# Research Papers — 2026-04 · bundle page 126 of 233 > Full-text markdown of papers #6251–6300 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/126 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/125.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/127.md) ### Multilingual Multi-Label Emotion Classification at Scale with Synthetic Data Authors: Vadim Borisov Published: 2026-04-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.12633v1 Emotion classification in multilingual settings remains constrained by the scarcity of annotated data: existing corpora are predominantly English, single-label, and cover few languages. We address this gap by constructing a large-scale synthetic training corpus of over 1M multi-label samples (50k per language) across 23 languages: Arabic, Bengali, Dutch, English, French, German, Hindi, Indonesian, Italian, Japanese, Korean, Mandarin, Polish, Portuguese, Punjabi, Russian, Spanish, Swahili, Tamil, Turkish, Ukrainian, Urdu, and Vietnamese, covering 11 emotion categories using culturally-adapted generation and programmatic quality filtering. We train and compare six multilingual transformer encoders, from DistilBERT (135M parameters) to XLM-R-Large (560M parameters), under identical conditions. On our in-domain test set, XLM-R-Large achieves 0.868 F1-micro and 0.987 AUC-micro. To validate against human-annotated data, we evaluate all models zero-shot on GoEmotions (English) and SemEval-2018 Task 1 E-c (English, Arabic, Spanish). On threshold-free ranking metrics, XLM-R-Large matches or exceeds English-only specialist models, tying on AP-micro (0.636) and LRAP (0.804) while surpassing on AUC-micro (0.810 vs. 0.787), while natively supporting all 23 languages. The best base-sized model is publicly available at https://huggingface.co/tabularisai/multilingual-emotion-classification --- ### Calibration-Aware Policy Optimization for Reasoning LLMs Authors: Ziqi Wang, Xingzhou Lou, Meiqi Wu, Zhengqi Wen, Junge Zhang Published: 2026-04-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.12632v1 Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity than correct ones, degrading relative calibration as described by the Area Under the Curve (AUC). Existing approaches either yield limited improvements in calibration or sacrifice gains in reasoning accuracy. We first prove that this degradation in GRPO-style algorithms stems from their uncertainty-agnostic advantage estimation, which inevitably misaligns optimization gradients with calibration. This leads to improved accuracy at the expense of degraded calibration. We then propose Calibration-Aware Policy Optimization (CAPO). It adopts a logistic AUC surrogate loss that is theoretically consistent and admits regret bound, enabling uncertainty-aware advantage estimation. By further incorporating a noise masking mechanism, CAPO achieves stable learning dynamics that jointly optimize calibration and accuracy. Experiments on multiple mathematical reasoning benchmarks show that CAPO-1.5B significantly improves calibration by up to 15% while achieving accuracy comparable to or better than GRPO, and further boosts accuracy on downstream inference-time scaling tasks by up to 5%. Moreover, when allowed to abstain under low-confidence conditions, CAPO achieves a Pareto-optimal precision-coverage trade-off, highlighting its practical value for hallucination mitigation. --- ### GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning Authors: Zhaochen Liu, Limeng Qiao, Guanglu Wan, Tingting Jiang Published: 2026-04-14 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.12630v1 Multimodal large language models (MLLMs) have exhibited remarkable performance in various visual tasks, yet still struggle with spatial reasoning. Recent efforts mitigate this by injecting geometric features from 3D foundation models, but rely on static single-layer extractions. We identify that such an approach induces a task misalignment bias: the geometric features naturally evolve towards 3D pretraining objectives, which may contradict the heterogeneous spatial demands of MLLMs, rendering any single layer fundamentally insufficient. To resolve this, we propose GeoAlign, a novel framework that dynamically aggregates multi-layer geometric features to realign with the actual demands. GeoAlign constructs a hierarchical geometric feature bank and leverages the MLLM's original visual tokens as content-aware queries to perform layer-wise sparse routing, adaptively fetching the suitable geometric features for each patch. Extensive experiments on VSI-Bench, ScanQA, and SQA3D demonstrate that our compact 4B model effectively achieves state-of-the-art performance, even outperforming larger existing MLLMs. --- ### KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance Authors: Linhao Yu, Tianmeng Yang, Siyu Ding, Renren Jin, Naibin Gu, Xiangzhao Hao, Shuaiyi Nie, Deyi Xiong, Weichong Yin, Yu Sun, Hua Wu Published: 2026-04-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.12627v1 RLVR improves reasoning in large language models, but its effectiveness is often limited by severe reward sparsity on hard problems. Recent hint-based RL methods mitigate sparsity by injecting partial solutions or abstract templates, yet they typically scale guidance by adding more tokens, which introduce redundancy, inconsistency, and extra training overhead. We propose \textbf{KnowRL} (Knowledge-Guided Reinforcement Learning), an RL training framework that treats hint design as a minimal-sufficient guidance problem. During RL training, KnowRL decomposes guidance into atomic knowledge points (KPs) and uses Constrained Subset Search (CSS) to construct compact, interaction-aware subsets for training. We further identify a pruning interaction paradox -- removing one KP may help while removing multiple such KPs can hurt -- and explicitly optimize for robust subset curation under this dependency structure. We train KnowRL-Nemotron-1.5B from OpenMath-Nemotron-1.5B. Across eight reasoning benchmarks at the 1.5B scale, KnowRL-Nemotron-1.5B consistently outperforms strong RL and hinting baselines. Without KP hints at inference, KnowRL-Nemotron-1.5B reaches 70.08 average accuracy, already surpassing Nemotron-1.5B by +9.63 points; with selected KPs, performance improves to 74.16, establishing a new state of the art at this scale. The model, curated training data, and code are publicly available at https://github.com/Hasuer/KnowRL. --- ### Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting Authors: Ziyuan Xia, Jingyi Xu, Chong Cui, Yuanhong Yu, Jiazhao Zhang, Qingsong Yan, Tao Ni, Junbo Chen, Xiaowei Zhou, Hujun Bao, Ruizhen Hu, Sida Peng Published: 2026-04-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.12626v2 Training embodied AI agents depends critically on the visual fidelity of simulation environments and the ability to model dynamic humans. Current simulators predominantly rely on mesh-based rasterization, for which photorealistic assets are costly to author at scale, and their support for dynamic human avatars is largely constrained to mesh representations, hindering agent generalization to human-populated real-world scenarios. We present Habitat-GS, a navigation-centric embodied AI simulator extended from Habitat-Sim that integrates 3D Gaussian Splatting scene rendering and drivable gaussian avatars while maintaining full compatibility with the Habitat ecosystem. Our system implements a 3DGS renderer for real-time photorealistic rendering and supports scalable 3DGS asset import from diverse sources. For dynamic human modeling, we introduce a gaussian avatar module that enables each avatar to simultaneously serve as a photorealistic visual entity and an effective navigation obstacle, allowing agents to learn human-aware behaviors in realistic settings. Experiments on point-goal navigation demonstrate that agents trained on 3DGS scenes achieve stronger cross-domain generalization. Evaluations on avatar-aware navigation further confirm that gaussian avatars enable effective human-aware navigation, while performance benchmarks validate the system's scalability. Code is available at https://github.com/zju3dv/habitat-gs. --- ### Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting Authors: Ziyuan Xia, Jingyi Xu, Chong Cui, Yuanhong Yu, Jiazhao Zhang, Qingsong Yan, Tao Ni, Junbo Chen, Xiaowei Zhou, Hujun Bao, Ruizhen Hu, Sida Peng Published: 2026-04-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.12626v1 Training embodied AI agents depends critically on the visual fidelity of simulation environments and the ability to model dynamic humans. Current simulators rely on mesh-based rasterization with limited visual realism, and their support for dynamic human avatars, where available, is constrained to mesh representations, hindering agent generalization to human-populated real-world scenarios. We present Habitat-GS, a navigation-centric embodied AI simulator extended from Habitat-Sim that integrates 3D Gaussian Splatting scene rendering and drivable gaussian avatars while maintaining full compatibility with the Habitat ecosystem. Our system implements a 3DGS renderer for real-time photorealistic rendering and supports scalable 3DGS asset import from diverse sources. For dynamic human modeling, we introduce a gaussian avatar module that enables each avatar to simultaneously serve as a photorealistic visual entity and an effective navigation obstacle, allowing agents to learn human-aware behaviors in realistic settings. Experiments on point-goal navigation demonstrate that agents trained on 3DGS scenes achieve stronger cross-domain generalization, with mixed-domain training being the most effective strategy. Evaluations on avatar-aware navigation further confirm that gaussian avatars enable effective human-aware navigation. Finally, performance benchmarks validate the system's scalability across varying scene complexity and avatar counts. --- ### Neural Dynamic GI: Random-Access Neural Compression for Temporal Lightmaps in Dynamic Lighting Environments Authors: Jianhui Wu, Jian Zhou, Zhi Zhou, Zhangjin Huang, Chao Li Published: 2026-04-14 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2604.12625v2 High-quality global illumination (GI) in real-time rendering is commonly achieved using precomputed lighting techniques, with lightmap as the standard choice. To support GI for static objects in dynamic lighting environments, multiple lightmaps at different lighting conditions need to be precomputed, which incurs substantial storage and memory overhead. To overcome this limitation, we propose Neural Dynamic GI (NDGI), a novel compression technique specifically designed for temporal lightmap sets. Our method utilizes multi-dimensional feature maps and lightweight neural networks to integrate the temporal information instead of storing multiple sets explicitly, which significantly reduces the storage size of lightmaps. Additionally, we introduce a block compression (BC) simulation strategy during the training process, which enables BC compression on the final generated feature maps and further improves the compression ratio. To enable efficient real-time decompression, we also integrate a virtual texturing (VT) system with our neural representation. Compared with prior methods, our approach achieves high-quality dynamic GI while maintaining remarkably low storage and memory requirements, with only modest real-time decompression overhead. To facilitate further research in this direction, we will release our temporal lightmap dataset precomputed in multiple scenes featuring diverse temporal variations. --- ### Efficient Semantic Image Communication for Traffic Monitoring at the Edge Authors: Damir Assylbek, Nurmukhammed Aitymbetov, Marko Ristin, Dimitrios Zorbas Published: 2026-04-14 Categories: cs.CV, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2604.12622v1 Many visual monitoring systems operate under strict communication constraints, where transmitting full-resolution images is impractical and often unnecessary. In such settings, visual data is often used for object presence, spatial relationships, and scene context rather than exact pixel fidelity. This paper presents two semantic image communication pipelines for traffic monitoring, MMSD and SAMR, that reduce transmission cost while preserving meaningful visual information. MMSD (Multi-Modal Semantic Decomposition) targets very high compression together with data confidentiality, since sensitive pixel content is not transmitted. It replaces the original image with compact semantic representations, namely segmentation maps, edge maps, and textual descriptions, and reconstructs the scene at the receiver using a diffusion-based generative model. SAMR (Semantic-Aware Masking Reconstruction) targets higher visual quality while maintaining strong compression. It selectively suppresses non-critical image regions according to semantic importance before standard JPEG encoding and restores the missing content at the receiver through generative inpainting. Both designs follow an asymmetric sender-receiver architecture, where lightweight processing is performed at the edge and computationally intensive reconstruction is offloaded to the server. On a Raspberry Pi~5, the edge-side processing time is about 15s for MMSD and 9s for SAMR. Experimental results show average transmitted-data reductions of 99% for MMSD and 99.1% for SAMR. In addition, MMSD achieves lower payload size than the recent SPIC baseline while preserving strong semantic consistency, whereas SAMR provides a better quality-compression trade-off than standard JPEG and SQ-GAN under comparable operating conditions. --- ### SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models Authors: You Qin, Linqing Wang, Hao Fei, Roger Zimmermann, Liefeng Bo, Qinglin Lu, Chunyu Wang Published: 2026-04-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.12617v2 The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundamental gap separates them. SFT optimizes the denoiser only on ground-truth states sampled from the forward noising process; once inference deviates from these ideal states, subsequent denoising relies on out-of-distribution generalization rather than learned correction, exhibiting the same exposure bias that afflicts autoregressive models, but accumulated along the denoising trajectory instead of the token sequence. RL can in principle address this mismatch, yet its terminal reward signal is sparse, suffers from credit-assignment difficulty, and risks reward hacking. We propose SOAR (Self-Correction for Optimal Alignment and Refinement), a bias-correction post-training method that fills this gap. Starting from a real sample, SOAR performs a single stop-gradient rollout with the current model, re-noises the resulting off-trajectory state, and supervises the model to steer back toward the original clean target. The method is on-policy, reward-free, and provides dense per-timestep supervision with no credit-assignment problem. On SD3.5-Medium, SOAR improves GenEval from 0.70 to 0.78 and OCR from 0.64 to 0.67 over SFT, while simultaneously raising all model-based preference scores. In controlled reward-specific experiments, SOAR surpasses Flow-GRPO in final metric value on both aesthetic and text-image alignment tasks, despite having no access to a reward model. Since SOAR's base loss subsumes the standard SFT objective, it can directly replace SFT as a stronger first post-training stage after pretraining, while remaining fully compatible with subsequent RL alignment. --- ### Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Authors: Jianhao Chen, Shiqin Wang, Haoyang Chen, Hanjie Zhao, Haozhe Liang, Zheng Wang, Tieyun Qian Published: 2026-04-14 Categories: cs.AI, cs.MM arXiv: https://arxiv.org/abs/2604.12616v3 Vision-Language Models (VLMs) expand the attack surface of safety-aligned systems by coupling visual perception with text generation. Existing multimodal jailbreak attacks primarily rely on crafted visual content, adversarial perturbations, or image-specific attack strategies, leaving the potential of reusable visual anchors in benign natural images largely unexplored. To address the problem, we introduce MemJack, a memory-augmented multi-agent framework for automated VLM red-teaming with natural images. MemJack combines visual-anchor discovery, visual-semantic camouflage, response evaluation, reflection-guided repair, and dynamic replanning within a closed-loop attack pipeline. Beyond attack generation, MemJack automatically transforms public images into attack anchors, enables the construction of MemJack-Bench, a dataset of over 113,000 interactive multimodal jailbreak trajectories for safety evaluation and defensive alignment. Extensive empirical evaluations across full, unmodified COCO val2017 images demonstrate that MemJack achieves a 71.48\% attack success rate (ASR) against Qwen3-VL-Plus, scaling to 90\% under extended budgets. Compared with representative multimodal jailbreak baselines under the same natural-image evaluation setting, MemJack achieves the highest ASR while requiring fewer mean rounds to success, demonstrating superior jailbreak effectiveness on VLMs. These results demonstrate that benign natural images can act as transferable jailbreak anchors and reveal substantial vulnerabilities in current safety-aligned VLMs. --- ### Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Authors: Jianhao Chen, Haoyang Chen, Hanjie Zhao, Haozhe Liang, Tieyun Qian Published: 2026-04-14 Categories: cs.AI, cs.MM arXiv: https://arxiv.org/abs/2604.12616v1 The rapid evolution of Vision-Language Models (VLMs) has catalyzed unprecedented capabilities in artificial intelligence; however, this continuous modal expansion has inadvertently exposed a vastly broadened and unconstrained adversarial attack surface. Current multimodal jailbreak strategies primarily focus on surface-level pixel perturbations and typographic attacks or harmful images; however, they fail to engage with the complex semantic structures intrinsic to visual data. This leaves the vast semantic attack surface of original, natural images largely unscrutinized. Driven by the need to expose these deep-seated semantic vulnerabilities, we introduce \textbf{MemJack}, a \textbf{MEM}ory-augmented multi-agent \textbf{JA}ilbreak atta\textbf{CK} framework that explicitly leverages visual semantics to orchestrate automated jailbreak attacks. MemJack employs coordinated multi-agent cooperation to dynamically map visual entities to malicious intents, generate adversarial prompts via multi-angle visual-semantic camouflage, and utilize an Iterative Nullspace Projection (INLP) geometric filter to bypass premature latent space refusals. By accumulating and transferring successful strategies through a persistent Multimodal Experience Memory, MemJack maintains highly coherent extended multi-turn jailbreak attack interactions across different images, thereby improving the attack success rate (ASR) on new images. Extensive empirical evaluations across full, unmodified COCO val2017 images demonstrate that MemJack achieves a 71.48\% ASR against Qwen3-VL-Plus, scaling to 90\% under extended budgets. Furthermore, to catalyze future defensive alignment research, we will release \textbf{MemJack-Bench}, a comprehensive dataset comprising over 113,000 interactive multimodal jailbreak attack trajectories, establishing a vital foundation for developing inherently robust VLMs. --- ### DeepTest Tool Competition 2026: Benchmarking an LLM-Based Automotive Assistant Authors: Lev Sorokin, Ivan Vasilev, Samuele Pasini Published: 2026-04-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.12615v1 This report summarizes the results of the first edition of the Large Language Model (LLM) Testing competition, held as part of the DeepTest workshop at ICSE 2026. Four tools competed in benchmarking an LLM-based car manual information retrieval application, with the objective of identifying user inputs for which the system fails to appropriately mention warnings contained in the manual. The testing solutions were evaluated based on their effectiveness in exposing failures and the diversity of the discovered failure-revealing tests. We report on the experimental methodology, the competitors, and the results. --- ### Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs Authors: Xudong Wang, Chaoning Zhang, Qigan Sun, Zhenzhen Huang, Chang Lu, Sheng Zheng, Zeyu Ma, Caiyan Qin, Yang Yang, Hengtao Shen Published: 2026-04-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.12610v1 Retrieval-Augmented Generation (RAG) mitigates hallucination in large language models (LLMs) by incorporating external knowledge during generation. However, the effectiveness of RAG depends not only on the design of the retriever and the capacity of the underlying model, but also on how retrieved evidence is structured and aligned with the query. Existing RAG approaches typically retrieve and concatenate unstructured text fragments as context, which often introduces redundant or weakly relevant information. This practice leads to excessive context accumulation, reduced semantic alignment, and fragmented reasoning chains, thereby degrading generation quality while increasing token consumption. To address these challenges, we propose Tri-RAG, a structured triplet-based retrieval framework that improves retrieval efficiency through reasoning-aligned context construction. Tri-RAG automatically transforms external knowledge from natural language into standardized structured triplets consisting of Condition, Proof, and Conclusion, explicitly capturing logical relations among knowledge fragments using lightweight prompt-based adaptation with frozen model parameters. Building on this representation, the triplet head Condition is treated as an explicit semantic anchor for retrieval and matching, enabling precise identification of query-relevant knowledge units without directly concatenating lengthy raw texts. As a result, Tri-RAG achieves a favorable balance between retrieval accuracy and context token efficiency. Experimental results across multiple benchmark datasets demonstrate that Tri-RAG significantly improves retrieval quality and reasoning efficiency, while producing more stable generation behavior and more efficient resource utilization in complex reasoning scenarios. --- ### LLM-Guided Prompt Evolution for Password Guessing Authors: Vladimir A. Mazin, Mikhail A. Zorin, Dmitrii S. Korzh, Elvir Z. Karimov, Dmitrii A. Bolokhov, Oleg Y. Rogov Published: 2026-04-14 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.12601v1 Passwords still remain a dominant authentication method, yet their security is routinely subverted by predictable user choices and large-scale credential leaks. Automated password guessing is a key tool for stress-testing password policies and modeling attacker behavior. This paper applies LLM-driven evolutionary computation to automatically optimize prompts for the LLM password guessing framework. Using OpenEvolve, an open-source system combining MAP-Elites quality-diversity search with an island population model we evolve prompts that maximize cracking rate on a RockYou-derived test set. We evaluate three configurations: a local setup with Qwen3 8B, a single compact cloud model Gemini-2.5 Flash, and a two-model ensemble of frontier LLMs. The approach raises the cracking rates from 2.02\% to 8.48\%. Character distribution analysis further confirms how evolved prompts produce statistically more realistic passwords. Automated prompt evolution is a low-barrier yet effective way to strengthen LLM-based password auditing and underlining how attack pipelines show tendency via automated improvements. --- ### Spatial-Spectral Adaptive Fidelity and Noise Prior Reduction Guided Hyperspectral Image Denoising Authors: Xuelin Xie, Xiliang Lu, Zhengshan Wang, Yang Zhang, Long Chen Published: 2026-04-14 Categories: cs.CV, math.NA arXiv: https://arxiv.org/abs/2604.12600v1 The core challenge of hyperspectral image denoising is striking the right balance between data fidelity and noise prior modeling. Most existing methods place too much emphasis on the intrinsic priors of the image while overlooking diverse noise assumptions and the dynamic trade-off between fidelity and priors. To address these issues, we propose a denoising framework that integrates noise prior reduction and a spatial-spectral adaptive fidelity term. This framework considers comprehensive noise priors with fewer parameters and introduces an adaptive weight tensor to dynamically balance the fidelity and prior regularization terms. Within this framework, we further develop a fast and robust pixel-wise model combined with the representative coefficient total variation regularizer to accurately remove mixed noise in HSIs. The proposed method not only efficiently handles various types of noise but also accurately captures the spectral low-rank structure and local smoothness of HSIs. An efficient optimization algorithm based on the alternating direction method of multipliers is designed to ensure stable and fast convergence. Extensive experiments on simulated and real-world datasets demonstrate that the proposed model achieves superior denoising performance while maintaining competitive computational efficiency. --- ### KumoRFM-2: Scaling Foundation Models for Relational Learning Authors: Valter Hudovernik, Federico López, Vid Kocijan, Akihiro Nitta, Jan Eric Lenssen, Jure Leskovec, Matthias Fey Published: 2026-04-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.12596v1 We introduce KumoRFM-2, the next iteration of a pre-trained foundation model for relational data. KumoRFM-2 supports in-context learning as well as fine-tuning and is applicable to a wide range of predictive tasks. In contrast to tabular foundation models, KumoRFM-2 natively operates on relational data, processing one or more connected tables simultaneously without manual table flattening or target variable generation, all while preserving temporal consistency. KumoRFM-2 leverages a large corpus of synthetic and real-world data to pre-train across four axes: the row and column dimensions at the individual table level, and the foreign key and cross-sample dimensions at the database level. In contrast to its predecessor, KumoRFM-2 injects task information as early as possible, enabling sharper selection of task-relevant columns and improved robustness to noisy data. Through extensive experiments on 41 challenging benchmarks and analysis around expressivity and sensitivity, we demonstrate that KumoRFM-2 outperforms supervised and foundational approaches by up to 8%, while maintaining strong performance under extreme settings of cold start and noisy data. To our knowledge, this is the first time a few-shot foundation model has been shown to surpass supervised approaches on common benchmark tasks, with performance further improving upon fine-tuning. Finally, while KumoRFM-1 was limited to small-scale in-memory datasets, KumoRFM-2 scales to billion-scale relational datasets. --- ### ELoG-GS: Dual-Branch Gaussian Splatting with Luminance-Guided Enhancement for Extreme Low-light 3D Reconstruction Authors: Yuhao Liu, Dingju Wang, Ziyang Zheng Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12592v2 This paper presents our approach to the NTIRE 2026 3D Restoration and Reconstruction Challenge (Track 1), which focuses on reconstructing high-quality 3D representations from degraded multi-view inputs. The challenge involves recovering geometrically consistent and photorealistic 3D scenes in extreme low-light environments. To address this task, we propose Extreme Low-light Optimized Gaussian Splatting (ELoG-GS), a robust low-light 3D reconstruction pipeline that integrates learning-based point cloud initialization and luminance-guided color enhancement for stable and photorealistic Gaussian Splatting. Our method incorporates both geometry-aware initialization and photometric adaptation strategies to improve reconstruction fidelity under challenging conditions. Extensive experiments on the NTIRE Track 1 benchmark demonstrate that our approach significantly improves reconstruction quality over the baselines, achieving superior visual fidelity and geometric consistency. The proposed method provides a practical solution for robust 3D reconstruction in real-world degraded scenarios. In the final testing phase, our method achieved a PSNR of 18.6626 and an SSIM of 0.6855 on the official platform leaderboard. Code is available at https://github.com/lyh120/FSGS_EAPGS. --- ### Relaxing Anchor-Frame Dominance for Mitigating Hallucinations in Video Large Language Models Authors: Zijian Liu, Sihan Cao, Pengcheng Zheng, Kuien Liu, Caiyan Qin, Xiaolin Qin, Jiwei Wei, Chaoning Zhang Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12582v1 Recent Video Large Language Models (Video-LLMs) have demonstrated strong capability in video understanding, yet they still suffer from hallucinations. Existing mitigation methods typically rely on training, input modification, auxiliary guidance, or additional decoding procedures, while largely overlooking a more fundamental challenge. During generation, Video-LLMs tend to over-rely on a limited portion of temporal evidence, leading to temporally imbalanced evidence aggregation across the video. To address this issue, we investigate a decoder-side phenomenon in which the model exhibits a temporally imbalanced concentration pattern. We term the frame with the highest aggregated frame-level attention mass the anchor frame. We find that this bias is largely independent of the input video and instead appears to reflect a persistent, model-specific structural or positional bias, whose over-dominance is closely associated with hallucination-prone generation. Motivated by this insight, we propose Decoder-side Temporal Rebalancing (DTR), a training-free, layer-selective inference method that rebalances temporal evidence allocation in middle-to-late decoder layers without altering visual encoding or requiring auxiliary models. DTR adaptively calibrates decoder-side visual attention to alleviate temporally imbalanced concentration and encourage under-attended frames to contribute more effectively to response generation. In this way, DTR guides the decoder to ground its outputs in temporally broader and more balanced video evidence. Extensive experiments on hallucination and video understanding benchmarks show that DTR consistently improves hallucination robustness across diverse Video-LLM families, while preserving competitive video understanding performance and high inference efficiency. --- ### PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting Authors: Kangmin Seo, MinKyu Lee, Tae-Young Kim, ByeongCheol Lee, JoonSeoung An, Jae-Pil Heo Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12580v2 Recent advances in 3D Gaussian Splatting (3DGS) have enabled impressive real-time photorealistic rendering. However, conventional training pipelines inherently assume full multi-view consistency among input images, which makes them sensitive to distractors that violate this assumption and cause visual artifacts. In this work, we revisit an underexplored aspect of 3DGS: its inherent ability to suppress inconsistent signals. Building on this insight, we propose PDF-GS (Progressive Distractor Filtering for Robust 3D Gaussian Splatting), a framework that amplifies this self-filtering property through a progressive multi-phase optimization. The progressive filtering phases gradually remove distractors by exploiting discrepancy cues, while the following reconstruction phase restores fine-grained, view-consistent details from the purified Gaussian representation. Through this iterative refinement, PDF-GS achieves robust, high-fidelity, and distractor-free reconstructions, consistently outperforming baselines across diverse datasets and challenging real-world conditions. Moreover, our approach is lightweight and easily adaptable to existing 3DGS frameworks, requiring no architectural changes or additional inference overhead, leading to a new state-of-the-art performance. The code is publicly available at https://github.com/kangrnin/PDF-GS. --- ### EEG-Based Multimodal Learning via Hyperbolic Mixture-of-Curvature Experts Authors: Runhe Zhou, Shanglin Li, Guanxiang Huang, Xinliang Zhou, Qibin Zhao, Motoaki Kawanabe, Yi Ding, Cuntai Guan Published: 2026-04-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.12579v3 Electroencephalography (EEG)-based multimodal learning integrates brain signals with complementary modalities to improve mental state assessment, providing great clinical potential. The effectiveness of such paradigms largely depends on the representation learning on heterogeneous modalities. For EEG-based paradigms, one promising approach is to leverage their hierarchical structures, as recent studies have shown that both EEG and associated modalities (e.g., facial expressions) exhibit hierarchical structures reflecting complex cognitive processes. However, Euclidean embeddings struggle to represent these hierarchical structures due to their flat geometry, while hyperbolic spaces, with their exponential growth property, are naturally suited for them. In this work, we propose EEG-MoCE, a novel hyperbolic mixture-of-curvature experts framework designed for multimodal neurotechnology. EEG-MoCE assigns each modality to an expert in a learnable-curvature hyperbolic space, enabling adaptive modeling of its intrinsic geometry. A curvature-aware fusion strategy then dynamically weights experts, emphasizing modalities with richer hierarchical information. Extensive experiments on benchmark datasets demonstrate that EEG-MoCE achieves state-of-the-art performance, including emotion recognition, sleep staging, and cognitive assessment. Code is available at https://github.com/zhourunhe/EEG-MoCE. --- ### StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation Authors: Yinxi He, Kang Liao, Chunyu Lin, Tianyi Wei, Yao Zhao Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12575v1 This paper introduces StructDiff, a generative framework based on a single-scale diffusion model for single-image generation. Single-image generation aims to synthesize diverse samples with similar visual content to the source image by capturing its internal statistics, without relying on external data. However, existing methods often struggle to preserve the structural layout, especially for images with large rigid objects or strict spatial constraints. Moreover, most approaches lack spatial controllability, making it difficult to guide the structure or placement of generated content. To address these challenges, StructDiff introduces an \textit{adaptive receptive field} module to maintain both global and local distributions. Building on this foundation, StructDiff incorporates 3D positional encoding (PE) as a spatial prior, allowing flexible control over positions, scale, and local details of generated objects. To our knowledge, this spatial control capability represents the first exploration of PE-based manipulation in single-image generation. Furthermore, we propose a novel evaluation criterion for single-image generation based on large language models (LLMs). This criterion specifically addresses the limitations of existing objective metrics and the high labor costs associated with user studies. StructDiff also demonstrates broad applicability across downstream tasks, such as text-guided image generation, image editing, outpainting, and paint-to-image synthesis. Extensive experiments demonstrate that StructDiff outperforms existing methods in structural consistency, visual quality, and spatial controllability. The project page is available at https://butter-crab.github.io/StructDiff/. --- ### Cross-Modal Knowledge Distillation for PET-Free Amyloid-Beta Detection from MRI Authors: Francesco Chiumento, Julia Dietlmeier, Ronan P. Killeen, Kathleen M. Curran, Noel E. O'Connor, Mingming Liu Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12574v1 Detecting amyloid-$β$ (A$β$) positivity is crucial for early diagnosis of Alzheimer's disease but typically requires PET imaging, which is costly, invasive, and not widely accessible, limiting its use for population-level screening. We address this gap by proposing a PET-guided knowledge distillation framework that enables A$β$ prediction from MRI alone, without requiring non-imaging clinical covariates or PET at inference. Our approach employs a BiomedCLIP-based teacher model that learns PET-MRI alignment via cross-modal attention and triplet contrastive learning with PET-informed (Centiloid-aware) online negative sampling. An MRI-only student then mimics the teacher via feature-level and logit-level distillation. Evaluated across four MRI contrasts (T1w, T2w, FLAIR, T2*) and two independent datasets, our approach demonstrates effective knowledge transfer (best AUC: 0.74 on OASIS-3, 0.68 on ADNI) while maintaining interpretability and eliminating the need for clinical variables. Saliency analysis confirms that predictions focus on anatomically relevant cortical regions, supporting the clinical viability of PET-free A$β$ screening. Code is available at https://github.com/FrancescoChiumento/pet-guided-mri-amyloid-detection. --- ### IDEA: An Interpretable and Editable Decision-Making Framework for LLMs via Verbal-to-Numeric Calibration Authors: Yanji He, Yuxin Jiang, Yiwen Wu, Bo Huang, Jiaheng Wei, Wei Wang Published: 2026-04-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.12573v1 Large Language Models are increasingly deployed for decision-making, yet their adoption in high-stakes domains remains limited by miscalibrated probabilities, unfaithful explanations, and inability to incorporate expert knowledge precisely. We propose IDEA, a framework that extracts LLM decision knowledge into an interpretable parametric model over semantically meaningful factors. Through joint learning of verbal-to-numerical mappings and decision parameters via EM, correlated sampling that preserves factor dependencies, and direct parameter editing with mathematical guarantees, IDEA produces calibrated probabilities while enabling quantitative human-AI collaboration. Experiments across five datasets show IDEA with Qwen-3-32B (78.6%) outperforms DeepSeek R1 (68.1%) and GPT-5.2 (77.9%), achieving perfect factor exclusion and exact calibration -- precision unattainable through prompting alone. The implementation is publicly available at https://github.com/leonbig/IDEA. --- ### Evolution-Inspired Sample Competition for Deep Neural Network Optimization Authors: Ying Zheng, Yiyi Zhang, Yi Wang, Lap-Pui Chau Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12568v1 Conventional deep network training generally optimizes all samples under a largely uniform learning paradigm, without explicitly modeling the heterogeneous competition among them. Such an oversimplified treatment can lead to several well-known issues, including bias under class imbalance, insufficient learning of hard samples, and the erroneous reinforcement of noisy samples. In this work, we present \textit{Natural Selection} (NS), a novel evolution-inspired optimization method that explicitly incorporates competitive interactions into deep network training. Unlike conventional sample reweighting strategies that rely mainly on predefined heuristics or static criteria, NS estimates the competitive status of each sample in a group-wise context and uses it to adaptively regulate its training contribution. Specifically, NS first assembles multiple samples into a composite image and rescales it to the original input size for model inference. Based on the resulting predictions, a natural selection score is computed for each sample to characterize its relative competitive variation within the constructed group. These scores are then used to dynamically reweight the sample-wise loss, thereby introducing an explicit competition-driven mechanism into the optimization process. In this way, NS provides a simple yet effective means of moving beyond uniform sample treatment and enables more adaptive and balanced model optimization. Extensive experiments on 12 public datasets across four image classification tasks demonstrate the effectiveness of the proposed method. Moreover, NS is compatible with diverse network architectures and does not depend on task-specific assumptions, indicating its strong generality and practical potential. The code will be made publicly available. --- ### Scalable Trajectory Generation for Whole-Body Mobile Manipulation Authors: Yida Niu, Xinhai Chang, Xin Liu, Ziyuan Jiao, Yixin Zhu Published: 2026-04-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.12565v1 Robots deployed in unstructured environments must coordinate whole-body motion -- simultaneously moving a mobile base and arm -- to interact with the physical world. This coupled mobility and dexterity yields a state space that grows combinatorially with scene and object diversity, demanding datasets far larger than those sufficient for fixed-base manipulation. Yet existing acquisition methods, including teleoperation and planning, are either labor-intensive or computationally prohibitive at scale. The core bottleneck is the lack of a scalable pipeline for generating large-scale, physically valid, coordinated trajectory data across diverse embodiments and environments. Here we introduce AutoMoMa, a GPU-accelerated framework that unifies AKR modeling, which consolidates base, arm, and object kinematics into a single chain, with parallelized trajectory optimization. AutoMoMa achieves 5,000 episodes per GPU-hour (over $80\times$ faster than CPU-based baselines), producing a dataset of over 500k physically valid trajectories spanning 330 scenes, diverse articulated objects, and multiple robot embodiments. Prior datasets were forced to compromise on scale, diversity, or kinematic fidelity; AutoMoMa addresses all three simultaneously. Training downstream IL policies further reveals that even a single articulated-object task requires tens of thousands of demonstrations for SOTA methods to reach $\approx 80\%$ success, confirming that data scarcity -- not algorithmic limitations -- has been the binding constraint. AutoMoMa thus bridges high-performance planning and reliable IL-based control, providing the infrastructure previously missing for coordinated mobile manipulation research. By making large-scale, kinematically valid training data practical, AutoMoMa showcases generalizable whole-body robot policies capable of operating in the diverse, unstructured settings of the real world. --- ### FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing Authors: Peng Wang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu Published: 2026-04-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.12559v1 Unstructured model editing aims to update models with real-world text, yet existing methods often memorize text holistically without reliable fine-grained fact access. To address this, we propose FABLE, a hierarchical framework that decouples fine-grained fact injection from holistic text generation. FABLE follows a two-stage, fact-first strategy: discrete facts are anchored in shallow layers, followed by minimal updates to deeper layers to produce coherent text. This decoupling resolves the mismatch between holistic recall and fine-grained fact access, reflecting the unidirectional Transformer flow in which surface-form generation amplifies rather than corrects underlying fact representations. We also introduce UnFine, a diagnostic benchmark with fine-grained question-answer pairs and fact-level metrics for systematic evaluation. Experiments show that FABLE substantially improves fine-grained question answering while maintaining state-of-the-art holistic editing performance. Our code is publicly available at https://github.com/caskcsg/FABLE. --- ### Cross-Attentive Multiview Fusion of Vision-Language Embeddings Authors: Tomas Berriel Martins, Martin R. Oswald, Javier Civera Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12551v1 Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically back-project and average 2D descriptors across views, or heuristically select a single representative one, often resulting in suboptimal 3D representations. In this work, we introduce a novel multiview transformer architecture that cross-attends across vision-language descriptors from multiple viewpoints and fuses them into a unified per-3D-instance embedding. As a second contribution, we leverage multiview consistency as a self-supervision signal for this fusion, which significantly improves performance when added to a standard supervised target-class loss. Our Cross-Attentive Multiview Fusion, which we denote with its acronym CAMFusion, not only consistently outperforms naive averaging or single-view descriptor selection, but also achieves state-of-the-art results on 3D semantic and instance classification benchmarks, including zero-shot evaluations on out-of-domain datasets. --- ### Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents Authors: Wanchun Ni, Jiugeng Sun, Yixian Liu, Mennatallah El-Assady Published: 2026-04-14 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2604.12545v1 Improving policymaking is a central concern in public administration. Prior human subject studies reveal substantial cross-cultural differences in citizens' emotional responses to red tape during policy implementation. While LLM agents offer opportunities to simulate human-like responses and reduce experimental costs, their ability to generate culturally appropriate emotional responses to red tape remains unverified. To address this gap, we propose an evaluation framework for assessing LLMs' emotional responses to red tape across diverse cultural contexts. As a pilot study, we apply this framework to a single red-tape scenario. Our results show that all models exhibit limited alignment with human emotional responses, with notably weaker performance in Eastern cultures. Cultural prompting strategies prove largely ineffective in improving alignment. We further introduce \textbf{RAMO}, an interactive interface for simulating citizens' emotional responses to red tape and for collecting human data to improve models. The interface is publicly available at https://ramo-chi.ivia.ch. --- ### A Two-Stage LLM Framework for Accessible and Verified XAI Explanations Authors: Georgios Mermigkis, Dimitris Metaxakis, Marios Tyrovolas, Argiris Sofotasios, Nikolaos Avgeris, Panagiotis Hadjidoukas, Chrysostomos Stylios Published: 2026-04-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.12543v1 Large Language Models (LLMs) are increasingly used to translate the technical outputs of eXplainable Artificial Intelligence (XAI) methods into accessible natural-language explanations. However, existing approaches often lack guarantees of accuracy, faithfulness, and completeness. At the same time, current efforts to evaluate such narratives remain largely subjective or confined to post-hoc scoring, offering no safeguards to prevent flawed explanations from reaching end-users. To address these limitations, this paper proposes a Two-Stage LLM Meta-Verification Framework that consists of (i) an Explainer LLM that converts raw XAI outputs into natural-language narratives, (ii) a Verifier LLM that assesses them in terms of faithfulness, coherence, completeness, and hallucination risk, and (iii) an iterative refeed mechanism that uses the Verifier's feedback to refine and improve them. Experiments across five XAI techniques and datasets, using three families of open-weight LLMs, show that verification is crucial for filtering unreliable explanations while improving linguistic accessibility compared with raw XAI outputs. In addition, the analysis of the Entropy Production Rate (EPR) during the refinement process indicates that the Verifier's feedback progressively guides the Explainer toward more stable and coherent reasoning. Overall, the proposed framework provides an efficient pathway toward more trustworthy and democratized XAI systems. --- ### When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP Authors: Mahounan Pericles Adjovi, Roald Eiselen, Prasenjit Mitra Published: 2026-04-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.12540v1 Data scarcity limits NLP development for low-resource African languages. We evaluate two data augmentation methods -- LLM-based generation (Gemini 2.5 Flash) and back-translation (NLLB-200) -- for Hausa and Fongbe, two West African languages that differ substantially in LLM generation quality. We assess augmentation on named entity recognition (NER) and part-of-speech (POS) tagging using MasakhaNER 2.0 and MasakhaPOS benchmarks. Our results reveal that augmentation effectiveness depends on task type rather than language or LLM quality alone. For NER, neither method improves over baseline for either language; LLM augmentation reduces Hausa NER by 0.24% F1 and Fongbe NER by 1.81% F1. For POS tagging, LLM augmentation improves Fongbe by 0.33% accuracy, while back-translation improves Hausa by 0.17%; back-translation reduces Fongbe POS by 0.35% and has negligible effect on Hausa POS. The same LLM-generated synthetic data produces opposite effects across tasks for Fongbe -- hurting NER while helping POS -- suggesting task structure governs augmentation outcomes more than synthetic data quality. These findings challenge the assumption that LLM generation quality predicts augmentation success, and provide actionable guidance: data augmentation should be treated as a task-specific intervention rather than a universally beneficial preprocessing step. --- ### MODIX: A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language Models Authors: Ruoxiang Huang, Zhen Yuan Published: 2026-04-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.12537v1 Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet their positional encoding mechanisms remain suboptimal. Existing approaches uniformly assign positional indices to all tokens, overlooking variations in information density within and across modalities, which leads to inefficient attention allocation where redundant visual regions dominate while informative content is underrepresented. We identify positional granularity as an implicit resource and propose MODIX (Multimodal Information-Driven Positional IndeX Scaling), a training-free framework that dynamically adapts positional strides based on modality-specific contributions. MODIX jointly models intra-modal density via covariance-based entropy and inter-modal interaction via cross-modal alignment to derive unified scores, which rescale positional indices to allocate finer granularity to informative modalities while compressing redundant ones, without requiring any modification to model parameters or architecture. Experiments across diverse architectures and benchmarks demonstrate that MODIX consistently improves multimodal reasoning and adaptively reallocates attention according to task-dependent information distributions, suggesting that positional encoding should be treated as an adaptive resource in Transformers for multimodal sequence modeling. --- ### MCAnalysis: An Open-Source Package for Preprocessing, Modelling, and Visualisation of Menstrual Cycle Effects in Digital Health Data Authors: Kyra Delray, Glyn Lewis, Bola Grace, Joseph Hayes, Robin Evans Published: 2026-04-14 Categories: stat.AP, stat.ML arXiv: https://arxiv.org/abs/2604.12536v1 The menstrual cycle influences numerous physiological and psychological outcomes, yet standardised, open-source statistical methods for quantifying these cyclic effects remain lacking. We developed mcanalysis, an open-source package in R and Python implementing a Fourier-basis generalised additive model (GAM) for menstrual cycle research. The package provides a complete pipeline: processing period dates, labelling cycle days relative to menstruation onset, filtering physiologically plausible cycles, normalising outcomes to individual means, fitting cyclic GAMs with bootstrap confidence intervals, and identifying turning points to generate phase-specific linear trend estimates. We demonstrate the package on 15 wearable and self-reported outcomes using data from the Juli chronic health management application (N = 2,816 users). Nine of 15 outcomes showed evidence of association with the menstrual cycle (p < 0.05), spanning physiological (HRV p < 0.001, oxygen saturation p = 0.002), sleep (p = 0.003), symptom (migraine p < 0.001, headache p = 0.005), mood (EMA mood p = 0.024, PHQ-8 lack of energy p = 0.008, mania p = 0.041), and activity (hours outside p = 0.019) domains. No tested confounders were significantly associated with cycle-normalised outcomes. mcanalysis provides a standardised, reproducible approach to menstrual cycle analysis for users at all levels of statistical expertise. The package is freely available at https://github.com/kyradelray/mcanalysis, with a no-code web interface at https://kyradelray.shinyapps.io/mcanalysis/. --- ### Technical Report -- A Context-Sensitive Multi-Level Similarity Framework for First-Order Logic Arguments: An Axiomatic Study Authors: Victor David, Jérôme Delobelle, Jean-Guy Mailly Published: 2026-04-14 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2604.12534v1 Similarity in formal argumentation has recently gained attention due to its significance in problems such as argument aggregation in semantics and enthymeme decoding. While existing approaches focus on propositional logic, we address the richer setting of First-Order Logic (FOL), where similarity must account for structured content. We introduce a comprehensive framework for FOL argument similarity, built upon: (1) an extended axiomatic foundation; (2) a four-level parametric model covering predicates, literals, clauses, and formulae similarity; (3) two model families, one syntax-sensitive via language models, both integrating contextual weights for nuanced and explainable similarity; and (4) formal constraints enforcing desirable properties. --- ### Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA Authors: Yogachandran Rahulamathavan, Nasir Iqbal, Juncheng Hu, Sangarapillai Lambotharan Published: 2026-04-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.12526v1 Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on everything else. This setting becomes especially difficult when deletion requests arrive sequentially, because the model must repeatedly adapt without erasing previously retained knowledge. Low-Rank Adaptation (LoRA) offers an efficient way to implement such updates, but naively combining many sequential LoRA modules leads to parameter collision, causing \textit{strong interference} between tasks. We propose a static alternative based on Singular Value Decomposition (SVD)-guided orthogonal subspace projection. Our method constrains each new LoRA update during training so that it lies in the orthogonal complement of the subspaces used by earlier unlearning tasks. This preserves task isolation without requiring dynamic routing at deployment. Experiments on CIFAR-100 with ResNet-20 and on MNIST show stable behavior across long sequences of unlearning tasks. After thirty sequential unlearning tasks, state-of-the-art static fusion reduces retained accuracy from 60.39\% to 12.70\%, whereas the proposed in-training constrained optimization maintains baseline performance ($\sim$58.1\%) while preserving strong unlearning efficacy. --- ### CoD-Lite: Real-Time Diffusion-Based Generative Image Compression Authors: Zhaoyang Jia, Naifu Xue, Zihan Zheng, Jiahao Li, Bin Li, Xiaoyi Zhang, Zongyu Guo, Yuan Zhang, Houqiang Li, Yan Lu Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12525v2 Recent advanced diffusion methods typically derive strong generative priors by scaling diffusion transformers. However, scaling fails to generalize when adapted for real-time compression scenarios that demand lightweight models. In this paper, we explore the design of real-time and lightweight diffusion codecs by addressing two pivotal questions. First, does diffusion pre-training benefit lightweight diffusion codecs? Through systematic analysis, we find that generation-oriented pre-training is less effective at small model scales whereas compression-oriented pre-training yields consistently better performance. Second, are transformers essential? We find that while global attention is crucial for standard generation, lightweight convolutions suffice for compression-oriented diffusion when paired with distillation. Guided by these findings, we establish a one-step lightweight convolution diffusion codec that achieves real-time $60$~FPS encoding and $42$~FPS decoding at 1080p. Further enhanced by distillation and adversarial learning, the proposed codec reduces bitrate by 85\% at a comparable FID to MS-ILLM, bridging the gap between generative compression and practical real-time deployment. Codes are released at https://github.com/microsoft/GenCodec/tree/main/CoD_Lite --- ### Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems Authors: Raghav Bongole, Tobias J. Oechtering, Mikael Skoglund Published: 2026-04-14 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2604.12519v1 Recent work established a generalized-Fano framework for lower bounding prior-predictive (Bayesian) CVaR in interactive statistical decision making. In this paper, we show how to instantiate that framework in concrete interactive problems and derive explicit Bayesian CVaR lower bounds from its abstract corollaries. Our approach compares a hard model with a reference model using squared Hellinger distance, and combines a lower bound on a reference hinge term with a bound on the distinguishability of the two models. We apply this approach to canonical examples, including Gaussian bandits, and obtain explicit bounds that make the dependence on key problem parameters transparent. These results show how the generalized-Fano Bayesian CVaR framework can be used as a practical lower-bound tool for interactive learning and risk-sensitive decision making. --- ### Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis Authors: Kang He, Yuzhe Ding, Xinrong Wang, Fei Li, Chong Teng, Donghong Ji Published: 2026-04-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.12518v2 Multimodal sentiment analysis (MSA) integrates heterogeneous text, audio, and visual signals to infer human emotions. While recent approaches leverage cross-modal complementarity, they often struggle to fully utilize weaker modalities. In practice, dominant modalities tend to overshadow non-verbal ones, inducing modality competition and limiting overall contributions. This imbalance degrades fusion performance and robustness under noisy or missing modalities. To address this, we propose a novel model, Enhance-then-Balance Modality Collaboration framework (EBMC). EBMC improves representation quality via semantic disentanglement and cross-modal enhancement, strengthening weaker modalities. To prevent dominant modalities from overwhelming others, an Energy-guided Modality Coordination mechanism achieves implicit gradient rebalancing via a differentiable equilibrium objective. Furthermore, Instance-aware Modality Trust Distillation estimates sample-level reliability to adaptively modulate fusion weights, ensuring robustness. Extensive experiments demonstrate that EBMC achieves state-of-the-art or competitive results and maintains strong performance under missing-modality settings. --- ### Agentic Control in Variational Language Models Authors: Yves Ruffenach Published: 2026-04-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.12513v1 We study whether a variational language model can support a minimal and measurable form of agentic control grounded in its own internal evidence. Our model combines local variational hidden computation (EVE), a homeostatic latent regulator, structurally aware checkpoint retention and a calibrated uncertainty-aware controller operating on top of the retained model. Rather than treating uncertainty as a passive diagnostic measured after prediction, we treat it as an operational signal that can regulate training, support checkpoint retention and guide inference-time intervention. The resulting framework is deliberately focused. It studies a closed-loop form of internal control in which structural and predictive signals become actionable. Empirically, the variational backbone improves over a matched deterministic reference on the language-modeling task while also exhibiting a richer and more usable uncertainty profile. On top of this backbone, the calibrated controller remains active, uses multiple actions under a full agentic evaluation and yields a positive quality-cost trade-off. These results support a precise claim: internal uncertainty can serve not only as a descriptive property of a variational language model, but also as a practical control interface for regulation, checkpoint retention and minimal agentic routing. --- ### NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1) Authors: Guanyi Qin, Jie Liang, Bingbing Zhang, Lishen Qu, Ya-nan Guan, Hui Zeng, Lei Zhang, Radu Timofte, Jianhui Sun, Xinli Yue, Tao Shao, Huan Hou et al. Published: 2026-04-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.12512v1 In this paper, we present an overview of the NTIRE 2026 challenge on the 3rd Restore Any Image Model in the Wild, specifically focusing on Track 1: Professional Image Quality Assessment. Conventional Image Quality Assessment (IQA) typically relies on scalar scores. By compressing complex visual characteristics into a single number, these methods fundamentally struggle to distinguish subtle differences among uniformly high-quality images. Furthermore, they fail to articulate why one image is superior, lacking the reasoning capabilities required to provide guidance for vision tasks. To bridge this gap, recent advancements in Multimodal Large Language Models (MLLMs) offer a promising paradigm. Inspired by this potential, our challenge establishes a novel benchmark exploring the ability of MLLMs to mimic human expert cognition in evaluating high-quality image pairs. Participants were tasked with overcoming critical bottlenecks in professional scenarios, centering on two primary objectives: (1) Comparative Quality Selection: reliably identifying the visually superior image within a high-quality pair; and (2) Interpretative Reasoning: generating grounded, expert-level explanations that detail the rationale behind the selection. In total, the challenge attracted nearly 200 registrations and over 2,500 submissions. The top-performing methods significantly advanced the state of the art in professional IQA. The challenge dataset is available at https://github.com/narthchin/RAIM-PIQA, and the official homepage is accessible at https://www.codabench.org/competitions/12789/. --- ### Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal Controllers Authors: Snehal Jauhri, Vignesh Prasad, Georgia Chalvatzaki Published: 2026-04-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.12509v1 Mobile Manipulation (MoMa) of articulated objects, such as opening doors, drawers, and cupboards, demands simultaneous, whole-body coordination between a robot's base and arms. Classical whole-body controllers (WBCs) can solve such problems via hierarchical optimization, but require extensive hand-tuned optimization and remain brittle. Learning-based methods, on the other hand, show strong generalization capabilities but typically rely on expensive whole-body teleoperation data or heavy reward engineering. We observe that even a sub-optimal WBC is a powerful structural prior: it can be used to collect data in a constrained, task-relevant region of the state-action space, and its behavior can still be improved upon using offline reinforcement learning. Building on this, we propose WHOLE-MoMa, a two-stage pipeline that first generates diverse demonstrations by randomizing a lightweight WBC, and then applies offline RL to identify and stitch together improved behaviors via a reward signal. To support the expressive action-chunked diffusion policies needed for complex coordination tasks, we extend offline implicit Q-learning with Q-chunking for chunk-level critic evaluation and advantage-weighted policy extraction. On three tasks of increasing difficulty using a TIAGo++ mobile manipulator in simulation, WHOLE-MoMa significantly outperforms WBC, behavior cloning, and several offline RL baselines. Policies transfer directly to the real robot without finetuning, achieving 80% success in bimanual drawer manipulation and 68% in simultaneous cupboard opening and object placement, all without any teleoperated or real-world training data. --- ### From Attenuation to Attention: Variational Information Flow Manipulation for Fine-Grained Visual Perception Authors: Jilong Zhu, Yang Feng Published: 2026-04-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.12508v1 While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine-grained perception tasks that require identifying tiny objects or discerning subtle visual relationships. We attribute this limitation to Visual Attenuation: a phenomenon where sparse fine-grained visual signals are prematurely suppressed or diluted by dominant textual tokens during network propagation, resulting in a "loss of focus" during the deep-level decision-making process. Existing input-centric solutions fail to fundamentally reverse this intrinsic mechanism of information loss. To address this challenge, we propose the Variational Information Flow (VIF) framework. Adopting a probabilistic perspective, VIF leverages a Conditional Variational Autoencoder (CVAE) to model the visual saliency relevant to the question-answer pair as a latent distribution. As a plug-and-play module, VIF can be integrated into existing architectures. Extensive evaluations across diverse benchmarks, covering General VQA, fine-grained perception, and visual grounding, demonstrate that VIF yields competitive improvements over previous methods, validating its effectiveness in enhancing the fine-grained perception of MLLMs. --- ### Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs Authors: Linhao Zhang, Yuhan Song, Aiwei Liu, Chuhan Wu, Sijun Zhang, Wei Jia, Yuan Liu, Houfeng Wang, Xiao Zhou Published: 2026-04-14 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2604.12506v1 Recent Audio Large Language Models (AudioLLMs) exhibit a striking performance inversion: while excelling at complex reasoning tasks, they consistently underperform on fine-grained acoustic perception. We attribute this gap to a fundamental limitation of ASR-centric training, which provides precise linguistic targets but implicitly teaches models to suppress paralinguistic cues and acoustic events as noise. To address this, we propose Unified Audio Schema (UAS), a holistic and structured supervision framework that organizes audio information into three explicit components -- Transcription, Paralinguistics, and Non-linguistic Events -- within a unified JSON format. This design achieves comprehensive acoustic coverage without sacrificing the tight audio-text alignment that enables reasoning. We validate the effectiveness of this supervision strategy by applying it to both discrete and continuous AudioLLM architectures. Extensive experiments on MMSU, MMAR, and MMAU demonstrate that UAS-Audio yields consistent improvements, boosting fine-grained perception by 10.9% on MMSU over the same-size state-of-the-art models while preserving robust reasoning capabilities. Our code and model are publicly available at https://github.com/Tencent/Unified_Audio_Schema. --- ### Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting Authors: Shuai Wang, Xixi Wang, Yinan Yu Published: 2026-04-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.12503v2 Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios. Knowledge Base Question Answering (KBQA) mitigates this by grounding generation in Knowledge Graphs (KGs). However, most multi-hop KBQA methods rely on explicit edge traversal, making them fragile to KG incompleteness. In this paper, we proposed a novel graph-based soft prompting framework that shifts the reasoning paradigm from node-level path traversal to subgraph-level reasoning. Specifically, we employ a Graph Neural Network (GNN) to encode extracted structural subgraphs into soft prompts, enabling LLM to reason over richer structural context and identify relevant entities beyond immediate graph neighbors, thereby reducing sensitivity to missing edges. Furthermore, we introduce a two-stage paradigm that reduces computational cost while preserving good performance: a lightweight LLM first leverages the soft prompts to identify question-relevant entities and relations, followed by a more powerful LLM for evidence-aware answer generation. Experiments on four multi-hop KBQA benchmarks show that our approach achieves state-of-the-art performance on three of them, demonstrating its effectiveness. Code is available at the repository: https://github.com/Wangshuaiia/GraSP. --- ### SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker Authors: Junbin Su, Ziteng Xue, Shihui Zhang, Kun Chen, Weiming Hu, Zhipeng Zhang Published: 2026-04-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.12502v1 Parameter-efficient fine-tuning (PEFT) in multimodal tracking reveals a concerning trend where recent performance gains are often achieved at the cost of inflated parameter budgets, which fundamentally erodes PEFT's efficiency promise. In this work, we introduce SEATrack, a Simple, Efficient, and Adaptive two-stream multimodal tracker that tackles this performance-efficiency dilemma from two complementary perspectives. We first prioritize cross-modal alignment of matching responses, an underexplored yet pivotal factor that we argue is essential for breaking the trade-off. Specifically, we observe that modality-specific biases in existing two-stream methods generate conflicting matching attention maps, thereby hindering effective joint representation learning. To mitigate this, we propose AMG-LoRA, which seamlessly integrates Low-Rank Adaptation (LoRA) for domain adaptation with Adaptive Mutual Guidance (AMG) to dynamically refine and align attention maps across modalities. We then depart from conventional local fusion approaches by introducing a Hierarchical Mixture of Experts (HMoE) that enables efficient global relation modeling, effectively balancing expressiveness and computational efficiency in cross-modal fusion. Equipped with these innovations, SEATrack advances notable progress over state-of-the-art methods in balancing performance with efficiency across RGB-T, RGB-D, and RGB-E tracking tasks. \href{https://github.com/AutoLab-SAI-SJTU/SEATrack}{\textcolor{cyan}{Code is available}}. --- ### Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design Authors: Leon Eshuijs, Shihan Wang, Antske Fokkens Published: 2026-04-14 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2604.12500v2 Specification gaming under Reinforcement Learning (RL) is known to cause LLMs to develop sycophantic, manipulative, or deceptive behavior, yet the conditions under which this occurs remain unclear. We train 11 instruction-tuned LLMs (0.5B-14B) with on-policy RL across 3 environments and find that model size acts as a safety buffer in some environments but enables greater harmful exploitation in others. Controlled ablations trace this reversal to environment-specific features such as role framing and implicit gameability cues. We further show that most safety benchmarks do not predict RL-induced misalignment, except in the case of Sycophancy scores when the exploit relies on inferring the user's preference. Finally, we find that on-policy RL preserves a safety buffer inherent in the model's own generation distribution, one that is bypassed during off-policy settings. --- ### Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design Authors: Leon Eshuijs, Shihan Wang, Antske Fokkens Published: 2026-04-14 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2604.12500v1 Specification gaming under Reinforcement Learning (RL) is known to cause LLMs to develop sycophantic, manipulative, or deceptive behavior, yet the conditions under which this occurs remain unclear. We train 11 instruction-tuned LLMs (0.5B--14B) with on-policy RL across 3 environments and find that model size acts as a safety buffer in some environments but enables greater harmful exploitation in others. Controlled ablations trace this reversal to environment-specific features such as role framing and implicit gameability cues. We further show that most safety benchmarks do not predict RL-induced misalignment, except in the case of Sycophancy scores when the exploit relies on inferring the user's preference. Finally, we find that on-policy RL preserves a safety buffer inherent in the model's own generation distribution, one that is bypassed during off-policy settings. --- ### Lit2Vec: A Reproducible Workflow for Building a Legally Screened Chemistry Corpus from S2ORC for Downstream Retrieval and Text Mining Authors: Mahmoud Amiri, Jamile Mohammad Jafari, Sara Mostafapour, Thomas Bocklitz Published: 2026-04-14 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2604.12498v1 We present Lit2Vec, a reproducible workflow for constructing and validating a chemistry corpus from the Semantic Scholar Open Research Corpus using conservative, metadata-based license screening. Using this workflow, we assembled an internal study corpus of 582,683 chemistry-specific full-text research articles with structured full text, token-aware paragraph chunks, paragraph-level embeddings generated with the intfloat/e5-large-v2 model, and record-level metadata including abstracts and licensing information. To support downstream retrieval and text-mining use cases, an eligible subset of the corpus was additionally enriched with machine-generated brief summaries and multi-label subfield annotations spanning 18 chemistry domains. Licensing was screened using metadata from Unpaywall, OpenAlex, and Crossref, and the resulting corpus was technically validated for schema compliance, embedding reproducibility, text quality, and metadata completeness. The primary contribution of this work is a reproducible workflow for corpus construction and validation, together with its associated schema and reproducibility resources. The released materials include the code, reconstruction workflow, schema, metadata/provenance artifacts, and validation outputs needed to reproduce the corpus from pinned public upstream resources. Public redistribution of source-derived text and broad text-derived representations is outside the scope of the general release. Researchers can reproduce the workflow by using the released pipeline with publicly available upstream datasets and metadata services. --- ### Allocating Human Oversight in AI-Enabled Analytics Authors: Zikun Ye, Jiameng Lyu, Rui Tao Published: 2026-04-14 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.12497v2 Organizations increasingly deploy AI as a low-cost prediction layer in customer-facing decision processes, including demand sensing, service-quality monitoring, product testing, and market research, but AI-generated signals are unevenly reliable across tasks, products, and customer segments. Firms therefore still need scarce human validation (labels, audits, survey responses, or follow-up measurements) to anchor AI outputs to ground truth. Because human ground truth is itself noisy, varying across labelers and even across repeated judgments, the firm must collect and average several human labels per task, which makes human validation costly. We study how to allocate a limited human-validation budget across many AI-assisted tasks when reliability is heterogeneous and unknown before deployment. We cast this within tuned prediction-powered inference. Each human label both sharpens the AI-assisted estimate and reveals the task's rectification difficulty, the variance that remains after the AI prediction is optimally used as a control variate. If difficulties were known, the optimal allocation would follow a Neyman square-root rule; because they are unknown, we propose a policy based on upper confidence bounds that learns them online and steers validation toward tasks where AI is least reliable. We prove that the policy's terminal efficiency loss relative to the oracle allocation vanishes as the budget grows. In synthetic experiments and a real digital-twin survey with 68 tasks and over 2000 respondents, it closes most of the gap to the oracle when reliability is heterogeneous, outperforming uniform and epsilon-greedy allocation; on the survey data it also outperforms explore-then-commit pilot designs and cuts uniform's 10--12% gap to 2--6%. The value of AI depends not only on model accuracy but also on the operational policy that targets human oversight where AI errors matter most. --- ### Latent Planning Emerges with Scale Authors: Michael Hanna, Emmanuel Ameisen Published: 2026-04-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.12493v1 LLMs can perform seemingly planning-intensive tasks, like writing coherent stories or functioning code, without explicitly verbalizing a plan; however, the extent to which they implicitly plan is unknown. In this paper, we define latent planning as occurring when LLMs possess internal planning representations that (1) cause the generation of a specific future token or concept, and (2) shape preceding context to license said future token or concept. We study the Qwen-3 family (0.6B-14B) on simple planning tasks, finding that latent planning ability increases with scale. Models that plan possess features that represent a planned-for word like "accountant", and cause them to output "an" rather than "a"; moreover, even the less-successful Qwen-3 4B-8B have nascent planning mechanisms. On the more complex task of completing rhyming couplets, we find that models often identify a rhyme ahead of time, but even large models seldom plan far ahead. However, we can elicit some planning that increases with scale when steering models towards planned words in prose. In sum, we offer a framework for measuring planning and mechanistic evidence of how models' planning abilities grow with scale. --- ### Calibrated Confidence Estimation for Tabular Question Answering Authors: Lukas Voss Published: 2026-04-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.12491v1 Large language models (LLMs) are increasingly deployed for tabular question answering, yet calibration on structured data is largely unstudied. This paper presents the first systematic comparison of five confidence estimation methods across five frontier LLMs and two tabular QA benchmarks. All models are severely overconfident (smooth ECE 0.35-0.64 versus 0.10-0.15 reported for textual QA). A consistent self-evaluation versus perturbation dichotomy replicates across both benchmarks and all four fully-covered models: self-evaluation methods (verbalized, P(True)) achieve AUROC 0.42-0.76, while perturbation methods (semantic entropy, self-consistency, and our Multi-Format Agreement) achieve AUROC 0.78-0.86. Per-model paired bootstrap tests reject the null at p<0.001 after Holm-Bonferroni correction, and a 3-seed check on GPT-4o-mini gives a per-seed standard deviation of only 0.006. The paper proposes Multi-Format Agreement (MFA), which exploits the lossless and deterministic serialization variation unique to structured data (Markdown, HTML, JSON, CSV) to estimate confidence at 20% lower API cost than sampling baselines. MFA reduces ECE by 44-63%, generalizes across all four models on TableBench (mean AUROC 0.80), and combines complementarily with sampling: an MFA + self-consistency ensemble lifts AUROC from 0.74 to 0.82. A secondary contribution, structure-aware recalibration, improves AUROC by +10 percentage points over standard post-hoc methods. ---