# Research Papers — 2026-06 · bundle page 5 of 260 > Full-text markdown of papers #201–250 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/5 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/4.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/6.md) ### Review Residuals: Update-Conditioned Residual Gating for Transformers Authors: Kyle Kramer Published: 2026-06-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.31859v1 Residual connections add every sublayer's proposed update with a fixed coefficient of one; the network never evaluates whether an update is reliable before committing it. Drawing on the human-factors principle of independent verification, we introduce Review Residuals, which scale each update by a learned, input-dependent gate conditioned on both the current state and the proposed update: h_l = h_{l-1} + r_l * u_l with r_l = sigmoid(W(RMSNorm(h_{l-1}), RMSNorm(u_l))). Conditioning the gate on the update is the property that distinguishes it from prior gated and scaled residuals. We report two findings. First, a depth-stability result: a convex (Highway-style) form of the gate reintroduces vanishing gradients and fails to train beyond ~20 layers, whereas the additive, identity-preserving form trains stably at all depths we tested. Second, an emergence-with-scale result: trained from scratch across five sizes (60M-1B parameters, multi-seed), Review Residuals show no advantage at small scale but at 590M significantly outperform both a parameter-matched Highway gate and a parameter-matched standard residual (p<0.05), with a larger advantage at 1B. The benefit grows with model size rather than shrinking. --- ### Low-dimensional topology of deep neural networks Authors: Junyu Ren, Lek-Heng Lim Published: 2026-06-30 Categories: cs.LG, math.GT arXiv: https://arxiv.org/abs/2606.31856v2 We study layered models, including feedforward networks, ResNets, and transformers, by limiting each layer to a width of $d = 3$, i.e., $\mathbb{R}^3$ as representation space. This allows us to track how a neural network changes low-dimensional topological invariants through its layers. Just about any topological structure may be simplified or even trivialized by simply increasing dimension; e.g., any knot is equivalent to an unknot in $\mathbb{R}^4$. By restricting to $\mathbb{R}^3$, we not only isolate the effects of activation and depth from that of width, we work in a space that lends itself to easy visualization. We focus on linking number here, deferring other invariants like link groups, Milnor's $\barμ$-invariants, knot types, ambient cobordisms, to a sequel. We provide full proofs and empirical experiments to justify the following insights: When measured by their power to effect changes in linking numbers, the layer-skipping feature in ResNets is as powerful as the attention mechanism in transformers; both ResNets and transformers are strictly more powerful than feedforward neural networks with monotonic activations, which are in turn more powerful than invertible and flow-based models; but replacing monotonic activation with a nonmonotonic one elevates a feedforward network into the same expressivity class as ResNets and transformers. These results suggest that low-dimensional topology can be a useful tool to guide designs of AI architectures. We also generalize our results from $d = 3$ to arbitrary $d > 3$. --- ### Low-dimensional topology of deep neural networks Authors: Junyu Ren, Lek-Heng Lim Published: 2026-06-30 Categories: cs.LG, math.GT arXiv: https://arxiv.org/abs/2606.31856v1 We study layered models, including feedforward networks, ResNets, and transformers, by limiting each layer to a width of $d = 3$, i.e., $\mathbb{R}^3$ as representation space. This allows us to track how a neural network changes low-dimensional topological invariants through its layers. Just about any topological structure may be simplified or even trivialized by simply increasing dimension; e.g., any knot is equivalent to an unknot in $\mathbb{R}^4$. By restricting to $\mathbb{R}^3$, we not only isolate the effects of activation and depth from that of width, we work in a space that lends itself to easy visualization. We focus on linking number here, deferring other invariants like link groups, Milnor's $\barμ$-invariants, knot types, ambient cobordisms, to a sequel. We provide full proofs and empirical experiments to justify the following insights: When measured by their power to effect changes in linking numbers, the layer-skipping feature in ResNets is as powerful as the attention mechanism in transformers; both ResNets and transformers are strictly more powerful than feedforward neural networks with monotonic activations, which are in turn more powerful than invertible and flow-based models; but replacing monotonic activation with a nonmonotonic one elevates a feedforward network into the same expressivity class as ResNets and transformers. These results suggest that low-dimensional topology can be a useful tool to guide designs of AI architectures. We also generalize our results from $d = 3$ to arbitrary $d > 3$. --- ### Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models Authors: Lang Cao, Renhong Chen, Luyi Li, Peng Wang, Mofan Peng, Yitong Li Published: 2026-06-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.31846v1 Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and continuous control. However, most existing policies remain limited by behavior cloning or supervised fine-tuning (SFT) from fixed demonstrations, which provides limited opportunity to improve from the policy's own failures. In this paper, we present Z-1, a reinforcement learning (RL) post-training framework for flow-based VLA models. Built on top of $π_{0.5}$, Z-1 uses only publicly released RoboCasa demonstrations for SFT and then applies a task-wise Group Relative Policy Optimization (GRPO) strategy across $24$ standard RoboCasa tasks. To improve the efficiency and stability of online optimization, Z-1 combines shared-prefix rollout construction, tree-structured trajectory branching, completion-aware reward calibration, and selective joint training of VLM and Action Expert. Across all $24$ RoboCasa tasks, Z-1 achieves an average success rate of $80.6\%$, improving over its SFT initialization by $13.2\%$ points and outperforms the published sota models. These results show that systematic GRPO post-training can substantially improve flow-based VLA policies without additional private demonstrations. --- ### Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors Authors: Mark Oskin Published: 2026-06-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.31845v1 A transformer's feed-forward (FFN) sublayer materializes the distinctions attention gathers, yet gives no account of what it computes. In a parameter-neutral replacement, each hidden unit is an explicit fuzzy set operation on sigmoid-bounded (0,1) memberships: intersection A*B and set-difference A*(1-B), the latter a bounded positive negation ("A but not B") that gated/bilinear units lack -- a negation-capable FFN (NC-FFN). On N-bit parity they are the most parameter-efficient reasoning basis at shallow depth; at scale (125M, OpenWebText) NC-FFN ties the GELU baseline's perplexity, every unit carrying explicit logical form. Two limits share one cause: two-operand logic localizes to layer 0 and erodes under training, and the one robust grammatical deficit concentrates in licensing and quantifiers, beyond within-token operators. We resolve both with a small block of sequence quantifiers: a soft existential and a soft proportion, each with a per-unit learned forgetting rate from a sticky init. This recovers the deficit at epoch one (halving the wider epoch-two gap), modestly leads on LAMBADA, and makes the FFN legible: the structure now holds and migrates into depth; the decay un-learns its stickiness (median half-life ~1.5 tokens; zero latch units); and at the semantic layers the units read, without dictionary learning, as grammatical licensing detectors: each fires on a licensor (a comparative, a passive participle, a negative-polarity item) and carries its memory forward to predict the licensed word (than, by, nor). This legibility is localized and free only up to a partition (a fully Boolean FFN diverges in training), but the result is a parameter-neutral, language-model-quality transformer with a readable, interpretable-by-construction grammatical mechanism -- an account not just of what a feed-forward layer represents but how it licenses. --- ### Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling Authors: Ziyan Wang, Tan Xiang, Peng Chen, Xintao Yan Published: 2026-06-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2606.31844v1 A local-to-global context mismatch arises when autoregressive traffic simulators trained on ego-centric driving logs are deployed in globally observable closed-loop environments. In such logs, the ego vehicle has rich local observations, while surrounding agents are only partially observed due to perception limits and occlusions. As a result, simulators may learn incomplete context--action mappings that remain hidden in log-based training but emerge during closed-loop rollouts, leading to unrealistic behaviors such as abnormal stops, unsafe interactions, and rule violations. We propose CRAFT, a Contextual pReference Alignment Framework for Traffic Simulation, to mitigate this mismatch via self-supervised failure discovery and preference-guided test-time alignment. CRAFT treats the base simulator as a globally observable sandbox, generating diverse what-if rollouts from logged initial states to expose context-induced failures. These failures are grounded with human-aligned driving priors and converted into preference supervision for training a Contextual Preference Evaluator (CPE). At inference time, CPE acts as a plug-in alignment module that scores candidate actions under complete scene context and reweights autoregressive decoding toward globally coherent behaviors. CRAFT mitigates this local-to-global contextual bias, reducing collisions by 31.2\% and traffic violations by 33.2\% without retraining the base simulator. --- ### Towards Voxel Spacing Consistency for Medical Image Segmentation Authors: Xin You, Runze Yang, Minghui Zhang, Hanxiao Zhang, Han Li, Yi Yu, Jie Yang, Nassir Navab, Yun Gu Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31839v1 Volumetric medical image segmentation is essential for both preoperative diagnosis and intraoperative guidance. While recent years have witnessed rapid progress in segmentation architectures, comparatively little attention is paid to the physical voxel spacing of anatomical data. Indeed, volumetric image resampling is a ubiquitous preprocessing step before segmentation, yet its interaction with downstream segmentation has not been systematically exploited. In this work, we study the correlation between image resampling and segmentation, and propose Consispace, a semantic-aware resampling framework that achieves consistent voxel spacing in the axial direction while preserving anatomical and semantic consistency. Consispace introduces an ODE-based anatomical constraint to model inter-slice dynamics with a continuous interpolator, enabling faithful reconstruction under complex anatomical transitions beyond discrete interpolation. To further couple resampling with segmentation objectives, we leverage dense features from a pretrained vision model to build intra-slice semantic correlation maps and inject class-wise semantic consistency via feature reweighting during resampling. Both intra-slice and inter-slice constraints are integrated into an implicit neural network, supporting arbitrary-scale resampling. Extensive experiments on multiple datasets demonstrate that Consispace achieves superior reconstruction quality and perceptual fidelity, produces smoother inter-slice anatomy, and improves downstream segmentation performance when used as a preprocessing step. --- ### Real-Time Source-Free Object Detection Authors: Sairam VCR, Varun Gopal, Poornima Jain, Vineeth N Balasubramanian, Muhammad Haris Khan Published: 2026-06-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.31834v1 Real-world detectors for autonomous driving, surveillance, and robotics must handle domain-shifts under strict latency and memory constraints, yet existing source-free object detection (SFOD) methods rely on heavyweight architectures that prioritize accuracy alone. We show this trade-off is unnecessary: building on YOLOv10, an NMS-free dual-head detector, we achieve state-of-the-art adaptation accuracy while being faster and more compact. We observe that directly applying vanilla mean-teacher self-training to dual-head detectors leads to suboptimal adaptation performance due to two key factors. First, simple pseudo-label generation strategies, such as using a single head or directly combining high-confidence predictions from both heads, yield suboptimal supervision under domain-shift. We propose DHF (Dual-Head Pseudo-Label Fusion) which selectively admits one-to-one (O2O) and one-to-many (O2M) head predictions, preserving precision and recovering missed objects. Second, we observe domain-shift collapses multi-scale feature discriminability. We propose the use of our MARD (Multi-scale Adaptive Representation Diversification) loss which mitigates this by enforcing detection-aware variance and covariance constraints on multi-scale feature maps. Both modules are training-time only, leaving inference unchanged. Across domain-shift benchmarks, our method, RT-SFOD yields 1.4 to 3.5\% mAP gains, 1.3$\times$ higher throughput, with $\sim$2$\times$ fewer parameters than prior state-of-the-art SFOD methods, thus advancing the Pareto frontier of the speed-accuracy-model size trade-off. We report main results with YOLOv10, and demonstrate generalizability with additional YOLO- and DETR-based dual-head detectors. Code is available here: https://github.com/Sairam13001/RT-SFOD/ --- ### An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping Authors: Renan Souza, Daniel Rosendo, Kelsey Carter, John Lagergren, Frédéric Suter, Shelaine L. Curd, Gerald A. Tuskan, Rafael Ferreira da Silva, David Weston Published: 2026-06-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.31831v1 High-throughput plant phenotyping now generates image derived datasets far faster than scientists can analyze them. At Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory (APPL), automated stations image hundreds of plants daily across multiple remote sensing modalities; yet, trait extraction and interpretation remain manual, expert-bound, and strictly post-hoc, making analysis, not acquisition, the binding constraint on discovery. We present an end-to-end agentic AI framework that turns the facility from a data factory into an interactive autonomous, discovery platform, where scientists partner with AI agents to accelerate time to insight. A conversational Co-Scientist Agent translates a scientist's natural-language question into a structured analysis plan, and a headless Compute Agent dispatches Vision Transformer segmentation and trait extraction on the Frontier exascale supercomputer. The two agents run in separate security and resource domains and communicate over a secure, token-authenticated streaming channel, a design that accounts for the federation, data-movement, and provenance realities cloud-native agentic frameworks ignore, ensuring end-to-end provenance is captured for every interaction. The framework turns a days- to weeks-long analysis process into an interactive loop where agents reason over results, recommend next analyses, and respond to follow-up questions in seconds. --- ### PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving Authors: Kyuhwan Yeon, Benjamin Ramtoula, Daniele De Martini Published: 2026-06-30 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2606.31830v1 Most end-to-end autonomous driving methods rely solely on instantaneous sensor observations, limiting them to reactive behavior without the anticipatory foresight human drivers employ through prior experience. We introduce geospatial visual priors, street-level visual context anchored to the intended driving route, providing visual-spatial foresight independent of real-time sensors. We propose a memory augmentation module featuring a dual-memory architecture and an adaptive memory gate, which can be easily integrated into existing end-to-end approaches. This design pairs a contextual memory for retrieved priors with a persistent fallback memory, and dynamically regulates the influence of memories based on current state compatibility. Evaluated on the NAVSIM-v2 benchmark, our approach consistently improves performance across diverse end-to-end baselines. Furthermore, because these priors are independent of onboard sensors, our method inherently improves robustness against sensor corruption, while the dual-memory design ensures safe fallback when the retrieved priors themselves become unreliable. Our project page is available at https://ori-mrg.github.io/PriorEye. --- ### Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Authors: Junha Jung, Minbyul Jeong, Suhyeon Lim, Sungwook Jung, Jaehoon Yun, Taeyun Roh, Mujeen Sung, Jaewoo Kang Published: 2026-06-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.31825v2 Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on final answer correctness or sequence-level preferences. This suffers from sparse credit assignment, making it difficult to optimize the reasoning process essential for clinical applications. Our analysis reveals that cascading errors from early-stage reasoning failures are a leading cause of incorrect predictions in medical visual question answering (VQA) benchmarks. Motivated by this, we propose Medical Reasoning-aware Policy Optimization (MRPO), an RL algorithm that incorporates step-wise process rewards. When the final answer is incorrect, MRPO assigns exponentially larger penalties to tokens in earlier invalid reasoning steps, breaking failure cascades without compromising successful paths. Across four multimodal LLM backbones, MRPO consistently outperforms standard GRPO and a recent RL baseline, and on Qwen3-VL-8B-Thinking even surpasses substantially larger medical MLLMs such as HuatuoGPT-Vision-34B by 4.59 points. Moreover, MRPO reduces early-stage reasoning failures from 58.6% to 13.4%, showing that targeted mitigation of cascading failures improves both reasoning quality and final answer accuracy. Our code is available at https://github.com/dmis-lab/MRPO --- ### Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Authors: Junha Jung, Minbyul Jeong, Suhyeon Lim, Sungwook Jung, Jaehoon Yun, Taeyun Roh, Mujeen Sung, Jaewoo Kang Published: 2026-06-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.31825v1 Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on final answer correctness or sequence-level preferences. This suffers from sparse credit assignment, making it difficult to optimize the reasoning process essential for clinical applications. Our analysis reveals that cascading errors from early-stage reasoning failures are a leading cause of incorrect predictions in medical visual question answering (VQA) benchmarks. Motivated by this, we propose Medical Reasoning-aware Policy Optimization (MRPO), an RL algorithm that incorporates step-wise process rewards. When the final answer is incorrect, MRPO assigns exponentially larger penalties to tokens in earlier invalid reasoning steps, breaking failure cascades without compromising successful paths. Across three multimodal LLM backbones, MRPO consistently outperforms standard GRPO and a recent RL baseline, and on Qwen3-VL-8B-Instruct even surpasses substantially larger medical MLLMs such as HuatuoGPT-Vision-34B by 2.79 points. Moreover, MRPO reduces early-stage reasoning failures from 64.0% to 13.0%, showing that targeted mitigation of cascading failures improves both reasoning quality and final answer accuracy. Our code is available at https://github.com/dmis-lab/MRPO --- ### Absorption-Feature-Guided Distance-Decoupled Estimation and Band Selection for LWIR Hyperspectral Passive Ranging Authors: Shuo Liu, Chen Fan, Zhihe Chen, Xiaolin Huang, Lilian Zhang Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31824v1 Long-wave infrared (LWIR) hyperspectral observations contain distance-dependent atmospheric absorption signatures, providing a physical basis for long-range passive ranging. However, in natural scenes, these signatures are nonlinearly coupled with target temperature, material emissivity, and path radiance, making distance inversion from observed radiance ill posed. Existing methods typically rely on full-band measurements and pixel-wise joint optimization, which is computationally expensive and does not explicitly exploit sharp atmospheric absorption structures. This paper proposes an Absorption-Guided Distance-Decoupled Estimation and Refinement (ADER) framework for LWIR hyperspectral passive ranging. ADER represents emissivity with B-spline control points under a smoothness prior, suppressing overfitting to atmospheric absorption structures and enabling distance-decoupled estimation. It further uses ozone-absorption cues to classify pixels into emission-dominant and reflection-dominant groups. For emission-dominant pixels, ADER compensates path radiance and transmittance and estimates distance by one-dimensional absorption-residual minimization. For reflection-dominant pixels, ADER refines the initial estimate using downwelling-radiance compensation based on the complete radiative model. To reduce spectral redundancy, ADER also introduces a greedy band selection strategy based on multi-scene effective Fisher information for the distance parameter. Experiments on real scenes show that ADER recovers LiDAR-consistent spatial distance structures under both full-band and 20-band settings, improves ranging accuracy in the evaluated regions, and achieves approximately two orders of magnitude speedup over a public full-band hyperspectral ranging method. --- ### Adaptive Cluster-First Route-Second Decomposition for Industrial-Scale Vehicle Routing Authors: Oguzhan Karaahmetoglu, Hyong Kim Published: 2026-06-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.31820v1 Large-scale capacitated vehicle routing problems (CVRPs) are commonly addressed using cluster-first route-second (CFRS) approaches that split a routing instance into smaller, computationally tractable subproblems. Existing splitting methods typically rely on fixed partitioning rules, predefined optimization objectives, or learned policies, which may perform inconsistently across instances exhibiting different spatial, demand, and operational characteristics. In this work, we propose an adaptive CFRS system that formulates a decomposition procedure as an iterative decision-making process. Motivated by the recent success of large language models (LLMs) in reasoning and tool selection, the system employs an LLM as a high-level decision maker that analyzes the evolving decomposition state and selectively applies further clustering, balancing, and refinement operators. The proposed algorithm jointly partitions customers and vehicles, enabling capacity-aware clustering while adapting partitioning decisions to the characteristics of each problem. We evaluate the approach on synthetic and benchmark-derived CVRP instances containing up to 500,000 customers. Experimental results demonstrate competitive performance on benchmark-scale instances while exhibiting improved scalability and robust routing quality on substantially larger problems. These results highlight the potential of adaptive, LLM-guided decision support as a practical approach for industrial-scale vehicle routing and large-scale logistics planning. --- ### Creating Intelligence: A Computational Foundation for AGI Authors: Peter Overmann Published: 2026-06-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.31819v1 This work introduces a new computational theory of mind grounded in set theory and hyperdimensional computing. Whereas traditional neural networks rely on continuous weights and matrix multiplication, this framework works with sparse binary data. It represents information as discrete sets, directly modeling biological neural population codes. I demonstrate that associative memory emerges naturally from network topologies featuring a combinatorially expanded hidden layer. Learning is driven by topological plasticity rather than scalar weight adjustments. This architecture unifies auto-associative and hetero-associative learning under a single core algorithm: information retrieval via subset pattern matching and exact nearest-neighbor search. Operating with constant-time complexity, these mechanisms bridge perceptual data (sparse distributed representations) and symbols (sparse holographic representations) without continuous bottlenecks. Mapping this framework to neuroanatomy, I propose that both the cerebellum and the neocortex implement variants of this algorithm, making subset pattern matching the fundamental engine of cognition. Because it relies on discrete logic rather than matrix arithmetic, this algorithm translates directly into in-memory hardware. This opens a new route toward synthetic intelligence with human-level energy efficiency. --- ### Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior Authors: Jiahui Fu, Zehao Huang, Han Li, Naiyan Wang, Si Liu Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31814v1 Lane topology reasoning aims to construct a lane graph from onboard sensor observations. Existing methods follow a detection and association paradigm that treats each lane instance independently, leading to geometric inconsistency at connected endpoints and incomplete graphs due to visual occlusions. To address these issues, we propose TopoGPT, a generative framework that learns the geometry prior from typical lane graph structures through autoregressive sequence modeling. Specifically, we construct a large-scale map dataset comprising 3.3M scenes. For each lane graph, a lane tokenizer serializes it into discrete tokens, while a scene context encoder converts it into a rasterized image and extracts global features as scene tokens. We pre-train an autoregressive lane sequence transformer via scene-conditioned next-token prediction, endowing the model with the geometry prior over lane graph structures. Building upon this prior, a perception adapter aligns BEV features from multi-view images with the pre-trained scene condition, transferring the learned geometry prior to sensor-based lane graph prediction. On the OpenLane-V2 benchmark, TopoGPT outperforms existing methods by an average of +6.4 on lane-level and +11.6 on point-level metrics, and produces geometrically consistent and structurally complete lane graphs. --- ### Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR Authors: Ruijia Zhang, Jiacheng Zhu, Hanqing Zhu, Laixi Shi Published: 2026-06-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.31813v1 Low-rank adaptation (LoRA) and its variants enable parameter-efficient fine-tuning of large language models under the supervised fine-tuning (SFT) paradigm. However, their efficacy and behavior under Reinforcement learning with verifiable rewards (RLVR) are less well understood. In particular, two structurally initialized LoRA variants, PiSSA and MiLoRA, which outperform standard LoRA under SFT, can underperform standard LoRA under RLVR and may even exhibit training instability. These observations suggest that how to initialize the low-rank matrices in RLVR remains unclear. In this work, we develop a theoretical analysis of LoRA in RLVR, showing that orthonormal initialization achieves the minimal gap between LoRA outcome and that of full fine-tuning. Guided by this insight, we propose geometry-preserving orthonormal initialization for low-rank adaptation in RLVR, leading to two new variants, RLPO and RLMO. Experiments on mathematical reasoning benchmarks show that the proposed orthonormal initialization stabilizes RLVR training and outperforms standard LoRA, contrasting with PiSSA and MiLoRA. Finally, our unified analysis for LoRA initialization also explains why PiSSA and MiLoRA can underperform in RLVR, which may be of independent interest. Code and checkpoints are publicly available at https://github.com/Richard-ZZZ/geometry-preserving-orthonormal-init-rlvr. --- ### MuSViT: A Foundation Vision Model for Sheet Music Representation Authors: Carlos Penarrubia, Antonio Rios-Vila, Eliseo Fuentes-Martinez, Juan C. Martinez-Sevilla, Francisco J. Castellanos, María Alfaro-Contreras, Jorge Calvo-Zaragoza Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31811v1 Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet music, as a visual encoding of musical language, lacks such a strong domain-specific backbone. We introduce MuSViT (Music Score Vision Transformer): the first foundation vision model for sheet music representation -- a ViT encoder pre-trained via Masked Autoencoders on 9.7 million pages from the IMSLP. To handle the complexity of real-world scores, we adopt a two-stage curriculum: a synthetic warm-up on typeset scores followed by large-scale training on the full IMSLP corpus. We evaluate MuSViT on four downstream tasks -- full-page and staff-level music score recognition, music symbol detection, and score difficulty classification -- under two scenarios: linear probing (frozen encoder) and fine-tuning. Under linear probing, MuSViT consistently outperforms modern vision encoders, revealing that general-purpose representations, regardless of scale, fall systematically short on the structured symbolic properties of musical notation. Under fine-tuning, MuSViT generally improves upon task-specific state-of-the-art methods. An additional embedding-transcription consistency analysis reveals that MuSViT encodes symbolic musical structure directly in its representation space -- unlike other encoders, whose embeddings do not correlate with music notation content. These results establish MuSViT as a foundation backbone for sheet music understanding. --- ### Large Databases Need Small, Open-Weight Language Models Authors: Parker Glenn, Alfy Samuel Published: 2026-06-30 Categories: cs.AI, cs.DB arXiv: https://arxiv.org/abs/2606.31808v1 Language model systems built around proprietary APIs often operate on a token-based cost model. This becomes prohibitively expensive in the context of large databases, where LM-enhanced relational operators can incur costs exceeding $10,000 for a single set of experiments, hindering thorough research and practical deployment. In this paper, we demonstrate that quantized, open-weight models running locally on just 16GB of VRAM can match or exceed the accuracy of closed-source counterparts at lower latency and a fraction of the price, challenging the prevailing assumption that closed-source LM APIs are necessary for effective LM-database integration. We present and analyze the key system optimizations required to efficiently deploy these open-weight models within an LM-DB system. By integrating these local models into the BlendSQL v0.1.0 framework, we demonstrate a 390x reduction in overall costs and 3.8x reduction in latency compared to a proprietary LM API. We make our code available at https://github.com/CapitalOne-Research/play-by-the-type-rules/tree/main/sembench. --- ### Relational and Sequential Conformal Inference for Energy Time Series over Graphs via Foundation Models Authors: Keivan Faghih Niresi, Alice Cicirello, Olga Fink Published: 2026-06-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.31804v1 Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neural networks (STGNNs) have recently achieved strong performance in point forecasting by jointly modeling temporal dynamics and relational dependencies across interconnected energy nodes. However, in real-world energy systems, accurate point forecasts alone are insufficient, as operators also require reliable uncertainty estimates to support risk-aware decision-making, grid stability, and operational planning under uncertainty. Conformal prediction provides a principled and model-agnostic framework for uncertainty quantification with statistical coverage guarantees, making it particularly attractive for safety-critical energy applications. However, existing conformal prediction approaches often fail to fully capture the complex spatial-temporal structure of energy systems. To address these limitations, we propose STOIC (Spatial-Temporal Graph Conformal Prediction with In-Context Learning), a novel framework that integrates graph-based forecasting with the zero-shot calibration capabilities of tabular foundation models. STOIC first generates point forecasts using an STGNN and subsequently reformulates spatial-temporal residuals into a tabular representation suitable for in-context learning. Leveraging a tabular foundation model, STOIC calibrates prediction intervals without task-specific retraining, effectively capturing both sequential and relational dependencies. We evaluate STOIC on five diverse benchmarks, including synthetic simulations as well as real-world electricity and district heating networks. Across all datasets, STOIC consistently outperforms existing conformal prediction baselines, delivering more reliable and robust uncertainty estimates for complex graph-structured energy time series. --- ### RAISE: LLM-based Automated Heuristic Design with Robust Adversary Instance Search Authors: Fei Liu, Alessio Figalli, Patrick Owen, Nicola Serra Published: 2026-06-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.31801v1 Automated Heuristic Design (AHD) with Large Language Models (LLMs) has shown remarkable progress in discovering high-quality heuristics. However, existing LLM-based AHD methods optimize heuristics for a fixed training instance set and may fail catastrophically when deployed under real-world distributional shifts. We propose Robust Adversary Instance Search (RAISE), a framework that integrates constrained worst-case instance search within a principled neighborhood of the training distribution into the LLM-based evolutionary search loop. RAISE treats robust AHD as a constrained adversarial instance search problem: the outer loop evolves heuristics via LLM operators, while an LLM-free inner loop efficiently identifies hard instances within an epsilon-ball around the training instance set using a basis distribution parameterization with boundary projection. Comprehensive experiments on Online Bin Packing (OBP), Online Job Shop Scheduling (OJSP), and Online Vehicle Routing (OVRP) across five distribution families demonstrate that existing LLM-based AHD methods degrade by up to 19 times under distribution shift, while RAISE consistently maintains strong performance across all tested distributions and problem scales --- ### Evo-PI: Aligning Medical Reasoning via Evolving Principle-Guided Supervision Authors: Xianda Zheng, Huan Gao, Meng-Fen Chiang, Michael Witbrock, Kaiqi Zhao, Shangyang Li Published: 2026-06-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.31800v1 Despite recent progress, the reasoning capabilities of large multimodal language models (MLLMs) remain fundamentally constrained by static supervision, where fixed prompts, rules, or reward models provide non-adaptive guidance throughout training. Such static signals are often sufficient to enforce output formats, but fail to shape the underlying reasoning process, leading to brittle generalization and performance saturation in complex decision-making tasks. We propose Evo-PI, a principle-centric learning framework that treats reasoning principles as explicit, language-based supervision signals that can be generated, evaluated, and iteratively evolved. Instead of relying on fixed rewards, Evo-PI enables a co-evolutionary loop in which principles guide model reasoning, while model behaviors in turn refine the principles that supervise them. This dynamic alignment mechanism allows supervision to progressively adapt to the model's reasoning deficiencies. We instantiate Evo-PI in medical visual question answering as a high-stakes testbed requiring structured visual-textual reasoning. Across eight benchmarks and multiple model backbones, Evo-PI consistently improves reasoning accuracy, achieving gains of up to 24.6%. Our results suggest that evolving principle-guided supervision offers a scalable and general paradigm for training expert-aligned reasoning in MLLMs. Code is available at https://github.com/zhengxianda/Evo_PI. --- ### CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield Authors: Dohyeon Kwon, Youngjin Park Published: 2026-06-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.31796v2 Frontier language capability is usually bought with frontier compute; CHERRY shows a different trade. It is a sovereign Korean model family built on one principle: supervise the tokens that decide the answer, and let shared weights carry the rest. Under matched compute this exposes a sharp, reproducible dissociation---selected-token supervision preserves held-out discrimination yet collapses free generation, and a full-sequence anchor recovers only part of the gap. The same signal drives a heal-after-merge recurrent-representational-yield loop that collapses 48 layers to 6 unique blocks at near-dense parity (227M at loss 2.934 vs a 566M dense model at 2.926) and composes them by MoEE fusion (2.789)---a recurrent-compression direction independently pursued by concurrent frontier looped-MoE work, which we project (not yet measure) to frontier scale. It also installs metacognition from two-token supervision (200 held-out KO prompts/type, kappa>0.82, +/-6.9pp): self-correction 12->47% and jailbreak 23->4% at 97.6% loss-retention on 1.2B, with a pre-registered 1B->13.7B ablation localising the operand-binding limit to capacity (1B lookup vs 13.7B H-PRESERVE); and it specializes a 1.8B model to reported human-expert level on CyberMetric (75.0% vs a 30-expert average 72.24%). The released 1.8B tokenizer is 9.2% more Korean-efficient than Gemma-4; the from-scratch 12B adds a sovereign Korean tokenizer (vocab 131,037). On the government-operated K-AI Korean-LLM leaderboard the released 1.8B leads the HLE(Ko) column (0.123 vs 0.077; overall 51/78). At the frontier we fine-tune and serve an adapted 122B model on one 120GB accelerator (83GB measured peak). Provenance differs by member and we state it exactly; the architecture and recipe are ours throughout, and every claim is bound to a released curated measurement. --- ### Distributed Hierarchical Temporal Memory with Shared Associative Memory for Cross-Entity Preemptive Warning Authors: Pavia Bera, Jennifer Adorno, Sanjukta Bhanja Published: 2026-06-30 Categories: cs.NE arXiv: https://arxiv.org/abs/2606.31789v1 Anomaly detection in multivariate time series remains a critical challenge in large-scale distributed systems, where related entities may exhibit transferable precursor behavior prior to anomaly onset. Existing methods typically operate independently on each data stream and therefore remain fundamentally reactive. To address this limitation, we introduce Distributed Hierarchical Temporal Memory (D-HTM), a neuromorphic framework that enables cross-entity preemptive warning through a Shared Associative Memory (SAM). D-HTM combines a Spatial Pooler (SP) that projects observations into a common Sparse Distributed Representation (SDR) space, Temporal Memory (TM) modules that learn entity-specific dynamics online, and a Shared Associative Memory that stores recurring pre-anomaly signatures. By reusing precursor knowledge across related entities, D-HTM can issue warnings prior to local anomaly onset while preserving HTM's online learning capabilities. We evaluate D-HTM on the Server Machine Dataset (SMD), the Soil Moisture Active Passive (SMAP) dataset, the Mars Science Laboratory (MSL) dataset, and a synthetic cascade benchmark designed to isolate precursor transfer. Experimental results demonstrate effective cross-entity warning propagation while maintaining competitive reactive anomaly detection performance. Across the real-world datasets, D-HTM provides an average warning lead time of 8.1 samples prior to anomaly onset. These findings demonstrate that transferable precursor structure can emerge within a shared SDR space and be reused for preemptive warning generation, extending HTM beyond isolated reactive detection toward distributed predictive reasoning. --- ### Self-Supervised Temporal Regularization for Landmark-Based Cardiac Segmentation with Automatic AHA Regional Mapping Authors: David Montalvo-García, Nicolás Gaggion, María J. Ledesma-Carbayo, Enzo Ferrante Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31785v1 Graph-based cardiac segmentation with implicit anatomical correspondences provides topological guarantees and population-level analysis capabilities, but models trained on independent frames of image sequences exhibit temporal discontinuities that affect reliable clinical measurements, particularly in cardiac ultrasound. In this work, we introduce self-supervised temporal regularization as a post-training refinement stage that exploits the temporal coherence in image sequences to enforce consistent cardiac segmentation and motion estimation over time, without requiring per-frame annotations. By penalizing velocity and acceleration discontinuities across consecutive frames, our method achieves temporally consistent segmentations while maintaining the learned anatomical correspondences. We further leverage these correspondences to automatically map landmarks to the AHA 17-segment clinical standard, enabling standardized regional assessment and detection of pathological myocardial motion patterns. Validation on CAMUS dataset demonstrates the clinical utility of combining temporal consistency with automatic regional mapping. The code is publicly available at https://github.com/david-montalvoo/MaskHybridGNet-TempReg --- ### SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks Authors: Thuan Bui, Duong Do, Tung Vu, Duc-Tho Mai, Cong-Kha Pham Published: 2026-06-30 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2606.31781v1 Log parsing is a fundamental step in automated log analysis, transforming raw system logs into structured event templates for downstream tasks such as anomaly detection and system monitoring. Existing log parsing methods range from rule-based and clustering-based approaches to neural models that learn semantic representations from log messages. However, neural approaches typically rely on dense matrix multiplications, which can result in high computational cost and energy consumption. This paper presents SpikeLogBERT, a spiking neural network framework for energy-efficient log parsing. The proposed model integrates a spiking transformer architecture with knowledge distillation from a BERT teacher model, enabling spike-driven computation while preserving semantic representation capability. By leveraging sparse spike activations and event-driven processing, the number of active operations during inference can be significantly reduced. As an initial benchmark study, experiments on the HDFS dataset demonstrate that SpikeLogBERT outperforms ANN-based neural log parsing models with a parsing accuracy of 0.99997, while reducing estimated theoretical energy consumption by up to 62.6% under standard 45nm CMOS assumptions. --- ### Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers Authors: Ying Fan, Anej Svete, Kangwook Lee Published: 2026-06-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.31779v2 Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token. Latent CoT offers an alternative: it performs multi-step reasoning in the model's hidden states, replacing decoded tokens with continuous representations for greater efficiency. However, existing latent CoT methods underperform explicit CoT beyond 1B parameters, and the gap widens with scale. Looped, or recurrent-depth, Transformers, which reuse their weights to increase computation depth without adding parameters, are a natural fit for latent reasoning. We therefore ask whether looped Transformers can bridge this gap. We answer affirmatively with a simple recipe: a looped padded Transformer that processes K latent blocks in parallel for R iterations, with a cross-entropy loss on each latent position's gold CoT-step token, similar to explicit CoT supervision. We instantiate it as LOTUS (Looped Transformers with parallel supervision on latents). LOTUS is, to our knowledge, the first latent-CoT method to bridge the gap to explicit CoT at the 3B scale, while cutting thought-phase latency by 2.5x-6.9x from compact math expressions to natural language. Projecting LOTUS's post-loop latents through the base LM head recovers the gold reasoning steps and even surfaces alternative valid intermediate steps, evidence that its latent space is interpretable and CoT-aligned. Ablations confirm that both the looped backbone and the parallel supervision on gold CoT tokens are essential. Code is available at https://github.com/yingfan-bot/lotus. --- ### Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation Authors: Gaochao Song, Haohan Weng, Luo Zhang, Zibo Zhao, Shenghua Gao Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31777v1 Autoregressive (AR) modeling has recently achieved remarkable progress in native 3D mesh generation, largely due to its natural ability to handle variable-length, discrete data structures. However, the inherent constraints of the AR paradigm severely restrict the generated meshes, leading to limited face counts, bounded vertex resolutions, and difficulties in supporting textures. To overcome these bottlenecks, we propose the Barycentric Dominance Field (BDF), a continuous representation defined on triangular mesh surfaces that elegantly encodes vertex topological connectivity. BDF bridges the fundamental gap between discrete mesh topology and continuous diffusion-based generative modeling by transforming connectivity into a continuous surface signal. As an intrinsic mesh property, BDF shares strong similarities with texture maps, enabling its seamless integration into existing 3D diffusion pipelines without requiring architectural modifications. Extensive experiments demonstrate that BDF empowers diffusion models to generate native meshes with significantly higher quality, greater scalability, and stronger robustness compared to state-of-the-art autoregressive methods. --- ### Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions Authors: Mingyi Li, Taira Tsuchiya, Kenji Yamanishi Published: 2026-06-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.31769v1 We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees together with data-dependent regret bounds. Recent work (Dann et al., 2023; Li et al., 2026) has shown that policy optimization can adapt to both adversarial and stochastic losses with first-order, second-order, and path-length bounds, but only under known transitions, leaving open whether such data-dependent guarantees are achievable by policy optimization when the transition kernel is unknown. We resolve this by developing a new algorithm based on optimistic follow-the-regularized-leader that attains these guarantees under unknown transitions. The key ingredient is a new design of optimistic $Q$-function estimators together with a data-dependent transition bonus that controls estimator bias through the loss-prediction error. Our analysis further identifies an unavoidable transition-dependent complexity term that captures the intrinsic cost of estimating the transition kernel. As a result, we obtain first-order, second-order, and path-length bounds with the transition-dependent complexity term while simultaneously achieving gap-dependent $\mathrm{polylog}(T)$ regret in the stochastic regime. --- ### NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics Authors: Jingye Qiu, Shizhe Zhou Published: 2026-06-30 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2606.31764v2 Differentiable rendering of planar rational splines remains largely underexplored, despite their widespread use in vector graphics and design. Existing differentiable vector renderers primarily focus on Bézier curves and rely on analytic rasterization, which can suffer from gradient instability and limited flexibility. We propose NURBS Splatting, a unified framework that represents planar rational curves as continuous Gaussian fields. By sampling Gaussians along the curve parameter domain and inside closed regions, rendering is reformulated as a smooth accumulation process with stable gradients. Our method naturally supports long splines, rational weights, non-uniform knots, and closed-region filling. We demonstrate its effectiveness in calligraphy reconstruction, vectorization frameworks, and long-spline image abstraction, showing improved stability and reconstruction quality over existing approaches. --- ### NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics Authors: Jingye Qiu, Shizhe Zhou Published: 2026-06-30 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2606.31764v1 Differentiable rendering of planar rational splines remains largely underexplored, despite their widespread use in vector graphics and design. Existing differentiable vector renderers primarily focus on Bézier curves and rely on analytic rasterization, which can suffer from gradient instability and limited flexibility. We propose NURBS Splatting, a unified framework that represents planar rational curves as continuous Gaussian fields. By sampling Gaussians along the curve parameter domain and inside closed regions, rendering is reformulated as a smooth accumulation process with stable gradients. Our method naturally supports long splines, rational weights, non-uniform knots, and closed-region filling. We demonstrate its effectiveness in calligraphy reconstruction, vectorization frameworks, and long-spline image abstraction, showing improved stability and reconstruction quality over existing approaches. --- ### A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols Authors: Yankai Jiang, Weiting Tang, Haoran Sun, Zhenyu Tang, Yuejie Hou, Yingnan Han, Rubo Wang, Yueyuxiao Yang, Cheng Liang, Lilong Wang, Wenjie Lou, Xiaosong Wang et al. Published: 2026-06-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.31763v2 Autonomous wet-lab experimentation requires more than plausible protocol text: biological intent, quantitative procedures, device constraints and experimental feedback must remain aligned from protocol and SOP design to code and physical execution. We developed ProtoPilot, a self-evolving multi-agent system, together with an expert-grounded benchmark and evaluation framework for testing this conversion as an experimental automation problem. The framework spans 294 synthetic-biology and molecular-biology tasks derived from 98 gold-standard protocols, wet-lab expert rubrics, device-level validity gates and real experimental tests. ProtoPilot incorporates layer-wise verifiability, multi-agent orchestration and a runtime-updated skill library to generate protocols, expand SOPs, synthesize SDK-compliant code and revise workflows from wet-lab feedback. It achieved a Top@3 expert-preference rate of 90.2%, an overall protocol-to-code gate pass rate of 89.5% and an Opentrons pass rate of 88.24%, compared with 32.35% for OpenTrons-AI. Wet-lab validation produced interpretable readouts, Sanger-confirmed products and feedback-corrected PCA-assembled DNA targets, establishing a verifiable route to autonomous experimentation. Together, these results show that the evaluation framework captures execution-relevant requirements for autonomous wet-lab automation, and that ProtoPilot can meet them by converting protocol and code generation into validated execution and feedback-guided revision. --- ### Estimating Velocity and Spin of Spherical Objects from Rolling-Shutter Image(s) Authors: Wenjie Xue, Jun Yang, Jingmin Wang, Limin Shang Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31760v2 Rolling-shutter cameras introduce characteristic distortions when imaging fast moving objects, and these effects are typically treated as artifacts to be corrected. In this work, we instead leverage rolling-shutter distortions as a valuable source of temporal information to estimate the 3D translational and angular velocities of rapidly moving spherical objects from a single rolling-shutter frame. We design a robust and easily detectable spherical pattern and propose a correspondence-free formulation that recovers motion by enforcing geometric consistency in a back-projection framework. By exploiting the geometry of the sphere, translational and rotational motions are decoupled and estimated through a two-stage optimization process, enabling reliable velocity recovery even for textureless objects. Extensive experiments on both synthetic and real datasets demonstrate accurate and robust estimation of motion parameters under challenging high-speed conditions. --- ### A Technical Typology of AI Systems in Public Administration Authors: Jonathan Rystrøm, Chris Schmitz, Nathan Davies, Gerhard Hammerschmid, Albert Meijer, Chris Russell Published: 2026-06-30 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2606.31755v1 Research on artificial intelligence (AI) in the public sector often treats "AI" as a single category, neglecting technical distinctions between different AI systems. But these distinctions affect how different systems impact core public values like accountability, procedural justice, and non-discrimination. This paper argues that public administration research would benefit from more technical precision on "AI" and makes three contributions to this end. First, we introduce a typology of five categories of AI systems: hand-coded, glass-box, black-box, general-purpose, and agentic systems. We calibrate the typology to public administration by grouping system types by their distinct implications for public values. Second, we evaluate technical precision in recent public administration research about AI by coding 91 highly-cited papers (2019-2025) using our typology. We find widespread imprecision: most papers (55\%) leave the studied system underspecified, 31\% motivate their work with a different system than they study, and 41\% make more general conclusions than the studied system supports. Finally, we give practical recommendations for future research. We highlight common pitfalls to avoid, and suggest that researchers should, at a minimum, provide enough technical detail to locate the studied system in our typology. To this end, we provide a practical guide -- a short set of diagnostic questions answerable from public information and without specialist technical knowledge. --- ### Addressing Over-Refusal in LLMs with Competing Rewards Authors: Taeyoun Kim, Aviral Kumar Published: 2026-06-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.31748v1 Safety training on language models often induces over-refusal: improved safety on harmful prompts at the cost of increased refusal on harmless ones. Though this trade-off can be mitigated by training models with reinforcement learning (RL) to reason before answering, it does not remove the underlying problem that reasoning can often be a "rubber stamp" for a predetermined response. In this paper, we address the safety-refusal trade-off by rethinking how models are trained to reason about safety. Our key insight is that unsafe reasoning can itself serve as a useful exploratory signal. Rather than preemptively blocking harmful thoughts, we encourage the model to sufficiently explore unsafe reasoning but produce a safe response. The harmful exploration improves the model's ability to distinguish harmful from harmless prompts by resolving ambiguity, allowing it to remain safe while complying only when appropriate. We cast this as an adversarial optimization problem in which a reasoning player explores strategies for producing an unsafe response and an answer player ensures that the final output is safe. We train a single model with dense rewards to play both roles within one chain-of-thought, across different segments. To achieve this, we find that process rewards are crucial for stable optimization of competing objectives. Our resulting model SEAR deliberately engages in harmful reasoning as exploration while reliably flipping back to a safe answer. We demonstrate that this behavior helps mitigate over-refusal and defend against attacks that directly manipulate the reasoning to be harmful. --- ### JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering Authors: Ziyuan Liu, Ruifei Zhu, Ouqiao Ma, Yuantao Gu Published: 2026-06-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.31745v1 Remote sensing change detection (CD) traditionally focuses on pixel-level binary segmentation, which identifies where changes occur but neither what nor why. To bridge this semantic gap, we introduce JL1-CC&QA, a multi-task benchmark that extends the JL1-CD dataset with two complementary annotation layers: change captioning (CC) and change question answering (QA). Built upon 5,000 bi-temporal image pairs acquired by the Jilin-1 satellite at 0.5-0.75m ground sample distance, the benchmark comprises: (i) JL1-CC, providing 17,021 quality-verified captions that describe diverse land-cover transformations; and (ii) JL1-QA, offering 20,060 question-answer pairs across eight question types, enabling fine-grained, interactive interrogation of surface changes. All annotations are produced via a three-stage pipeline consisting of multi-modal large language model (LLM) generation, vision-grounded LLM judging, and human expert verification. We hope that JL1-CC&QA, as a benchmark unifying binary change masks, change captions, and change-oriented QA over the same image set, will serve as a valuable resource for the community to advance multi-task change understanding in remote sensing. The dataset is available at https://github.com/circleLZY/JL1-CD. --- ### FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning Authors: Maximilian Andreas Hoefler, Karsten Mueller, Wojciech Samek Published: 2026-06-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.31742v1 Explainable AI (XAI) methods have demonstrated significant success in recent years at identifying relevant features in input data that drive deep learning model decisions, enhancing interpretability for users. However, the potential of XAI beyond providing model transparency has remained largely unexplored in adjacent machine learning domains. In this paper, we show for the first time how XAI can be utilized in the context of federated learning. Specifically, while federated learning enables collaborative model training without raw data sharing, it suffers from performance degradation when client data distributions exhibit statistical heterogeneity. We introduce FedXDS (Federated Learning via XAI-guided Data Sharing), the first approach to utilize feature attribution techniques to identify precisely which data elements should be selectively shared between clients to mitigate heterogeneity. By employing propagation-based attribution, our method identifies task-relevant features through a single backward pass, enabling selective data sharing that aligns client contributions. To protect sensitive information, we incorporate metric privacy techniques that provide formal privacy guarantees while preserving utility. Experimental results demonstrate that our approach consistently achieves higher accuracy and faster convergence compared to existing methods across varying client numbers and heterogeneity settings. We provide theoretical privacy guarantees and empirically demonstrate robustness against both membership inference and feature inversion attacks. Code is available at https://github.com/MaxH1996/FedXDS. --- ### STEB: Style Text Embedding Benchmark Authors: Rafael Rivera Soto, Anna Wegmann, Cristina Aggazzotti Published: 2026-06-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.31741v1 While semantic embeddings are rigorously evaluated on the Massive Text Embedding Benchmark, the evaluation of style embeddings remains fragmented, with each work relying on their own set of tasks and datasets. To bridge this gap, we introduce the Style Text Embedding Benchmark, a comprehensive open-source benchmark intended to standardize the evaluation of style embeddings. STEB encompasses 96 datasets across 7 languages, spanning applications such as authorship verification, authorship retrieval, AI-text detection, probing of linguistic features, and others. We find that semantic embeddings consistently fail in stylistic tasks, and that there is no style embedding that is universally superior across all tasks evaluated. We open-source the STEB code base at: https://github.com/rrivera1849/STEB. --- ### Rhythm-Structured Predictive Learning for Remote Photoplethysmography Authors: Ba-Thinh Nguyen, Huu-Dung Nguyen, Thi-Duyen Ngo, Thanh-Ha Le Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31736v1 Remote photoplethysmography (rPPG) estimates physiological signals from facial videos by analyzing subtle pulse induced skin color variations. Despite recent progress, existing self-supervised rPPG methods mainly reconstruct masked pixels or low-level visual representations, which can bias the model toward facial appearance rather than latent physiological dy namics. Moreover, most recent Mamba-based approaches scan facial video tokens only in chronological order, limiting their ability to exploit the cyclic structure of pulse signals. To ad dress these limitations, we propose RhythmJEPA, a rhythm structured joint-embedding predictive learning framework for rPPG. Instead of reconstructing RGB frames, RhythmJEPA predicts latent teacher representations from masked facial videos, thereby encouraging physiology-aware representation learning in the embedding space. To explicitly model pulse-related tem poral structure, we introduce a Cyclic Rhythm-State Plan ner (CRSP), which estimates frame-wise latent physiological states and decodes the most plausible cyclic state path via dynamic programming with a constrained transition grammar. Guided by the decoded states, we further design a Dual Order Mamba Encoder (DOM), which combines conventional chronological scanning with state-ordered scanning to capture both local temporal continuity and long-range rhythm-consistent dependencies. Finally, a lightweight Spatial Pulse Mixer (SPM) extracts compact pulse-sensitive facial tokens with a favorable balance between complexity and performance. Experiments on PURE, UBFC-rPPG, and MMPD show competitive performance over representative rPPG methods. The codes are available at https://github.com/deconasser/RhythmJEPA. --- ### MemLearner: Learning to Query Context memory for Video World Models Authors: Jiwen Yu, Jianxiong Gao, Jianhong Bai, Yiran Qin, Kaiyi Huang, Quande Liu, Xintao Wang, Pengfei Wan, Kun Gai, Xihui Liu Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31734v1 Video World Models are interactive video generation models that predict future world states based on user actions and history video frames. A critical challenge in video world models is the lack of memory, causing inconsistent generated scenes over extended durations. Previous methods explored rule-based context frame retrieval as memory, but they fail to generalize in scenarios with scene occlusions and dynamic objects. We propose MemLearner, a learning-based adaptive context query method using query tokens to bridge context and predicted tokens. By leveraging the video generation model itself for context querying, MemLearner exploits pre-trained visual priors without training additional modules from scratch, and incorporates efficient strategies for training and inference. We collect a dataset of long videos with scene occlusions and dynamic objects, paired with camera pose annotations, and propose a multi-dataset training strategy leveraging both annotated rendered and unannotated real-world videos. Extensive experiments demonstrate that MemLearner significantly outperforms prior video world models in terms of scene consistency and memory, particularly under challenging occlusion and dynamic scenarios. --- ### UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization Authors: Yaozhi Zheng, Yilei Jiang, Manyuan Zhang, Yuxuan Wan, Kaituo Feng, Tianshuo Peng, Bo Zhang, Xiangyu Yue Published: 2026-06-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.31732v1 Visual-to-Code generation, which transforms scientific plots, vector graphics, and webpages into executable scripts, demands a level of pixel-precise alignment that standard Multimodal Large Language Models (MLLMs) fail to achieve through Supervised Fine-Tuning (SFT) alone. While Reinforcement Learning (RL) offers a theoretical pathway to bridge this gap, its application is hindered by two fundamental obstacles: (1) \textit{Reward Coarseness}, where semantic metrics like CLIP scores fail to penalize fine-grained element deviations, and (2) \textit{Exploration Stagnation}, where the sparse, heterogeneous code search space prevents the policy from bootstrapping valid trajectories. To overcome these limitations, we introduce UniCoder, a unified RL framework that integrates two novel mechanisms. First, we propose \textbf{Symbolic Attribute Alignment}, which employs a lightweight auxiliary LLM to parse generated code into discrete visual attributes (e.g., hex colors, coordinate limits), enabling dense, element-wise reward computation. Second, to escape local optima, we devise \textbf{Reference-Guided Code Optimization}, a strategy that dynamically injects ground-truth trajectories into low-performing rollout groups, transforming blind exploration into guided policy improvement. Extensive experiments on ChartMimic, UniSVG, Design2Code and ScreenBench benchmarks demonstrate that our 8B-parameter model not only surpasses all open-source baselines but also achieves state-of-the-art performance comparable to proprietary models, establishing a new paradigm for generalized visual-to-code synthesis. --- ### Is Natural Always Appropriate? Investigating Naturalness and Appropriateness Across Different Domains for TTS Evaluation Authors: Dominika Woszczyk, Andreas Triantafyllopoulos, Jura Miniota, Éva Székely, Bjoern Schuller Published: 2026-06-30 Categories: eess.AS, cs.LG arXiv: https://arxiv.org/abs/2606.31729v1 Text-to-speech (TTS) evaluation is an open challenge. While the primary target was "naturalness," recent fidelity gains shifted focus toward "appropriateness" and whether speech is correct for its context. In this work, we examine how perception changes when the expected downstream use varies. We measure the appropriateness and human-likeness of five SOTA TTS systems across five domains: AI assistant, reader, actor, animated character, and spontaneous speaker. Results show appropriateness varies across domains independently of naturalness. While systems shine at reading, expressive domains remain challenging, and optimizing for one can degrade others. Furthermore, naturalness scores tend to penalize stylized speech while rewarding spontaneity. Finally, our study also highlights blind spots in one-size-fits-all evaluation metrics across more expressive domains. We demonstrate that TTS performance is not "solved" but depends on the target domain, requiring context-aware evaluation. --- ### Adapting Foundation ASR Models to Dysarthric Speech: A Case Study Authors: Christian Huber, Laura Kernahan, Alexander Waibel Published: 2026-06-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.31722v2 Automatic speech recognition (ASR) systems often perform poorly in dysarthric speech, limiting their usefulness to affected speakers in everyday communication. This paper presents a personalized ASR system for a dysarthric speaker, built by adapting a foundation ASR model to speaker-specific data. Using the TEQST tool, we collected 92 hours of read speech and later added 8.8 hours of user corrections gathered through a deployed mobile application. Starting from Whisper, fine-tuning reduced word error rate to 15.8% with only 1.4 hours of adaptation data on the read test set, reached 10.7% / 16.1% with 22.5 hours on the read and corrections test sets, respectively, and achieved the best result of 9.7% when using all available data including the corrections on the read test set and 7.8% on the corrections test set. Using LoRA adaptation and/or Qwen3-ASR as foundation model performed worse in this setting. The results show that personalized fine-tuning can make foundation ASR models substantially more effective for dysarthric speech and suitable for practical deployment. --- ### Adapting Foundation ASR Models to Dysarthric Speech: A Case Study Authors: Christian Huber, Laura Kernahan, Alexander Waibel Published: 2026-06-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.31722v1 Automatic speech recognition (ASR) systems often perform poorly in dysarthric speech, limiting their usefulness to affected speakers in everyday communication. This paper presents a personalized ASR system for a dysarthric speaker, built by adapting a foundation ASR model to speaker-specific data. Using the TEQST tool, we collected 92 hours of read speech and later added 8.8 hours of user corrections gathered through a deployed mobile application. Starting from Whisper, fine-tuning reduced word error rate to 15.8% with only 1.4 hours of adaptation data, reached 10.7% with 22.5 hours, and achieved the best result of 9.7% when using all available data including the corrections. Using LoRA adaptation and/or Qwen3-ASR as foundation model performed worse in this setting. The results show that personalized fine-tuning can make foundation ASR models substantially more effective for dysarthric speech and suitable for practical deployment. --- ### Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue Authors: Nan Li, Albert Gatt, Massimo Poesio Published: 2026-06-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.31719v1 In collaborative dialogue, shared perception does not guarantee shared interpretation. Mutual understanding must be established through interaction. We investigate whether vision-language models (VLMs) can distinguish what could be shared from what has been shared between dialogue participants through grounding. We formulate this as an interpretation-matching task on 13,077 annotated reference expressions from HCRC MapTask dialogues, and evaluate VLMs under systematically controlled manipulations of dialogue context and map-information access. Our results show that providing authentic map images improves overall performance but shifts models toward over-predicting alignment. Textual descriptions of the same map content reproduce this bias, while non-informative images suppress alignment predictions entirely, indicating that the bias is driven by task-relevant map content, not the visual channel. This improvement comes at the cost of degraded accuracy on non-aligned cases. Calibration analysis and reference-chain tracking further suggest that models rely on static referential cues on the maps rather than tracking how grounding unfolds through dialogue history. We observe these patterns most clearly in Qwen3-VL-8B-Instruct and, to varying degrees, in four additional models from two architecture families. In models that exhibit the bias, map content, whether presented visually or textually, is treated as evidence of mutual understanding, conflating potential with established common ground. --- ### Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian Authors: Dragos-Mitrut Vasile, Elena-Simona Apostol, Stefan-Adrian Toma, Adrian Paschke, Ciprian-Octavian Truica Published: 2026-06-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.31718v1 Relation extraction (RE) for low-resource languages is typically constrained by the lack of annotated corpora. We investigate the feasibility of cross-lingual RE for Romanian by combining automatic dataset translation with large language model (LLM) inference. We translate the SemEval-2010 Task 8 benchmark from English to Romanian using an LLM-based translation pipeline and evaluate Gemma 4 31B under zero-shot, few-shot, and QLoRA fine-tuned configurations, against four encoder baselines spanning 125M to 560M parameters: XLM- RoBERTa (base and large), Romanian BERT, and RoBERT- large. We assess two task formulations: relation classification with marked entities and end-to-end extraction. Our results show that Romanian incurs a 3 to 5 percentage point (pp) drop relative to English in prompt-only settings, that few-shot prompting provides marginal gains over zero-shot, and that QLoRA fine-tuning improves macro F1-Score by more than 22 percentage points in both languages while reducing the cross-lingual gap from 3.3 to 1.4pp. The encoder baselines come within 1-4pp of QLoRA Gemma on Romanian despite being 50-250 times smaller, with monolingual Romanian BERT at 125M parameters matching multilingual XLM-R at 278M. The case for using a 31B model for single-task RE on Romanian is therefore weak in deployment scenarios where compute matters. We release the translated dataset, evaluation code, and trained models. --- ### Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints Authors: Shuai Yuan, Sudong Cai, Bingzhi Chen, Shuyuan Zheng, Chuan Xiao, Makoto Onizuka, Rui Mao Published: 2026-06-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.31717v1 Low-rank adaptation (LoRA) is commonly viewed as an update-space approximation to full fine-tuning, yet this view is incomplete for self-gated Transformer feed-forward networks. In gated FFNs, a low-rank residual can change not only projected features but also the nonlinear selection weights that determine which channels contribute to the output. We formalize this effect as selection misalignment and connect it to the local effective homogeneity of self-gated activations. This motivates a nonlinearity-aware principle for parameter-efficient fine-tuning: low-rank updates should allocate capacity to gate channels whose nonlinear states remain responsive and should shape the temporal evolution of selection. We propose NA-LoRA, a training-only method with two lightweight mechanisms: a derivative-based temporal-importance mask for gate-related LoRA updates and an activation-specific step-scaling rule when a meaningful coarse effective-homogeneity partition is available. NA-LoRA adds no auxiliary loss and incurs no inference-time overhead. Experiments on language-model fine-tuning and vision-language transfer benchmarks show that NA-LoRA consistently improves over vanilla LoRA and is competitive with or better than strong PEFT variants. --- ### Exploiting Overlapping Fields of View for Redundancy-Aware Uplink Transmission in Vehicular 6G Authors: Hamidreza Mazandarani, Masoud Shokrnezhad, Tarik Taleb, Onur Günlü Published: 2026-06-30 Categories: cs.NI, cs.CV arXiv: https://arxiv.org/abs/2606.31715v3 Emerging uplink-dominant 6G use cases, such as cooperative vehicular streaming, require efficient transmission of high-volume visual data over limited wireless resources. While semantic communications can reduce traffic by prioritizing task-relevant content, most existing approaches treat users independently and therefore overlook spatial redundancy among nearby devices' observations. This paper proposes a semantic-aware multiple access scheme that exploits overlapping fields of view among vehicular users to reduce redundant uplink transmissions. We formulate a joint perception and transmission control problem in which users decide which image patches to transmit, when to transmit them, and over which channel, subject to communication constraints. To address the resulting complexity, we introduce a practical two-phase approach. First, nearby vehicles share selected observation patches over Vehicle-to-Vehicle (V2V) links to calculate inter-user spatial redundancy. Second, users transmit only semantically important, non-redundant patches to the base station, where observations can be reconstructed using the received patches and complementary views from neighboring vehicles. Simulation results in a dense urban vehicular scenario demonstrate that our approach improves the proportion of users who achieve high-fidelity reconstruction, highlighting the potential of semantic-aware multiple access for sustainable and resource-efficient 6G uplink systems. --- ### Exploiting Overlapping Fields of View for Redundancy-Aware Uplink Transmission in Vehicular 6G Authors: Hamidreza Mazandarani, Masoud Shokrnezhad, Tarik Taleb, Onur Günlü Published: 2026-06-30 Categories: cs.NI, cs.CV arXiv: https://arxiv.org/abs/2606.31715v2 Emerging uplink-dominant 6G use cases, such as cooperative vehicular streaming, require efficient transmission of high-volume visual data over limited wireless resources. While semantic communications can reduce traffic by prioritizing task-relevant content, most existing approaches treat users independently and therefore overlook spatial redundancy among nearby devices' observations. This paper proposes a semantic-aware multiple access scheme that exploits overlapping fields of view among vehicular users to reduce redundant uplink transmissions. We formulate a joint perception and transmission control problem in which users decide which image patches to transmit, when to transmit them, and over which channel, subject to communication constraints. To address the resulting complexity, we introduce a practical two-phase approach. First, nearby vehicles share selected observation patches over Vehicle-to-Vehicle (V2V) links to calculate inter-user spatial redundancy. Second, users transmit only semantically important, non-redundant patches to the base station, where observations can be reconstructed using the received patches and complementary views from neighboring vehicles. Simulation results in a dense urban vehicular scenario demonstrate that our approach improves the proportion of users who achieve high-fidelity reconstruction, highlighting the potential of semantic-aware multiple access for sustainable and resource-efficient 6G uplink systems. --- ### Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist Authors: Yuanhao Ban, Tong Xie, Sohyun An, Yunqi Hong, Evan Frick, I-Hung Hsu, Wei-Lin Chiang, Ion Stoica, Cho-Jui Hsieh Published: 2026-06-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.31711v1 Faithfulness -- how precisely a generated image aligns with its prompt -- is increasingly central to the real-world utility of text-to-image (T2I) models. Existing faithfulness benchmarks, however, rely on simple atomic instructions, on which top-tier systems already achieve near-perfect scores. As T2I models enter creative workflows, users issue multi-faceted requests combining intricate spatial relationships, stylistic constraints, and complex text rendering. In this setting, a single binary VLM-judge score no longer captures which specific constraints the model fails to satisfy. We introduce Arena-T2I Hard, a 310-prompt stress benchmark drawn from real arena T2I logs, with approximately 30 decomposed yes/no constraints per prompt spanning six categories, including text rendering. The strongest closed-source system we evaluate reaches 0.855 with a 33~pp performance gap across 11 systems, demonstrating substantial discriminative power. Moreover, high public-arena rankings fail to predict faithfulness, confirming that holistic Bradley-Terry (BT) preference scores prioritize aesthetics over fine-grained prompt adherence. We propose a dependency-aware checklist reward that decomposes each prompt into a DAG of yes/no questions and zeroes descendants of failed parents, turning faithfulness into a per-constraint training signal. Combined with a BT aesthetic reward via group-decoupled normalization (GDPO), which standardizes each reward within its rollout group so neither collapses, the recipe attains a strictly better faithfulness-aesthetics trade-off on SD3.5-Medium and FLUX.1-dev under MMRB2 pairwise comparisons than every single-reward, naive weighted-sum, or 4-reward BT-ensemble baseline. ---