# Research Papers — 2026-02 · bundle page 99 of 210

> Full-text markdown of papers #4901–4950 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/99
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/98.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/100.md)

### IndicFairFace: Balanced Indian Face Dataset for Auditing and Mitigating Geographical Bias in Vision-Language Models

Authors: Aarish Shah Mohsin, Mohammed Tayyab Ilyas Khan, Mohammad Nadeem, Shahab Saquib Sohail, Erik Cambria, Jiechao Gao
Published: 2026-02-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.12659v1

Vision-Language Models (VLMs) are known to inherit and amplify societal biases from their web-scale training data with Indian being particularly misrepresented. Existing fairness-aware datasets have significantly improved demographic balance across global race and gender groups, yet they continue to treat Indian as a single monolithic category. The oversimplification ignores the vast intra-national diversity across 28 states and 8 Union Territories of India and leads to representational and geographical bias. To address the limitation, we present IndicFairFace, a novel and balanced face dataset comprising 14,400 images representing geographical diversity of India. Images were sourced ethically from Wikimedia Commons and open-license web repositories and uniformly balanced across states and gender. Using IndicFairFace, we quantify intra-national geographical bias in prominent CLIP-based VLMs and reduce it using post-hoc Iterative Nullspace Projection debiasing approach. We also show that the adopted debiasing approach does not adversely impact the existing embedding space as the average drop in retrieval accuracy on benchmark datasets is less than 1.5 percent. Our work establishes IndicFairFace as the first benchmark to study geographical bias in VLMs for the Indian context.

---

### PMG: Parameterized Motion Generator for Human-like Locomotion Control

Authors: Chenxi Han, Yuheng Min, Zihao Huang, Ao Hong, Hang Liu, Yi Cheng, Houde Liu
Published: 2026-02-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.12656v2

Recent advances in data-driven reinforcement learning and motion tracking have substantially improved humanoid locomotion, yet critical practical challenges remain. In particular, while low-level motion tracking and trajectory-following controllers are mature, whole-body reference-guided methods are difficult to adapt to higher-level command interfaces and diverse task contexts: they require large, high-quality datasets, are brittle across speed and pose regimes, and are sensitive to robot-specific calibration. To address these limitations, we propose the Parameterized Motion Generator (PMG), a real-time motion generator grounded in an analysis of human motion structure that synthesizes reference trajectories using only a compact set of parameterized motion data together with high-dimensional control commands. Combined with an imitation-learning pipeline and an optimization-based sim-to-real motor parameter identification module, we validate the complete approach on our humanoid prototype ZERITH Z1 and show that, within a single integrated system, PMG produces natural, human-like locomotion, responds precisely to high-dimensional control inputs-including VR-based teleoperation-and enables efficient, verifiable sim-to-real transfer. Together, these results establish a practical, experimentally validated pathway toward natural and deployable humanoid control. Website: https://pmg-icra26.github.io/

---

### CBEN -- A Multimodal Machine Learning Dataset for Cloud Robust Remote Sensing Image Understanding

Authors: Marco Stricker, Masakazu Iwamura, Koichi Kise
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12652v2

Clouds are a common phenomenon that distorts optical satellite imagery, which poses a challenge for remote sensing. However, in the literature cloudless analysis is often performed where cloudy images are excluded from machine learning datasets and methods. Such an approach cannot be applied to time sensitive applications, e.g., during natural disasters. A possible solution is to apply cloud removal as a preprocessing step to ensure that cloudfree solutions are not failing under such conditions. But cloud removal methods are still actively researched and suffer from drawbacks, such as generated visual artifacts. Therefore, it is desirable to develop cloud robust methods that are less affected by cloudy weather. Cloud robust methods can be achieved by combining optical data with radar, a modality unaffected by clouds. While many datasets for machine learning combine optical and radar data, most researchers exclude cloudy images. We identify this exclusion from machine learning training and evaluation as a limitation that reduces applicability to cloudy scenarios. To investigate this, we assembled a dataset, named CloudyBigEarthNet (CBEN), of paired optical and radar images with cloud occlusion for training and evaluation. Using average precision (AP) as the evaluation metric, we show that state-of-the-art methods trained on combined clear-sky optical and radar imagery suffer performance drops of 23-33 percentage points when evaluated on cloudy images. We then adapt these methods to cloudy optical data during training, achieving relative improvement of 17.2-28.7 percentage points on cloudy test cases compared with the original approaches. Code and dataset are publicly available at: https://github.com/mstricker13/CBEN

---

### Uncovering spatial tissue domains and cell types in spatial omics through cross-scale profiling of cellular and genomic interactions

Authors: Rui Yan, Xiaohan Xing, Xun Wang, Zixia Zhou, Md Tauhidul Islam, Lei Xing
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12651v1

Cellular identity and function are linked to both their intrinsic genomic makeup and extrinsic spatial context within the tissue microenvironment. Spatial transcriptomics (ST) offers an unprecedented opportunity to study this, providing in situ gene expression profiles at single-cell resolution and illuminating the spatial and functional organization of cells within tissues. However, a significant hurdle remains: ST data is inherently noisy, large, and structurally complex. This complexity makes it intractable for existing computational methods to effectively capture the interplay between spatial interactions and intrinsic genomic relationships, thus limiting our ability to discern critical biological patterns. Here, we present CellScape, a deep learning framework designed to overcome these limitations for high-performance ST data analysis and pattern discovery. CellScape jointly models cellular interactions in tissue space and genomic relationships among cells, producing comprehensive representations that seamlessly integrate spatial signals with underlying gene regulatory mechanisms. This technique uncovers biologically informative patterns that improve spatial domain segmentation and supports comprehensive spatial cellular analyses across diverse transcriptomics datasets, offering an accurate and versatile framework for deep analysis and interpretation of ST data.w

---

### Multi-Task Learning with Additive U-Net for Image Denoising and Classification

Authors: Vikram Lakkavalli, Neelam Sinha
Published: 2026-02-13
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.12649v1

We investigate additive skip fusion in U-Net architectures for image denoising and denoising-centric multi-task learning (MTL). By replacing concatenative skips with gated additive fusion, the proposed Additive U-Net (AddUNet) constrains shortcut capacity while preserving fixed feature dimensionality across depth. This structural regularization induces controlled encoder-decoder information flow and stabilizes joint optimization. Across single-task denoising and joint denoising-classification settings, AddUNet achieves competitive reconstruction performance with improved training stability. In MTL, learned skip weights exhibit systematic task-aware redistribution: shallow skips favor reconstruction, while deeper features support discrimination. Notably, reconstruction remains robust even under limited classification capacity, indicating implicit task decoupling through additive fusion. These findings show that simple constraints on skip connections act as an effective architectural regularizer for stable and scalable multi-task learning without increasing model complexity.

---

### Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics

Authors: Jashaswimalya Acharjee, Balaraman Ravindran
Published: 2026-02-13
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2602.12643v2

We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead. By embedding state-action pairs into a latent space in which the true value function is approximately linear, our method supports a single set of hyperparameters across diverse domains -- from continuous control with low-dimensional and pixel inputs to high-dimensional Atari games. We prove that, under mild conditions, the fixed point of our embedding-based temporal-difference updates coincides with that of a corresponding linear model-based value expansion, and we derive explicit error bounds relating embedding fidelity to value approximation quality. In practice, ULD employs synchronized updates of encoder, value, and policy networks, auxiliary losses for short-horizon predictive dynamics, and reward-scale normalization to ensure stable learning under sparse rewards. Evaluated on 80 environments spanning Gym locomotion, DeepMind Control (proprioceptive and visual), and Atari, our approach matches or exceeds the performance of specialized model-free and general model-based baselines -- achieving cross-domain competence with minimal tuning and a fraction of the parameter footprint. These results indicate that value-aligned latent representations alone can deliver the adaptability and sample efficiency traditionally attributed to full model-based planning.

---

### Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR

Authors: Dohyung Kim, Minbeom Kim, Jeonghye Kim, Sangmook Lee, Sojeong Rhee, Kyomin Jung
Published: 2026-02-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.12642v2

Reward-maximizing RL methods have shown to be capable of enhancing the reasoning performance of LLMs, but often lead to reduced generation diversity. Recent works address this issue by adopting GFlowNets, training LLMs to match a target distribution while jointly learning its partition function. In contrast to prior works that treat this partition function solely as a normalizer, we reinterpret it as a per-prompt expected-reward (i.e., online accuracy) signal, leveraging this unused information to improve sample efficiency. Specifically, we first establish a theoretical relationship between the partition function and per-prompt accuracy estimates. Building on this key insight, we propose Partition Function-Guided RL (PACED-RL), a post-training framework that leverages accuracy estimates to prioritize informative question prompts during training, and further improves sample efficiency through an accuracy estimate error-prioritized replay. Crucially, both components reuse information already produced during GFlowNet training, effectively amortizing the compute overhead into the existing optimization process. Extensive experiments across diverse benchmarks demonstrate strong performance improvements over GRPO and prior GFlowNet approaches, highlighting PACED-RL as a promising direction for a more sample efficient distribution-matching training for LLMs.

---

### Artic: AI-oriented Real-time Communication for MLLM Video Assistant

Authors: Jiangkai Wu, Zhiyuan Ren, Junquan Zhong, Liming Liu, Xinggong Zhang
Published: 2026-02-13
Categories: cs.NI, cs.AI, cs.HC, cs.MM
arXiv: https://arxiv.org/abs/2602.12641v1

AI Video Assistant emerges as a new paradigm for Real-time Communication (RTC), where one peer is a Multimodal Large Language Model (MLLM) deployed in the cloud. This makes interaction between humans and AI more intuitive, akin to chatting with a real person. However, a fundamental mismatch exists between current RTC frameworks and AI Video Assistants, stemming from the drastic shift in Quality of Experience (QoE) and more challenging networks. Measurements on our production prototype also confirm that current RTC fails, causing latency spikes and accuracy drops. To address these challenges, we propose Artic, an AI-oriented RTC framework for MLLM Video Assistants, exploring the shift from "humans watching video" to "AI understanding video." Specifically, Artic proposes: (1) Response Capability-aware Adaptive Bitrate, which utilizes MLLM accuracy saturation to proactively cap bitrate, reserving bandwidth headroom to absorb future fluctuations for latency reduction; (2) Zero-overhead Context-aware Streaming, which allocates limited bitrate to regions most important for the response, maintaining accuracy even under ultra-low bitrates; and (3) Degraded Video Understanding Benchmark, the first benchmark evaluating how RTC-induced video degradation affects MLLM accuracy. Prototype experiments using real-world uplink traces show that compared with existing methods, Artic significantly improves accuracy by 15.12% and reduces latency by 135.31 ms. We will release the benchmark and codes at https://github.com/pku-netvideo/DeViBench.

---

### ImageRAGTurbo: Towards One-step Text-to-Image Generation with Retrieval-Augmented Diffusion Models

Authors: Peijie Qiu, Hariharan Ramshankar, Arnau Ramisa, René Vidal, Amit Kumar K C, Vamsi Salaka, Rahul Bhagat
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12640v1

Diffusion models have emerged as the leading approach for text-to-image generation. However, their iterative sampling process, which gradually morphs random noise into coherent images, introduces significant latency that limits their applicability. While recent few-step diffusion models reduce the number of sampling steps to as few as one to four steps, they often compromise image quality and prompt alignment, especially in one-step generation. Additionally, these models require computationally expensive training procedures. To address these limitations, we propose ImageRAGTurbo, a novel approach to efficiently finetune few-step diffusion models via retrieval augmentation. Given a text prompt, we retrieve relevant text-image pairs from a database and use them to condition the generation process. We argue that such retrieved examples provide rich contextual information to the UNet denoiser that helps reduce the number of denoising steps without compromising image quality. Indeed, our initial investigations show that using the retrieved content to edit the denoiser's latent space ($\mathcal{H}$-space) without additional finetuning already improves prompt fidelity. To further improve the quality of the generated images, we augment the UNet denoiser with a trainable adapter in the $\mathcal{H}$-space, which efficiently blends the retrieved content with the target prompt using a cross-attention mechanism. Experimental results on fast text-to-image generation demonstrate that our approach produces high-fidelity images without compromising latency compared to existing methods.

---

### CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation

Authors: Yiran Rex Ma, Yuxiao Ye, Huiyuan Xie
Published: 2026-02-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.12639v2

Legal text generated by large language models (LLMs) can usually achieve reasonable factual accuracy, but it frequently fails to adhere to the specialised stylistic norms and linguistic conventions of legal writing. In order to improve stylistic quality, a crucial first step is to establish a reliable evaluation method. However, having legal experts manually develop such a metric is impractical, as the implicit stylistic requirements in legal writing practice are difficult to formalise into explicit rubrics. Meanwhile, existing automatic evaluation methods also fall short: reference-based metrics conflate semantic accuracy with stylistic fidelity, and LLM-as-a-judge evaluations suffer from opacity and inconsistency. To address these challenges, we introduce CLASE (Chinese LegAlese Stylistic Evaluation), a hybrid evaluation method that focuses on the stylistic performance of legal text. The method incorporates a hybrid scoring mechanism that combines 1) linguistic feature-based scores and 2) experience-guided LLM-as-a-judge scores. Both the feature coefficients and the LLM scoring experiences are learned from contrastive pairs of authentic legal documents and their LLM-restored counterparts. This hybrid design captures both surface-level features and implicit stylistic norms in a transparent, reference-free manner. Experiments on 200 Chinese legal documents show that CLASE achieves substantially higher alignment with human judgments than traditional metrics and pure LLM-as-a-judge methods. Beyond improved alignment, CLASE provides interpretable score breakdowns and suggestions for improvements, offering a scalable and practical solution for professional stylistic evaluation in legal text generation (Code and data for CLASE is available at: https://github.com/rexera/CLASE).

---

### CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation

Authors: Yiran Rex Ma, Yuxiao Ye, Huiyuan Xie
Published: 2026-02-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.12639v1

Legal text generated by large language models (LLMs) can usually achieve reasonable factual accuracy, but it frequently fails to adhere to the specialised stylistic norms and linguistic conventions of legal writing. In order to improve stylistic quality, a crucial first step is to establish a reliable evaluation method. However, having legal experts manually develop such a metric is impractical, as the implicit stylistic requirements in legal writing practice are difficult to formalise into explicit rubrics. Meanwhile, existing automatic evaluation methods also fall short: reference-based metrics conflate semantic accuracy with stylistic fidelity, and LLM-as-a-judge evaluations suffer from opacity and inconsistency. To address these challenges, we introduce CLASE (Chinese LegAlese Stylistic Evaluation), a hybrid evaluation method that focuses on the stylistic performance of legal text. The method incorporates a hybrid scoring mechanism that combines 1) linguistic feature-based scores and 2) experience-guided LLM-as-a-judge scores. Both the feature coefficients and the LLM scoring experiences are learned from contrastive pairs of authentic legal documents and their LLM-restored counterparts. This hybrid design captures both surface-level features and implicit stylistic norms in a transparent, reference-free manner. Experiments on 200 Chinese legal documents show that CLASE achieves substantially higher alignment with human judgments than traditional metrics and pure LLM-as-a-judge methods. Beyond improved alignment, CLASE provides interpretable score breakdowns and suggestions for improvements, offering a scalable and practical solution for professional stylistic evaluation in legal text generation (Code and data for CLASE is available at: https://github.com/rexera/CLASE).

---

### Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL

Authors: Xin Liu, Yixuan Li, Yuhui Chen, Yuxing Qin, Haoran Li, Dongbin Zhao
Published: 2026-02-13
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2602.12636v1

Designing suitable rewards poses a significant challenge in reinforcement learning (RL), especially for embodied manipulation. Trajectory success rewards are suitable for human judges or model fitting, but the sparsity severely limits RL sample efficiency. While recent methods have effectively improved RL via dense rewards, they rely heavily on high-quality human-annotated data or abundant expert supervision. To tackle these issues, this paper proposes Dual-granularity contrastive reward via generated Episodic Guidance (DEG), a novel framework to seek sample-efficient dense rewards without requiring human annotations or extensive supervision. Leveraging the prior knowledge of large video generation models, DEG only needs a small number of expert videos for domain adaptation to generate dedicated task guidance for each RL episode. Then, the proposed dual-granularity reward that balances coarse-grained exploration and fine-grained matching, will guide the agent to efficiently approximate the generated guidance video sequentially in the contrastive self-supervised latent space, and finally complete the target task. Extensive experiments on 18 diverse tasks across both simulation and real-world settings show that DEG can not only serve as an efficient exploration stimulus to help the agent quickly discover sparse success rewards, but also guide effective RL and stable policy convergence independently.

---

### Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats

Authors: Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Manyi Zhang, Yuanyong Luo, Ziwei Yu, Xin Wang, Mingxuan Yuan, Xianzhi Yu et al.
Published: 2026-02-13
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.12635v3

As LLMs scale, low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. In this work, we evaluate HiFloat (HiF8 and HiF4), a family of formats tailored for Ascend NPUs. Through rigorous comparison across weight-activation and KV-cache tasks, we provide three key insights: (1) INT8 suits narrow-range data, while floating-point formats excel with high-variance data; (2) in 4-bit regimes, HiF4's hierarchical scaling prevents the accuracy collapse seen in integer formats; and (3) HiFloat is fully compatible with state-of-the-art post-training quantization frameworks. Overall, HiFloat provides a solution for high-efficiency LLM inference on NPUs.

---

### AI Agents for Inventory Control: Human-LLM-OR Complementarity

Authors: Jackie Baek, Yaopeng Fu, Will Ma, Tianyi Peng
Published: 2026-02-13
Categories: cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2602.12631v2

Inventory control is a fundamental operations problem in which ordering decisions are traditionally guided by theoretically grounded operations research (OR) algorithms. However, such algorithms often rely on rigid modeling assumptions and can perform poorly when demand distributions shift or relevant contextual information is unavailable. Recent advances in large language models (LLMs) have generated interest in AI agents that can reason flexibly and incorporate rich contextual signals, but it remains unclear how best to incorporate LLM-based methods into traditional decision-making pipelines. We study how OR algorithms, LLMs, and humans can interact and complement each other in a multi-period inventory control setting. We construct InventoryBench, a benchmark of over 1,000 inventory instances spanning both synthetic and real-world demand data, designed to stress-test decision rules under demand shifts, seasonality, and uncertain lead times. Through this benchmark, we find that OR-augmented LLM methods outperform either method in isolation, suggesting that these methods are complementary rather than substitutes. We further investigate the role of humans through a controlled classroom experiment that embeds LLM recommendations into a human-in-the-loop decision pipeline. Contrary to prior findings that human-AI collaboration can degrade performance, we show that, on average, human-AI teams achieve higher profits than either humans or AI agents operating alone. Beyond this population-level finding, we formalize an individual-level complementarity effect and derive a distribution-free lower bound on the fraction of individuals who benefit from AI collaboration; empirically, we find this fraction to be substantial.

---

### TensorCommitments: A Lightweight Verifiable Inference for Language Models

Authors: Oguzhan Baser, Elahe Sadeghi, Eric Wang, David Ribeiro Alves, Sam Kazemian, Hong Kang, Sandeep P. Chinchali, Sriram Vishwanath
Published: 2026-02-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.12630v1

Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiable LLM inference, where a prover (the service) must convince a verifier (the client) that an inference was run correctly without rerunning the LLM. Existing cryptographic works are too slow at the LLM scale, while non-cryptographic ones require a strong verifier GPU. We propose TensorCommitments (TCs), a tensor-native proof-of-inference scheme. TC binds the LLM inference to a commitment, an irreversible tag that breaks under tampering, organized in our multivariate Terkle Trees. For LLaMA2, TC adds only 0.97% prover and 0.12% verifier time over inference while improving robustness to tailored LLM attacks by up to 48% over the best prior work requiring a verifier GPU.

---

### Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps

Authors: Sangwoo Jo, Sungjoon Choi
Published: 2026-02-13
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.12624v1

Diffusion-based generative models have achieved remarkable performance across various domains, yet their practical deployment is often limited by high sampling costs. While prior work focuses on training objectives or individual solvers, the holistic design of sampling, specifically solver selection and scheduling, remains dominated by static heuristics. In this work, we revisit this challenge through a geometric lens, proposing SDM, a principled framework that aligns the numerical solver with the intrinsic properties of the diffusion trajectory. By analyzing the ODE dynamics, we show that efficient low-order solvers suffice in early high-noise stages while higher-order solvers can be progressively deployed to handle the increasing non-linearity of later stages. Furthermore, we formalize the scheduling by introducing a Wasserstein-bounded optimization framework. This method systematically derives adaptive timesteps that explicitly bound the local discretization error, ensuring the sampling process remains faithful to the underlying continuous dynamics. Without requiring additional training or architectural modifications, SDM achieves state-of-the-art performance across standard benchmarks, including an FID of 1.93 on CIFAR-10, 2.41 on FFHQ, and 1.98 on AFHQv2, with a reduced number of function evaluations compared to existing samplers. Our code is available at https://github.com/aiimaginglab/sdm.

---

### Efficient Personalized Federated PCA with Manifold Optimization for IoT Anomaly Detection

Authors: Xianchao Xiu, Chenyi Huang, Wei Zhang, Wanquan Liu
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12622v1

Internet of things (IoT) networks face increasing security threats due to their distributed nature and resource constraints. Although federated learning (FL) has gained prominence as a privacy-preserving framework for distributed IoT environments, current federated principal component analysis (PCA) methods lack the integration of personalization and robustness, which are critical for effective anomaly detection. To address these limitations, we propose an efficient personalized federated PCA (FedEP) method for anomaly detection in IoT networks. The proposed model achieves personalization through introducing local representations with the $\ell_1$-norm for element-wise sparsity, while maintaining robustness via enforcing local models with the $\ell_{2,1}$-norm for row-wise sparsity. To solve this non-convex problem, we develop a manifold optimization algorithm based on the alternating direction method of multipliers (ADMM) with rigorous theoretical convergence guarantees. Experimental results confirm that the proposed FedEP outperforms the state-of-the-art FedPG, achieving excellent F1-scores and accuracy in various IoT security scenarios. Our code will be available at \href{https://github.com/xianchaoxiu/FedEP}{https://github.com/xianchaoxiu/FedEP}.

---

### Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models

Authors: Omer Faruk Deniz, Ruiyu Mao, Ruochen Li, Yapeng Tian, Latifur Khan
Published: 2026-02-13
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.12618v1

Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either before the LLM, limiting generality due to diverse encoder-projector designs or within the LLM using heuristics that are incompatible with FlashAttention. We take a different approach: rather than identifying unimportant tokens, we treat the LLM itself as the optimal guide for compression. Observing that deeper layers naturally transmit vision-to-text information, we introduce Attention-Driven Self-Compression (ADSC), a simple, broadly applicable method that progressively reduces vision tokens using only the LLM's attention mechanism. Our method applies uniform token downsampling at selected layers, forming bottlenecks that encourage the model to reorganize and compress information into the remaining tokens. It requires no score computation, auxiliary modules, or attention modification, and remains fully compatible with FlashAttention. Applied to LLaVA-1.5, ADSC reduces FLOPs by 53.7% and peak KV-cache memory by 56.7%, while preserving 98.2% of the original model performance. Across multiple benchmarks, it outperforms prior pruning approaches in both efficiency and accuracy. Crucially, under high compression ratios, our method remains robust while heuristic-based techniques degrade sharply.

---

### GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics

Authors: Modi Jin, Yiming Zhang, Boyuan Sun, Dingwen Zhang, MingMing Cheng, Qibin Hou
Published: 2026-02-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.12617v1

This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs in performance and interpretability but still remain concerns because of their reliance on AI-generated chain-of-thought (CoT) data and training strategies, which conflict with geographic characteristics. To address these issues, we first introduce GeoSeek, a new geolocation dataset comprising CoT data annotated by geographic experts and professional players. We further thoroughly explore the inherent characteristics of geographic tasks and propose a geo-similarity reward and a consistency reward assessed by a consistency agent to assist training. This encourages the model to converge towards correct answers from a geographic perspective while ensuring the integrity and consistency of its reasoning process. Experimental results show that GeoAgent outperforms existing methods and a series of general VLLMs across multiple grains, while generating reasoning that closely aligns with humans.

---

### Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction

Authors: Zulun Zhu, Siqiang Luo
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12613v1

Temporal Graph Neural Networks (TGNNs) are pivotal in processing dynamic graphs. However, existing TGNNs primarily target one-time predictions for a given temporal span, whereas many practical applications require continuous predictions, that predictions are issued frequently over time. Directly adapting existing TGNNs to continuous-prediction scenarios introduces either significant computational overhead or prediction quality issues especially for large graphs. This paper revisits the challenge of { continuous predictions} in TGNNs, and introduces {\sc Coden}, a TGNN model designed for efficient and effective learning on dynamic graphs. {\sc Coden} innovatively overcomes the key complexity bottleneck in existing TGNNs while preserving comparable predictive accuracy. Moreover, we further provide theoretical analyses that substantiate the effectiveness and efficiency of {\sc Coden}, and clarify its duality relationship with both RNN-based and attention-based models. Our evaluations across five dynamic datasets show that {\sc Coden} surpasses existing performance benchmarks in both efficiency and effectiveness, establishing it as a superior solution for continuous prediction in evolving graph environments.

---

### Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback

Authors: Sein Kim, Sangwu Park, Hongseok Kang, Wonjoong Kim, Jimin Seo, Yeonjun In, Kanghoon Yoon, Hyunsik Jeon, Chanyoung Park
Published: 2026-02-13
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.12612v2

Traditional methods for automating recommender system design, such as Neural Architecture Search (NAS), are often constrained by a fixed search space defined by human priors, limiting innovation to pre-defined operators. While recent LLM-driven code evolution frameworks shift fixed search space target to open-ended program spaces, they primarily rely on scalar metrics (e.g., NDCG, Hit Ratio) that fail to provide qualitative insights into model failures or directional guidance for improvement. To address this, we propose Self-EvolveRec, a novel framework that establishes a directional feedback loop by integrating a User Simulator for qualitative critiques and a Model Diagnosis Tool for quantitative internal verification. Furthermore, we introduce a Diagnosis Tool - Model Co-Evolution strategy to ensure that evaluation criteria dynamically adapt as the recommendation architecture evolves. Extensive experiments demonstrate that Self-EvolveRec significantly outperforms state-of-the-art NAS and LLM-driven code evolution baselines in both recommendation performance and user satisfaction. Our code is available at https://github.com/Sein-Kim/self_evolverec.

---

### QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching

Authors: Ke Xu, Yixin Wang, Zhongcheng Li, Hao Cui, Jinshui Hu, Xingyi Zhang
Published: 2026-02-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.12609v1

Elastic precision quantization enables multi-bit deployment via a single optimization pass, fitting diverse quantization scenarios.Yet, the high storage and optimization costs associated with the Transformer architecture, research on elastic quantization remains limited, particularly for large language models.This paper proposes QuEPT, an efficient post-training scheme that reconstructs block-wise multi-bit errors with one-shot calibration on a small data slice. It can dynamically adapt to various predefined bit-widths by cascading different low-rank adapters, and supports real-time switching between uniform quantization and mixed precision quantization without repeated optimization. To enhance accuracy and robustness, we introduce Multi-Bit Token Merging (MB-ToMe) to dynamically fuse token features across different bit-widths, improving robustness during bit-width switching. Additionally, we propose Multi-Bit Cascaded Low-Rank adapters (MB-CLoRA) to strengthen correlations between bit-width groups, further improve the overall performance of QuEPT. Extensive experiments demonstrate that QuEPT achieves comparable or better performance to existing state-of-the-art post-training quantization methods.Our code is available at https://github.com/xuke225/QuEPT

---

### RelBench v2: A Large-Scale Benchmark and Repository for Relational Data

Authors: Justin Gu, Rishabh Ranjan, Charilaos Kanatsoulis, Haiming Tang, Martin Jurkovic, Valter Hudovernik, Mark Znidar, Pranshu Chaturvedi, Parth Shroff, Fengyu Li, Jure Leskovec
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12606v2

Relational deep learning (RDL) has emerged as a powerful paradigm for learning directly on relational databases by modeling entities and their relationships across multiple interconnected tables. As this paradigm evolves toward larger models and relational foundation models, scalable and realistic benchmarks are essential for enabling systematic evaluation and progress. In this paper, we introduce RelBench v2, a major expansion of the RelBench benchmark for RDL. RelBench v2 adds four large-scale relational datasets spanning scholarly publications, enterprise resource planning, consumer platforms, and clinical records, increasing the benchmark to 11 datasets comprising over 22 million rows across 29 tables. We further introduce autocomplete tasks, a new class of predictive objectives that require models to infer missing attribute values directly within relational tables while respecting temporal constraints, expanding beyond traditional forecasting tasks constructed via SQL queries. In addition, RelBench v2 expands beyond its native datasets by integrating external benchmarks and evaluation frameworks: we translate event streams from the Temporal Graph Benchmark into relational schemas for unified relational-temporal evaluation, interface with ReDeLEx to provide uniform access to 70+ real-world databases suitable for pretraining, and incorporate 4DBInfer datasets and tasks to broaden multi-table prediction coverage. Experimental results demonstrate that RDL models consistently outperform single-table baselines across autocomplete, forecasting, and recommendation tasks, highlighting the importance of modeling relational structure explicitly.

---

### Block-Sample MAC-Bayes Generalization Bounds

Authors: Matthias Frey, Jingge Zhu, Michael C. Gastpar
Published: 2026-02-13
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2602.12605v1

We present a family of novel block-sample MAC-Bayes bounds (mean approximately correct). While PAC-Bayes bounds (probably approximately correct) typically give bounds for the generalization error that hold with high probability, MAC-Bayes bounds have a similar form but bound the expected generalization error instead. The family of bounds we propose can be understood as a generalization of an expectation version of known PAC-Bayes bounds. Compared to standard PAC-Bayes bounds, the new bounds contain divergence terms that only depend on subsets (or \emph{blocks}) of the training data. The proposed MAC-Bayes bounds hold the promise of significantly improving upon the tightness of traditional PAC-Bayes and MAC-Bayes bounds. This is illustrated with a simple numerical example in which the original PAC-Bayes bound is vacuous regardless of the choice of prior, while the proposed family of bounds are finite for appropriate choices of the block size. We also explore the question whether high-probability versions of our MAC-Bayes bounds (i.e., PAC-Bayes bounds of a similar form) are possible. We answer this question in the negative with an example that shows that in general, it is not possible to establish a PAC-Bayes bound which (a) vanishes with a rate faster than $\mathcal{O}(1/\log n)$ whenever the proposed MAC-Bayes bound vanishes with rate $\mathcal{O}(n^{-1/2})$ and (b) exhibits a logarithmic dependence on the permitted error probability.

---

### Differentially Private Two-Stage Empirical Risk Minimization with Applications to Individualized Treatment Rule

Authors: Joowon Lee, Guanhua Chen
Published: 2026-02-13
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.12604v2

Differential privacy provides a formal framework for releasing statistical estimators that limit how much any single observation can influence the output, by injecting calibrated random noise. We study differentially private estimation in two-stage procedures common in causal inference and individualized treatment rule (ITR) learning, in which data-dependent weights are first estimated to enforce covariate balance and a parameter of interest is then obtained by weighted empirical risk minimization. We propose Differentially Private Two-Stage Empirical Risk Minimization (DP-2ERM), which privatizes the final estimator directly through objective perturbation calibrated to the data-dependent sensitivity of the full pipeline. The analysis combines deterministic weight-perturbation bounds for several covariate-balancing methods (inverse propensity weighting, entropy balancing weighting, and maximum mean discrepancy weighting) with probabilistic sensitivity bounds for the second-stage solution. The resulting calibration is sharper than the natural stage-wise composition baseline, which the same sensitivity analysis supplies as a byproduct. Simulation studies and a benchmark application to ITR learning demonstrate the improved privacy--utility trade-off.

---

### HyperMLP: An Integrated Perspective for Sequence Modeling

Authors: Jiecheng Lu, Shihao Yang
Published: 2026-02-13
Categories: cs.LG, cs.AI, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2602.12601v1

Self-attention is often viewed as probabilistic query-key lookup, motivating designs that preserve normalized attention scores and fixed positional semantics. We advocate a simpler and more unified perspective: an autoregressive attention head can be viewed as a dynamic two-layer MLP whose weights are instantiated from the context history. From this view, attention scores form an ever-growing hidden representation, and standard MLP activations such as ReLU or GLU naturally implement input-conditioned selection over a context-dependent memory pool rather than a probability distribution. Based on this formulation, we introduce HyperMLP and HyperGLU, which learn dynamic mixing in both feature space and sequence space, using a reverse-offset (lag) layout to align temporal mixing with autoregressive semantics. We provide theoretical characterizations of the expressivity and implications of this structure, and empirically show that HyperMLP/HyperGLU consistently outperform strong softmax-attention baselines under matched parameter budgets.

---

### RQ-GMM: Residual Quantized Gaussian Mixture Model for Multimodal Semantic Discretization in CTR Prediction

Authors: Ziye Tong, Jiahao Liu, Weimin Zhang, Hongji Ruan, Derick Tang, Zhanpeng Zeng, Qinsong Zeng, Peng Zhang, Tun Lu, Ning Gu
Published: 2026-02-13
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.12593v1

Multimodal content is crucial for click-through rate (CTR) prediction. However, directly incorporating continuous embeddings from pre-trained models into CTR models yields suboptimal results due to misaligned optimization objectives and convergence speed inconsistency during joint training. Discretizing embeddings into semantic IDs before feeding them into CTR models offers a more effective solution, yet existing methods suffer from limited codebook utilization, reconstruction accuracy, and semantic discriminability. We propose RQ-GMM (Residual Quantized Gaussian Mixture Model), which introduces probabilistic modeling to better capture the statistical structure of multimodal embedding spaces. Through Gaussian Mixture Models combined with residual quantization, RQ-GMM achieves superior codebook utilization and reconstruction accuracy. Experiments on public datasets and online A/B tests on a large-scale short-video platform serving hundreds of millions of users demonstrate substantial improvements: RQ-GMM yields a 1.502% gain in Advertiser Value over strong baselines. The method has been fully deployed, serving daily recommendations for hundreds of millions of users.

---

### Power Interpretable Causal ODE Networks: A Unified Model for Explainable Anomaly Detection and Root Cause Analysis in Power Systems

Authors: Yue Sun, Likai Wang, Rick S. Blum, Parv Venkitasubramaniam
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.12592v1

Anomaly detection and root cause analysis (RCA) are critical for ensuring the safety and resilience of cyber-physical systems such as power grids. However, existing machine learning models for time series anomaly detection often operate as black boxes, offering only binary outputs without any explanation, such as identifying anomaly type and origin. To address this challenge, we propose Power Interpretable Causality Ordinary Differential Equation (PICODE) Networks, a unified, causality-informed architecture that jointly performs anomaly detection along with the explanation why it is detected as an anomaly, including root cause localization, anomaly type classification, and anomaly shape characterization. Experimental results in power systems demonstrate that PICODE achieves competitive detection performance while offering improved interpretability and reduced reliance on labeled data or external causal graphs. We provide theoretical results demonstrating the alignment between the shape of anomaly functions and the changes in the weights of the extracted causal graphs.

---

### Vehicle behaviour estimation for abnormal event detection using distributed fiber optic sensing

Authors: Hemant Prasad, Daisuke Ikefuji, Shin Tominaga, Hitoshi Sakurai, Manabu Otani
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12591v1

The distributed fiber-optic sensing (DFOS) system is a cost-effective wide-area traffic monitoring technology that utilizes existing fiber infrastructure to effectively detect traffic congestions. However, detecting single-lane abnormalities, that lead to congestions, is still a challenge. These single-lane abnormalities can be detected by monitoring lane change behaviour of vehicles, performed to avoid congestion along the monitoring section of a road. This paper presents a method to detect single-lane abnormalities by tracking individual vehicle paths and detecting vehicle lane changes along a section of a road. We propose a method to estimate the vehicle position at all time instances and fit a path using clustering techniques. We detect vehicle lane change by monitoring any change in spectral centroid of vehicle vibrations by tracking a reference vehicle along a highway. The evaluation of our proposed method with real traffic data showed 80% accuracy for lane change detection events that represent presence of abnormalities.

---

### Unbiased Gradient Estimation for Event Binning via Functional Backpropagation

Authors: Jinze Chen, Wei Zhai, Han Han, Tiankai Ma, Yang Cao, Bin Li, Zheng-Jun Zha
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12590v1

Event-based vision encodes dynamic scenes as asynchronous spatio-temporal spikes called events. To leverage conventional image processing pipelines, events are typically binned into frames. However, binning functions are discontinuous, which truncates gradients at the frame level and forces most event-based algorithms to rely solely on frame-based features. Attempts to directly learn from raw events avoid this restriction but instead suffer from biased gradient estimation due to the discontinuities of the binning operation, ultimately limiting their learning efficiency. To address this challenge, we propose a novel framework for unbiased gradient estimation of arbitrary binning functions by synthesizing weak derivatives during backpropagation while keeping the forward output unchanged. The key idea is to exploit integration by parts: lifting the target functions to functionals yields an integral form of the derivative of the binning function during backpropagation, where the cotangent function naturally arises. By reconstructing this cotangent function from the sampled cotangent vector, we compute weak derivatives that provably match long-range finite differences of both smooth and non-smooth targets. Experimentally, our method improves simple optimization-based egomotion estimation with 3.2\% lower RMS error and 1.57$\times$ faster convergence. On complex downstream tasks, we achieve 9.4\% lower EPE in self-supervised optical flow, and 5.1\% lower RMS error in SLAM, demonstrating broad benefits for event-based visual perception. Source code can be found at https://github.com/chjz1024/EventFBP.

---

### Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers

Authors: Anrui Chen, Ruijun Huang, Xin Zhang, Fang Dong, Hengjie Cao, Zhendong Huang, Yifeng Yang, Mengyi Chen, Jixian Zhou, Mingzhi Dong, Yujiang Wang, Jinlong Hou et al.
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12587v1

Mixture-of-Experts (MoE) architectures are often considered a natural fit for continual learning because sparse routing should localize updates and reduce interference, yet MoE Transformers still forget substantially even with sparse, well-balanced expert utilization. We attribute this gap to a pre-routing bottleneck: multi-head attention concatenates head-specific signals into a single post-attention router input, forcing routing to act on co-occurring feature compositions rather than separable head channels. We show that this router input simultaneously encodes multiple separately decodable semantic and structural factors with uneven head support, and that different feature compositions induce weakly aligned parameter-gradient directions; as a result, routing maps many distinct compositions to the same route. We quantify this collision effect via a route-wise effective composition number $N_{eff}$ and find that higher $N_{eff}$ is associated with larger old-task loss increases after continual training. Motivated by these findings, we propose MH-MoE, which performs head-wise routing over sub-representations to increase routing granularity and reduce composition collisions. On TRACE with Qwen3-0.6B/8B, MH-MoE effectively mitigates forgetting, reducing BWT on Qwen3-0.6B from 11.2% (LoRAMoE) to 4.5%.

---

### Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models

Authors: Joshua Ong Jun Leang, Yu Zhao, Mihaela Cătălina Stoian, Wenda Li, Shay B. Cohen, Eleonora Giunchiglia
Published: 2026-02-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.12586v2

While plan-and-infill decoding in Masked Diffusion Models (MDMs) shows promise for mathematical and code reasoning, performance remains highly sensitive to slot infilling order, often yielding substantial output variance. We introduce McDiffuSE, a framework that formulates slot selection as decision making and optimises infilling orders through Monte Carlo Tree Search (MCTS). McDiffuSE uses look-ahead simulations to evaluate partial completions before commitment, systematically exploring the combinatorial space of generation orders. Experiments show an average improvement of 3.2% over autoregressive baselines and 8.0% over baseline plan-and-infill, with notable gains of 19.5% on MBPP and 4.9% on MATH500. Our analysis reveals that while McDiffuSE predominantly follows sequential ordering, incorporating non-sequential generation is essential for maximising performance. We observe that larger exploration constants, rather than increased simulations, are necessary to overcome model confidence biases and discover effective orderings. These findings establish MCTS-based planning as an effective approach for enhancing generation quality in MDMs.

---

### VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction

Authors: Xin-Qiang Cai, Masashi Sugiyama
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.12579v2

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning, yet its reliance on external verifiers limits its scalability. Recent findings suggest that RLVR primarily functions by eliciting latent capabilities, motivating the development of verifier-free algorithms. However, in such settings, standard methods like Group Relative Policy Optimization face a critical challenge: destructive gradient variance that often leads to training collapse. To address this issue, we introduce Verifier-Independent Curriculum Reinforcement Learning (VI-CuRL), a framework that leverages the model's intrinsic confidence to construct a curriculum independent from external verifiers. By prioritizing high-confidence samples, VI-CuRL effectively manages the bias-variance trade-off, specifically targeting the reduction of action and problem variance. We provide a rigorous theoretical analysis, proving that our estimator guarantees asymptotic unbiasedness. Empirically, VI-CuRL promotes stability and consistently outperforms verifier-dependent/independent baselines across math and general reasoning benchmarks with/without verifiers.

---

### Discovering Semantic Latent Structures in Psychological Scales: A Response-Free Pathway to Efficient Simplification

Authors: Bo Wang, Yuxuan Zhang, Yueqin Hu, Hanchao Hou, Kaiping Peng, Shiguang Ni
Published: 2026-02-13
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.12575v2

Psychological scale refinement traditionally relies on response-based methods such as factor analysis, item response theory, and network psychometrics to optimize item composition. Although rigorous, these approaches require large samples and may be constrained by data availability and cross-cultural comparability. Recent advances in natural language processing suggest that the semantic structure of questionnaire items may encode latent construct organization, offering a complementary response-free perspective. We introduce a topic-modeling framework that operationalizes semantic latent structure for scale simplification. Items are encoded using contextual sentence embeddings and grouped via density-based clustering to discover latent semantic factors without predefining their number. Class-based term weighting derives interpretable topic representations that approximate constructs and enable merging of semantically adjacent clusters. Representative items are selected using membership criteria within an integrated reduction pipeline. We benchmarked the framework across DASS, IPIP, and EPOCH, evaluating structural recovery, internal consistency, factor congruence, correlation preservation, and reduction efficiency. The proposed method recovered coherent factor-like groupings aligned with established constructs. Selected items reduced scale length by 60.5% on average while maintaining psychometric adequacy. Simplified scales showed high concordance with original factor structures and preserved inter-factor correlations, indicating that semantic latent organization provides a response-free approximation of measurement structure. Our framework formalizes semantic structure as an inspectable front-end for scale construction and reduction. To facilitate adoption, we provide a visualization-supported tool enabling one-click semantic analysis and structured simplification.

---

### Monte Carlo Tree Search with Reasoning Path Refinement for Small Language Models in Conversational Text-to-NoSQL

Authors: Xubang Xiong, Raymond Chi-Wing Wong, Yuanfeng Song
Published: 2026-02-13
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2602.12574v1

NoSQL databases have been widely adopted in big data analytics, geospatial applications, and healthcare services, due to their flexibility and scalability. However, querying NoSQL databases requires specialized technical expertise, creating a high barrier for users. While recent studies have explored text-to-NoSQL problem, they primarily focus on single-turn interactions, ignoring the conversational nature of real-world queries. To bridge this gap, we introduce the Conversational Text-to-NoSQL task, which generates NoSQL queries given a natural language question, a NoSQL database, and the dialogue history. To address this task, we propose Stage-MCTS, a framework that endows small language models (SLMs) with NoSQL-specific reasoning capabilities by formulating query generation as a search problem. The framework employs Monte Carlo Tree Search (MCTS) guided by a rule-based reward to produce stepwise reasoning data, followed by progressive supervised fine-tuning (SFT) and self-training strategies. We further construct CoNoSQL, a cross-domain dataset with over 2,000 dialogues and 150 databases, to support evaluation. Experiments demonstrate that our approach outperforms state-of-the-art large reasoning models, improving execution value match (EVM) accuracy by up to 7.93%.

---

### Fractional Order Federated Learning for Battery Electric Vehicle Energy Consumption Modeling

Authors: Mohammad Partohaghighi, Roummel Marcia, Bruce J. West, YangQuan Chen
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12567v1

Federated learning on connected electric vehicles (BEVs) faces severe instability due to intermittent connectivity, time-varying client participation, and pronounced client-to-client variation induced by diverse operating conditions. Conventional FedAvg and many advanced methods can suffer from excessive drift and degraded convergence under these realistic constraints. This work introduces Fractional-Order Roughness-Informed Federated Averaging (FO-RI-FedAvg), a lightweight and modular extension of FedAvg that improves stability through two complementary client-side mechanisms: (i) adaptive roughness-informed proximal regularization, which dynamically tunes the pull toward the global model based on local loss-landscape roughness, and (ii) non-integer-order local optimization, which incorporates short-term memory to smooth conflicting update directions. The approach preserves standard FedAvg server aggregation, adds only element-wise operations with amortizable overhead, and allows independent toggling of each component. Experiments on two real-world BEV energy prediction datasets, VED and its extended version eVED, show that FO-RI-FedAvg achieves improved accuracy and more stable convergence compared to strong federated baselines, particularly under reduced client participation.

---

### To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models

Authors: Haoqing Wang, Xiang Long, Ziheng Li, Yilong Xu, Tingguang Li, Yehui Tang
Published: 2026-02-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.12566v4

Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level performance in some specific domains via RLVR, such as coding or math. When a general multi-domain expert-level model is required, we need to carefully consider the collaboration of RLVR across different domains. The current state-of-the-art models mainly employ two different training paradigms for multi-domain RLVR: mixed multi-task RLVR and separate RLVR followed by model merging. However, most of the works did not provide a detailed comparison and analysis about these paradigms. To this end, we choose multiple commonly used high-level tasks (e.g., math, coding, science, instruction following, and agent) as our target domains and design extensive qualitative and quantitative experiments using open-source datasets. We find the RLVR across domains exhibits small mutual interferences, and reasoning-intensive domains have mutually synergistic effects. Furthermore, we analyze the internal mechanisms from the perspectives of information constraints, model prediction behavior and self-verification. Our homepage is at https://github.com/Mosi-AI/M2RL.

---

### To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models

Authors: Haoqing Wang, Xiang Long, Ziheng Li, Yilong Xu, Tingguang Li, Yehui Tang
Published: 2026-02-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.12566v3

Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level performance in some specific domains via RLVR, such as coding or math. When a general multi-domain expert-level model is required, we need to carefully consider the collaboration of RLVR across different domains. The current state-of-the-art models mainly employ two different training paradigms for multi-domain RLVR: mixed multi-task RLVR and separate RLVR followed by model merging. However, most of the works did not provide a detailed comparison and analysis about these paradigms. To this end, we choose multiple commonly used high-level tasks (e.g., math, coding, science, instruction following, and agent) as our target domains and design extensive qualitative and quantitative experiments using open-source datasets. We find the RLVR across domains exhibits few mutual interferences, and reasoning-intensive domains demonstrate mutually synergistic effects. Furthermore, we analyze the internal mechanisms of mutual gains from the perspectives of weight space geometry, information constraints, model prediction behavior and self-verification. This project is named as M2RL that means Mixed multi-task training or separate training followed by model Merging for Reinforcement Learning, and the homepage is at https://github.com/Mosi-AI/M2RL.

---

### The Constant Eye: Benchmarking and Bridging Appearance Robustness in Autonomous Driving

Authors: Jiabao Wang, Hongyu Zhou, Yuanbo Yang, Jiahao Shao, Yiyi Liao
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12563v1

Despite rapid progress, autonomous driving algorithms remain notoriously fragile under Out-of-Distribution (OOD) conditions. We identify a critical decoupling failure in current research: the lack of distinction between appearance-based shifts, such as weather and lighting, and structural scene changes. This leaves a fundamental question unanswered: Is the planner failing because of complex road geometry, or simply because it is raining? To resolve this, we establish navdream, a high-fidelity robustness benchmark leveraging generative pixel-aligned style transfer. By creating a visual stress test with negligible geometric deviation, we isolate the impact of appearance on driving performance. Our evaluation reveals that existing planning algorithms often show significant degradation under OOD appearance conditions, even when the underlying scene structure remains consistent. To bridge this gap, we propose a universal perception interface leveraging a frozen visual foundation model (DINOv3). By extracting appearance-invariant features as a stable interface for the planner, we achieve exceptional zero-shot generalization across diverse planning paradigms, including regression-based, diffusion-based, and scoring-based models. Our plug-and-play solution maintains consistent performance across extreme appearance shifts without requiring further fine-tuning. The benchmark and code will be made available.

---

### PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesis

Authors: Yuanbo Li, Dule Shu, Yanying Chen, Matt Klenk, Daniel Ritchie
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.12561v1

Recovering Computer-Aided Design (CAD) programs from 3D geometries is a widely studied problem. Recent advances in large language models (LLMs) have enabled progress in CAD program synthesis, but existing methods rely on supervised training with paired shape-program data, which is often unavailable. We introduce PLLM, a self-training framework for CAD program synthesis from unlabeled 3D shapes. Given a pre-trained CAD-capable LLM and a shape dataset, PLLM iteratively samples candidate programs, selects high-fidelity executions, and augments programs to construct synthetic program-shape pairs for fine-tuning. We experiment on adapting CAD-Recode from DeepCAD to the unlabeled ABC dataset show consistent improvements in geometric fidelity and program diversity.

---

### SD-MoE: Spectral Decomposition for Effective Expert Specialization

Authors: Ruijun Huang, Fang Dong, Xin Zhang, Hengjie Cao, Zhendong Huang, Anrui Chen, Jixian Zhou, Mengyi Chen, Yifeng Yang, Mingzhi Dong, Yujiang Wang, Jinlong Hou et al.
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.12556v1

Mixture-of-Experts (MoE) architectures scale Large Language Models via expert specialization induced by conditional computation. In practice, however, expert specialization often fails: some experts become functionally similar, while others functioning as de facto shared experts, limiting the effective capacity and model performance. In this work, we analysis from a spectral perspective on parameter and gradient spaces, uncover that (1) experts share highly overlapping dominant spectral components in their parameters, (2) dominant gradient subspaces are strongly aligned across experts, driven by ubiquitous low-rank structure in human corpus, and (3) gating mechanisms preferentially route inputs along these dominant directions, further limiting specialization. To address this, we propose Spectral-Decoupled MoE (SD-MoE), which decomposes both parameter and gradient in the spectral space. SD-MoE improves performance across downstream tasks, enables effective expert specialization, incurring minimal additional computation, and can be seamlessly integrated into a wide range of existing MoE architectures, including Qwen and DeepSeek.

---

### A consequence of failed sequential learning: A computational account of developmental amnesia

Authors: Qi Zhang
Published: 2026-02-13
Categories: q-bio.NC, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2602.12547v1

Developmental amnesia, featured with severely impaired episodic memory and almost normal semantic memory, has been discovered to occur in children with hippocampal atrophy. This unique combination of characteristics seems to challenge the understanding that early loss of episodic memory may impede cognitive development and result in severe mental retardation. Although a few underlying mechanisms have been suggested, no computational model has been reported that is able to mimic the unique combination of characteristics. In this study, a cognitive system is presented, and developmental amnesia is demonstrated computationally in terms of impaired episodic recall, spared recognition and spared semantic learning. Impaired sequential/spatial learning ability of the hippocampus is suggested to be the cause of such amnesia. Simulation shows that impaired sequential leaning may only result in severe impairment of episodic recall, but affect neither recognition ability nor semantic learning. The spared semantic learning is inline with the view that semantic learning is largely associated with the consolidation of episodic memory, a process in which episodic memory may be mostly activated randomly, instead of sequentially. Furthermore, retrograded amnesia is also simulated, and the result and its mechanism are in agreement with most computational models of amnesia reported previously.

---

### Decoder-only Conformer with Modality-aware Sparse Mixtures of Experts for ASR

Authors: Jaeyoung Lee, Masato Mimura
Published: 2026-02-13
Categories: eess.AS, cs.AI, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2602.12546v1

We present a decoder-only Conformer for automatic speech recognition (ASR) that processes speech and text in a single stack without external speech encoders or pretrained large language models (LLM). The model uses a modality-aware sparse mixture of experts (MoE): disjoint expert pools for speech and text with hard routing and top-1 selection, embedded in hybrid-causality Conformer blocks (bidirectional for speech, causal for text). Training combines CTC on speech positions with label-smoothed cross-entropy for text generation. Our 113M-parameter model consistently improves WER over a 139M AED baseline on Librispeech (2.8% vs. 3.2% test-clean; 5.6% vs. 6.0% test-other). On Common Voice 16.1 with a single multilingual model across five languages, our approach reduces average WER from 12.2% to 10.6%. To our knowledge, this is the first randomly initialized decoder-only ASR that surpasses strong AED baselines via modality-aware routing and sparse MoE, achieving better accuracy with fewer active parameters and without alignment/adaptation modules.

---

### Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation

Authors: Lajanugen Logeswaran, Jaekyeom Kim, Sungryull Sohn, Creighton Glasscock, Honglak Lee
Published: 2026-02-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.12544v1

We present a scalable pipeline for automatically generating high-quality training data for web agents. In particular, a major challenge in identifying high-quality training instances is trajectory evaluation - quantifying how much progress was made towards task completion. We introduce a novel constraint-based evaluation framework that provides fine-grained assessment of progress towards task completion. This enables us to leverage partially successful trajectories, which significantly expands the amount of usable training data. We evaluate our method on a new benchmark we propose called BookingArena, which consists of complex booking tasks across 20 popular websites, and demonstrate that our distilled student model outperforms open-source approaches and matches or exceeds commercial systems, while being a significantly smaller model. Our work addresses the challenge of efficiently creating diverse, realistic web interaction datasets and provides a systematic evaluation methodology for complex structured web tasks.

---

### Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal Inference

Authors: Pengfei Hu, Chang Lu, Feifan Liu, Yue Ning
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.12542v2

Deep learning models for clinical event prediction on electronic health records (EHR) often suffer performance degradation when deployed under different data distributions. While domain adaptation (DA) methods can mitigate such shifts, their "black-box" nature prevents widespread adoption in clinical practice where transparency is essential for trust and safety. We propose ExtraCare to decompose patient representations into invariant and covariant components. By supervising these two components and enforcing their orthogonality during training, our model preserves label information while exposing domain-specific variation at the same time for more accurate predictions than most feature alignment models. More importantly, it offers human-understandable explanations by mapping sparse latent dimensions to medical concepts and quantifying their contributions via targeted ablations. ExtraCare is evaluated on two real-world EHR datasets across multiple domain partition settings, demonstrating superior performance along with enhanced transparency, as evidenced by its accurate predictions and explanations from extensive case studies.

---

### Self-Supervised JEPA-based World Models for LiDAR Occupancy Completion and Forecasting

Authors: Haoran Zhu, Anna Choromanska
Published: 2026-02-13
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.12540v1

Autonomous driving, as an agent operating in the physical world, requires the fundamental capability to build \textit{world models} that capture how the environment evolves spatiotemporally in order to support long-term planning. At the same time, scalability demands learning such models in a self-supervised manner; \textit{joint-embedding predictive architecture (JEPA)} enables learning world models via leveraging large volumes of unlabeled data without relying on expensive human annotations. In this paper, we propose \textbf{AD-LiST-JEPA}, a self-supervised world model for autonomous driving that predicts future spatiotemporal evolution from LiDAR data using a JEPA framework. We evaluate the quality of the learned representations through a downstream LiDAR-based occupancy completion and forecasting (OCF) task, which jointly assesses perception and prediction. Proof of concept experiments show better OCF performance with pretrained encoder after JEPA-based world model learning.

---

### Linear Regression with Unknown Truncation Beyond Gaussian Features

Authors: Alexandros Kouridakis, Anay Mehrotra, Alkis Kalavasis, Constantine Caramanis
Published: 2026-02-13
Categories: stat.ML, cs.DS, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2602.12534v2

In truncated linear regression, samples $(x,y)$ are shown only when the outcome $y$ falls inside a certain survival set $S^\star$ and the goal is to estimate the unknown $d$-dimensional regressor $w^\star$. This problem has a long history of study in Statistics and Machine Learning going back to the works of (Galton, 1897; Tobin, 1958) and more recently in, e.g., (Daskalakis et al., 2019; 2021; Lee et al., 2023; 2024). Despite this long history, however, most prior works are limited to the special case where $S^\star$ is precisely known. The more practically relevant case, where $S^\star$ is unknown and must be learned from data, remains open: indeed, here the only available algorithms require strong assumptions on the distribution of the feature vectors (e.g., Gaussianity) and, even then, have a $d^{\mathrm{poly} (1/\varepsilon)}$ run time for achieving $\varepsilon$ accuracy. In this work, we give the first algorithm for truncated linear regression with unknown survival set that runs in $\mathrm{poly} (d/\varepsilon)$ time, by only requiring that the feature vectors are sub-Gaussian. Our algorithm relies on a novel subroutine for efficiently learning unions of a bounded number of intervals using access to positive examples (without any negative examples) under a certain smoothness condition. This learning guarantee adds to the line of works on positive-only PAC learning and may be of independent interest.

---

### AMPS: Adaptive Modality Preference Steering via Functional Entropy

Authors: Zihan Huang, Xintong Li, Rohan Surana, Tong Yu, Rui Wang, Julian McAuley, Jingbo Shang, Junda Wu
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.12533v1

Multimodal Large Language Models (MLLMs) often exhibit significant modality preference, which is a tendency to favor one modality over another. Depending on the input, they may over-rely on linguistic priors relative to visual evidence, or conversely over-attend to visually salient but facts in textual contexts. Prior work has applied a uniform steering intensity to adjust the modality preference of MLLMs. However, strong steering can impair standard inference and increase error rates, whereas weak steering is often ineffective. In addition, because steering sensitivity varies substantially across multimodal instances, a single global strength is difficult to calibrate. To address this limitation with minimal disruption to inference, we introduce an instance-aware diagnostic metric that quantifies each modality's information contribution and reveals sample-specific susceptibility to steering. Building on these insights, we propose a scaling strategy that reduces steering for sensitive samples and a learnable module that infers scaling patterns, enabling instance-aware control of modality preference. Experimental results show that our instance-aware steering outperforms conventional steering in modulating modality preference, achieving effective adjustment while keeping generation error rates low.

---

### Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models

Authors: Bowen Ping, Chengyou Jia, Minnan Luo, Hangwei Qian, Ivor Tsang
Published: 2026-02-13
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.12529v3

Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face fragmented codebases, model-specific implementations, and engineering complexity. We introduce Flow-Factory, a unified framework that decouples algorithms, models, and rewards through through a modular, registry-based architecture. This design enables seamless integration of new algorithms and architectures, as demonstrated by our support for GRPO, DiffusionNFT, and AWM across Flux, Qwen-Image, and WAN video models. By minimizing implementation overhead, Flow-Factory empowers researchers to rapidly prototype and scale future innovations with ease. Flow-Factory provides production-ready memory optimization, flexible multi-reward training, and seamless distributed training support. The codebase is available at https://github.com/X-GenGroup/Flow-Factory.

---

### DiffuRank: Effective Document Reranking with Diffusion Language Models

Authors: Qi Liu, Kun Ai, Jiaxin Mao, Yanzhao Zhang, Mingxin Li, Dingkun Long, Pengjun Xie, Fengbin Zhu, Ji-Rong Wen
Published: 2026-02-13
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2602.12528v1

Recent advances in large language models (LLMs) have inspired new paradigms for document reranking. While this paradigm better exploits the reasoning and contextual understanding capabilities of LLMs, most existing LLM-based rerankers rely on autoregressive generation, which limits their efficiency and flexibility. In particular, token-by-token decoding incurs high latency, while the fixed left-to-right generation order causes early prediction errors to propagate and is difficult to revise. To address these limitations, we explore the use of diffusion language models (dLLMs) for document reranking and propose DiffuRank, a reranking framework built upon dLLMs. Unlike autoregressive models, dLLMs support more flexible decoding and generation processes that are not constrained to a left-to-right order, and enable parallel decoding, which may lead to improved efficiency and controllability. Specifically, we investigate three reranking strategies based on dLLMs: (1) a pointwise approach that uses dLLMs to estimate the relevance of each query-document pair; (2) a logit-based listwise approach that prompts dLLMs to jointly assess the relevance of multiple documents and derives ranking lists directly from model logits; and (3) a permutation-based listwise approach that adapts the canonical decoding process of dLLMs to the reranking tasks. For each approach, we design corresponding training methods to fully exploit the advantages of dLLMs. We evaluate both zero-shot and fine-tuned reranking performance on multiple benchmarks. Experimental results show that dLLMs achieve performance comparable to, and in some cases exceeding, that of autoregressive LLMs with similar model sizes. These findings demonstrate the promise of diffusion-based language models as a compelling alternative to autoregressive architectures for document reranking.

---