# Research Papers — 2026-06 · bundle page 192 of 260

> Full-text markdown of papers #9551–9600 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/192
[← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/191.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-06/page/193.md)

### Scaling Decision-Focused Learning to Large Problems with Lagrangian Decomposition

Authors: Stéphane Eilles-Chan Way, Hugo Percot, Quentin Cappart, Tias Guns, Louis-Martin Rousseau
Published: 2026-06-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.08797v1

Decision-focused learning has shown great promise for addressing predict-then-optimize problems, particularly in the presence of under-specified models. However, its practical deployment is often hindered by high computational costs and limited scalability, as it requires solving a constrained optimization problem for each training instance at every iteration. To address these challenges, we propose a novel framework that incorporates Lagrangian decomposition into the decision-focused learning paradigm. Specifically, we introduce a new surrogate objective along with two loss functions for evaluating and training the underlying prediction model. We further propose two variants of our approach, which offer different trade-offs between computational efficiency and solution quality. Our framework can be seamlessly integrated with standard decision-focused learning methods, including Smart Predict-then-Optimize (SPO+) and Implicit Maximum Likelihood Estimation (IMLE). Through experiments on two standard benchmarks, the multi-dimensional knapsack problem and quadratic portfolio optimization, we demonstrate that our approach achieves competitive performance while remaining amenable to parallelization. In particular, it consistently outperforms traditional decision-focused learning methods on large-scale instances, involving up to eight times more variables than those typically considered in related work. The implementation is available at https://github.com/corail-research/DFL-LD.

---

### PairWise Image Finder: An Open-source Tool for Finding Visually Aligned Street-Level Image Pairs for Urban Perception Studies

Authors: Jussi Torkko
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08795v1

Change detection and scene recognition techniques have been widely applied to Street View Imagery (SVI) to understand changes in scenes across the years. However, metadata alone is often insufficient to reliably find visually aligned image pairs. This study introduces the PairWise image finder, a tool that integrates feature detection and matching, supported by semantic segmentation masks to quantify the visual alignment of two images of varying time periods. The tool outputs the share of matched key features, the matched feature distance and coverage, and the alignment of semantic masks, which enables the user to filter image pairs depending on the alignment quality and use case. The visually aligned pairs derived from the tool can be used to accurately study explicit longitudinal change and help reduce manual effort for perception studies. The usability of the tool is demonstrated through a comparison of longitudinal changes, highlighting the importance of perspective when quantifying changes. The proposed method provides a scalable and open tool for researchers and stakeholders to find high-quality image pairs for urban analysis, perception and related applications.

---

### AI-Augmented Closed-Loop Quality Engineering: A Reference Architecture for Continuous Software Quality Intelligence

Authors: Dimple Bajaj
Published: 2026-06-07
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2606.08793v1

The quality of software engineering is still under a challenge due to disjointed processes between requirements, testing, and production, which hinders the opportunity to implement quality strategies in consecutive releases. Existing approaches tend to be fixed-model or single-optimization approaches and lack production feedback learning mechanisms. The paper at hand proposes a closed-loop reference architecture of continuous software quality intelligence with AI enhancements. The model synthesizes requirement feature mining, risk-based test prioritization, defect prediction, and production incident analysis as an element of a feedback-based pipeline. A limited feedback learning model is introduced that is used to propagate the production signal-based on defect severity and incident impact- to the following release to ensure stability, and the time. The method is evaluated using a semi-synthetic test dataset of 4,500 requirements, 27,049 test cases, 13,089 defects and 7,841 incidents in six release cycles. The experimental results show that the proposed system reduces the defect leakage by 0.19 to 0.13, increases the effectiveness of the detection system to 0.72 to 0.84, and shortens the test execution by up to 35 percent compared to the non-adaptive baselines. The changes are stable release to release. The findings indicate that through the integration of feedback-based learning in a closed-loop architecture, it can be continued to enhance quality process, which offers practical foundation of adaptive quality engineering of software.

---

### The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model

Authors: Wendy K. Tam
Published: 2026-06-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.08792v1

Large language models are rapicly replacing search engines as the primary interface between people and information. Unlike search engines, which retrieve existing content, LLMs generate novel text shaped by internal representations learned during training. Here we show that partisan political identity is encoded in the model's activation space, and that this direction directly shapes generation. Using 190,491 tweets from sitting members of the U.S. Congress as labeled training data, we train linear probes on the hidden states of the Llama 3.1 8B Instruct model. We identify a single geometric axis at layer 18 that separates Republican from Democratic text with an AUC of 0.945 and a Cohen's d of 1.94, and use sparse autoencoders to decompose that axis into interpretable partisan features. Causally intervening along this axis, ablating or amplifying the partisan component mid-generation, produces systematic shifts in the model's output. We witness stance reversals, register shifting, and structured fabrications of authority. Our results demonstrate that partisan bias in language models is not a vague emergent property but a learned geometric feature that can be precisely located and steered. Partisan bias is not a bug to be patched, but a structural property of how these models encode information about their users. As LLMs displace search engines as the interface to knowledge, understanding that product design (and its consequences) will be essential for navigating the legal, social, and political transitions from an information ecosystem that is curated to one that is generated.

---

### Evaluating AI Investment Strategies

Authors: Irene Aldridge
Published: 2026-06-07
Categories: econ.EM, cs.AI, q-fin.PM, q-fin.RM, q-fin.ST
arXiv: https://arxiv.org/abs/2606.08791v1

We study the problem of auditing a black-box algorithmic decision-maker from observable inputs and outputs alone. Our main result is an exact decomposition: under precisely characterized conditions, the cumulative \emph{regret} of a dynamic policy equals the sum of per-period covariances between the cost vector and the policy's decision. This extends the single-period identity of Aldridge~(2026) to the full multi-period setting of stochastic dynamic programming. We prove the identity holds exactly under i.i.d. costs and mean-unbiased Markov policies, derive closed-form bias corrections for non-stationary and time-varying cases, and establish the discounted-horizon analog. A Bellman recursion for the covariance regret functional connects the result to standard reinforcement learning algorithms; for rolling-window policies, the estimation-error bias is $O(d/w)$. The decomposition has direct implications for algorithmic auditing in strategic environments: in platform mechanism design, it provides a welfare-based audit metric without access to the agent's private type; in repeated games, covariance reduction is a sufficient condition for policy improvement; in procurement and ad auctions, the bias correction quantifies welfare loss from strategic misreporting. The associated trajectory estimator is consistent, asymptotically normal with HAC variance, and computable in $O(T \cdot nd)$ time. This makes the proposed approach a tractable, model-free audit tool for platform mechanisms, algorithmic portfolio strategies, and any sequential decision system subject to external performance review.

---

### RAILS: Verification-Native Clearing For Agentic Commerce

Authors: Adrian de Valois-Franklin, Alex Bogdan
Published: 2026-06-07
Categories: cs.AI, cs.CR, cs.MA
arXiv: https://arxiv.org/abs/2606.08790v1

Autonomous agents negotiate, purchase, deploy code, and move funds, but no neutral mechanism determines whether they met their delegated obligation, who is responsible when they did not, or which settlement action follows. This is the agentic clearing problem. Tool protocols (MCP), inter-agent communication (A2A), payment rails (x402), mandate and network agent protocols (AP2, Visa, Mastercard), and settlement-risk standards each assume that determination and none produce it. Clearing is the missing primitive. Payment is not clearing. Authorization is not clearing. LLM-as-judge evaluation is not clearing. Settlement-risk escrow is not clearing: it consumes clearing decisions. RAILS (Real-Time Agent Integrity & Ledger Settlement) is the integrity and clearing layer for agentic commerce, spanning a per-output reliability score, a published reliability record, and a clearing function that consumes them. The clearing protocol at its core closes that gap. Seven primitives (Obligation Object, Evidence Envelope, Verification Mesh, Clearing Decision, Settlement Instruction, Clearing Passport, Finality Rules), bound by a formal model of admissibility-graded verification, together yield a soundness property: no financially material settlement is supported by evidence below the obligation's admissibility floor. The property is falsifiable against the spec. We are not aware of a prior agent-commerce verification mechanism that states a property of this kind. The approaches nearest to it emit a pass, a delivery guarantee, a bare score, or an equilibrium. This paper specifies that clearing protocol.

---

### MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training

Authors: Lianyu Pang, Tianlin Pan, Cheng Da, Changqian Yu, Huan Yang, Kun Gai, Song Guo, Wenhan Luo
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08788v1

Representation alignment with pretrained vision models has recently shown strong potential for accelerating diffusion transformer training. By aligning intermediate diffusion features with clean-image representations from self-supervised vision encoders, existing methods improve convergence and generation quality. However, such alignment also introduces a non-trivial constraint: diffusion models operate on noisy inputs whose usable information varies across timesteps, while the reference features are extracted from clean images. In this paper, we revisit this mismatch from a token-level perspective. We find that, under full-token representation alignment, tokens with large alignment-gradient norms exhibit a stable spatial preference, suggesting that the alignment objective does not affect all tokens uniformly and may encourage the model to rely on the complete set of clean-image tokens. To address this issue, we propose MaskAlign, a token-subset representation alignment method that applies alignment to randomly sampled token subsets during training. By exposing the model to different token subsets across iterations, MaskAlign reduces the dependence of representation alignment on the complete token set and encourages alignment behavior that is more stable under token-subset perturbations. To mitigate the information loss caused by directly dropping tokens, we further introduce a lightweight pre-mask token mixing block that shares information across tokens before masking.

---

### OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality

Authors: Ganzhao Yuan
Published: 2026-06-07
Categories: math.OC, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2606.08783v2

Orthogonalized momentum updates, as used in Muon-style optimizers, have recently shown strong empirical stability in large-scale deep learning. However, most current orthogonalized methods are still paired with fixed, externally scheduled, or otherwise open-loop magnitude rules, so their scale is not directly calibrated from the realized optimization trajectory. Motivated by the closed-loop perspective behind Lipschitz-free and noise-adaptive methods, we propose OptMuon, a family of adaptive momentum orthogonalization methods for stochastic nonconvex optimization. OptMuon combines Muon-style polar-factor directions with a trajectory-dependent AdaGrad-Norm-type coefficient schedule, so that the update magnitude is determined by the observed gradient and momentum history rather than by a prescribed Lipschitz-dependent rule. The schedule does not use the smoothness constant, the variance level, or the bounded-gradient constant in parameter selection, and its running-maximum correction prevents isolated gradient spikes from causing excessive coefficient collapse. Under lower-boundedness, unbiased stochastic gradients with bounded variance, smoothness, and an almost-sure bounded stochastic-gradient condition, we prove two complementary expected-stationarity guarantees. OptMuon-A achieves the noise-adaptive rate \(\tilde{\mathcal O}(T^{-1/2}+σ^{1/2}T^{-1/4})\) under average smoothness, while OptMuon-I achieves \(\tilde{\mathcal O}(T^{-1/2}+σ^{1/3}T^{-1/3})\) under individual smoothness. In the zero-noise regime, both bounds automatically reduce to a nearly optimal deterministic first-order rate \(\tilde{\mathcal O}(T^{-1/2})\) without manual hyperparameter retuning. These results show that closed-loop scalar adaptation can be combined with Muon-style momentum orthogonalization while retaining noise adaptivity and zero-noise optimality up to logarithmic factors.

---

### DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarization

Authors: Sheng-Wei Chan, Yung-Che Wang, Hsin-Jui Pan, Chia-Min Lin, Jen-Shiun Chiang
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08781v2

Document image binarization aims to separate foreground text from degraded backgrounds while preserving thin, broken, and low-contrast strokes. Although deep learning methods have improved binarization performance, most existing approaches rely on convolutional, transformer-based, or generative architectures, while Mamba-based state space models remain largely unexplored for this task. In this work, we investigate Mamba-based feature propagation and observe that direct state-space propagation may dilute weak foreground cues during long-range modeling, especially faint ink traces, fragmented characters, and boundary-sensitive stroke details. To address this problem, we propose DeepMine-Mamba, a Mamba-based binarization framework equipped with a novel Anti-Dilution Gate that estimates propagation-induced feature changes and selectively restores stroke-sensitive local responses while suppressing unnecessary background enhancement. Experiments on DIBCO/H-DIBCO benchmarks under a strict leave-one-year-out protocol show that DeepMine-Mamba achieves competitive overall performance, with strong average FM and Fps across benchmark years. Ablation results further show that the Anti-Dilution Gate is the key component for mitigating propagation-induced foreground dilution and improving stroke preservation.

---

### Beyond Consistency: Preserving Temporal Structure in Zero-Shot Video Editing

Authors: Deyin Liu, Yisheng Ding, Zhe Jin, Xiatian Zhu, Anjan Dutta, Lin Wu
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08780v1

Existing zero-shot video editing methods rely on pre-trained diffusion models, successfully achieving spatial control and basic temporal consistency but fundamentally fail to preserve the video's original temporal structure.This distinction is critical: temporal consistency ensures visual smoothness, but temporal structure dictates the video's high-level narrative, rhythm, and semantic flow. Without this preservation, the edited output, especially for long videos with complex semantic variations, becomes narratively incoherent and semantically ambiguous. To address this limitation, we introduce a novel zero-shot editing approach that, for the first time, explicitly focuses on preserving the source video's temporal structure. We achieve this by adaptively partitioning the video into semantically distinct clips based on feature similarity and selecting a representative anchor frame for each clip. To enhance both intra-clip fidelity and computational efficiency, we design a clip-adaptive token merging strategy which leverages the anchor's semantic dominance to stabilize the editing. Furthermore, we employ an alternating combination strategy that ensures seamless inter-clip transitions while maintaining semantic distinction. Extensive experiments demonstrate that our method achieves state-of-the-art results, successfully balancing the preservation of original temporal structure with computational efficiency, and setting a new benchmark for zero-shot video editing fidelity.

---

### Reformulate LLM Reinforcement Learning for Efficient Training under Black-box Discrepancy

Authors: Jiashun Liu, Runze Liu, Xu Wan, Jing Liang, Hongyao Tang, Ling Pan
Published: 2026-06-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.08779v2

Reinforcement Learning (RL) has emerged as a pivotal post-training paradigm, yet it frequently suffers from unpredictable sub-optimum performance or even training collapses. Recent findings attribute these failures to a hidden train-inference discrepancy (or mismatch), stemming from the disparate underlying engines and architecture. We find that the training policy can actively self-correct such a discrepancy when provided with an appropriate learning signal. Then, we further empirically identify a discrepancy tolerance region: within this region, aggressively narrowing the discrepancy can suppress policy exploration and reduce learning efficiency, whereas outside this region, reducing excessive discrepancy improves optimization consistency and raises the achievable local performance ceiling. According to such findings, we formulate this problem as a Discrepancy-Constrained Markov Decision Process (DCMDP), where reward maximization is coupled with a constraint that aligns training-Inference behavior, achieving stable dual-objective optimization. To adaptively balance performance improvement and discrepancy control, we introduce a Lagrangian relaxation mechanism that dynamically adjusts the relative weight of the two objectives according to the current degree of discrepancy violation. This enables stable dual-objective optimization: the policy is allowed to explore freely within the tolerance region, while being guided back when the discrepancy exceeds the safe boundary. Empirically, DCMDP significantly improves the performance of 8B dense model (Qwen-3-8b) and 30B Mixture-of-Expert model (Qwen-3-30bA3b), and enables a heterogeneous training paradigm, where LLMs can be optimized in high-fidelity training setup while being explicitly aligned for low-cost, resource-constrained inference deployment.

---

### How Many Counterfactuals Does It Take? Probing VLM Hallucinations Through Circuits and Causal Effects

Authors: Abhivansh Gupta, Simardeep Singh, Advika Sinha, Shreyansh Modi, Akshat Tomar
Published: 2026-06-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.08777v1

Visual Language Models (VLMs) are known to produce hallucinated predictions that are not grounded in visual evidence, yet existing approaches lack a principled understanding of how robust such predictions are under counterfactual perturbations. In this work, we study the sample complexity of counterfactual robustness for hallucinated outputs in VLMs. We define a causal influence metric based on log-probability differences between factual, counterfactual, and activation-patched runs, and use it to characterize the stability of hallucinated predictions. By leveraging circuit discovery techniques (CD-T), we identify model components responsible for these predictions and track their activation differences across counterfactual samples. We then derive empirical bounds on the minimum number of counterfactual samples m required to reliably detect instability in hallucinated outputs, using concentration inequalities and variance estimates of the causal influence distribution.

---

### Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks

Authors: Raktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun, Farshad Khorrami
Published: 2026-06-07
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2606.08775v1

Visual world models have shown great potential in learning complex system dynamics. Recent advancements leverage these models as transition functions within Model Predictive Control (MPC) frameworks to solve various control tasks. When applied to robotics, however, they are limited to single-stage tasks such as reaching or grasping, and struggle with multi-stage ones that demand complex sequential planning. In this work, we introduce WorldDP, a world model framework designed for multi-stage robotic manipulation. Our hierarchical approach utilizes a high-level world model as a transition function to optimize for feasible subgoals during runtime, which are subsequently reached by a low-level Diffusion Policy. To further aid in learning dynamics and planning, we incorporate object-centric representations that decouple environmental entities and enable us to plan sequentially with respect to each. Evaluated across several robotics benchmarks, WorldDP consistently outperforms existing baselines, validating that coupling the world model's physically grounded planning with diffusion policy's efficient execution yields superior multi-stage performance.

---

### TeamHerald@CHIPSAL 2026: Hate Speech Detection and Sentiment Analysis of Nepali Memes using Transformer-based Architectures and Ensemble Learning

Authors: Ashish Acharya, Anish Khatiwada, Rohit Khadka, Pragya Aryal
Published: 2026-06-07
Categories: cs.CL, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2606.08770v1

The analysis of internet memes in the Nepali language is complicated by frequent code-mixing and a lack of established baseline resources. While memes inherently combine visual and textual elements, this study focuses on a text-centric approach by extracting embedded text using an OCR layer and modeling it with Transformer-based architectures. We evaluate six distinct models and investigate the comparative effectiveness of Hard and Soft Voting ensemble strategies across two tasks: binary hate speech detection and three-class sentiment analysis. Experimental results show that a standalone decoder-only model achieved the highest performance for binary classification, whereas the Soft Voting ensemble performed best for the multi-class sentiment task, yielding a 15.8% relative improvement in Macro F1-score over the strongest standalone baseline. These findings suggest that ensemble strategies behave differently across binary and multi-class tasks, highlighting the importance of selecting aggregation methods suited to the classification objective.

---

### RadOT-Eval: Auditable Structured-Evidence Transport for Radiology Report Evaluation

Authors: Weixin Liu, Juming Xiong, Yang Li, Qingyuan Song, Susannah Rose, Murat Kantarcioglu, Bradley Malin, Zhijun Yin
Published: 2026-06-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.08769v1

Automatic evaluation is critical for high-stakes text generation, where errors often involve omitted findings, hallucinated content, polarity reversals, location changes, uncertainty mismatches, and temporal-comparison errors rather than low surface similarity alone. Radiology report generation provides a challenging test case because generated reports must preserve structured clinical evidence across sources. We present RadOT-Eval, an interpretable structured-evidence optimal transport framework for offline auditing of radiology report generation. RadOT-Eval decomposes reference and candidate reports into attribute-structured clinical evidence units, aligns corresponding evidence using entropy-regularized optimal transport, and uses clinically meaningful side-channel discrepancies in a monotone risk model to predict error burden. All transport, feature, and readout choices are selected using the ReXVal dataset, and the frozen system is evaluated on the independent RadEvalX dataset. RadOT-Eval achieves Spearman correlations of 0.715, 0.548, and 0.399 with total, clinically significant, and clinically insignificant annotated error burden, respectively, yielding higher point estimates than standard evaluation metrics and the open-source large language model (LLM)-based evaluator GREEN-radllama2-7B. In a frozen auxiliary corruption-sensitivity stress test on ReXErr-v1, RadOT-Eval achieves 0.768 AUROC and a 0.990 corrupted-greater-than-clean paired win rate. These results show that structured evidence transport provides an auditable, rank-oriented evaluation tool for high-stakes generated clinical text under ReXVal-only model selection and frozen RadEvalX testing.

---

### Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions

Authors: Blanka Köver, Alexandra Butoi, Anej Svete, Michael Hahn, Ryan Cotterell
Published: 2026-06-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.08768v1

Transformers consistently fail to learn certain simple functions that are provably expressible with specific parameter settings. This gap between learnability and expressivity is particularly prominent for sensitive functions -- functions whose output is likely to change if a single bit of the input is flipped -- for example, PARITY. While prior work has established that transformers exhibit a bias toward functions with low average sensitivity, the precise mechanism underlying this bias remains poorly understood. To shed light on this phenomenon, we study the geometry of transformers' parameter space. We show that sensitive functions -- even when representable -- occupy a vanishingly small region that random initialization is very likely to miss. Specifically, we shift the focus from average sensitivity to the full sensitivity profile -- the distribution of sensitivity values across all inputs -- and prove that randomly initialized transformers almost surely compute functions which have low-sensitivity strings. Consequently, any function that lacks such strings is provably unlearnable.

---

### Tac2Pix: Image-Space Visuo-Tactile Fusion for Dexterous Manipulation

Authors: Shengcheng Luo, Kefei Wu, Xiaoying Zhou, Wanlin Li, Ziyuan Jiao, Chenxi Xiao
Published: 2026-06-07
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2606.08765v3

Vision and touch are naturally complementary for dexterous manipulation. Yet they are represented in fundamentally different forms: visual observations are dense and spatially structured, whereas tactile measurements are sparse, heterogeneous, and robot-centric. This mismatch makes it challenging to establish explicit spatial correspondence between the two modalities, particularly when they are fused in latent space. However, each tactile measurement is associated with a known location on the robot's kinematic chain, offering a localization prior that could bridge this representational gap. This raises a natural question: can this localization prior be used to construct a shared representation that explicitly aligns touch with vision? We introduce Tac2Pix, an image-space visuo-tactile fusion framework that projects sparse tactile measurements onto the RGB image plane using forward kinematics and camera calibration, then renders them as force-aware saliency maps. By expressing touch in the same pixel space as vision, Tac2Pix directly leverages pretrained 2D visual representations. We further employ zero-initialized input adaptation to preserve the original visual pathway at the start of policy learning. To assess whether this geometry-based interface yields consistent policy gains, we evaluate Tac2Pix on three simulated and three real-world dexterous manipulation tasks. In simulation, Tac2Pix consistently improves visuo-tactile policy learning across tasks, policy architectures, and visual backbones. In real-world experiments, it improves average success under visual occlusion by 26.7 percentage points over the strongest latent visuo-tactile fusion baseline, with gains persisting under both random and physical occlusions. Together, these results support image space as an effective interface for fusing sparse touch with pretrained visual representations.

---

### RGB-S: Image-Aligned Tactile Saliency for Robust Dexterous Manipulation

Authors: Shengcheng Luo, Kefei Wu, Xiaoying Zhou, Wanlin Li, Ziyuan Jiao, Chenxi Xiao
Published: 2026-06-07
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2606.08765v2

Effective visuo-tactile integration is critical for robotic dexterous manipulation, especially when visual observations are unreliable or occluded. However, robustly aligning sparse, heterogeneous tactile measurements with dense visual representations remains a fundamental challenge. Most existing approaches require policies to learn cross-modal correspondences implicitly from limited demonstrations, without leveraging geometric priors. As a result, they are often data-inefficient and generalize poorly when visual observations are degraded. To address this limitation, we propose a framework that explicitly grounds physical contacts in the image domain. Using robot forward kinematics and camera calibration, we project tactile sensor locations directly onto the RGB image plane. We then render force-modulated Gaussian saliency maps to model spatial uncertainty arising from kinematic and calibration errors. By integrating these 2D spatial anchors through a zero-initialized conditioning architecture, our method injects physical contact priors into standard visual backbones while preserving pre-trained visual representations. We evaluate our method on six dexterous manipulation tasks in both simulation and the real world under severe visual occlusions. Real-world experiments show that explicit RGB-S grounding in the image domain improves real-world occluded manipulation success rates by $26.7$ percentage points over the strongest implicit visuo-tactile baseline, suggesting its improved spatial reasoning and robustness to occlusion. Project page: touch-as-saliency.github.io

---

### APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing

Authors: Hong Guo, Nianhui Guo, Weixing Wang, Jona Otholt, Christoph Meinel, Haojin Yang
Published: 2026-06-07
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2606.08761v2

W4A4 quantization promises full utilization of INT4 Tensor Cores, yet group dequantization overhead on CUDA Cores has driven existing systems to mixed-precision fallbacks. We present the first systematic study of how intra-SM compute balance governs this bottleneck. Through controlled benchmarks across four GPUs from Ampere and Ada architectures, we identify the Tensor Cores to CUDA Cores throughput ratio ($ρ$) as the primary hardware indicator: the W4A4-g128 kernel yields $2.0$--$2.5\times$ speedup on RTX~3090 ($ρ=16$) yet degrades to $0.43$--$0.47\times$ on A100 ($ρ=64$) in compute-bond scenarios, establishing W4A4 viability as platform-dependent rather than universally infeasible. Guided by this finding, we build \textbf{APEX4}, which co-designs pure INT4 GEMM kernels with $ρ$-aware granularity adaptation to mitigate the CUDA Cores dequantization bottleneck. APEX4 achieves perplexity within 0.63 of FP16 on LLaMA-2-70B and outperforms W4Ax Atom-g128 by 4.0\%--4.4\% in zero-shot accuracy. Deployed as a drop-in replacement in unmodified vLLM, it delivers up to $1.66\times$ end-to-end speedup on L40S ($ρ=8$), and $1.78\times$ on RTX~3090 ($ρ=16$), $2.09\times$ on A40 ($ρ=16$), while recovering A100 ($ρ=64$) to $1.20$--$1.40\times$ via the mixed-granularity mode. Our code is available at https://github.com/APEX4-W4A4/APEX4-W4A4.

---

### Co-Evolving Skill Generation and Policy Optimization

Authors: Zhiwei Zhang, Yudi Lin, Nikki Lijing Kuang, Linlin Wu, Xiaomin Li, Songtao Liu, Fenglong Ma
Published: 2026-06-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.08755v1

Skill-augmented reinforcement learning improves language agents by storing reusable procedural knowledge acquired from past experience. Existing methods typically use strong language models to analyze trajectories, generate skills, and update a retrievable skill bank during online training. However, they rarely assess whether a newly generated skill is useful before it is stored and reused. We find that this assumption is unreliable: even skills generated by proprietary frontier LLMs exhibit highly mixed utility, with many providing little benefit or even degrading performance. Once such skills enter the bank, their effects are difficult to identify, because subsequent rollout feedback is delayed and usually reflects the combined effect of multiple retrieved skills rather than the marginal contribution of any individual skill. We propose an online reinforcement learning framework for pre-storage skill validation. The framework estimates whether a candidate skill contributes useful information beyond the skills already retrieved for the current task. It uses the standard rollout budget to form two matched groups under the same task and retrieval context: base rollouts conditioned on the currently retrieved skills, and skill-augmented rollouts conditioned on the same skills plus one candidate skill induced from the base trajectories. The reward gap between these two groups estimates the candidate skill's context-dependent marginal utility, enabling the framework to promote useful skills while filtering ineffective or harmful ones without additional rollout overhead. The framework further uses this marginal-utility signal to train the policy itself as a skill generator, reducing reliance on repeated calls to proprietary models. The learned skill-generation likelihood serves as a context-dependent score for retrieval-time reranking and outdated-skill pruning as the policy evolves.

---

### Less Is More: Training-Free Acceleration Framework of 3D Diffusion Models for Low-Count PET Denoising via Global-Local Trajectory Reduction

Authors: Yuhan Liu, Scott M. Leonard, Marlee Crews, Muhannad Fadhel, Jinkui Hao, Tianqi Chen, Ryan J. Avery, Bo Zhou
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08751v1

Accurate quantification and uptake measurement in PET are critical for assessing disease progression and supporting clinical decision-making. While high-count PET provides reliable image quality, the associated radiation dose and prolonged acquisition remain significant clinical concerns, motivating the adoption of low-count protocols. Diffusion-model-based methods have demonstrated strong potential for restoring low-count PET to near high-count quality, but their iterative sampling procedure becomes prohibitively expensive when applied to high-resolution 3D PET volumes, introducing substantial inference latency that limits practical clinical deployment. To address these challenges, we propose a training-free Global-Local Skipping Strategy that accelerates diffusion model-based 3D PET denoising while simultaneously improving reconstruction quality. The proposed method is plug-and-play and directly applicable to pre-trained diffusion models without retraining or architectural modification. Specifically, we introduce: (i) a global denoising step skipping strategy that initializes the reverse diffusion process from an intermediate denoising step using a noise-consistent transformation of the low-count input, substantially reducing the number of required denoising steps; and (ii) a local feature reuse shortcut that reuses slowly-varying high-level U-Net features across neighboring denoising steps, further reducing per-step computation while preserving image fidelity. We evaluate the proposed approach on multiple PET tracers from in-house and public datasets, including 18F-FDG PET, 68Ga-DOTATATE PET, and 18F-PSMA PET, demonstrating consistent acceleration of over an order of magnitude alongside improved or comparable reconstruction performance relative to the full-step baseline. Blinded reader studies further confirm enhanced clinical confidence and perceived diagnostic quality.

---

### HydraQE: OSU's Submission for the IWSLT 2026 Speech Translation Metrics Shared Task

Authors: Kevin Krahn, Eric Fosler-Lussier
Published: 2026-06-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.08748v1

We present HydraQE, our contribution to the IWSLT 2026 Speech Translation Metrics shared task. HydraQE is an end-to-end, reference-free quality estimation (QE) system for speech translation built on a Qwen3-ASR backbone, which accepts source audio and a translation hypothesis as joint input. Hidden states from all backbone layers are combined via a learnable sparsemax scalar mix, then re-encoded by a lightweight bidirectional Transformer to enable full cross-modal interaction prior to pooling into a shared embedding. Three independent prediction heads are trained on complementary supervision signals: human direct assessment (DA) annotations, MetricX-24 pseudo-labels, and xCOMET pseudo-labels. To address the scarcity of human-annotated data, we train on a combination of synthetically corrupted examples and silver pseudo-labeled machine translation outputs, using a curriculum that begins on synthetic and silver data and gradually shifts toward human-annotated examples. HydraQE outperforms cascaded text-based baselines and prior direct speech QE systems, demonstrating that end-to-end speech translation QE is competitive with cascaded approaches.

---

### Stain-Aware Wavelet Regularization for Instant Adversarial Purification in Histopathology

Authors: Zhe Li, Bernhard Kainz
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08745v2

Deep learning has become prevalent in computational pathology pipelines that support tasks such as cancer screening and digital pathology analysis. However, the susceptibility of neural networks to adversarial perturbations raises safety concerns for reliable deployment in clinical practice. In histopathological images, this challenge is exacerbated by the difficulty of distinguishing high-frequency adversarial noise from subtle and diagnostically relevant tissue structures. To address this issue, we propose Stain-Aware Wavelet Regularization (SAWR), an adversarial purification framework that leverages multi-level wavelet-domain regularization based on Haar transform to hierarchically disentangle adversarial perturbations from diagnostic structural information. This spectral constraint is further extended to individual histological channels, enabling stain-specific frequency regulation consistent with the biological properties of Hematoxylin and Eosin. Extensive experiments demonstrate that SAWR improves adversarial robustness by up to 10.69\% over the baseline approach, while maintaining texture and spectral fidelity under adversarial perturbations.

---

### Stain-Aware Wavelet Regularization for Instant Adversarial Purification in Histopathology

Authors: Zhe Li, Bernhard Kainz
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08745v1

Deep learning has become prevalent in computational pathology pipelines that support tasks such as cancer screening and digital pathology analysis. However, the susceptibility of neural networks to adversarial perturbations raises safety concerns for reliable deployment in clinical practice. In histopathological images, this challenge is exacerbated by the difficulty of distinguishing high-frequency adversarial noise from subtle and diagnostically relevant tissue structures. To address this issue, we propose Stain-Aware Wavelet Regularization (SAWR), an adversarial purification framework that leverages multi-level wavelet-domain regularization based on Haar transform to hierarchically disentangle adversarial perturbations from diagnostic structural information. This spectral constraint is further extended to individual histological channels, enabling stain-specific frequency regulation consistent with the biological properties of Hematoxylin and Eosin. When integrated into an instant purification framework, SAWR improves adversarial robustness by up to 10.69\% over the baseline approach, while maintaining texture and spectral fidelity under adversarial perturbations.

---

### MB-Loc: Multi-planar Bird's-eye-view Localization in outdoor LiDAR scenes

Authors: Ayaan Choudhury, Preet Savalia, Anirudh Pydah, Avinash Sharma
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08744v2

Global LiDAR localization is a fundamental task for autonomous navigation systems. Recent methods perform Scene Coordinate Regression (SCR) and achieve superior accuracy over Absolute Pose Regression (APR) solutions by predicting dense 3D world coordinates. However, SCR approaches introduce two major bottlenecks: severe computational inefficiency from processing raw 3D geometries and significant performance degradation under varying sensor viewpoints. To address these limitations, we present MB-Loc, a lightweight and viewpoint-robust SCR framework. Instead of relying on heavy 3D convolutions, we project the input LiDAR scan into a 2.5D Multi-planar Bird's-Eye View (BEV) representation. By slicing the point-cloud along the Z-axis and mapping signed depths into discrete 2D planes, MB-Loc retains essential 3D geometric structures while exploiting the computational tractability of standard 2D CNNs. To handle the inherent sparsity of outdoor LiDAR, we introduce a KL-regularized latent bottleneck that explicitly models spatial uncertainty without injecting stochastic noise. Finally, to ensure rotation robustness, we apply 3D spatial augmentations prior to planar projection, forcing the network to implicitly learn viewpoint-invariant features. We perform extensive experiments on the publicly available NCLT dataset and demonstrate that our proposed method outperforms the current state-of-the-art. Operating at real-time inference speeds, MB-Loc significantly outperforms traditional 3D-SCR architectures in computational efficiency.

---

### AUCp: Pseudo-AUC for Inference Model Selection with Unlabeled Validation Data in Abnormality Detection

Authors: Md Mahfuzur Rahman Siddiquee, Fazle Rafsani, Jay Shah, Teresa Wu, Catherine D Chong, Todd J Schwedt, Baoxin Li
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08742v1

Abnormality detection is a crucial yet challenging task in medical image analysis. Distinguishing abnormalities from normal data by learning to reconstruct normal-only data alleviates the reliance on labeled datasets. However, many studies, even if unsupervised, rely on a labeled validation set to select the best model for inference from multiple training iterations. For many diseases labeled data are unavailable and substantially time consuming to obtain. To address this, AUCp - a novel metric that supports abnormality detection for unsupervised and self-supervised methods is proposed. Instead of evaluating the realism of reconstructed images to select the best of model for inference, it focuses on actual detection performance and without requiring an annotated test set. Assuming the pseudo ground truth of all unannotated samples in the test set as abnormal/positive and using traditional AUC calculation, AUCp scores are derived. Given a large and representative training set of normal samples, we show mathematical and empirical evidence that model selection using AUCp scores improves disease detection in terms of unsupervised and self-supervised methods over conventional metrics. Using two unsupervised methods for neurologic disease detection and self-supervised methods on diverse datasets, our results demonstrate that the AUCp score effectively identifies the optimal model for inference, significantly enhancing abnormality and disease detection. The corresponding implementations are available in https://github.com/mahfuzmohammad/AUCp.

---

### Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmark

Authors: Muhammed Rasin
Published: 2026-06-07
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2606.08736v1

We study a capability the dominant paradigm in synthetic tabular data does not provide: exact satisfaction of a declared analytical outcome with no source data. Imitation methods (copulas, GANs, diffusion) learn a real distribution and sample from it, and are judged on fidelity to real data. A large, practical class of needs is different: generating data with no source data ("cold start") that reproduces a declared outcome (a revenue curve, a churn rate, a group share) across a relational schema. Off-the-shelf imitation tools offer no interface for such targets, and no sampler can hit an exact aggregate, because sampling has variance. On a real public dataset, off-the-shelf learned synthesizers trained on that very data miss the declared monthly aggregate by 74 to 86 percent; a per-period steelman cuts the miss to about 19 percent and still cannot reach 0; a closed-form generator reaches exactly 0. We name this task outcome-conformant synthesis, argue its evaluation axis is conformance rather than fidelity, and show the two axes are orthogonal. We contribute: (1) a formal account showing a widely-used family of exact-aggregate generators is exactly conditional-sum sampling of a Gamma population (via Lukacs' characterization), with closed-form exactness, a closed-form marginal CV, and scale-invariance; a controlled experiment maps the boundary, enforcing the exact aggregate costs at most 0.006 in 1-Wasserstein distance to an arbitrary external marginal, the rest being shape-family mismatch; (2) SpecBench, to our knowledge the first benchmark to measure conformance to analytical outcomes for cold-start relational synthesis; and (3) a closed-form, deterministic reference system. Exact aggregation alone is trivial; the contribution is conformance jointly with closed-form marginals, integrity, determinism, and zero source data. We concede fidelity to imitation where real data exists.

---

### Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning

Authors: Lianrong Zuo, Peilan Xu, Yong Liu, Wenjian Luo
Published: 2026-06-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.08735v1

Quality-diversity reinforcement learning (QD-RL) aims to construct policy repertoires that contain both high-performing and behaviorally diverse policies. Existing QD-RL methods mainly diversify policy instances after rollout evaluation or use learned value information to improve policy quality and behavior targeting, while the learning branches that generate candidate policies remain less explored. This paper proposes SV-QD-RL, a structure-value coupled framework that represents each candidate as a structure-conditioned actor-critic branch. Each branch contains an actor, a structural mask, a branch-specific critic, a replay state, and evaluation attributes including behavior, return, sparsity, and value profile. The structural mask defines the actor subspace in which the branch learns, while the branch-specific critic and replay state shape its value-learning trajectory. A branch-aware QD archive then evaluates and retains branches according to behavioral quality, structural footprint, and value-profile information. Experiments on MuJoCo continuous-control tasks show that SV-QD-RL constructs policy repertoires with strong archive quality and behaviorally useful diversity. Ablation and diagnostic analyses further indicate that structural conditioning, critic differentiation, and memory-consistent refinement make complementary contributions to behavioral specialization. Schedule-aware repertoire evaluation shows that the learned archive provides selectable policy alternatives under changing behavior-level requirements. These results suggest that coupling actor structure with branch-specific value learning is an effective mechanism for generating diverse QD-RL policy repertoires.

---

### IR-SIM: A Lightweight Declarative Simulator for Navigation Learning and Benchmarking

Authors: Ruihua Han, Shuai Wang, Chengyang Li, Rui Gao, Xinyi Wang, Zhe Liu, Guoliang Li, Yupu Lu, Qi Hao, Jia Pan, Hengshuang Zhao
Published: 2026-06-07
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2606.08729v2

Developing navigation policies requires simulation scenarios that support repeatable training and evaluation. Despite the availability of numerous simulators, constructing diverse navigation scenarios often involves writing simulator-specific code, using complex graphical interfaces, performing substantial manual configuration, or relying on resource-intensive computing platforms, making scenarios difficult to reproduce and reuse across experiments. To this end, we develop the Intelligent Robot Simulator (IR-SIM), a lightweight declarative simulator implemented as a Python library to support navigation learning and benchmarking through rapid construction of reusable and diverse scenarios and efficient execution on accessible platforms. IR-SIM represents scenarios as human-readable YAML configurations, in which necessary objects, behaviors, sensors, maps, and environment parameters can be flexibly specified and composed. This declarative representation makes IR-SIM friendly to large language model (LLM)-powered agents, enabling them to compose and modify executable navigation scenario files through the provided agent skills, instead of writing a large amount of code that is difficult to reuse. Despite its lightweight implementation, IR-SIM provides the essential components for navigation simulation, while retaining interfaces to high-fidelity simulators for downstream validation. Experiments demonstrate that IR-SIM runs up to several hundred times faster on the evaluated CPU platform, while agent skills reduce mean LLM-based scenario construction time by more than $50\%$ across both evaluated models. The experiments further show ability to support reproducible benchmarking and RL-based navigation policy learning.

---

### IR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking

Authors: Ruihua Han, Shuai Wang, Chengyang Li, Rui Gao, Xinyi Wang, Zhe Liu, Guoliang Li, Yupu Lu, Qi Hao, Jia Pan, Hengshuang Zhao
Published: 2026-06-07
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2606.08729v1

Simulation plays a key role in automated robotics research supported by large language models (LLMs). However, existing simulators often require custom code or complex interfaces, creating a barrier to rapid prototyping and automated algorithm development. To this end, we propose the Intelligent Robot Simulator (IR-SIM), a lightweight skill-native navigation simulator designed for rapid scenario construction, benchmarking, and robot learning. In IR-SIM, scenarios are entirely defined by YAML configuration files that specify mobile robot kinematics, geometric collision checking, LiDAR sensing, visualization, and behavior modules. This design makes robotic simulation fully describable and reproducible, allowing scenarios to be generated and modified from text prompts through the proposed IR-SIM agent skills. The resulting scenarios can be used for automated benchmarking of navigation algorithms and for automated generation of training data for learning methods. Furthermore, IR-SIM provides bridges to high fidelity simulators and real world deployment, allowing users to validate their algorithms in more realistic settings after prototyping without extra coding. The experiments showcase the convenience and versatility of IR-SIM in multiple tasks: constructing navigation scenarios from natural language, training a collision avoidance policy, benchmarking social navigation policies, and bridging to high fidelity simulators and real world deployment. The project website is available at https://github.com/hanruihua/ir-sim.

---

### Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery

Authors: Syed Rifat Raiyan, Mohsinul Kabir, Hasan Mahmud, Md Kamrul Hasan, Sophia Ananiadou
Published: 2026-06-07
Categories: cs.AI, cs.CL, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2606.08728v4

Mathematical reasoning has long served as a stringent test of machine intelligence; over the past decade, it has moved from a niche problem within NLP to one of the most consequential AI frontiers. This survey provides a unified account of the field's evolution, from early rule-based math word problem (MWP) solvers and template-driven geometry systems, through neural expression generation and LLM prompting, to contemporary reasoning models, multi-agent systems, neuro-symbolic theorem provers, and verified discovery workflows. We organize the landscape along four axes: (i) informal reasoning over text and diagrams, spanning MWP solving, multimodal geometry, and VLMs; (ii) formal reasoning in proof assistants, including autoformalization, tactic prediction, compiler-guided repair, and proof search; (iii) mathematical discovery, where systems propose constructions, improve bounds, or assist attacks on open problems; and (iv) the inference and training-time techniques, including CoT prompting, tool use, process reward models, and RLVR, that increasingly connect generation with verification. We catalog major benchmarks across grade-school arithmetic, competition mathematics, geometry, formal proving, multimodal and multilingual reasoning, and expert evaluation, and we examine benchmark saturation, contamination, reporting mismatches, and the distinction between pass@1, majority voting, and verifier-assisted pass@$k$. We critically assess failure modes: brittleness under perturbation, reward hacking, multimodal grounding failures, fragile formalization, and the energy cost of reasoning-scale inference. Drawing on recent perspectives from working mathematicians, we identify future directions centered on verified-discovery workflows, reasoning efficiency, and infrastructure to make AI-assisted formalization broadly usable. Companion materials: https://github.com/Starscream-11813/awesome-AI4Math.

---

### Compositional Approximation Can Strictly Outperform Superpositional Approximation

Authors: Dennis Elbrächter, Philipp Petersen
Published: 2026-06-07
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2606.08727v1

Many classically studied function classes are known to be approximated optimally by superpositional methods, i.e. with approximants constructed as the linear combination of elements in some dictionary. Here optimality means that the uniform approximation error viewed as a function of the number of parameters used has polynomial decay of the highest order achievable by any parametrized method whose parameters can be encoded as a bit string of length proportional, up to logarithmic factors, to the number of parameters. While compositional methods like neural networks are structurally different, their approximation rates can be made comparable by imposing constraints that ensure such a proportional bit string encoding. In this work we study function classes exhibiting structural properties that limit superpositional approximation rates to be strictly lower than compositional approximation rates. In particular, we construct explicit examples for which there is an arbitrarily large gap.

---

### Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding

Authors: Matteo Spanio, Mohammad Torabi, Andrea Poltronieri, Antonio Rodà
Published: 2026-06-07
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2606.08722v1

Symbolic music evaluation for large language models remains fragmented across representations, datasets, and metrics. We introduce LilyBench, a LilyPond-based benchmark that jointly evaluates symbolic music generation and music understanding on the same family of open-weight LLMs. The benchmark includes a 200-prompt generation suite and ten understanding tasks adapted from ABC-Eval, covering syntax, metadata prediction, structural sequencing, and music recognition. Generation quality is evaluated using compile rate, MusPy descriptor distributions via Jensen-Shannon similarity, and LilyBERT-based Fréchet Music Distance (FMD). Experiments on four open-weight models show that executable LilyPond generation is achievable in zero-shot settings, while structural understanding tasks remain challenging despite strong performance on composer and genre recognition. Our experiments also reveal systematic disagreements between descriptor-based and embedding-based metrics, suggesting that symbolic music evaluation benefits from metric triangulation rather than single-score ranking. We release the benchmark, prompt bank, and evaluation code to support future research in symbolic music generation and understanding at https://github.com/CSCPadova/lilybench

---

### Directional Linear Separability of Neural Representations: Geometry and Transformations

Authors: Yi Wei, Xuan Qi, Suorong Yang, Furao Shen
Published: 2026-06-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.08721v2

Neural networks build representations through affine maps and nonlinear activations. Injective affine maps preserve linear separability, raising the problem of how they prepare data for nonlinear improvement and how much gain can be guaranteed before complete separation. We introduce the directional linear separability measure (D-LSM), which quantifies unavoidable competing-sample intrusion over affine halfspaces retaining every target sample, characterize its supporting geometry, and prove invariance under injective affine embeddings. For gated activations including ReLU, GELU, and SiLU, pre-activation projection bounds yield sufficient conditions for preserving all previous exclusions and recovering additional samples, with a gain bound determined by the certified recovery count. Under an aggregate-tube condition, an explicit affine construction realizes recovery with sufficient width, scaling conditions, and simultaneous multiclass guarantees through a shared layer. Exact controlled experiments compare certified and realized gains, assess certificate coverage, and exhibit bound attainment before complete separation and in affine-tube constructions. In learned Vision Transformer (ViT) representations, a feasible lower-bound estimator yields earlier post-GELU saturation certificates of exact separability, while boundary transport numerically supports affine invariance.

---

### A Geometric Measure of Linear Separability for Neural Representations

Authors: Yi Wei, Xuan Qi, Furao Shen
Published: 2026-06-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.08721v1

Modern neural classifiers commonly rely on linear readouts, yet predictive metrics alone do not characterize the class-wise geometry of the representations on which such readouts operate. We introduce the directional linear separability measure (LSM), a finite-sample diagnostic for one-sided affine separability. For a target class A and a competing set B, LSM searches over affine halfspaces that contain all samples in A and measures the smallest competing-sample intrusion that must remain on the target side, normalized by |A|. The resulting quantity is asymmetric, class-wise, target-normalized, and applicable to finite representations extracted from neural networks. We establish its supporting-hyperplane characterization, relate it to optimal affine classification accuracy, and prove invariance under full-rank linear embeddings. These results separate changes caused by linear reparameterization from those caused by information loss or nonlinear geometric transformations. We also give a penalty-based affine search for estimating class-wise LSM in high-dimensional features, with reported values computed from the original discrete preservation and violation criterion. Finally, we analyze coordinatewise gated nonlinearities as finite-sample geometric operators and empirically use LSM to diagnose class-wise intrusion across common deep-learning components and architectures.

---

### Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation

Authors: Yishuo Cai, Jiahui Liu, Yuanxin Liu, Haobo Deng, Linli Yao, Yuhao Zheng, Kun Ouyang, Zhimo Li, Ziyue Wang, Xu Sun, Haoli Bai, Xiaohui Li
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08719v1

''Thinking with Images'' has emerged as an effective paradigm for fine-grained visual reasoning: by explicitly zooming into relevant regions and reasoning over crops, models can access local evidence that is difficult to recover from a single global image. However, this benefit comes with redundant tool invocations and longer inference traces. Moreover, when such behaviors are learned mainly from outcome reward, the resulting intermediate crops or visual cues can be noisy or fail to faithfully capture task-relevant visual evidence. In this work, we ask whether the reasoning benefits of ''Thinking with Images'' can be internalized through Thinking with Imagination: an internal process that decides where to look and imagines what visual cues closer inspection would reveal without actually invoking tools. We propose Imagine-OPD, an on-policy self-distillation framework in which a teacher plays the role of a ''Thinking with Images'' reasoner during training: it receives privileged zoomed evidence views derived from annotated regions, and supervises the model's own imagination reasoning trajectories. Imagine-OPD does not require an external teacher or high-quality imagination demonstrations. Experiments on vision-centric benchmarks show that Imagine-OPD achieves the best average performance among compared models while significantly reducing inference overhead compared with ''Thinking with Images'' methods.

---

### Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency

Authors: Md Abdullah Al Forhad, Weishi Shi
Published: 2026-06-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.08718v1

While Deep Active Learning (DAL) effectively reduces human annotation costs, its efficacy is constrained by human annotation errors. This is because the data sampled for active learning is assumed to be highly informative for training. When human annotators introduce errors into this informative data at a certain rate, the active learning performance drops significantly and, in some cases, even exhibits worse outcomes than passive learning. In this paper, we first analyze the impact of human annotation errors in the DAL setting. Then we propose a framework to address the human annotation noise problem for DAL. Informed by human learning patterns, the core idea of our proposed solution involves allocating a portion of the human annotation budget to re-annotate data that has already been labeled. Previous theoretical work suggests that when the model possesses a certain level of ability to identify potentially noisy data, even re-labeling a small fraction of the data can effectively remove noise from the active training set. To achieve this, we implement two active noise sampling strategies to detect noise under different circumstances and allocate a part of the annotation budget to re-annotate these instances. Our approach imbues active learning with a revisiting and introspective behavior. Our experiments demonstrate that, under the same annotation budget, our method is more data-efficient and yields a relatively noise-free annotation dataset in the end.

---

### Operationalizing Linguistic Methods through Prompt-Engineering Skills: An Automatic Chinese Web Neologism Detection Pipeline

Authors: Yufeng Wu, Meichun Liu
Published: 2026-06-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.08715v1

We present a method for automatic Chinese web neologism detection that operationalizes traditional linguistic identification principles as prompt-engineering skills. The method has four stages: tokenizer-independent character n-gram candidate generation; dictionary anchoring with a Pointwise Mutual Information pre-filter; a well-formedness skill based on Chinese word-formation principles; and a combined rule and three-way classification skill that distinguishes neologism, entity, and none. Applied to the BAAI CCI 3.0 corpus (267M documents), the method produces 226,959 classified candidates including 4,853 labeled neologisms. To evaluate the method, we develop a per-stage conditional recall decomposition in which the pipeline's strict recall factors mathematically into the product of stage conditional recalls. Applied to Hou (2023) (4,199 entries), the decomposition exposes Stage 1 candidate coverage and Stage 4B LLM semantic judgment as the two bottlenecks (R=41.5% and 60.0% respectively), while intermediate stages are near-lossless. A length-stratified analysis further reveals that the structural well-formedness skill is length-invariant (>= 96.9%) whereas the semantic novelty-classification skill is length-dependent (65.6%/59.0%/44.1% across 2/3/4-character candidates), mapping a current boundary of skill-based linguistic operationalization. We release the method, pipeline outputs, and evaluation protocol as public resources.

---

### Hybrid Neural Network and Conventional Controller Approach for Robust Control of Highly Unstable Systems: Application to Tilt-Rotor Control

Authors: Ali Kafili Gavgani, Amin Talaeizadeh, Aria Alasty, Hossein Nejat Pishkenari
Published: 2026-06-07
Categories: eess.SY, cs.AI, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2606.08714v1

Multirotors are widely used in applications ranging from surveillance to precision agriculture, yet conventional designs remain limited by their under-actuation. Tilt-rotor configurations overcome this limitation by enabling full actuation. This paper investigates neural-network-based control strategies for a fully actuated tilt-rotor system with four thrust-vectoring inputs. Our work is structured in two parts. First, we deliberately present a negative result by evaluating a direct input-output control approach. In this method, multilayer perceptrons (MLPs), long short-term memory (LSTM) networks, and transformer models are trained to map system states and their desired values directly to control signals. We show that this strategy fails to stabilize the system, highlighting the inherent difficulty of applying direct input-output learning to highly unstable plants. Second, as the main contribution, we propose a neural-network-enhanced sliding mode controller (SMC). The method decomposes the system dynamics into input-independent and input-dependent components, with the former learned from a small dataset using lightweight networks, thereby reducing real-time computational demands. Moreover, the proposed method can be trained using flight logs collected from low-performance controllers, and the resulting dynamic model learned from real-world data can be used in simulation. We further compare MLP- and LSTM-based implementations under model uncertainties and external disturbances, demonstrating the robustness and effectiveness of the proposed approach; in particular, the controller with the LSTM plant dynamics predictor achieves superior performance to its MLP-based counterpart while also exhibiting lower runtime.

---

### SNR-ST-Mix: Sample-specific Neighborhood Regression Mixup for Augmented Spatial Transcriptomics Imputation with Deep Neural Network

Authors: Hongyi Yu, Yaoyu Fang, Jiahe Qian, Xinkun Wang, Lee A. Cooper, Bo Zhou
Published: 2026-06-07
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2606.08712v1

Purpose: Spatial transcriptomics (ST) enables gene expression measurements within the tissue context. However, these measurements are often noisy, low-resolution, and sparsely sampled, which limits the recovery of fine spatial structure. Deep neural networks have become powerful tools for expression imputation from histology, but their performance remains constrained by limited sample sizes and a lack of biologically informed augmentation. Most of the existing augmentation strategies for learning are designed for classification tasks rather than regression, which neglect spatial and transcriptomic relationships, leading to biologically implausible interpolations that hinder prediction performance. Approach: To address these limitations, we propose SNR-ST-Mix, a geometry- and expression-aware data augmentation framework designed specifically for ST data. It constrains mixing to a spot's k-nearest spatial neighbors and adaptively weights interpolation coefficients based on expression similarity, generating augmented samples that preserve local biological structure while ensuring spatial smoothness. This dual conditioning yields synthetic examples that expand the effective training manifold, promote generalization, and enhance prediction stability under sample-specific training. Results: Extensive experiments with various tissue types demonstrate that SNR-ST-Mix consistently outperforms conventional augmentation methods without requiring architectural changes or additional computation. Conclusions: SNR-ST-Mix provides an effective and biologically principled augmentation strategy for spatial transcriptomics regression tasks. By explicitly leveraging spatial geometry and transcriptomic similarity, it expands the effective training manifold and improves predictive performance without increasing model complexity.

---

### Structuring agentic AI for HPC code modernization

Authors: Anthony Marinov, Igor Sfiligoi
Published: 2026-06-07
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2606.08710v1

Modernization of legacy scientific codes is often necessary to keep up with the ever-evolving changes in the compute resource ecosystem. Parallelization and migration from poorly supported software ecosystems are two of the most time-consuming activities in the research software engineering field. This paper presents our experience in the successful, two-phase AI-assisted modernization of NMAP-RKPM, a roughly 60,000-line, 3D explicit solid mechanics physics engine based on the Reproducing Kernel Particle Method (RKPM). We converted this single-threaded, Fortran based MPI application into a OpenMP-parallel C++ based MPI tool in the span of a few months. While Large Language Model (LLM) based tools on their own proved inadequate, we developed a highly structured "hand-holding" agentic AI methodology, like providing manually created examples, ensuring continuous buildability and limiting session scope, that was instead highly effective. The paper provides both the AI-assisted steps that were successful and the problems that we had to overcome, alongside the reasoning behind the chosen path.

---

### PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping

Authors: Qiming Li, Tianlun Li, Xiaolong Cheng, Hangyu Li, Ruiyan Gong, Kangning Niu, Kaitao Jiang, Mu Xu
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08708v1

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective paradigm for improving the reasoning capability of Large Vision-Language Models (LVLMs). However, existing RLVR methods primarily rely on trajectory-level outcome rewards, which assign identical learning signals across all generated tokens. This coarse-grained credit assignment is fundamentally mismatched to multimodal reasoning, where only a sparse subset of tokens is causally grounded in visual evidence. Consequently, these pivotal perceptual tokens receive weak supervision and are often overwhelmed by language priors or reasoning-template tokens. To address this limitation, we propose Perception-Reinforced Policy Optimization (PRPO), a token-level reinforcement learning framework that explicitly identifies and reinforces pivotal perceptual tokens within long-horizon multimodal reasoning trajectories. PRPO introduces Robust Visual Dependency (RVD), a principled metric that identifies tokens whose predictions are both visually grounded and perturbation-stable, filtering out brittle or noisy visual tokens. Based on RVD, we further propose Perceptual Advantage Reshaping (PAR), a token-level credit assignment technique that amplifies perceptually informative tokens while preserving stable gradients for non-perceptual tokens. Extensive experiments on seven multimodal reasoning benchmarks demonstrate that PRPO consistently outperforms strong LVLM baselines across both 3B and 7B model scales, achieving average gains of 23.3% and 21.1%, respectively. PRPO achieves state-of-the-art performance with improved training efficiency and stronger cross-task generalization. Our findings highlight the importance of fine-grained credit assignment for scalable multimodal reinforcement learning.

---

### Analyzing the Correlation Between Hallucinations and Knowledge Conflicts in Large Language Models

Authors: Lucrezia Laraspata, Giovanna Castellano, Gennaro Vessio
Published: 2026-06-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.08705v1

Hallucinations -- factually incorrect or unverifiable outputs -- remain one of the most challenging limitations of Large Language Models (LLMs), especially in knowledge-intensive tasks. One proposed explanation is internal knowledge conflicts arising from fixed, outdated training data. This paper investigates whether internal representations linked to knowledge conflicts correlate with hallucination behaviors in LLMs. Using probing techniques inspired by two prior works, we analyzed activations from hidden, attention, and MLP layers, as well as output logits, across predefined tasks. We probed LLaMA-3-8B on hallucination detection benchmarks and Falcon-7B on a knowledge conflict dataset. Our findings show that, although conceptually related, hallucination activation patterns cannot be fully reduced to or explained by knowledge conflict representations. Nonetheless, probing proves a robust tool across multiple languages and activation types, supporting its role in improving LLM interpretability. This work advances the broader understanding of hallucinations in LLMs and underscores the value of fine-grained analysis of their internal behavior.

---

### ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems

Authors: Zhixun Tan, Qiang Chen, Tairan Huang, Xiu Su, Yi Chen
Published: 2026-06-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.08702v1

Recent advances have improved the adaptive capabilities of LLM-based multi-agent systems (MAS) through memory-, skill-, and learning-based approaches, yet these approaches remain challenged by noisy trajectories, insufficient modeling of memory-skill relations, and reliance on additional training or high-quality supervision. To address these limitations, we propose ConMem, a relation-aware and training-free framework that enables efficient multi-agent adaptation through cross-experience coordination. Specifically, ConMem distills historical interaction trajectories into structured memory cards to capture reusable strategies and cues, organizing them into a relation-aware memory graph. At runtime, ConMem retrieves cards according to task needs and coordinates them through the card graph to resolve strategy conflicts and recover their dependencies. Combined, these modules yield structured and relation-aware guidance, enabling robust, lightweight adaptation in multi-agent systems without additional training. Extensive experiments across multiple benchmarks and mainstream MAS architectures show consistent gains over existing memory architectures, with improved inference-time efficiency through pruning more than 50% of expanded candidates and reducing planning overhead by over 80%. Our codes are available at https://anonymous.4open.science/r/ConMemCode

---

### Agentic Search for Counterfactual Recourse under Fixed LLM Budgets

Authors: Yasuo Tabei
Published: 2026-06-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.08696v2

Counterfactual recourse aims to provide actionable feature changes that would alter an unfavorable decision made by a predictive model. In practice, affected individuals often benefit from multiple feasible alternatives rather than a single optimal explanation. A natural way to produce such alternatives is to prompt large language models (LLMs). However, prompting incurs a practical constraint: the number of LLM calls is often the dominant computational and economic cost. Together, the need for multiple alternatives and this cost constraint shift the problem from finding a single high-quality counterfactual to efficiently generating a set of oracle-validated counterfactuals under a fixed LLM-call budget. In this work, we study counterfactual recourse generation in the LLM-agentic setting as a fixed-budget search problem and propose Recourse Monte Carlo Tree Search (ReCo-MCTS), an agentic tree-search framework that aims to increase the yield of unique, oracle-validated counterfactuals under this budget while accounting for the extent of the required changes. ReCo-MCTS combines LLM-based multi-candidate generation, constraint checking, black-box oracle evaluation, and UCT-guided tree search to accumulate valid counterfactuals under a fixed LLM-call budget. On four real-world tabular datasets, ReCo-MCTS returns more counterfactuals than the evaluated baselines in our main comparison under the specified resource limits, with trade-offs in the extent of the required changes.

---

### Agentic Search for Counterfactual Recourse under Fixed LLM Budgets

Authors: Yasuo Tabei
Published: 2026-06-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.08696v1

Counterfactual recourse aims to provide actionable feature changes that would alter an unfavorable decision made by a predictive model. In practice, affected individuals often benefit from multiple feasible alternatives rather than a single optimal explanation. A natural way to produce such alternatives is to prompt large language models (LLMs). However, prompting incurs a practical constraint: the number of LLM calls is often the dominant computational and economic cost. Together, the need for multiple alternatives and this cost constraint shift the problem from finding a single high-quality counterfactual to efficiently generating a set of oracle-validated counterfactuals under a fixed LLM-call budget. In this work, we study counterfactual recourse generation in the LLM-agentic setting as a fixed-budget search problem and propose Comp-MCTS, an agentic tree-search framework that maximizes the yield of unique, oracle-validated counterfactuals under this budget while maintaining favorable quantity--quality trade-offs. Comp-MCTS allocates the budget toward novel intervention directions via LLM-based proposal generation, oracle validation, and compression-guided pruning, in a training-free, oracle-only setting. Experiments on four real-world tabular datasets show that Comp-MCTS substantially outperforms single-candidate LATS-style baselines in the yield of unique, oracle-validated counterfactuals, and offers favorable quantity--quality--efficiency trade-offs against stronger multi-candidate variants: comparable or higher yield at similar or lower oracle-evaluation cost on three of four datasets, plus competitive proximity, sparsity, and novelty.

---

### Discovering and decoding latent mean-field structure with variational autoencoders

Authors: Marco Biroli, Max Welling, Vincenzo Vitelli
Published: 2026-06-07
Categories: cond-mat.soft, cond-mat.stat-mech, cs.LG
arXiv: https://arxiv.org/abs/2606.08694v1

Generative models are increasingly used to capture correlations in many-body systems, but the representations they learn remain largely opaque to physical interpretation. Here, we establish an intuitive criterion that quantifies the capacity of a variational autoencoder (VAE) to faithfully reconstruct the joint probability distribution of a many body system. In a nutshell, a bound on the VAE capacity is obtained by comparing the rate of the latent channel to the bipartite mutual information of the data. Using this bound, we show that the conditionally independent decoder of any successful VAE is structurally identical to a finite-size mean-field factorization. Hence, a successful reconstruction is direct evidence for a latent mean-field theory and the microscopic parameters of that theory can be read off the trained decoder. We validate these conclusions on a hierarchy of solvable models with scalar (Curie-Weiss), vector (Hopfield) and tensor (Maier-Saupe) order parameters, recovering the full Hopfield pattern matrix from equilibrium samples alone. We find that, when applied to Salamander retinal recordings, a two-latent VAE reproduces the population statistics with only two effective collective variables allowing us to recover the `stored patterns' of the neural population and write a generalized Hopfield model which correctly models the experimental data.

---

### Hierarchical Projection for Adaptive Knowledge Transfer

Authors: Samhita Pal, Tian Gu
Published: 2026-06-07
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2606.08691v2

Modern data-driven applications increasingly involve learning from multiple heterogeneous sources, where a target dataset is limited but related information is available across domains. Naively combining these sources can degrade performance when relevance varies or spurious signals are present, posing a fundamental challenge for trustworthy cross-domain learning. We propose Projection Transfer Learning (ProjectionTL), a unified framework that integrates hierarchical Bayesian modeling with adaptive projection for selective knowledge transfer. The key idea is to decouple transfer at two levels: first, we construct a source-guided hierarchical prior that aggregates information across sources using data-driven weights, capturing global alignment between each source and the target; second, we refine this borrowing through a posterior-projection step that operates at the feature level, selectively retaining coordinates that exhibit local agreement with the target signal. This two-stage design enables the method to simultaneously perform source selection and feature selection, thereby mitigating negative transfer while preserving interpretability. ProjectionTL provides a principled approach to integrating heterogeneous data across domains, bridging statistical modeling and modern machine learning paradigms for robust and interpretable transfer. Through simulations and real-world biomedical applications, we demonstrate improved accuracy, stability, and interpretability compared to existing methods. Our framework offers a scalable and generalizable strategy for trustworthy cross-domain learning in high-dimensional settings.

---

### PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback

Authors: Chunji Lv, Jiaxi Ye, Yuchen Jiang, Rexar Lin, Changsheng Li
Published: 2026-06-07
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2606.08688v1

Achieving fully automated, physically plausible 3D motion synthesis is a core objective in graphics and generative AI. However, configuring complex environmental force fields still relies entirely on manual expert intervention, creating a severe bottleneck for large-scale simulation data generation. Existing automated methods primarily focus on material optimization and exhibit severe modality gaps and technical flaws when applied to the vastly more complex force field optimization space: naive Large Language Models (LLMs) lack underlying simulation feedback, causing severe physical inaccuracies, while traditional Score Distillation Sampling (SDS) suffers from sluggish gradients, local optima entrapment, and a mathematical inability to dynamically switch discrete force fields. To address this, we propose PhysAgent, the first simulator-in-the-loop multi-agent framework that leverages multimodal inputs for automated, physically grounded 4D synthesis. By decoupling intrinsic materials from extrinsic dynamics, PhysAgent utilizes a Semantic Agent equipped with an externalized Force Field Skill module to master simulation rules and generate valid initializations. Subsequently, the Refine Agents, driven by Trajectory-Grounded Multi-Agent Feedback, leverage vision foundation models to extract dense point trajectories from rendered frames. By converting these explicit motion trajectories into structured textual descriptors, the agent harnesses LLM commonsense reasoning to execute zero-shot macroscopic leaps, effectively escaping local optima and dynamically switching discrete force fields. Extensive experiments demonstrate that PhysAgent rapidly generates stable, diverse physical scenes from arbitrary multimodal prompts, significantly outperforming existing baselines in both generation diversity and physical accuracy.

---

### Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation

Authors: Xingyue Zhao, Wenke Huang, Linghao Zhuang, Haoran Wu, Anwen Jiang, Zhifeng Wang, Wenwen He, Ming Feng, Mang Ye, Bo Xu
Published: 2026-06-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.08687v1

Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of segmentation foundation models for medical imaging. However, most federated LoRA methods adopt a uniform aggregation rule, which breaks under the encoder-decoder asymmetry in medical segmentation: the encoder is dominated by appearance shifts, while the decoder is dominated by supervision variations. This mismatch entangles shared anatomy with site-specific biases and harms generalization. To address this, we propose Inverse Asymmetric Tuning (IAT). IAT aligns adaptation with heterogeneity sources by personalizing module-specific components in the encoder to absorb appearance shifts and in the decoder to accommodate site-dependent supervision, while retaining a shared pathway for transferable consensus. However, structural separation alone is insufficient under LoRA's bilinear parameterization, where multiplicative coupling can still cause site-specific updates to leak into the shared direction. We therefore introduce a Subspace Orthogonality Regularizer that penalizes shared-local collinearity in the effective update space, mitigating leakage without extra communication. Experiments show consistent improvements over strong federated LoRA and parameter-efficient FL baselines.

---