jafari-Raddani Published: 2026-06-19 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2606.24915v1 End-to-end automatic speech recognition systems frequently hallucinate rare entities and domain-specific terms, especially in low-resource languages. While retrieval-augmented generation frameworks can mitigate these errors using large language models, current architectures face significant challenges. They either rely on standard sparse retrieval that ignores phonetic misrecognitions or utilize heavyweight cross-modal embeddings that introduce high latency. This letter proposes a highly efficient, purely lexical error-aware framework designed to explicitly resolve phonetic and loop hallucinations. Our approach integrates a symmetric text normalization module with a novel error-aware term frequency-inverse document frequency algorithm. By constructing a sparse diagonal penalty matrix based on historical errors, the retriever mathematically prioritizes corrective documents containing specific high-risk misrecognitions. Evaluated on the Persian subset of the FLEURS dataset, our method increased the error-aware hit rate from 53.7% to 90.9%. In end-to-end evaluations, the integrated framework reduced the final word error rate from 23.06% to 18.83%, achieving significant accuracy gains with near-zero inference latency. --- ### Velocity Prediction in Automatic Guitar Transcription Authors: Jackson Loth, Xavier Riley, Simon Dixon, Emmanouil Benetos Published: 2026-06-19 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2606.24912v1 Automatic Music Transcription (AMT) models have achieved a high level of success in polyphonic transcription of various instruments. Velocity, typically a measure of note intensity, is less commonly predicted in these models due to the absence of velocity labels in available datasets and lack of a proper definition for instruments other than piano. We present a methodology and model for velocity prediction in Automatic Guitar Transcription (AGT) which uses virtual instruments to generate synthetic training data with velocity labels. We first pretrain a model on this synthetic data. These weights are then transferred to a different model and trained on real guitar audio, allowing the model to retain the working velocity prediction while also achieving high performance and generalisability from the real training data. The velocity prediction is shown to outperform a baseline model which does not use the pretrained velocity weights, when evaluated on synthetic data. In addition, using the pretrained velocity weights offers a small improvement in note transcription, though the magnitude of this improvement is limited and not always significant depending on the testing data. Overall the model achieves results comparable to the state of the art in guitar transcription, while also successfully predicting velocity. --- ### Attractive and Repulsive Pattern Control in Sequence Generation Authors: Francois Pachet Published: 2026-06-19 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2606.24911v1 Variable-order Markov models preserve local symbolic syntax by adapting context length, but long continuations can enter recurring high-order "tunnels": repeated suffixes, locally periodic passages, or copied fragments longer than the formal Markov order. This paper introduces signed pattern control for variable-order Markov generation with BP-Regular sampling. A weighted recurrence automaton computes an activation R for a chosen family of target patterns, and belief propagation samples exactly from P_beta(x) proportional to P_0(x) exp(beta R(x)). Negative coupling makes the target patterns costly during sampling; positive coupling rewards the same patterns and turns them into controlled attractors. The target family may be mined online from overactive generated material, supplied by a score or style vocabulary, or designed as an experimental probe. The main experiments use the online homeostatic case, choosing patterns that become overactive in the sampling history. On six duration-bearing monophonic sources, including Bach and Telemann material, the negative branch reduces generated 8-gram self-reuse, increases the effective number of generated 8-grams, and increases coverage of training-supported 4-gram contexts while preserving substantial lower-order support. A pitch-sequence replication on five Weimar Jazz Database solos gives the same anti-reuse signature outside Baroque material. The same signed mechanism also provides a positive branch for probing attractor basins, phase transitions, and hysteresis in the underlying variable-order model. --- ### End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users Authors: Allan Henry, Solange Rossato, Christian Graff, Sylvain Huet, Jose-Ernesto Gomez-Balderas Published: 2026-06-19 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2606.24910v1 Voice control offers an intuitive alternative to manual drone piloting, yet most existing systems rely on rigid command vocabularies that fail to handle the spontaneous, disfluent speech of naive users. This paper addresses this gap by proposing an End-to-End Spoken Language Understanding architecture for real-time human-drone interaction in French. Our model combines a frozen Self-Supervised Learning acoustic encoder with a lightweight LSTM-based classification head, augmented by a cross-modal knowledge distillation objective that aligns acoustic representations with semantic embeddings from a text teacher, without requiring transcription at inference time. We evaluate our approach on VoiceStick, a novel French corpus of spontaneous speech collected during real teleoperation sessions with 29 nonexpert dyads. On simple voice commands, our best configuration achieves 93% accuracy at 7 ms inference latency, outperforming cascade baselines (79%, 202 ms) with a 29x speedup. On the full spontaneous speech test set, our architecture reaches 82% accuracy, with crossmodal distillation consistently improving robustness across all configurations. These results demonstrate that End-to-End architectures are not only feasible but preferable for spontaneous voice-guided UAV teleoperation, combining semantic robustness, low latency, and calibrated confidence. --- ### Computational references are not experiments: pre-registered validation of machine-learned sodium-cathode voltages Authors: Krishna Teja Vepa Published: 2026-06-19 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2606.23725v2 Machine-learning screens for battery materials are trained and judged almost entirely against computed reference voltages, and those references carry their own systematic errors. We report a case in which this matters quantitatively: our own screening stack (a graph-network voltage screen, a prior-art triage layer, and a local PBE+U bench) fails pre-registered validation against experiment-anchored literature values. Verdict thresholds, failure modes, and the primary metric were committed before analysis. On an operator-audited set of known Na-ion cathodes (n = 6 after one documented exclusion; verdict unchanged at n = 7), the raw held-out mean absolute error was 0.67 V, the pre-registered conservative metric, the upper 95% confidence bound of the cross-validated bias-corrected error, was 1.09 V, and the residual was strongly voltage-dependent (r = -0.94), so no additive calibration is valid. On the two compounds where prediction, database reference, and experiment could all be compared, the Materials Project PBE+U reference sat about 0.54 V below measurement: the reference, not the model, dominated the error. A prior-art screen found at least 70% of the targeted Na substitution space already published. We retire the screen, bound what "verified" means for our DFT ledger, and pre-register a calibration audit of it against four benchmark Li couples. --- ### EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering Authors: Fengchen Gu, Xiaotian Ren, Zhengyong Jiang, Zhilu Zhang, Ángel F. García-Fernández, Angelos Stefanidis, Mian Zhou, Huakang Li, Jionglong Su Published: 2026-06-19 Categories: cs.IR, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2606.23724v1 Large language models are increasingly used to answer questions over annual reports, earnings decks, and analyst notes, yet their outputs remain difficult to verify in high-stakes financial workflows. A fluent answer can blend directly grounded statements, weak synthesis, and unsupported claims across narrative text, tables, and charts. We present EvidenceLens, a visual analytics prototype that treats financial question answering as a claim-evidence alignment problem. The system decomposes an answer into atomic claims, summarizes support composition and confidence, support gaps, and coordinates claim-level inspection with source passages, table cells, and chart regions. Its core visual representation is a multimodal claim-evidence matrix that makes coverage, contradiction, and modality imbalance immediately visible. To support reproducibility, we also specify a JSON-based artifact schema, a lightweight multimodal alignment pipeline, and a deterministic review-priority ranking that maps backend signals into an auditable visual structure. Through representative report-auditing scenarios, we show how EvidenceLens helps analysts distinguish grounded claims from overconfident synthesis that conventional chat interfaces flatten. --- ### Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Images Authors: Jingyuan Chen, Kangrui Ruan, Junzhe Zhang Published: 2026-06-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.21806v2 Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains. A common source is an unobserved confounder that shapes both an attribute the user wants to control at sampling time and an attribute expected to vary in response. Existing causal generative approaches resolve the resulting ambiguity by imposing structural assumptions strong enough to single out one interventional distribution; in image domains, such assumptions are rarely warranted, and the data is generally consistent with a set of distinct causal mechanisms -- a feasible region of interventional distributions. We propose CauVaDE (Causal Variational Deep Embedding), built on a canonical augmented SCM in which the unobserved confounder collapses, without loss of generality, into a discrete latent cluster of bounded support while continuous variation is absorbed into independent noises. We prove that this canonical class is dense, in both observational and interventional Wasserstein distance, in the class of augmented SCMs compatible with a given causal diagram, and instantiate it as a mixture variational autoencoder whose cluster variable plays the role of the canonical confounder. An entropy regularizer with weight $γ$ on the cluster posterior then traces a family of candidate causal effects that fit the observational data to comparable likelihood while spanning the feasible region. Experiments on image data benchmarks show that CauVaDE produces diverse interventional samples and improves FID against an unconfounded reference. --- ### Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Images Authors: Jingyuan Chen, Kangrui Ruan, Junzhe Zhang Published: 2026-06-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.21806v1 Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains. A common source is an unobserved confounder that shapes both an attribute the user wants to control at sampling time and an attribute expected to vary in response. Existing causal generative approaches resolve the resulting ambiguity by imposing structural assumptions strong enough to single out one interventional distribution; in image domains, such assumptions are rarely warranted, and the data is generally consistent with a set of distinct causal mechanisms -- a feasible region of interventional distributions. We propose CauVaDE (Causal Variational Deep Embedding), built on a canonical augmented SCM in which the unobserved confounder collapses, without loss of generality, into a discrete latent cluster of bounded support while continuous variation is absorbed into independent noises. We prove that this canonical class is dense, in both observational and interventional Wasserstein distance, in the class of augmented SCMs compatible with a given causal diagram, and instantiate it as a mixture variational autoencoder whose cluster variable plays the role of the canonical confounder. An entropy regularizer with weight $γ$ on the cluster posterior then traces a family of candidate causal effects that fit the observational data to comparable likelihood while spanning the feasible region. Experiments on image data benchmarks show that CauVaDE produces diverse interventional samples and improves FID against an unconfounded reference. --- ### Is Agent Code Less Maintainable Than Human Code? Authors: Shaswat Patel, Betty Li Hou, Arun Purohit, Kai Xu, Jane Pan, He He, Valerie Chen Published: 2026-06-19 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.21804v2 Maintainability is a core dimension of software engineering, shaping how code is written, reviewed, and developed over time. While coding agents have demonstrated strong performance on single-issue tasks, it remains unclear how maintainable their code is when future agents build on top of it, potentially leading to compounding downstream effects. We investigate how agent code compares to human code in these maintenance settings, presenting CodeThread, a framework to construct controlled experiments from repository-level coding benchmarks. Applying CodeThread to four frontier coding agents and four benchmarks, we find that agents are less effective at resolving tasks when building on agent code compared to human code, with task resolve rate drops of up to 13.1%. Regression analysis reveals that many traditional software engineering maintainability metrics do not explain this difference. Instead, the clearest signals are subtler behavioral differences in agent code, such as changes to input validation and error handling, along with differences in downstream code size and task difficulty. These findings highlight the need to evaluate these systems not only by immediate task resolution but also by code maintainability, and point to potential sources of downstream errors introduced by agent code. --- ### Is Agent Code Less Maintainable Than Human Code? Authors: Shaswat Patel, Betty Li Hou, Arun Purohit, Kai Xu, Jane Pan, He He, Valerie Chen Published: 2026-06-19 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.21804v1 Maintainability is a core dimension of software engineering, shaping how code is written, reviewed, and developed over time. While coding agents have demonstrated strong performance on single-issue tasks, it remains unclear how maintainable their code is when future agents build on top of it, potentially leading to compounding downstream effects. We investigate how agent code compares to human code in these maintenance settings, presenting CodeThread, a framework to construct controlled experiments from repository-level coding benchmarks. Applying CodeThread to four frontier coding agents and four benchmarks, we find that agents are less effective at resolving tasks when building on agent code compared to human code, with task resolve rate drops of up to 13.1%. Regression analysis reveals that many traditional software engineering maintainability metrics do not explain this difference. Instead, the clearest signals are subtler behavioral differences in agent code, such as changes to input validation and error handling, along with differences in downstream code size and task difficulty. These findings highlight the need to evaluate these systems not only by immediate task resolution but also by code maintainability, and point to potential sources of downstream errors introduced by agent code. --- ### Test-Time Training with Next-Token Prediction Authors: Xuan Ouyang, Zefan Cai, Junjie Hu Published: 2026-06-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.21803v2 Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test time. We study whether this signal can define the inner-loop objective for test-time training (TTT) in pretrained long-context language models. Many TTT architectures require models to be trained with test-time adaptation in mind, limiting their direct applicability to released LLM checkpoints. While recent in-place TTT methods make fast-weight adaptation possible for pretrained LLMs without redesigning the backbone, they leave a central question unresolved: what should each test-time write store? Existing recipes train the fast weight to match a learned local value proxy but they are not directly tied to the self-supervised next-token prediction signal. We introduce Test-Time Training with Next-Token Prediction (TTT-NTP), a drop-in fast-weight adaptation method for pretrained LLMs that instead supervises updates using the model's own next contextual hidden state. This makes each local write follow the same causal computation that supports next-token prediction: the value target is a pointwise linear projection of a single next-position contextual state. On RULER Full-13, averaged over 4k to 32k contexts, TTT-NTP is the only method that consistently improves the released backbone across four models spanning three families and a 0.6-8B size range, by 3.9 points on Llama-3.1-8B, 3.0 on Mistral-7B-v0.3, 4.1 on Qwen3-4B, and 2.9 on Qwen3-0.6B. On the real-world LongBench-v2 long-document QA benchmark, TTT-NTP improves over the base model by 5.6 points on Llama-3.1-8B and 3.7 on Mistral-7B-v0.3, while preserving commonsense and knowledge performance. Our code is publicly available at https://github.com/yancyou/TTT-NTP. --- ### Test-Time Training with Next-Token Prediction Authors: Xuan Ouyang, Zefan Cai, Junjie Hu Published: 2026-06-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.21803v1 Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test time. We study whether this signal can define the inner-loop objective for test-time training (TTT) in pretrained long-context language models. Many TTT architectures require models to be trained with test-time adaptation in mind, limiting their direct applicability to released LLM checkpoints. While recent in-place TTT methods make fast-weight adaptation possible for pretrained LLMs without redesigning the backbone, they leave a central question unresolved: what should each test-time write store? Existing recipes train the fast weight to match a learned local value proxy but they are not directly tied to the self-supervised next-token prediction signal. We introduce Test-Time Training with Next-Token Prediction (TTT-NTP), a drop-in fast-weight adaptation method for pretrained LLMs that instead supervises updates using the model's own next contextual hidden state. This makes each local write follow the same causal computation that supports next-token prediction: the value target is a pointwise linear projection of a single next-position contextual state. On RULER Full-13 (averaged over 4k, 8k, 16k, and 32k context lengths), TTT-NTP is the only method that consistently improves the released backbone across four models spanning three families and a 0.6--8B size range: Llama-3.1-8B (+3.9), Mistral-7B-v0.3 (+3.0), and the Qwen3 series (Qwen3-4B +4.1, Qwen3-0.6B +2.9). On the real-world LongBench-v2 long-document QA benchmark, TTT-NTP improves over the base model on both Llama-3.1-8B (+5.6) and Mistral-7B-v0.3 (+3.7), while preserving commonsense and knowledge performance. --- ### When to Plan, When to Polish: Noise Level as a Granularity Axis for Diffusion Language Models Authors: Peihong Li, Yuanjie Shi, Yan Yan Published: 2026-06-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.21802v2 Standard tokenwise diffusion LMs keep training corruption and inference commitment at token granularity throughout denoising. At high noise, this leaves scattered local fragments rather than coherent evidence, making it hard to form early coarse structure, exactly what planning-sensitive generation requires. Hierarchical planning methods add coarse stages to separate planning from wording, but they need extra planners, block latents, or two stage designs. We propose Noise Dependent Granularity Control (NDGC), a single-level diffusion method that uses the noise level as a granularity cue. NDGC aligns training exposure and inference commitment with denoising progress. High noise steps use coherent token groups to support early meaning commitment, while low noise steps return to token level refinement. This creates planning like coarse to fine denoising without an explicit planner or hierarchical architecture. Across controlled tests, ablations, and WritingPrompts, NDGC shows earlier skeleton formation, better ordered recovery, and healthier outputs. --- ### When to Plan, When to Polish: Noise Level as a Granularity Axis for Diffusion Language Models Authors: Peihong Li, Yuanjie Shi, Yan Yan Published: 2026-06-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.21802v1 Standard tokenwise diffusion LMs keep training corruption and inference commitment at token granularity throughout denoising. At high noise, this leaves scattered local fragments rather than coherent evidence, making it hard to form early coarse structure, exactly what planning-sensitive generation requires. Hierarchical planning methods add coarse stages to separate planning from wording, but they need extra planners, block latents, or two stage designs. We propose Noise Dependent Granularity Control (NDGC), a single-level diffusion method that uses the noise level as a granularity cue. NDGC aligns training exposure and inference commitment with denoising progress. High noise steps use coherent token groups to support early meaning commitment, while low noise steps return to token level refinement. This creates planning like coarse to fine denoising without an explicit planner or hierarchical architecture. Across controlled tests, ablations, and WritingPrompts, NDGC shows earlier skeleton formation, better ordered recovery, and healthier outputs. --- ### Discretizing Reward Models Authors: Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika, Chirag Nagpal, Tongshuang Wu, Graham Neubig, Yuning Mao Published: 2026-06-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.21795v1 Despite their widespread use, the role of reward models in shaping reinforcement learning is poorly understood. Reward models offer a tempting promise: they automatically estimate response quality in the absence of verifiers or human judges. Unlike "verifiable rewards" which typically produce binary scores, reward models typically produce continuous scores, allowing them to be sensitive to fine-grained differences in responses. However, we show this apparent strength is a serious weakness: many popular reward models are oversensitive, assigning different scores to equally good responses. Theoretically, we show that seemingly perfect reward models can be highly oversensitive; empirically, this oversensitivity can lead to bad policies. In place of existing notions of "reward model accuracy," we propose evaluating reward models using distinct measures of "discriminative ability" and "specificity" (the complement of oversensitivity). As a solution, we describe a training-free algorithm that uses Monte Carlo dropout on any neural reward model to produce discrete reward clusters. Theoretically, we prove there exist discretizations that reduce oversensitivity at minimal expense of discriminative ability; empirically we show, in both controlled and natural RL settings, that discretizing rewards leads to less reward hacking and better policies than training on the original rewards. --- ### THREAD: Trajectory Planning for Hybrid Rigid-Soft Manipulators with Environment-Aware Diffusion Authors: Shivani Kamtikar, Pranav Asthana, Naveen Kumar Uppalapati, Girish Krishnan, Girish Chowdhary Published: 2026-06-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.21792v1 Manipulation in confined environments, such as threading a manipulator through narrow apertures, remains a fundamental challenge, especially for conventional rigid robots. Hybrid rigid-soft manipulators offer promise but face two compounding planning challenges: backbone shapes feasible in free space become infeasible under environmental contact, and planning rigid and soft segments independently ignores their kinematic coupling. We present THREAD, the first diffusion-based trajectory planner for hybrid manipulation, learning a generative prior over physically realizable backbone trajectories conditioned on local environment geometry, with physics-inspired losses encoding curvature, smoothness, and collision constraints jointly across both segments. Trained in simulation, THREAD achieves 92.4% task success with 5x fewer collisions than the strongest baseline. We show cross-embodiment real-world transfer with minimal online updates, successfully threading through apertures as small as 1.3x the soft segment diameter. --- ### What Do Lorentz-Equivariant Jet Taggers Learn? Authors: Jay Agarwal, Siddharth Khare, Dhruv Kumar Published: 2026-06-19 Categories: cs.LG, hep-ex, hep-ph, physics.data-an arXiv: https://arxiv.org/abs/2606.21790v1 We study what Lorentz-equivariant jet taggers learn internally, using equivariance tests, linear probes and grade ablations across five models including L-GATr, L-GATr-slim and LLoCa-T. Linear probes show that equivariant models suppress frame-dependent pseudorapidity to zero while encoding jet mass and N-subjettiness strongly. Grade ablations on L-GATr reveal that bivector channels are negligible for top-quark tagging while vector-like channels are dominant but seed variable, consistent with the network exploiting multiple representational pathways. These results characterize which physical features and algebraic grade structures carry discriminative information in equivariant taggers and may inform future development of such models. --- ### Bayesian three-dimensional seismic travel-time tomography for active- and passive-source seismic data using physics-informed neural network Authors: Ryoichiro Agata, Kazuya Shiraishi, Gou Fujie, Dan Bassett Published: 2026-06-19 Categories: physics.geo-ph, cs.LG arXiv: https://arxiv.org/abs/2606.21789v1 Accurate 3D seismic velocity modeling through seismic travel-time tomography using both active- and passive-source data provides critical underpinning models for seismicity monitoring and hazard assessment. Because travel-time tomography is an inherently ill-posed inverse problem, UQ of the estimated models using Bayesian methods is also important for reliable downstream interpretations and analyses. However, Bayesian inference for 3D tomography based on conventional grid-based representations faces the ``curse of dimensionality'' and severe computational bottlenecks. Consequently, rigorous Bayesian UQ for margin-wide 3D travel-time tomography has remained largely unexplored. In this study, we propose a meshless 3D Bayesian travel-time tomography method that combines PINNs with a neural representation of the velocity structure, enabling tractable and data-efficient Bayesian inference through function-space particle-based variational inference. To efficiently integrate passive-source data into the Bayesian estimation of the velocity structure, we conduct analytical marginalization treating uncertain source parameters as nuisance parameters, with passive-source relocation carried out in post-processing. We validated the capability of our approach for 3D problems through synthetic experiments. Furthermore, we applied the method to a real-world dataset from marine active-source surveys and natural earthquakes off the Kii Peninsula, Nankai Trough. Our probabilistic 3D ensemble successfully resolves key geological features and provides data-consistent uncertainty maps. The posterior mean hypocenters shifted mainly in the vertical direction by 10-15 km, consistent with a previous relocation result. Finally, the neural representation drastically reduces storage requirements for the entire ensemble velocity model, highlighting the scalability and data efficiency of the proposed framework. --- ### Rotation-Aware Point-Cloud Embeddings for Vision-Based In-Hand Reorientation Authors: Yashom Dighe, Karthik Dantu Published: 2026-06-19 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2606.21788v1 Point-cloud goals provide a direct way to specify dexterous in-hand reorientation: instead of defining an object-specific pose frame or estimating 6D pose at test time, the policy is given the desired 3D geometry of the object. Yet raw point-cloud goal conditioning is poorly conditioned for policy learning. Current and goal clouds are unordered, independently sampled, and often visibility-dependent, so their discrepancy entangles object rotation with permutation, resampling, and unstable correspondence structure. For this reason, prior point-cloud manipulation methods typically add structure outside the representation itself, such as explicit pose or relative-pose inputs, dense flow features, or distillation from privileged teachers. We close this gap by learning a rotation-aware point-cloud embedding whose Euclidean latent distance is calibrated to the SO(3) geodesic error between object orientations. The resulting representation turns current-goal comparison into a smooth control signal, allowing a model-free RL policy to act from current and goal point-cloud embeddings, proprioception, and centroid metadata, without object pose, relative pose, dense flow, or teacher-action supervision. In in-hand reorientation experiments, this interface matches privileged-state and distillation-based baselines while avoiding brittle test-time computation of structured pose or flow inputs. These results suggest that point-cloud goals become practical for this task when the representation, rather than an external module, encodes the task-relevant geometry of rotation. We also show evidence that generic visual point-cloud pretraining is insufficient for such a current-goal comparison because it discards the task-relevant state and preserves only shape features. --- ### RocketPFN: Accurate Time Series Classification via In-Context Learning Authors: Franco Martino O'Rourke, Ana Trisovic, Dimitris Bertsimas Published: 2026-06-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.21786v1 We introduce RocketPFN, a training-free pipeline for time series classification that combines random convolutional feature extraction (Rocket) with in-context classification via a pretrained tabular foundation model (TabPFN v2.5). On 92 UCR datasets (30-resample protocol), RocketPFN matches HC2, the strongest published method on the archive, in mean accuracy (both 0.900, Wilcoxon p=0.50), with no training on the target data and a median inference time of 30 seconds per fold. It also significantly outperforms every individual classifier in the HC2 ensemble. On UEA (20 datasets) the difference is likewise not statistically significant. A separate comparison concerns TSC foundation models: when paired with the same downstream classifier, MOMENT, Mantis, and MantisV2 are all significantly outperformed by RocketPFN using fewer extracted features and no learned parameters (p<0.001 in each case). This holds even when the encoders were pretrained on corpora that include the UCR training samples. We propose this two-stage pipeline as a reference point for evaluating zero-shot TSC foundation models. --- ### Physics-Preserving Latent Compression for Zero-Shot Resolution Transfer in 3D Turbulence Authors: Yilong Dai, Yiming Sun, Yiheng Chen, Ziyi Wang, Shengyu Chen, Xiaowei Jia, Runlong Yu Published: 2026-06-19 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2606.21781v1 High-resolution turbulence modeling is essential for scientific computing, but remains constrained by the cost of direct numerical simulation and the scarcity of full-resolution data. Existing scientific compressors reduce storage but typically operate on per-frame representations, whereas learned compressors yield compact latents that are often resolution-dependent and weakly aligned with the physics of turbulence. This raises the need for a compression framework that reduces data size, preserves physical diagnostics, and transfers from low-resolution training fields to high-resolution test fields without retraining. In this paper, we propose Physics-Preserving Latent Compression (PPLC), a patch-local latent compressor for three-dimensional turbulence. Motivated by inertial-range scale similarity, PPLC treats fixed-size patches as transferable units and applies a shared variational autoencoder independently of the global grid size. It combines exact mean preservation, zero-mean fluctuation encoding, an invertible Haar wavelet front-end, shift-consistency regularization, and overlap-aware reconstruction. Instantiated on forced isotropic turbulence, PPLC is trained only on stride-downsampled 256^3 fields and transfers zero-shot to 1024^3 fields. Experiments show that PPLC improves the balance between reconstruction accuracy and physical fidelity over classical and learned baselines, keeping diagnostics such as dissipation, enstrophy, energy spectra, and incompressibility closer to the ground truth. Beyond turbulence compression, PPLC offers a general strategy for physics-preserving latent representations that support data-efficient scientific surrogate modeling. --- ### CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks Authors: Ashwin Vinod, Ying Ding, Elias Stengel-Eskin Published: 2026-06-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.21777v1 LLM agents in knowledge intensive question answering take retrieval and reasoning actions with incomplete knowledge about whether their current answer is uncertain, unsupported, or already complete. This produces two failure modes: committing to confident but unsupported answers, which hurts accuracy, and over-retrieving when the evidence in hand already suffices, resulting in wasted compute. To give agents a more complete picture of the state space they are operating in, we introduce calibrated verifier telemetry (CalVerT), which augments the agent's state with additional telemetry: a calibrated self-confidence score and a grounding verifier score. We show that CalVerT can improve agents in both training-free and training-based settings. On four QA benchmarks, we find that CalVerT raises F1 by triggering retrieval in cases where agents over-rely on parametric knowledge, while cutting redundant retrieval in cases where agents have sufficient context to answer. We show that CalVerT can augment existing QA frameworks without training. Moreover, CalVerT also improves trained systems: by simply augmenting an agent's state with telemetry, we observe improvements after reinforcement learning, as compared to an agent with identical training but no CalVerT telemetry. --- ### A Causal DAG Prior for Synthetic Time-Series Classification Datasets Authors: Franco Martino O'Rourke, Ana Trisovic, Dimitris Bertsimas Published: 2026-06-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.21776v1 A Prior-data fitted Network learns the posterior predictive induced by its training prior; bringing this paradigm to multivariate time-series classification therefore calls for a synthetic generator that produces complete labelled datasets with temporal structure. We introduce a causal prior that synthesizes each dataset from a randomly sampled DAG over typed nodes across two modalities (tabular attributes and time series), natively producing multivariate, multi-class TSC datasets with cross-modal causal structure across channels, timesteps and labels, a regime not addressed by existing synthetic priors. To validate the prior, we finetune TabPFN v2.5 with minimal adaptations and evaluate on 75 UCR/UEA datasets within TabPFN's operating regime. Finetuning on our generator significantly outperforms both the unmodified upstream model and a tabular-only ablation of the same prior (Wilcoxon signed-rank $p=3.0\times 10^{-8}$ on ROC-AUC), isolating the contribution of the cross-modal temporal structure. --- ### Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning Authors: Tianqi Du, Qi Zhang, Yifei Wang, Yisen Wang Published: 2026-06-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.21775v1 Recently, world models have emerged as a promising paradigm for building intelligent agents by learning predictive models that estimate future environment states conditioned on observations and actions. In particular, JEPA-style latent world models provide an efficient alternative to pixel space prediction by learning action-conditioned dynamics in compact representation spaces. However, existing latent world models typically rely on one-step prediction and must be recursively rolled out for long-horizon planning, which leads to compounding errors and a mismatch between training objectives and downstream planning tasks. To address this limitation, we propose Variable-length Latent World Models (VLWMs), a framework that learns to predict future latent states conditioned on action sequences of variable lengths. Instead of training only on one-step transitions, VLWMs directly model temporally extended dynamics, allowing the same predictor to evaluate action plans over different horizons. We further introduce a curriculum training strategy that progressively expands the action horizon, stabilizing optimization from short-range dynamics to long-range prediction. At test time, we design planning methods tailored to VLWMs to better exploit their variable-length predictive capabilities. Experiments on long-horizon control tasks show that VLWMs significantly improve latent space world models, achieving 13\% average improvement over the state-of-the-art LeWM across different datasets, with especially large gains on tasks requiring extended planning. These results suggest that VLWM provides a simple yet effective paradigm for improving long-horizon prediction and planning in latent world models. --- ### Decision-Focused Learning: When and Why Traditional Prediction Models Fail Authors: Mo Liu Published: 2026-06-19 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2606.21773v1 Plugging predictions of unknown parameters into downstream optimization problems, often referred to as the ``predict-then-optimize'' paradigm, has long been a standard approach in decision-making under uncertainty. However, improved predictive accuracy does not, in general, translate into improved decision quality. This disconnect has motivated growing interest in decision-focused learning (DFL) within the operations research community. This tutorial reviews recent developments in DFL and highlights key methodological insights, with a particular focus on stochastic linear programming as the downstream decision-making problem. We discuss why several widely used tools in traditional statistical learning are not directly suited to decision-focused settings and must be rethought, including (i) data collection strategies driven purely by predictive uncertainty and (ii) distributional distance measures such as the Wasserstein distance. We summarize properties of DFL that distinguish it from conventional predictive modeling and provide insights into the development of new decision-focused tools. --- ### Motion-Aware Reinforcement Learning For Object Localization Authors: Prithvi Raj Singh, Satyendra Singh Published: 2026-06-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21764v1 We present MARLNet (Motion-Aware Reinforcement Learning Network), a PPO-based bounding-box refinement agent that incorporates a constant-velocity motion prior into the observation state and an action smoothness penalty into the reward function. The agent operates on 268-dimensional observations encoding the current proposal, a kinematic prediction, the previous action, and a 256-dimensional EfficientNet-B0 crop feature, and learns a five-dimensional policy controlling coordinate adjustments and a binary termination trigger. Evaluated on Pascal VOC 2012 and VisDrone 2019, MARLNet trains stably across all regularization strengths tested and achieves consistent gains in detection success rate at $\text{IoU} \geq 0.5$: up to $+0.011$ on VOC ($λ_\text{phys}{=}0.10$), where the motion prior prevents the overshooting that causes plain PPO to regress on this metric, and $+0.007$ on VisDrone ($λ_\text{phys}{=}0.70$), where unconstrained PPO achieves a larger gain ($+0.025$) owing to the weaker base detector. Through reward design ablations and training dynamics analysis, we identify a reward interference in which combining a constant-velocity deviation penalty with an absolute IoU term causes trigger collapse, and show that replacing it with the action smoothness penalty resolves this failure. We further characterize a representational ceiling facing crop-feature refinement agents that share a backbone with their base detector, confirmed through a global-plus-local observation ablation. Project page: https://prithviraj97.github.io/marl-net --- ### From Gradient Clipping to Structural Refinement: Improving DPSGD for Medical Image Segmentation Authors: Shiva Parsarad, Parth Shandilya, Isabel Wagner Published: 2026-06-19 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2606.21763v1 Medical image segmentation is widely used for disease detection but relies on sensitive data, raising privacy concerns as trained models can leak information. Differential privacy, typically implemented via Differential Private Stochastic Gradient Descent (DPSGD), provides a solution, though at the cost of reduced utility. Recent DPSGD variants, including Automatic clipping (Auto-S), Normalised SGD with perturbation (NSGD), and Per-sample adaptive clipping (PSAC), have shown promise in image classification, but their behavior in medical segmentation remains underexplored. We evaluate these methods across binary and multi-class tasks and analyze gradient alignment, showing that prior assumptions, particularly for PSAC, do not consistently hold. We further demonstrate that combining clipping strategies with morphological refinement improves segmentation quality under privacy constraints. Finally, we propose an adaptive DP-Morph variant that captures class-specific structures and enhances performance in multi-class settings. --- ### AdaPrivate-TS: Private Thompson Sampling for Contextual Bandits with Privacy Amplification Authors: Mohammadreza Riyazat, Eranga Ukwatta Published: 2026-06-19 Categories: cs.LG, cs.CR, stat.ML arXiv: https://arxiv.org/abs/2606.21757v1 We present AdaPrivate-TS, a differentially private contextual bandit algorithm that combines Thompson Sampling with batched zCDP composition. Our key insight is that differential privacy noise inflates the posterior covariance in a structured way: adding Gaussian noise $N(0,σ^2 I)$ to $b$ yields sampling covariance $v^2 A^{-1} + σ^2 A^{-2}$, which Thompson Sampling interprets as increased uncertainty rather than pure corruption. Under event-level privacy (protecting individual interactions) with stochastic contexts, we prove that the privacy cost is only $O(\sqrt{d}\,\log T/\sqrtρ)$, logarithmic in $T$, because parallel composition amortizes noise across batches. Additionally, we explore privacy amplification via Poisson subsampling, which can reduce effective noise at stringent privacy budgets. Experiments on synthetic and real-world datasets demonstrate: (1) AdaPrivate-TS achieves 93-99% of non-private performance at $\varepsilon \in (0.5, 5)$, outperforming UCB by 0.5-3.7% and up to 18% with tuned adaptive exploration at extreme $\varepsilon$; (2) privacy amplification provides additional 2-5% gains at low $\varepsilon$; (3) on MovieLens and Jester, AdaPrivate-TS achieves the best overall performance among event-level baselines, dominating at $\varepsilon \geq 2$; (4) under DP-SVD private features, TS's advantage over UCB grows to +11%, confirming noise-as-uncertainty is not limited to reward privacy. We provide rigorous proofs for privacy guarantees under interactive zCDP composition and comprehensive evaluation including convergence curves, 12-seed CIs, and DP-SVD feature ablation. --- ### Scaling up fine-grained intracranial vessel annotations in computed tomography angiography Authors: Chu-Hsuan Lin, Alberto Mario Ceballos-Arroyo, Jisoo Kim, Shrikanth M. Yadav, Huaizu Jiang, Lei Qin, Geoffrey S. Young Published: 2026-06-19 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2606.21756v1 In this work, we present SemanticVessel, a dataset for fine-grained brain vessel segmentation in computed tomography angiography scans. Based on the detailed contrast provided by dynamic 4D-CTA scans, we generate segmentation traces for arteries and veins. We then use intensity-guided region growing to obtain segmentations of the majority of vascular territories in the human brain, which are refined and annotated with 20 unique arterial classes by an expert radiologist. Unlike existing datasets, where minor arteries are discarded as background content, we merge these minor arteries into a generic arterial class. Due to the multiple-phase acquisition of dynamic 4D-CTA, labels for a single phase can be re-used for other phases in the same series, greatly increasing the size of our dataset with no additional annotation cost. The results show that models trained with the additional generic artery class produce better fine-grained segmentations across the board. We will make our code, annotation GUI, and model weights available to the scientific community. Code, weights, and data will be made available on https://github.com/alceballosa/robust-vessel-segmentation --- ### Embedded Polygon Symbolic Transfer Entropy (EPSTE): A Geometric Token and Deep Learning Approach to Estimating Transfer Entropy in Neuroimaging Time Series Authors: David Alexander Finnigan Published: 2026-06-19 Categories: cs.IT, stat.ML arXiv: https://arxiv.org/abs/2606.21754v1 Inferring directed interactions between neural systems from EEG and MEG remains challenging due to noise, nonstationarity, and the high sample complexity of information-theoretic estimators. Transfer Entropy (TE) provides a principled and model-free measure of directed information flow; however, its practical estimation is not stable in finite data regimes (particularly as embedding dimension increases). This work introduces Embedded Polygon Symbolic Transfer Entropy (EPSTE), a framework that reframes TE estimation as a learnable problem operating on structured symbolic representations of local temporal morphology rather than raw signal amplitudes. Neural time series are decomposed into sequences of geometric primitives derived from local triplets of samples encoding complementary aspects of waveform structure such as magnitude, curvature and directional change. These primitives are discretised into symbolic tokens, yielding a compact but expressive state space over which symbolic TE is estimated. A recurrent neural network with attention-based multiple-instance learning is trained to predict surrogate-validated TE values from bags of symbolic temporal windows. The method is evaluated on source-reconstructed MEG data parcellated using the AAL90 atlas and compared against a standard symbolic baseline using identical architectures and supervision. The results demonstrate that while local window-level predictions are noisy, aggregation across trials and channel pairs yields stable directed dependencies. At the pair level, EPSTE achieves near-perfect recovery of ground-truth directed structure and significantly lower absolute error than the baseline, indicating that representational geometry plays a critical role in enabling practical learnability of information-theoretic dependencies. --- ### Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats Authors: Xiaoyang Liu, Shangzhe Wu, Kai Han Published: 2026-06-19 Categories: cs.GR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.21753v1 3D Gaussian Splatting (3DGS) has achieved state-of-the-art photorealistic rendering, but the representation gap prevents these assets from being physically interactive. Production-grade physics engines do not understand the 3DGS representation, while prior physics-for-3DGS methods are monolithic silos. These prior works are fundamentally limited, demonstrating only object-centric physics in isolated environments, such as on an ideal plane. They are incapable of interacting with complex static collision geometry or heterogeneous assets. We propose a novel framework that, for the first time, bridges this gap by enabling 3DGS assets to participate in scene-level, heterogeneous, multi-solver physical simulations. Our core contribution is a Representation Abstraction Framework that translates all diverse assets, including 3DGS, virtual meshes, and fluids, into a unified physical particle set. This abstraction is key to enabling complex behaviors, such as the non-rigid deformation of 3DGS assets, within a unified physics pipeline. This particle set, along with the static scene collision boundaries derived from scene capture, is processed within a solver-agnostic physics kernel. The physical results are then mapped back to drive each asset's specific visual reconstruction. This architecture unlocks capabilities impossible with prior art. We demonstrate complex, two-way interactions between deformable 3DGS assets, standard CG assets such as fluids and meshes, and large-scale captured static environments, showcasing realistic coupled phenomena that were previously unattainable. --- ### Configurable Algorithms for Histopathologic Cancer Detection on Quantum Hardware Authors: Nandika Goyal, Glen Uehara, Andreas Spanias Published: 2026-06-19 Categories: eess.IV, cs.CV, quant-ph arXiv: https://arxiv.org/abs/2606.21752v1 Histopathologic cancer detection is challenging due to tissue variability, staining differences, and subtle visual distinctions between disease classes. We propose two quantum algorithms for this task: a configurable dual-gradient CSWAP circuit (DG-CSWAP) that computes multi-directional edge responses in a single execution via per-pixel local Ry encoding, and a hardware-efficient destructive swap circuit (DG-DST) natively matched to quantum processing unit (QPU) gate sets at substantially lower circuit complexity. We prove algebraic equivalence between DG-CSWAP and DG-DST, enabling a two-circuit QPU validation strategy. A three-stage NISQ mitigation pipeline, including readout error correction, bias subtraction, and slope regression, reduces single-pixel hardware MSE by ~8x. Validated on five quantum processors via Amazon Braket, the method achieves inter-platform Pearson r ~ 0.93-0.94 across all local-simulator pairs. Compared to a prior Quantum Fourier Transform (QFT) based amplitude-encoding baseline requiring 12-qubit global state preparation and a three-model ensemble (85.55% on PatchCamelyon), the proposed method uses shot-based measurements, executes on real quantum hardware, and achieves 79.80% accuracy with a single ResNet-50. A Lite configuration delivers a 17x preprocessing speedup at a 2.59% accuracy cost. To the best of our knowledge, this is the first quantum hardware implementation study with noise mitigation for histopathologic image classification. --- ### Quantile Adaptive Temperature Scaling for Confidence Calibration Authors: Omprakash Chakraborty, Leo Fillioux, Ismail Ben Ayed, Jose Dolz Published: 2026-06-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21749v1 Deep neural networks often produce poorly calibrated confidence estimates, overstating their certainty even when predictions are incorrect. Temperature Scaling remains the most widely used posthoc calibration method due to its simplicity and effectiveness, yet its global, uniform rescaling of logits fails to correct the highly heterogeneous structure of miscalibration observed across the confidence spectrum. In particular, the largest correctness confidence discrepancies arise in different quantile regions depending on the setting, low confidence predictions, where uncertainty matters most, tend to exhibit the largest correctness confidence discrepancies, which standard TS leaves largely unaddressed. We introduce Quantile Adaptive Temperature Scaling (QaTS), a simple and efficient post hoc calibration method that adapts the temperature as a function of a predictions empirical confidence quantile. By mapping confidences into the quantile space, QaTS normalizes the calibration problem, makes the structure of miscalibration explicit and enables a monotone temperature function that adapts across quantiles while leaving well calibrated high confidence predictions largely unchanged. preserving high confidence behavior. This quantile aware formulation aligns naturally with a reparameterized Expected Calibration Error (ECE) objective and yields a sample wise temperature that is robust across a variety of challenging scenarios, such as class imbalance and distributional shifts. Across a broad range of datasets, architectures, evaluation scenarios and diverse tasks, QaTS consistently, and substantially, outperforms state of the art post hoc calibration methods, delivering more reliable and trustworthy confidence estimates without modifying model predictions. --- ### Cohort Organized Learning: Clustering Through Agreement Authors: Finn Henry O'Shea, Maria Elena Monzani Published: 2026-06-19 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2606.21743v1 In this article we describe Cohort Organized Learning (CoOL), a method for clustering data without explicit distance or similarity computations. Herein, we will describe CoOL, derive the gradients determined by expectation maximization to train the networks, show how to monitor convergence during training and evaluate the clusters after training, and discuss a series of examples and use cases. We also discuss CoOL's limitations and future prospects on related tasks. Because CoOL uses neural networks to estimate the clusters, it can be used to cluster any data that can be made compatible and we illustrate this on vector data and images. --- ### Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents Authors: Rajesh Mangannavar, Zachary Coalson, Pranay Dugar, Prasad Tadepalli Published: 2026-06-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.21740v1 Translating natural-language planning intent into verified plans is a longstanding challenge: people communicate goals in language, while classical planners require formal PDDL specifications. Recent agentic frameworks bridge this gap by orchestrating a pool of specialized repair agents inside a verifier-checked refinement loop, but the orchestrator at the centre is itself a prompted frontier LLM, paying a frontier-LLM API call at every refinement step. We present HALO (Hybrid Agent-Learned Orchestrator), which trains the orchestrator from refinement trajectories that an external verifier has certified as ending in valid plans, across 11 PDDL domains. HALO pairs a small QLoRA-tuned policy with three hardcoded rules for trivially decidable selections, and operates over an expanded 21-agent action space. Unlike approaches that prompt a frontier LLM at every step or learn an orchestrator from sparse end-of-episode rewards, our key observation is that the verifier already provides strong guidance: every accepted trajectory is a sequence of demonstrably correct (state, agent) decisions, directly usable as supervision. Across PlanBench, Natural Plan, and classical planning benchmarks, HALO matches or exceeds the GPT-5-mini prompted baseline on success rate, sits within three percentage points of the stronger Gemini-3-Flash prompted baseline, reduces orchestration cost by more than an order of magnitude (\$0.18 to \$0.004 per task against GPT-5-mini, roughly 45$\times$ cheaper; roughly 15$\times$ cheaper than Gemini-3-Flash), and cuts total LLM calls per episode by 40 to 50 percent. --- ### Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization Authors: Zhipeng Xu, De Cheng, Xinyang Jiang, Nannan Wang, Dongsheng Li, Xinbo Gao Published: 2026-06-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.21736v1 Single domain generalization (SDG) aims to learn a robust model, which could perform well on many unseen domains while there is only one single domain available for training. One of the promising directions for achieving single-domain generalization is to generate out-of-domain (OOD) training data through data augmentation or image generation. Given the rapid advancements in AI-generated content (AIGC), this paper is the first to propose leveraging powerful pre-trained text-to-image (T2I) foundation models to create the training data. However, manually designing textual prompts to generate images for all possible domains is often impractical, and some domain characteristics may be too abstract to describe with words. To address these challenges, we propose a novel Progressive Adversarial Prompt Tuning (PAPT) framework for pre-trained diffusion models. Instead of relying on static textual domains, our approach learns two sets of abstract prompts as conditions for the diffusion model: one that captures domain-invariant category information and another that models domain-specific styles. This adversarial learning mechanism enables the T2I model to generate images in various domain styles while preserving key categorical features. Extensive experiments demonstrate the effectiveness of the proposed method, achieving superior performances to state-of-the-art single-domain generalization approaches. --- ### HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning Authors: Awais Rauf, Ahmed Hasssan, Greg Slabaugh Published: 2026-06-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.21734v1 Understanding long videos requires fine-grained perception and multi-step, higher-order reasoning over complex, long-range spatio-temporal dynamics. Vision-language models (VLMs) encode video frames into visual tokens and attempt to perform both perception and multi-step planning latently, within a single forward pass. This coupled formulation, however, is bottlenecked by the LLM's limited capacity to discover and execute multi-step strategies in its latent representations. To address this bottleneck, we propose Hierarchical Programmatic Probing (HPP), a framework that decouples semantic perception from higher-order temporal reasoning by reformulating long video understanding as iterative, programmatic exploration of a hierarchically segmented video. Specifically, a coding-capable LLM plans and executes a multi-step strategy in an interactive coding environment, probing the video for information and invoking a VLM for localized perception on demand. To make probing tractable over long videos, we introduce three components: information-density-aware hierarchical segmentation, late-interaction semantic retrieval, and structured probing functions for coarse-to-fine temporal localization. We validate HPP on LongVideoBench, which requires both fine-grained perception and long-range relational reasoning, and show that decoupling the two via iterative programmatic probing yields substantial gains. Further results on EgoSchema, VideoMME, and MLVU demonstrate the effectiveness of our approach across diverse long-video benchmarks. --- ### Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents Authors: Zesen Liu, Zihan Zhang, Dongdong She Published: 2026-06-19 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2606.21732v1 Summarization-based prompt compression is increasingly used by LLM agents to shorten long, distributed contexts, but it shifts the security boundary: filters inspect the pre-compression prompt while the backend acts on a newly generated compressed context. We identify relinking, a compression-boundary vulnerability where the compressor behaves as a confused deputy, summarizing distributed, locally benign fragments into a complete malicious instruction. Unlike prompt injection, relinking need not place an explicitly malicious payload in the source context. We show that relinking arises from summarization itself: attention makes separated fragments jointly available, pre-training makes compatible fragments plausible to connect, and post-training favors compact backend-actionable summaries. We formalize the attacker-induced form as adversarial relinking and present Relink, an automated DSL-based tool that splits malicious payloads into benign fragments while keeping the complete payload absent before compression. Across four long-context agent benchmarks, Relink achieves 86.9% Relink Rate and Backend Action Rate versus 17.0% for clean-split controls. Existing defenses fail to reliably capture adversarial relinking; our KBRA defense reduces residual Backend Action Rate to 0.0%. ---