# Research Papers — 2026-05 · bundle page 286 of 326

> Full-text markdown of papers #14251–14300 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-05/page/286
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/285.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/287.md)

### CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels

Authors: Xing Ma, Yangjie Zhou, Wu Sun, Zihan Liu, Jingwen Leng, Yun Lin, Shixuan Sun, Minyi Guo, Jin Song Dong
Published: 2026-05-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.05023v1

Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Existing frameworks and compilers trade performance for flexibility, while expert-written kernels achieve high efficiency but are difficult to adapt. Recent work explores large language models (LLMs) for GPU kernel generation, but prior studies report unstable correctness and significant performance gaps for complex operators such as attention. We present CuBridge, an LLM-based framework that adapts expert-written attention kernels through a structured lift-transfer-lower workflow. CuBridge starts from expert-written CUDA attention kernels and lifts them into an executable intermediate representation that makes execution orchestration explicit while abstracting low-level CUDA syntax. Given a user-provided PyTorch specification, CuBridge generates and verifies a target IR program, then reconstructs optimized CUDA code via reference-guided lowering. Across diverse attention variants and GPU platforms, CuBridge consistently produces correct kernels and substantially outperforms general frameworks, compiler-based approaches, and prior LLM-based methods.

---

### Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning

Authors: Shawn Ray
Published: 2026-05-06
Categories: cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2605.05020v1

System Neural Diversity (SND) measures behavioral heterogeneity in multi-agent reinforcement learning by averaging pairwise distances over all $\binom{n}{2}$ agent pairs, making each call quadratic in team size. We introduce Graph-SND, which replaces this complete-graph average with a weighted average over the edges of an arbitrary graph $G$. Three regimes follow: $G=K_n$ recovers SND exactly; a fixed sparse $G$ defines a localized diversity measure at $O(|E|)$ cost; and random edge samples yield an unbiased Horvitz-Thompson estimator and a normalized sample mean with $O(1/\sqrt{m})$ concentration in the sampled edge count $m$. For fixed sparse graphs we prove forwarding-index distortion bounds for expanders and a spectral refinement under low-rank distance structure; for random $d$-regular graphs we prove an unconditional probabilistic $\widetilde{\mathcal{O}}(D_{\max}/\sqrt{n})$ bound. On VMAS we verify recovery, unbiasedness, concentration, and wall-clock scaling, with a PettingZoo TVD panel checking non-Gaussian transfer. In a 500-iteration $n=100$ PPO run, Bernoulli-$0.1$ Graph-SND tracks full SND while reducing per-call metric time by about $10\times$, and frozen-policy GPU timing up to $n=500$ follows the predicted $\binom{n}{2}/|E|$ speedup. Random $d$-regular expanders empirically achieve $\mathrm{SND}_{G}^{\mathrm{u}}/\mathrm{SND} \in (0.9987, 1.0013)$ at $Θ(n \log n)$ edges. In DiCo diversity control at $n=50$, Bernoulli-$0.1$ Graph-SND preserves set-point tracking with paired reward differences indistinguishable from zero across nine matched cells while cutting per-call metric cost by ${\sim}9.5\times$. Together, these results show that the SND aggregation bottleneck can be removed without changing the metric's semantics, yielding a drop-in sparse alternative that scales beyond complete-graph SND and supports both passive measurement and closed-loop diversity control.

---

### Position: Embodied AI Requires a Privacy-Utility Trade-off

Authors: Xiaoliang Fan, Jiarui Chen, Zhuodong Liu, Ziqi Yang, Peixuan Xu, Ruimin Shen, Junhui Liu, Jianzhong Qi, Cheng Wang
Published: 2026-05-06
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2605.05017v1

Embodied AI (EAI) systems are rapidly transitioning from simulations into real-world domestic and other sensitive environments. However, recent EAI solutions have largely demonstrated advancements within isolated stages such as instruction, perception, planning and interaction, without considering their coupled privacy implications in high-frequency deployments where privacy leakage is often irreversible. This position paper argues that optimizing these components independently creates a systemic privacy crisis when deployed in sensitive settings, thereby advancing the position that privacy in EAI is a life cycle-level architectural constraint rather than a stage-local feature. To address these challenges, we propose Secure Privacy Integration in Next-generation Embodied AI (SPINE), a unified privacy-aware framework that treats privacy as a dynamic control signal governing cross-stage coupling throughout the entire EAI life cycle. SPINE decomposes the EAI pipeline into various stages and establishes a multi-criterion privacy classification matrix to orchestrate contextual sensitivity across stage boundaries. We conduct preliminary simulation and real-world case studies to conceptually validate how privacy constraints propagate downstream to reshape system behavior, illustrating the insufficiency of fragmented privacy patches and motivating future research directions into secure yet functional embodied AI systems. We detail the SPINE framework and case studies at https://github.com/rminshen03/EAI_Privacy_Position.

---

### CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography

Authors: Gasser Elazab, Frank Neuhaus, Tilman Koß, Malte Splietker, Aditya Date, Michael Unterreiner, Maximilian Jansen, Olaf Hellwich
Published: 2026-05-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.05014v2

Autonomous driving must operate across diverse surfaces to enable safe mobility. However, most driving datasets are captured on well-paved flat roads. Moreover, recent driving datasets primarily provide sparse LiDAR ground truth for images, which is insufficient for assessing fine-grained geometry in depth estimation and completion. To address these gaps, we introduce CARD, a multi-modal driving dataset that delivers quasi-dense 3D ground truth across continuous sequences rich in speed bumps, potholes, irregular surfaces and off-road segments. Our sensor suite includes synchronized global-shutter stereo cameras, front and rear LiDARs, 6-DoF poses from LiDAR-inertial odometry, per-wheel motion traces, and full calibration. Notably, our multi-LiDAR fusion yields ~500K valid depth pixels per frame, about 6.5x more than KITTI Depth Completion and 10x more on average than other public driving datasets. The dataset spans ~110 km and 4.7 hours across Germany and Italy. In addition, CARD provides 2D bounding boxes targeting road-topography irregularities, enabling accurate benchmarking for both geometry and perception tasks. Furthermore, we establish a standardized evaluation protocol for road surface irregularities on CARD and benchmark state-of-the-art depth estimation models to provide strong baselines. The CARD dataset is hosted on https://huggingface.co/CARD-Data.

---

### Chaotic Contrastive Learning for Robust Texture Classification

Authors: Joao B Florindo
Published: 2026-05-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.05012v1

Texture classification is a pivotal task in computer vision, presenting unique challenges due to high inter-class similarity and the sensitivity of structural patterns to scale and illumination changes. While Convolutional Neural Networks (CNNs) and recent Vision Transformers have set performance benchmarks, they often require extensive labeled datasets or struggle to generalize across domains due to an over-reliance on color and shape features. This paper introduces a novel framework that synergizes Self-Supervised Learning (SSL) with deterministic chaotic dynamics. We propose a chaotic contrastive pre-training strategy, where pixel-wise chaotic maps, specifically Logistic, Tent, and Sine maps, act as non-linear data augmentation techniques. These chaotic perturbations, grounded in ergodic theory, force the network to learn topologically robust features by mimicking complex environmental noise and reflectance variations. Furthermore, we introduce an attention-based feature ensemble that fuses high-level semantic representations from a supervised large backbone with low-frequency structural features from a chaos-pretrained tiny encoder. Experimental results on six texture benchmarks (FMD, UMD, KTH-TIPS2-b, DTD, GTOS, and 1200Tex) demonstrate the superiority of the proposed method, outperforming state-of-the-art approaches and achieving promising accuracies on all the analyzed datasets.

---

### Learned Neighbor Trust for Collaborative Deployment in Model-Agnostic Decentralized Learning

Authors: Michael Lanier, Luise Ge, Sastry Kompella, Yevgeniy Vorobeychik
Published: 2026-05-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.05009v1

Many decentralized distillation methods are designed around training-time coordination, yet deploy each node in isolation even when more capable neighbors remain available at inference time. This is an incomplete objective for settings such as IoT, where devices are heterogeneous, data is scarce and skewed, and a node's strongest neighbors may far exceed its own local capacity. We study how nodes should train so that their predictions compose well at deployment, and how each node should learn whom to trust. Under a server-free, model-agnostic protocol where nodes exchange only queries and soft predictions, we propose Learned Neighbor Trust (LNTrust) wherein each node learns a compact trust function over its neighborhood from local validation evidence. This trust function gates auxiliary distillation during training and defines a deployment ensemble at inference, so that collaboration learned during training transfers directly to deployment. Across datasets and topologies, LNTrust improves deployed accuracy over the strongest output-only baseline by large margins while using significantly less communication than previous methods.

---

### Scalable inference of spatial regions and temporal signatures from time series

Authors: Jiayu Weng, Alec Kirkley
Published: 2026-05-06
Categories: stat.ML, cs.LG, cs.SI, physics.soc-ph
arXiv: https://arxiv.org/abs/2605.05008v1

Regionalization aims to partition a spatial domain into contiguous regions that share similar characteristics, enabling more effective spatial analysis, policy making, and resource management. Existing approaches for spatial regionalization typically rely on static spatial snapshots rather than evolving time series. Meanwhile, most time series clustering methods ignore spatial structure or enforce spatial continuity through ad hoc regularization, constraining the number of inferred regions a priori either explicitly or implicitly. Utilizing the minimum description length principle from information theory, here we propose an efficient and fully nonparametric framework for the regionalization of spatial time series. Our method jointly infers a spatial partition along with a set of representative time series archetypes ("drivers") that best compress a spatiotemporal dataset, with a runtime log-linear in the number of time series. We demonstrate that this method can accurately recover planted regional structure and drivers in synthetic time series, and can extract meaningful structural regularities in large-scale empirical air quality and vegetation index records. Our method provides a principled and scalable framework for spatially contiguous partitioning, allowing interpretable temporal patterns and homogeneous regions to emerge directly from the data itself.

---

### Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation

Authors: Zhiqing Cui, Haotong Xie, Jiahao Yuan, Cheng Yang, Hanqing Wang, Yuxin Wu, Yifan Wu, Siru Zhong, Tao Yu, Yifu Guo, Siyu Zhang, Xinlei Yu et al.
Published: 2026-05-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.05007v1

Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so decomposition depth, worker choice, and inference budget are not jointly optimized under one objective. We introduce Uno-Orchestra, a unified orchestration policy that selectively decomposes a task and dispatches each subtask to an admissible (model, primitive) pair, with both decisions learned together from curated RL trajectories grounded in real worker interactions. Against 22 baselines on a 13-benchmark suite spanning math, code, knowledge, long-context, and agentic tool-use, Uno-Orchestra reaches 77.0% macro pass@1, roughly 16% above the strongest workflow baseline, at roughly an order of magnitude lower per-query cost, advancing the accuracy-efficiency frontier of selective delegation.

---

### Misaligned by Reward: Socially Undesirable Preferences in LLMs

Authors: Gayane Ghazaryan, Esra Dönmez
Published: 2026-05-06
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2605.05003v1

Reward models are a key component of large language model alignment, serving as proxies for human preferences during training. However, existing evaluations focus primarily on broad instruction-following benchmarks, providing limited insight into whether these models capture socially desirable preferences. As a result, important failures in social alignment can remain hidden. We extend reward-model benchmarking to four socially consequential domains: bias, safety, morality, and ethical reasoning. We introduce a framework that converts social evaluation datasets into pairwise preference data, leveraging gold labels where available and directional bias indicators otherwise. This enables us to test whether reward models prefer socially undesirable responses, and whether their preferences produce systematically biased distributions over selected outputs. Across five publicly available reward models and two instruction-tuned models used as reward proxies, we find substantial variation across domains, with no single model performing best overall. The models fall well short of strong social intelligence: they often prefer socially undesirable options, and their preferences produce systematically biased distributions. Moreover, stronger bias avoidance can reduce sensitivity to context, revealing a key alignment trade-off between avoiding biased outcomes and preserving contextual faithfulness. These findings show that standard reward benchmarks are insufficient for assessing social alignment and highlight the need for evaluations that directly measure the social preferences encoded in reward models.

---

### Agentic Vulnerability Reasoning on COTS Binaries

Authors: Hwiwon Lee, Jongseong Kim, Lingming Zhang
Published: 2026-05-06
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2605.05000v2

LLM agents have been increasingly adopted for solving security tasks. However, existing evaluations usually require source code access, while commercial off-the-shelf (COTS) binaries dominate deployed software and require reasoning from stripped, optimized machine code. This discrepancy raises an important question: can modern LLM agents reason about vulnerabilities in critical COTS binaries? Motivated by this question, we build SLYP, a REACT-style pipeline for end-to-end vulnerability discovery and validation of COTS binaries. SLYP combines extensible MCP servers for binary exploration and dynamic debugging, and validates candidate vulnerabilities by synthesizing debugger-verified proof-of-concept (PoC) crashes. We evaluate SLYP and production coding agents, including Claude Code and Codex, on COTS Windows binaries centered on a 20-object COM benchmark. SLYP uncovers all 64 vulnerable entry functions while default production agents miss up to 15; SLYP also surfaces more true vulnerabilities than the state-of-the-art static analyzer, which discovers at most 35 with a large number of false positives. For validation, SLYP generates debugger-verified PoCs for 67.5% of cases, while default production agents generate none. Further ablations show that tool sets and model choice materially affect COTS binary reasoning. Our additional evaluation also demonstrates the generalizability of SLYP on Windows kernel targets. To date, SLYP has uncovered 39 zero-day vulnerabilities, 31 in COM/RPC services and 8 in kernel drivers, all disclosed to the Microsoft Security Response Center (MSRC), with 23 assigned CVEs and $203,000 bounty awards.

---

### Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation

Authors: Jinju Lee
Published: 2026-05-06
Categories: cs.SD, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2605.04998v3

This revision updates a pop-to-jazz chord-generation rehearsal study. Best-epoch metrics still show that modest pop rehearsal preserves pop accuracy while improving jazz prediction, but v2 corrects released-checkpoint selection: the released F1 equals Phase 0, F2 had a transcription error, and ft-pop80-v2 restores a hash-distinct jazz-adapted F1 across 3 seeds.

---

### DualTCN: A Physics-Constrained Temporal Convolutional Network for 2 Time-Domain Marine CSEM Inversion

Authors: Khaled Ahmed, Ghada Omar
Published: 2026-05-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.04997v1

DualTCN is the first deep-learning framework for inverting time-domain marine controlled-source electromagnetic (MCSEM) transient data. Moving away from traditional subsurface discretization, the framework regresses four earth-model parameters -- $σ_1$, $σ_2$, $d_1$, $d_2$ -- and reconstructs conductivity-depth profiles using a differentiable soft-step decoder. The optimized architecture (379K parameters) features a Temporal Convolutional Network (TCN) encoder paired with a late-time branch and an auxiliary seafloor-depth head. This design achieves a 25.3\% loss reduction over baseline models, with high predictive accuracy ($R^2 = 0.898$ for $σ_2$) and an inversion speed of 3.5~ms per sample on an A100 GPU. The framework demonstrates high robustness to noise through curriculum-based amplitude augmentation, maintaining a mean $\bar{R}^2$ of 0.858 at $\pm2\%$ random amplitude error, compared to $0.363$ without augmentation. DualTCN generalizes effectively to three-layer extensions (seawater/resistive layer/basement), accurately resolving basement conductivity ($R^2 \approx 0.88$), though thin-layer resolution remains a physical limitation ($R^2 \approx 0.23$). In comparative benchmarks, DualTCN significantly outperforms traditional local optimization methods like Levenberg-Marquardt and L-BFGS-B, yielding a mean $\bar{R}^2 = 0.877$ versus 0.129-0.439 for multi-start baselines, while operating at up to 21,000$\times$ lower computational cost. Finally, the framework incorporates uncertainty quantification via Monte Carlo (MC) Dropout. While well-calibrated for $σ_1$ (PICP90 = 0.944), inherent signal limitations at short offsets (200m) lead to under-coverage for $d_2$ (PICP90 = 0.572), which can be mitigated through post-hoc temperature scaling or split conformal prediction.

---

### Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning

Authors: Anastasis Kratsios, A. Martina Neuman, Philipp Petersen
Published: 2026-05-06
Categories: cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2605.04995v1

We compare in-context learning with fixed queries and agentic learning with adaptive queries for uniform approximation of task families. We consider two settings: an unrestricted regime, where querying and approximation are arbitrary functions, and a realizable regime, where we require these operations to be implemented by ReLU neural networks. In both settings, adaptivity never hinders approximation performance. However, this advantage can change when one passes from the unrestricted regime to the realizable regime. We identify four distinct approximation scenarios, each witnessed by an explicit task family: (a) no advantage of adaptivity; (b) an advantage in the unrestricted regime that persists under ReLU realizability; (c) an advantage that arises only under realizability; and (d) an advantage that disappears under realizability. This demonstrates that representational constraints interact profoundly with the effect of adaptivity.

---

### Federated Learning for Early Prediction of EV Charging Demand

Authors: Vasilis Perifanis, Foteini Nikolaidou, Nikolaos Pavlidis, Panagiotis Thomakos, Andreas Sendros
Published: 2026-05-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.04993v1

Accurate forecasting of electric vehicle (EV) charging demand is critical for grid stability, infrastructure planning, and real-time charging optimization. In this work, we study the problem of early prediction of charging demand, where the total energy of a session is estimated using only information available at plug-in time and during the first minutes of charging. This enables actionable decisions while the session is still in progress, which is of direct importance for EV network operators. We construct a session-level dataset from the Adaptive Charging Network (ACN), combining session metadata with early-window charging measurements, and derive tabular features capturing user intent, temporal patterns, and initial charging behavior. We focus on a single operational depot, Caltech, and model intra-depot heterogeneity through station-level client partitions while evaluating multiple model families in a federated learning (FL) setting. Our results show that federated models can approach centralized predictive performance while keeping data in-depot, enabling privacy-enhanced training across distributed charging infrastructures. Overall, we demonstrate that reliable demand estimates can be obtained early in the session with minimal data, and that FL provides a practical pathway toward scalable and privacy-aware analytics for EV charging networks. Code is available at https://github.com/Indigma-Innovations/federated-learning-ev-charging-demand.

---

### Low-Rank Adaptation of Geospatial Foundation Models for Wildfire Mapping Using Sentinel-2 Data

Authors: Ali Shibli, Andrea Nascetti, Yifang Ban
Published: 2026-05-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.04989v1

Wildfire burned-area mapping is essential for damage assessment, emissions modeling, and understanding fire-climate interactions across diverse ecological regions. Recent geospatial foundation models provide strong general-purpose representations for satellite imagery, yet there is still no clear understanding of how to efficiently adapt these models for downstream Earth observation tasks, particularly under geographic and temporal domain shift. This study evaluates three state-of-the-art Geospatial Foundation Models (GFMs) - Terramind, DINOv3, and Prithvi-v2 - for burned-area mapping across the United States and Canada using Sentinel-2 data. Leveraging 3,820 wildfire events from 2017-2023, we conduct spatial and temporal generalization tests across diverse biomes. We systematically compare full fine-tuning, decoder-only fine-tuning, and Low-Rank Adaptation (LoRA) for adapting each model. Across all experiments, LoRA provides the strongest cross-domain generalization while updating less than 1% of parameters, demonstrating a favorable trade-off between accuracy and efficiency. Prithvi-v2 with LoRA achieves the highest overall accuracy and the largest improvement compared to full fine-tuning. These findings indicate that geospatial foundation models, when adapted using lightweight parameter-efficient methods such as LoRA, offer a robust and scalable solution for large-scale burned-area mapping. Code is available at https://github.com/alishibli97/wildfire-lora-gfm.

---

### Attention-Based Chaotic Self-Supervision for Medical Image Classification

Authors: Joao Batista Florindo, Amanda Pontes de Oliveira Ornelas
Published: 2026-05-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.04985v1

Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard transfer learning from ImageNet. Self-Supervised Learning (SSL) has emerged as a powerful alternative, yet common methods like masked autoencoders (MAEs) may inadvertently destroy fine-grained diagnostic features by using random masking. In this paper, we propose a novel SSL pre-training strategy, the Chaotic Denoising Autoencoder (CDAE). Instead of masking, we apply a chaotic transformation to the input image, tasking an autoencoder to reconstruct the original. We hypothesize this forces the encoder to learn robust, domain-specific features by "inverting the chaos". Furthermore, we propose an attentive fusion mechanism that combines features from our CDAE-trained encoder with a standard encoder, leveraging the strengths of both general and domain-specific representations. Our method is evaluated on two public medical datasets: ISIC 2018 (skin lesions) and APTOS 2019 (diabetic retinopathy). The proposed model achieves high performance, with an accuracy of 0.9221 and an F1-macro of 0.8530 on ISIC 2018, and an accuracy of 0.8644 and F1-macro of 0.7433 on APTOS 2019, demonstrating the efficacy of our approach.

---

### Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers

Authors: Senkang Hu, Yong Dai, Xudong Han, Zhengru Fang, Yuzhi Zhao, Sam Tak Wu Kwong, Yuguang Fang
Published: 2026-05-06
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.04984v1

Long-horizon LLM agents depend on intermediate information-gathering turns, yet training feedback is usually observed only at the final answer, because process-level rewards require high-quality human annotation. Existing turn-level shaping methods reward turns that increase the likelihood of a gold answer, but they require answer supervision or stable task-specific verifiers. Conversely, label-free RL methods extract self-signals from output distributions, but mainly at the answer or trajectory level and therefore cannot assign credit to intermediate turns. We propose Self-Induced Outcome Potential (SIOP), which treats semantic clusters of final answers as latent future outcome states for potential-based turn-level credit assignment. For each query, SIOP samples multiple rollouts, clusters final answers into semantic outcome modes, and builds a reliability-aware target distribution over these states. It then rewards turns for increasing posterior support for reliable future states using a tractable cluster-level approximation. The objective generalizes information-potential shaping from gold-answer supervision to settings without task-specific gold verifiers while avoiding the broadcasted rollout-level advantages used by standard GRPO. We formalize the framework, characterize its supervised gold-answer limit, and show that SIOP improves average performance over verifier-free outcome-level baselines on seven search-augmented agentic reasoning benchmarks while approaching a gold-supervised outcome baseline. Code is available at https://github.com/dl-m9/SIOP.git.

---

### Conceptors for Semantic Steering

Authors: Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao, Miranda Muqing Miao, Sunny Rai, Lyle Ungar, Sharath Chandra Guntuku, Neville Ryant, João Sedoc
Published: 2026-05-06
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.04980v1

Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely unexamined. Rather than selecting a single steering direction, we use conceptors: soft projection matrices estimated from activations pooled across both poles of a bipolar concept, which preserve the concept's full multidimensional subspace. A geometric analysis shows the bipolar subspace strictly subsumes the single-vector baseline. We further show that the conceptor quota provides a parameter-free layer-selection diagnostic, predicting concept separability with Pearson correlations up to r=0.96 across three instruction-tuned models and three semantic dimensions. Beyond selection, conceptors admit a closed-form Boolean algebra (AND, OR, NOT): we evaluate conceptor compositionality on thematically related sub-concepts. Across a systematic five-axis design-space evaluation, conceptors match or outperform additive baselines at layers where concept subspaces are multi-dimensional while producing substantially fewer degenerate outputs. Conceptor steering is a geometrically principled, compositional, and practically safer alternative to single-direction steering from a limited number of contrastive pairs.

---

### On-line Learning in Tree MDPs by Treating Policies as Bandit Arms

Authors: Anvay Shah, Ramsundar Anandanarayanan, Sharayu Moharir, Shivaram Kalyanakrishnan
Published: 2026-05-06
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.04979v1

A Tree Markov Decision Problem (T-MDP) is a finite-horizon MDP with a starting state $s_{1}$, in which every state is reachable from $s_{1}$ through exactly one state-action trajectory. T-MDPs arise naturally as abstractions of decision making in sequential games with perfect recall, against stationary opponents. We consider the problem of on-line learning in T-MDPs, both in the PAC and the regret-minimisation regimes. We show that well-known bandit algorithms -- \textsc{Lucb} and \textsc{Ucb} -- can be applied on T-MDPs by treating each policy as an arm. The apparent technical challenge in this approach is that the number of policies is exponential in the number of states. Our main innovation is in the design of confidence bounds based on data shared by the policies, so that the bandit algorithms can yet be implemented with polynomial memory and per-step computation. We obtain instance-dependent upper bounds on sample complexity and regret that sum a ``gap term'' from every terminal state, rather than every policy. Empirically, our algorithms consistently outperform available alternatives on a suite of hidden-information games.

---

### ICPR 2026 Competition on Privacy-Preserving Person Re-Identification from Top-View RGB-Depth Camera (TVRID)

Authors: Raphaël Delécluse, Hazem Wannous, Laurent Guimas
Published: 2026-05-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.04977v1

This companion paper reports the ICPR 2026 TVRID competition on privacy-aware top-view person re-identification. We present the competition setting, the released RGB-Depth dataset, and a summary of final results with descriptions of the top entries. TVRID contains 86 identities captured by four synchronized overhead Intel RealSense D455 cameras, with paired RGB/Depth streams and structured geometric variation across flat, ascent, descent, and oblique viewpoints. The evaluation protocol includes three tracks: RGB Re-ID, Depth Re-ID, and RGB$\leftrightarrow$Depth cross-modal retrieval. Submissions are ranked using mAP and CMC-1 under a unified server-side evaluation. The final results show a clear difficulty ordering (RGB $>$ Depth $>$ Cross-Modal), highlighting both the challenge of modality-constrained retrieval and the feasibility of strong performance with modality-invariant learning. By releasing the dataset at https://zenodo.org/records/17909410, the evaluation scripts at https://github.com/RaphaelDel/ICPR-TVRID, and the accompanying documentation, TVRID establishes a reproducible benchmark for top-view, depth-based, and cross-modal person re-id.

---

### Architectural Constraints Alignment in AI-assisted, Platform-based Service Development

Authors: Julius Irion, Moritz Leugers, Paul Hartwig, Simon Kling, Tachmyrat Annayev, Alexander Schwind, Maria C. Borges, Sebastian Werner
Published: 2026-05-06
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2605.04973v1

AI-assisted development tools enable rapid prototyping of services but often lack awareness of architectural constraints, infrastructure dependencies, and organizational standards required in production environments. Consequently, generated artifacts may exhibit brittle behavior and limited deployability. We propose a retrieval-augmented scaffolding approach that combines platform-based code generation with agentic clarification loops to expose and resolve architectural constraint ambiguities. By combining template retrieval with structured interaction, the method embeds production-relevant considerations during service scaffolding. Evaluation indicates improved architectural consistency and deployability compared to general-purpose AI code generation workflows, suggesting that constraint-aware retrieval is essential for aligning AI-assisted service development with production software engineering practices.

---

### Why Expert Alignment Is Hard: Evidence from Subjective Evaluation

Authors: Tzu-Mi Lin, Wataru Hirota, Tatsuya Ishigaki, Lung-Hao Lee, Chung-Chi Chen
Published: 2026-05-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.04972v1

Aligning large language models with expert judgment is especially difficult in subjective evaluation tasks, where experts may disagree, rely on tacit criteria, and change their judgments over time. In this paper, we study expert alignment as a way to understand this difficulty. Using expert evaluations and follow-up questionnaires, we examine how different forms of expert information affect alignment and what this reveals about subjective judgment. Our findings show four consistent patterns. First, alignment difficulty varies substantially across experts, suggesting that expert evaluation styles differ widely in their distance from a model's prior behavior. Second, explicit criteria and reasoning do not always improve alignment, indicating that expert judgment is not fully captured by verbalized rules. Third, editing is sensitive to both the number and the identity of examples, with small numbers of edits providing useful but unstable gains. Fourth, alignment difficulty differs across evaluation dimensions: dimensions grounded more directly in proposal content are easier to align, while dimensions requiring external knowledge or value-based judgment remain harder. Taken together, these results suggest that expert alignment is difficult not only because of model limitations, but also because subjective evaluation is inherently heterogeneous, partly tacit, dimension-dependent, and temporally unstable.

---

### Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking

Authors: Kyungwon Jeong, Won-Gi Paeng, Honggyo Suh
Published: 2026-05-06
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.04971v1

Weight matrices in deep networks exhibit geometric continuity -- principal singular vectors of adjacent layers point in similar directions. While this property has been widely observed, its origin remains unexplained. Through experiments on toy MLPs and small transformers, we identify two mechanisms: residual connections create cross-layer gradient coherence that aligns weight updates across layers, and symmetry-breaking nonlinearities constrain all layers to a shared coordinate frame, preventing the rotation drift that would otherwise destabilize weight structure. Crucially, a nonlinear but rotation-preserving activation fails to retain continuity, isolating symmetry breaking -- not nonlinearity itself -- as the active ingredient. Activation and normalization play distinct roles: activation concentrates continuity in the leading singular direction, while normalization distributes it across multiple directions. In transformers, continuity is projection-specific: Q, K, Gate, and Up (which read from the residual stream) develop input-space ($\mathbf{v}_1$) continuity; O and Down (which write to it) develop output-space ($\mathbf{u}_1$) continuity; V alone, lacking an adjacent nonlinearity, develops only low continuity.

---

### Skill Neologisms: Towards Skill-based Continual Learning

Authors: Antonin Berthon, Nicolas Astorga, Mihaela van der Schaar
Published: 2026-05-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.04970v3

Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable manner is an open problem: fine-tuning and parameter-efficient variants risk catastrophic forgetting, while context-based approaches have limited expressiveness and are constrained by the model's effective context. We explore skill neologisms--soft tokens integrated in the model's vocabulary and optimized to improve capabilities over a specific skill--as a way to selectively acquire new skills without weight updates. We first observe that pretrained LLMs already exhibit tokens associated with procedural knowledge. We then show on a controlled synthetic task that skill neologisms can be learned to improve model capabilities on specific skills while being composable with out-of-distribution skills, and that independently trained skill neologisms can be composed zero-shot. Finally, we validate zero-shot composition of independently learned skill neologisms on the more realistic natural language setting of the Skill-Mix benchmark. These results suggest that skill neologisms may provide a scalable path towards skill-based continual learning.

---

### Reliable Modeling of Distribution Shifts via Displacement-Reshaped Optimal Transport

Authors: Philip Naumann, Jacob Kauffmann, Klaus-Robert Müller, Grégoire Montavon
Published: 2026-05-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.04965v1

Optimal transport (OT) is a central framework for modeling distribution shifts. Because OT compares distributions directly in input space, a well-designed ground metric between observations is essential to ensure that the optimizer does not violate the true geometry of change. We propose Displacement-Reshaped Optimal Transport (ReshapeOT), a method that reshapes the ground metric by integrating observed sample displacements as an additional source of knowledge. Technically, ReshapeOT replaces the Euclidean metric with a Mahalanobis distance estimated from displacement second moments. This effectively carves expressways through the input space, inviting transport solutions that better align with observed displacements. Our method is computationally lightweight, integrates seamlessly into any OT solver that operates on a cost matrix, and can be kernelized for further flexibility. Experiments on synthetic and real-world data show that ReshapeOT achieves substantial gains in transport reliability. We further demonstrate our method's usefulness in two practical use cases.

---

### TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding

Authors: Minjie Qiang, Mingming Zhang, Xiaoyi Bao, Xing Fu, Yu Cheng, Weiqiang Wang, Zhongqing Wang, Ningtao Wang
Published: 2026-05-06
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2605.04962v1

Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack retrieval-compatible vector outputs, whereas text embedding models often fail to capture tabular structure and numerical semantics. To bridge this gap, we first introduce the Tabular Embedding Benchmark (TabBench), a comprehensive suite designed to evaluate the tabular understanding capability of embedding models. We then propose TabEmbed, the first generalist embedding model that unifies tabular classification and retrieval within a shared embedding space. By reformulating diverse tabular tasks as semantic matching problems, TabEmbed leverages large-scale contrastive learning with positive-aware hard negative mining to discern fine-grained structural and numerical nuances. Experimental results on TabBench demonstrate that TabEmbed significantly outperforms state-of-the-art text embedding models, establishing a new baseline for universal tabular representation learning. Code and datasets are publicly available at https://github.com/qiangminjie27/TabEmbed and https://huggingface.co/datasets/qiangminjie27/TabBench.

---

### EP-GRPO: Entropy-Progress Aligned Group Relative Policy Optimization with Implicit Process Guidance

Authors: Song Yu, Li Li, Wenwen Zhao, Zhisheng Yang
Published: 2026-05-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.04960v1

Reinforcement learning with verifiable rewards (RLVR), particularly Group Relative Policy Optimization (GRPO), has advanced LLM reasoning. However, GRPO suffers from three credit assignment failures: uniform token-level granularity that ignores heterogeneous informational value, uniform polarity that penalizes correct steps and rewards incorrect ones, and zero-variance collapse that erases outcome-driven gradients. We systematically quantify these failures, revealing highly non-uniform token informativeness, widespread step-level polarity misalignment, and substantial training waste. To address these limitations, we propose Entropy-Progress Aligned GRPO (EP-GRPO), a framework that mines the model's intrinsic information flow for dense, self-supervised guidance. EP-GRPO integrates entropy-gated modulation to prioritize high entropy decision pivots, implicit process signals from policy divergence anchored to outcome advantages for directional token-level feedback without external reward models, and cumulative entropy mapping that enables progress-aligned advantage normalization, naturally maintaining gradient flow under zero reward variance. Extensive experiments on mathematical reasoning benchmarks demonstrate that EP-GRPO achieves superior accuracy and efficiency compared to GRPO and its variants. The code will be available.

---

### Delving into Non-Exchangeability for Conformal Prediction in Graph-Structured Multivariate Time Series

Authors: Ruichao Guo, Xingyao Han, Luo Wenshui, Zhe Liu, Chen Gong, Hesheng Wang
Published: 2026-05-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.04957v1

Point forecasting for graph-structured multivariate time series is a fundamental problem, but rigorous uncertainty quantification for such predictions is still underexplored. Conformal prediction (CP) offers uncertainty estimation with a solid coverage guarantee under the exchangeability assumption, which requires the joint data distribution to be unchanged under permutation. However, in graph-structured time series, inherent cross-node coupling can violate the exchangeability condition, making direct application of CP unreliable. Inspired by the spectral graph theory, such coupling resides in global trends and can be characterized by the low-frequency components, while high-frequency components are nearly exchangeable. Therefore, we propose a novel concept named Spectral Graph Conditional Exchangeability (SGCE), which conditions exchangeable high-frequency components on low-frequency ones to preserve global trends and enable effective CP in the spectral domain. Based on SGCE, we further propose Spectral Conformal prediction via wAveLEt transform (SCALE). SCALE uses graph wavelets to decompose low/high-frequency components and conformalizes high-frequency residuals via adaptive gating over a low-frequency embedding. Experimental results on real-world traffic datasets show that SCALE not only achieves valid coverage but also consistently improves the coverage-efficiency trade-off over the state-of-the-art CP methods.

---

### KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

Authors: Han Wang, Jintao Zhang, Kai Jiang, Haoxu Wang, Jianfei Chen, Jun Zhu
Published: 2026-05-06
Categories: cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2605.04956v2

LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capability break down, and why? We present KernelBenchX, a benchmark designed to answer this question through category-aware evaluation of correctness and hardware efficiency across 176 tasks in 15 categories. Our systematic comparison of five representative methods yields three main findings. First, task structure determines correctness more than method design. Category explains nearly three times more variance in semantic correctness than method (9.4% vs 3.3% explained deviance), and 72% of Fusion tasks fail across all five methods while Math tasks are solved consistently. Second, iterative refinement improves correctness, but not performance. Across GEAK iterations, compile rate rises from 52.3% to 68.8% while average speedup declines from $1.58\times$ to $1.44\times$; newly rescued kernels consistently underperform persistently correct ones ($1.16\times$ vs $1.58\times$ speedup in round~0$\to$1). Third, correctness does not imply efficiency. 46.6% of correct kernels are slower than the PyTorch eager baseline, and cross-hardware speedup variance reaches $21.4\times$. Besides, quantization remains completely unsolved (0/30 successes) despite non-trivial compilation rates, revealing systematic misunderstanding of numerical computation contracts rather than surface-level syntax errors. These findings suggest that future progress depends on handling global coordination, explicitly modeling numerical precision, and incorporating hardware efficiency into generation. The code is available at https://github.com/BonnieW05/KernelBenchX

---

### Order-based Rehearsal Learning

Authors: Yu-Xuan Tao, Tian-Zuo Wang, Zhi-Hua Zhou
Published: 2026-05-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.04955v1

When a machine learning (ML) model forecasts an undesired event, one often seeks a decision to avoid it, known as the avoiding undesired future (AUF) problem. Many rehearsal learning methods have been proposed for AUF, but they rely on an underlying graph structure; learning such a graph from observational data is challenging and can incur substantial estimation error. In this work, we demonstrate that the order structure can be sufficient for AUF decision-making, and propose the first order-based rehearsal learning method. Although an order is less informative than a graph, it can be sufficient to identify the influence of decisions from observational data, suggesting that learning the entire graph is not always necessary. To learn the order, we develop an information-theoretic method that imposes no restrictions on the form of structural functions or the type of noise distributions. For AUF decision-making, we construct an order-based sampler to approximate the influence of decisions and, combined with a surrogate objective for maximizing the post-decision success probability, reduce the AUF task to a differentiable optimization problem. Experiments show that our order learning method outperforms existing methods, and that our AUF approach not only surpasses methods relying on learned graphs or learned orders, but also matches or even exceeds oracle baselines that are given the true graph.

---

### On the Influence of the Feature Computation Budget on Per-Instance Algorithm Selection for Black-Box Optimization

Authors: Koen van der Blom, Diederick Vermetten
Published: 2026-05-06
Categories: cs.NE, cs.LG
arXiv: https://arxiv.org/abs/2605.04954v2

Per-instance algorithm selection (PIAS) takes advantage of complementarity between a set of algorithms by deciding which algorithm to run on a given instance. This decision is based on features of the instances, which, in the context of black-box optimization (BBO), require a part of the optimization budget to be computed. This raises two questions: (a) from which fraction of the budget spent on feature computation does PIAS become worth it for BBO, and (b) which fraction of the budget optimizes the tradeoff between feature accuracy and PIAS performance. To this end, we perform a broad study where PIAS with varying sampling budgets for feature computation is compared to the single best algorithm on a broad range of algorithm selection scenarios. These scenarios consist of two portfolio sizes, three problem sets, 4 dimensionalities, and 10 target budgets. We find that PIAS is viable for the majority of tested scenarios, even when as much as a quarter of the total budget is spent on feature computation. The tradeoff for the fraction of the budget spent on feature computation to maximize the benefit of PIAS is highly dependent on the specific AS scenario. Further, on average 20 percent of PIAS loss to the virtual best solver is explained by the budget spent on feature computation, highlighting the importance of properly accounting for the feature budget.

---

### Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts

Authors: Klaus-Rudolf Kladny, Maximilian Mordig, Bernhard Schölkopf, Michael Muehlebach
Published: 2026-05-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.04952v1

Mixture-of-experts (MoE) models enable scalable transformer architectures by activating only a subset of experts per token. Recent evidence suggests that performance improves with increasingly granular experts, i.e., many small experts instead of a few large ones. However, this regime substantially increases routing cost, which can dominate computation. We introduce adaptive inverted-index routing for MoE (AIR-MoE), an inverted-index-inspired routing architecture based on vector quantization (VQ). In a first stage, AIR-MoE performs coarse shortlisting by assigning tokens to VQ codewords to construct a candidate set of experts. In a second stage, fine scoring computes exact routing scores restricted to this shortlist. This two-stage procedure approximates true top-k routing while avoiding full expert scoring and, in contrast to prior work, imposing no structural constraints on expert parameters. AIR-MoE serves as a drop-in replacement for standard routers and requires no modifications to the model architecture or loss function. We further provide a lower bound on the mass recall achieved by AIR-MoE that yields insights into its inner workings. Empirically, we demonstrate that AIR-MoE achieves improved performance compared to existing routing approaches in granular MoE settings.

---

### Adapting Large Language Models to a Low-Resource Agglutinative Language: A Comparative Study of LoRA and QLoRA for Bashkir

Authors: Mullosharaf K. Arabov, Svetlana S. Khaybullina
Published: 2026-05-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.04948v2

This paper presents a comparative study of parameter-efficient fine-tuning (PEFT) methods, including LoRA and QLoRA, applied to the task of adapting large language models to the Bashkir language, a low-resource agglutinative language of the Turkic family. Experimental evaluation is conducted on a Bashkir text corpus of 71k documents (46.9M tokens) using models of various architectures: DistilGPT2, GPT-2 (base, medium), Phi-2, Qwen2.5-7B, DeepSeek-7B, and Mistral-7B. To improve the reliability of results, each configuration was trained with three different random seeds. The lowest perplexity on the test set was obtained for GPT-2 medium with full fine-tuning (3.34). Meanwhile, QLoRA applied to Mistral-7B (3.79) and Phi-2 (3.81) achieved comparable quality with over 40 times fewer trainable parameters. However, we also observed cases of significant quality degradation when using PEFT for certain architectures (e.g., DeepSeek-7B with rank 8, perplexity = 129.55), indicating that the outcome depends critically on the choice of the base model and its tokenizer. Additionally, a qualitative analysis of generated texts based on Bashkir prompts revealed that models with the best perplexity do not necessarily produce the most coherent outputs: QLoRA-tuned models generated monolingual Bashkir continuations, whereas the fully fine-tuned model with the lowest perplexity frequently switched to English. The results suggest that QLoRA on 7B-scale models offers an effective compromise between quality and computational cost for Bashkir. To ensure reproducibility, open data, code, and trained adapters will be released upon acceptance.

---

### Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks

Authors: Xuan Qi, Yi Wei, Fanqi Yu, Furao Shen, Vittorio Murino, Cigdem Beyan
Published: 2026-05-06
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2605.04946v2

Batch normalization (BN) is central to modern deep networks, but its effect on the realized function during training remains less understood than its optimization benefits. We study training-time BN in continuous piecewise-affine (CPA) networks through the geometry of switching hyperplanes and the induced affine-region partition. Conditioned on a mini-batch, we show that BN defines for each neuron a reference hyperplane through the batch centroid, and that breakpoint-switching hyperplanes are parallel translates whose offsets are expressed in batch-standardized coordinates and are independent of the raw bias. This yields an exact criterion for when a switching hyperplane intersects a local $\ell_\infty$ window and motivates a local region-density functional based on exact affine-region counts. Under explicit sufficient conditions, we show that BN increases expected local partition refinement in ReLU and more general piecewise-affine networks, and that this mechanism transfers locally through depth inside parent affine regions where the upstream representation map is an affine embedding. These results provide a function-level geometric account of training-time BN as a batch-conditional recentering mechanism near the data.

---

### DART: A Vision-Language Foundation Model for Comprehensive Rope Condition Monitoring

Authors: Anju Rani, Daniel Ortiz-Arroyo, Petar Durdevic
Published: 2026-05-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.04943v1

The condition monitoring (CM) of synthetic fibre ropes (SFRs) used in offshore, maritime, and industrial settings demands more than a classifier: inspectors need continuous severity estimates, maintenance recommendations, anomaly flags, deterioration timelines, and automated reports, all from a single inspection image. We present DART (Damage Assessment via Rope Transformer), a vision-language foundation model that addresses the full rope inspection workflow through a unified multi-task architecture. DART extends the Joint-Embedding Predictive Architecture (JEPA) to the cross-modal domain by coupling a Vision Transformer (ViT-H/14) with Llama-3.2-3B-Instruct via a Severity-Conditioned Cross-Modal Fusion (SC-CMF) module. Three architectural innovations drive the model's versatility: (1) HD-MASK, a saliency-guided masking strategy that focuses self-supervised reconstruction on damage-dense patches; (2) per-class learnable severity gates that adaptively weight language grounding by damage category; and (3) a Contrastive Damage Disentanglement (CDD) loss that shapes the embedding space to simultaneously encode damage type, severity ordering, and cross-modal semantics. Trained once on 4,270 images spanning 14 fine-grained rope damage classes, the frozen DART backbone supports downstream tasks without any task-specific fine-tuning: damage classification (93.22 % accuracy, 91.04 % macro-F1, +38.5 pp over a vision-only baseline), continuous severity regression (Spearman rho = 0.94, within-1-ordinal accuracy 99.6 %), few-shot recognition (89.2 % macro-F1 at 20 shots). These results demonstrate that DART functions as a general-purpose CM backbone that goes well beyond classification, providing actionable inspection intelligence from a single shared representation.

---

### UFAL-CUNI at SemEval-2026 Task 11: An Efficient Modular Neuro-symbolic Method for Syllogistic Reasoning

Authors: Ivan Kartáč, Kristýna Onderková, Jan Bronec, Zdeněk Kasner, Mateusz Lango, Ondřej Dušek
Published: 2026-05-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.04941v1

This paper describes our system submitted to SemEval-2026 Task 11: Disentangling Content and Formal Reasoning in Large Language Models. We present an efficient modular neuro-symbolic approach, combining a symbolic prover with small reasoning LLMs (4B parameters). The system consists of an LLM-based parser that translates natural language syllogisms to a first-order logic (FOL) representation, an automated theorem prover, and two optional modules: machine translation for multilingual inputs and a symbolic retrieval component for the identification of relevant premises. The system achieves competitive accuracy and relatively low content effect on most subtasks. Our ablations show that this approach outperforms LLM-based zero-shot baselines in this parameter size range, but also reveal limited multilingual capabilities of small LLMs. Finally, we include a discussion of the task's main ranking metric and analyze its limitations.

---

### Modular Reinforcement Learning For Cooperative Swarms

Authors: Erel Shtossel, Gal A. Kaminka
Published: 2026-05-06
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2605.04939v1

A cooperative robot swarm is a collective of computationally-limited robots that share a common goal. Each robot can only interact with a small subset of its peers, without knowing how this affects the collective utility. Recent advances in distributed multi-agent reinforcement learning have demonstrated that it is possible for robots to learn how to interact effectively with others, in a manner that is aligned with the common goal, despite each robot learning independently of others. However, this requires each robot to represent a potentially combinatorial number of interaction states, challenging the memory capabilities of the robots. This paper proposes an alternative approach for representing spatial interaction states for multi-robot reinforcement learning in swarms. A modular (decomposed) representation is used, where each feature of the state is handled by a separate learning procedure, and the results aggregated. We demonstrate the efficacy of the approach in numerous experiments with simulated robot swarms carrying out foraging.

---

### Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift

Authors: Jonathan R. Landers
Published: 2026-05-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2605.04932v2

We study long-horizon deployment of a frozen predictor under dynamic covariate shift. A time-domain Poincare inequality first reduces temporal risk volatility to derivative energy. A Jacobian-velocity theorem then supplies the corresponding pathwise control. Given explicit regularity and domination assumptions, the theorem identifies directional tangent energy along the deployment path as the governing quantity. Under low-rank drift, that quantity reduces to directional Jacobian energy in the drift subspace, motivating drift-aligned tangent regularization (DTR) and a matched monitoring proxy. Rather than smoothing the network isotropically, DTR penalizes sensitivity only along estimated drift directions. We validate the theorem-to-method pipeline in four experiments: a synthetic benchmark for the time-domain inequality, a controlled synthetic comparison against isotropic Jacobian regularization, and two frozen-deployment studies on the UCI Air Quality and Tetouan power-consumption datasets. DTR reduces risk volatility and directional gain in the controlled low-rank regime and beats isotropic smoothing there. It also gives validation-selected deployment gains on both real datasets, with the Air Quality subspace estimated from target-orthogonal sensor motion. Moderate drift-subspace misspecification is tolerable while orthogonal misspecification largely removes the benefit.

---

### When Does Gene Regulatory Network Inference Break? A Controlled Diagnostic Study of Causal and Correlational Methods on Single-Cell Data

Authors: Miguel Fernandez-de-Retana, Ruben Sanchez-Corcuera, Unai Zulaika, Aritz Bilbao-Jayo, Aitor Almeida
Published: 2026-05-06
Categories: cs.LG, cs.AI, q-bio.GN, q-bio.QM, stat.ML
arXiv: https://arxiv.org/abs/2605.04930v1

Despite theoretical advantages, causal methods for Gene Regulatory Network (GRN) inference from single-cell RNA-seq data consistently fail to match or outperform correlation-based baselines in many realistic benchmarks, a persistent puzzle which casts doubt on the value of causality for this task. We argue that existing benchmarks are insufficiently controlled to answer this question because they evaluate on real or semi-real data where multiple pathologies co-occur, confounding failure modes, and obscuring the specific conditions under which different inference methods excel or fail. To address this gap, we introduce a controlled diagnostic framework that isolates seven biologically motivated pathologies (dropout, latent confounders, cell-type mixing, feedback loops, network density, sample size, and pseudotime drift) and measure how six representative methods spanning three inference paradigms degrade as each pathology intensifies. Across 6,120 controlled experiments, we find that causal methods genuinely dominate in clean and structurally favorable regimes, but specific pathologies (notably dropout and latent confounders) selectively neutralize their advantages. We further introduce an error-type decomposition that reveals methods with similar aggregate accuracy commit qualitatively different errors. To probe whether single-pathology effects persist when multiple stressors co-occur, we perform an interaction sweep over the three most impactful pathologies and find that their joint effects are sub-additive, while also exposing density-conditional cross-overs invisible to single-dial analysis. Our findings offer a nuanced understanding of when and why different methods succeed or fail for GRN inference, providing actionable insights for method development and practical guidance for practitioners.

---

### Unintended Negative Impacts of Promotional Language in Patent Evaluation

Authors: Bingkun Zhao, Chenwei Zhang, Hao Peng
Published: 2026-05-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.04926v2

Promotional language has been increasingly used to aid the communication of innovative ideas in science. Yet, less is known about its role in the context of technological innovation. Here, we use a validated and domain-diagnosed lexicon of 135 promotional words to study the association between promotional language and patent evaluation outcomes among 2.7 million USPTO patent applications. Our large-scale study reveals three unexpected findings. First, in contrast to scientific evaluation, we find that a higher frequency of promotional words is negatively associated with the probability of an application being (i) granted a patent, (ii) transferred ownership, and (iii) successfully appealed. This promotional penalty holds even after accounting for a range of confounding factors and is largely robust across different technological areas. Among matched samples, the difference in the success rate between the lowest and highest promotional density quintile is 5.5, 5.9, and 5.3 percentage points for patentability, transferability, and rejection reversal. Second, contrary to institutional skepticism, we show that promotional language is not a mask of weak technology, but objectively reflects the degree of combinatorial novelty and future citation impact. Third, digging into the mechanisms, we find that the tolerance to promotional framing is strongly moderated by human factors, with men and experienced examiners showing a higher acceptance of promotional narratives than women and novice examiners. By revealing an emerging paradox in the patent system, our study offers theoretical and practical implications for improving patent evaluation through more objective scrutiny of linguistic patterns in patent filings.

---

### Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation

Authors: Jiangwen Dong, Bo Li, Wanyu Lin
Published: 2026-05-06
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2605.04922v2

LLM-empowered multi-agent systems offer new potential to accelerate scientific discovery by generating novel research ideas. However, existing methods typically coordinate agents through temporary texts, such as drafts or chat logs; it is difficult to pinpoint the weaknesses in the generated ideas and how the agents refine them. To this end, we introduce \textbf{Evolving Idea Graphs} (EIG), a graph-based multi-agent scientific ideation framework that can generate high-performance research ideas across various benchmark-native metrics, such as novelty, feasibility, and clarity. Instead of coordinating solely through texts, EIG represents a partially formed proposal as an evolving idea graph, where nodes capture scientific claims and edges encode relations (e.g., support and conflict), enabling unresolved weaknesses to remain identifiable throughout the idea evolving process. Specifically, a learned two-head controller operates over the evolving graph to guide the ideation: one head selects graph edits for agents to execute, while the other decides when the graph is ready for commit as final proposal synthesis. On AI Idea Bench 2025 and LiveIdeaBench, EIG outperforms all compared systems on both automatic benchmark scores and blinded expert ratings. Ablations show that the graph-based state, its typed relations, and the learned edit-and-commit control each contribute to final proposal quality.

---

### Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation

Authors: Jiangwen Dong, Bo Li, Wanyu Lin
Published: 2026-05-06
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2605.04922v1

LLM-empowered multi-agent systems offer new potential to accelerate scientific discovery by generating novel research ideas. However, existing methods typically coordinate agents through temporary texts, such as drafts or chat logs; it is difficult to pinpoint the weaknesses in the generated ideas and how the agents refine them. To this end, we introduce \textbf{Evolving Idea Graphs} (EIG), a graph-based multi-agent scientific ideation framework that can generate high-performance research ideas across various benchmark-native metrics, such as novelty, feasibility, and clarity. Instead of coordinating solely through texts, EIG represents a partially formed proposal as an evolving idea graph, where nodes capture scientific claims and edges encode relations (e.g., support and conflict), enabling unresolved weaknesses to remain identifiable throughout the idea evolving process. Specifically, a learned two-head controller operates over the evolving graph to guide the ideation: one head selects graph edits for agents to execute, while the other decides when the graph is ready for commit as final proposal synthesis. On AI Idea Bench 2025 and LiveIdeaBench, EIG outperforms all compared systems on both automatic benchmark scores and blind expert ratings. Ablations further show that explicit graph state provides the main performance gains, and learned edit-and-commit control adds consistent improvements.

---

### Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization

Authors: Xiyan Fu, Wei Liu
Published: 2026-05-06
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.04920v1

Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fine-tuning, which encourages models to imitate target outputs. This token-level training paradigm fails to capture the global compositional structure required for generalizing to unseen combinations. In this work, we investigate whether compositional generalization can instead be improved through outcome-level reinforcement learning. We adopt Group Relative Policy Optimization to optimize models based on feedback on their final outputs. Within this framework, we explore both a simple binary outcome reward and a composite reward that provides additional composition feedback. Experiments on multiple compositional benchmarks show that reinforcement learning improves compositional generalization compared to supervised fine-tuning. Further analysis reveals that supervised models tend to overfit frequent training compositions, whereas reinforcement learning improves compositional generalization by reshaping the output distribution, particularly for more complex composition types.

---

### Neural Discovery of Strichartz Extremizers

Authors: Nicolás Valenzuela, Ricardo Freire, Claudio Muñoz
Published: 2026-05-06
Categories: math.AP, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2605.04918v2

Strichartz inequalities are a cornerstone of the modern theory of dispersive PDEs, but their extremizers are known explicitly only in a handful of sharp cases. The non-convexity of the underlying functional makes the problem hard, and to our knowledge no systematic numerical attack has been attempted. We propose a simple neural-network-based pipeline that searches for extremizers as critical points of the Strichartz ratio, and apply it in three settings. First, on the Schrödinger group we recover the Gaussian extremizers of Foschi and Hundertmark--Zharnitsky in dimensions $d=1,2$ to within $10^{-3}$ relative error, with no analytical prior. Second, on $59$ further admissible pairs in $d=1$ where the answer is conjectural, the method consistently finds Gaussians, supporting the conjecture that Gaussians are the universal extremizers in the admissible range. Third, on the critical Airy--Strichartz inequality at $γ=1/q$, where existence is open, the optimization does not converge to any $L^2$ profile: instead, the iterates organize themselves as mKdV breathers $B(0,\cdot;α,1,0,0)$ with growing internal frequency $α$, and the discovered ratio approaches the Frank--Sabin universal lower bound $\widetilde A_{q,r}$ from below with a power-law gap $\simα^{-0.9}$. We confirm the same picture with an independent Hermite-basis ansatz. We propose a precise conjecture: the supremum equals $\widetilde A_{q,r}$ and is approached, but not attained, along the breather family. The pipeline thus serves both as a validator on known cases and as a discovery tool when no extremizer exists.

---

### Koopman Identification of Nonlinear Systems via Reservoir Liftings

Authors: Weibin Gu, Chen Yang, Lu Shi
Published: 2026-05-06
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2605.04917v1

Learning tractable linear representations of nonlinear dynamical systems via Koopman operator theory is often hindered by dictionary selection, temporal memory encoding, and numerical ill-conditioning. Inspired by Reservoir Computing (RC) paradigm, this paper introduces the RC-Koopman framework, which interprets reservoir as a stateful, finite-dimensional Koopman dictionary whose temporal depth is explicitly controlled by its spectral radius. We show that the Echo State Property (ESP) guarantees well-posedness and favorable numerical conditioning of the lifted Koopman approximation. A correlation-based spectral radius selection algorithm aligns reservoir memory with dominant system timescales. Analysis reveals how the finite memory of the reservoir determines which Koopman eigenfunctions remain observable from the lifted features. Evaluation on synthetic benchmarks demonstrates that RC-Koopman achieves a favorable balance between reconstruction accuracy of the underlying nonlinear dynamics and dynamical stability, compared to Extended Dynamic Mode Decomposition (EDMD) and Hankel-based lifting approaches. Code available at: https://github.com/NEAR-the-future/RC-Koopman.git

---

### A Foundation Model for Zero-Shot Logical Rule Induction

Authors: Yin Jun Phua
Published: 2026-05-06
Categories: cs.AI, cs.LG, cs.SC
arXiv: https://arxiv.org/abs/2605.04916v2

Inductive Logic Programming (ILP) learns interpretable logical rules from data. Existing methods are transductive: their learned parameters are bound to specific predicates and require retraining for each new task. We introduce Neural Rule Inducer (NRI), a pretrained model for zero-shot rule induction. Rather than encoding literal identities, NRI represents literals using domain-agnostic statistical properties such as class-conditional rates, entropy, and co-occurrence, which generalize across variable identities and counts without retraining. The model consists of a statistical encoder and a parallel slot-based decoder. Parallel decoding preserves the permutation invariance of logical disjunction; an autoregressive decoder would instead impose an arbitrary clause order. Product T-norm relaxation makes rule execution differentiable, allowing end-to-end training on prediction accuracy alone. We evaluate NRI on rule recovery, robustness to label noise and spurious correlations, and zero-shot transfer to real-world benchmarks, and we believe this work opens up the possibility of foundation models for symbolic reasoning. Code and the reference checkpoint are available at https://github.com/phuayj/neural-rule-inducer.

---

### Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training

Authors: Hengyu Shi, Tianyang Han, Peizhe Wang, Zhiling Wang, Xu Yang, Junhao Su
Published: 2026-05-06
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.04913v4

LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it couples task adaptation to full-depth activation storage, long-range backward dependencies and direct task-gradient access to pretrained representations. We argue that this full-depth backward coupling can be unnecessarily expensive and intrusive, particularly when post-training supervision is much narrower than pre-training. To this end, we propose \textbf{LoPT}: Local-Learning Post-Training, a simple post-training strategy that makes gradient reach an explicit design choice. LoPT places a single gradient boundary at the transformer midpoint: the second-half block learns from the task objective, while the first-half block is updated by a lightweight feature-reconstruction objective to preserve useful representations and maintain interface compatibility. LoPT shortens the task-induced backward path while limiting direct interference from narrow task gradients on early-layer representations. Extensive experiments demonstrate that LoPT achieves competitive performance with lower memory cost, higher training efficiency and better retention of pretrained capabilities. Our code is available at: https://github.com/HumyuShi/LoPT

---

### Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning

Authors: Xinyan Han, Yan Lu, Xiaoyu Lin, Yuanyuan Jiang, Yuanrui Wang, Xuanyue Li, Wenchao Zou, Xingxuan Zhang
Published: 2026-05-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.04911v1

Tabular data synthesis aims to generate high-quality data while preserving privacy. However, we find that existing tabular generative models exhibit a clear tradeoff in the small-data regime: improving data quality typically comes at the cost of increased memorization of training samples, thereby weakening privacy protection. This tradeoff arises because small training sets make it difficult for dataset-specific generative models to distinguish generalizable structure from sample-specific patterns. To address this, we propose DiffICL, which formulates tabular data generation as an in-context learning problem. Instead of fitting each dataset from scratch,DiffICL leverages pretrained structural priors learned from a large collection of datasets, enabling it to infer data distributions from limited context rather than memorizing individual samples. We evaluate DiffICL on 14 real-world datasets. Results show that DiffICL improves both data quality and privacy, and generate synthetic data that provides effective data augmentation. Our findings suggest that the quality-privacy tradeoff can be improved through better training paradigms.

---

### Curated AI beats frontier LLMs at pharma asset discovery

Authors: Łukasz Kidziński, Kevin Thomas
Published: 2026-05-06
Categories: cs.AI, q-bio.QM
arXiv: https://arxiv.org/abs/2605.04908v1

General-purpose LLMs with web search are increasingly used to scout the competitive landscape of pharmaceutical pipelines. We benchmark Gosset -- an AI platform with a chat interface backed by curated target-, modality-, and indication-level drug-asset annotations -- against four frontier systems with web access (Claude Opus 4.7, GPT 5.5, Gemini 3.1 Pro, Perplexity sonar-pro) on ten niche oncology/immunology targets where most of the pipeline lives in the long tail of preclinical and Asian-developed assets. All five systems receive the same natural-language query and the same JSON output schema. Across 10 targets Gosset returns 3.2x more verified drugs per query than the best frontier system, at perfect precision and 100% recall against the cross-system union of verified drugs. The same curated index is exposed as a Gosset MCP server that any frontier model can call as a tool, suggesting that each of these systems can close most of the recall gap by swapping generic web search for a curated index behind the same chat interface.

---

### Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games

Authors: Yidong He, Yutao Lai, Pengxu Yang, Jiarui Gan, Jiexin Wang, Yi Cai, Mengchen Zhao
Published: 2026-05-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.04906v2

While Large Language Models (LLMs) excel in certain reasoning tasks, they struggle in multi-agent games where the final outcome depends on the joint strategies of all agents. In multi-agent games, the non-stationarity of other agents brings significant challenges on the evaluation of the reasoning process and the credit assignment over multiple reasoning steps. Existing single-agent reinforcement learning (RL) approaches and their multi-agent extensions fail to address these challenges as they do not incorporate other agents in the reasoning process. In this work, we propose Strat-Reasoner, a novel RL-based framework that improves LLMs' strategic reasoning ability in multi-agent games. We introduce a novel recursive reasoning paradigm where an agent's reasoning also integrates other agents' reasoning processes. To provide effective reward signals for the intermediate reasoning sequences, we employ a centralized Chain-of-Thought (CoT) comparison module to evaluate the reasoning quality. Finally, we compute an accurate hybrid advantage and develop a group-relative RL approach to optimize the LLM policy. Experimental results show that Strat-Reasoner substantially improves strategic abilities of underlying LLMs, achieving 22.1\% average performance improvements across various multi-agent games. Code is publicly available at https://github.com/ydhe1012/Strat-Reasoner.

---