# Research Papers — 2026-02 · bundle page 95 of 210

> Full-text markdown of papers #4701–4750 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/95
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/94.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/96.md)

### Why is Normalization Preferred? A Worst-Case Complexity Theory for Stochastically Preconditioned SGD under Heavy-Tailed Noise

Authors: Yuchen Fang, James Demmel, Javad Lavaei
Published: 2026-02-13
Categories: cs.LG, math.NA, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2602.13413v1

We develop a worst-case complexity theory for stochastically preconditioned stochastic gradient descent (SPSGD) and its accelerated variants under heavy-tailed noise, a setting that encompasses widely used adaptive methods such as Adam, RMSProp, and Shampoo. We assume the stochastic gradient noise has a finite $p$-th moment for some $p \in (1,2)$, and measure convergence after $T$ iterations. While clipping and normalization are parallel tools for stabilizing training of SGD under heavy-tailed noise, there is a fundamental separation in their worst-case properties in stochastically preconditioned settings. We demonstrate that normalization guarantees convergence to a first-order stationary point at rate $\mathcal{O}(T^{-\frac{p-1}{3p-2}})$ when problem parameters are known, and $\mathcal{O}(T^{-\frac{p-1}{2p}})$ when problem parameters are unknown, matching the optimal rates for normalized SGD, respectively. In contrast, we prove that clipping may fail to converge in the worst case due to the statistical dependence between the stochastic preconditioner and the gradient estimates. To enable the analysis, we develop a novel vector-valued Burkholder-type inequality that may be of independent interest. These results provide a theoretical explanation for the empirical preference for normalization over clipping in large-scale model training.

---

### Evolutionary design of thermodynamic logic gates and their heat emission

Authors: Stephen Whitelam
Published: 2026-02-13
Categories: cond-mat.stat-mech, cs.NE
arXiv: https://arxiv.org/abs/2602.13410v2

Landauer's principle bounds the heat generated by logical operations, but in practice the thermodynamic cost of computation is dominated by the control systems that implement logic. CMOS gates dissipate energy far above the Landauer bound, while laboratory demonstrations of near-Landauer erasure rely on external measurement or feedback systems whose energy costs exceed that of the logic operation by many orders of magnitude. Here we use simulations to show that a genetic algorithm can program a thermodynamic computer to implement logic operations in which the total heat emitted by the control system is of a similar order of magnitude to that of the information-bearing degrees of freedom. Moreover, the computer can be programmed so that heat is drawn away from the information-bearing degrees of freedom and dissipated within the control unit, suggesting the possibility of computing architectures in which heat management is an integral part of the program design.

---

### Evolutionary design of thermodynamic logic gates and their heat emission

Authors: Stephen Whitelam
Published: 2026-02-13
Categories: cond-mat.stat-mech, cs.NE
arXiv: https://arxiv.org/abs/2602.13410v1

Landauer's principle bounds the heat generated by logical operations, but in practice the thermodynamic cost of computation is dominated by the control systems that implement logic. CMOS gates dissipate energy far above the Landauer bound, while laboratory demonstrations of near-Landauer erasure rely on external measurement or feedback systems whose energy costs exceed that of the logic operation by many orders of magnitude. Here we use simulations to show that a genetic algorithm can program a thermodynamic computer to implement logic operations in which the total heat emitted by the control system is of a similar order of magnitude to that of the information-bearing degrees of freedom. Moreover, the computer can be programmed so that heat is drawn away from the information-bearing degrees of freedom and dissipated within the control unit, suggesting the possibility of computing architectures in which heat management is an integral part of the program design.

---

### On-Policy Supervised Fine-Tuning for Efficient Reasoning

Authors: Anhao Zhao, Ziyang Chen, Junlong Tong, Yingqi Fan, Fanghua Ye, Shuhao Li, Yunpu Ma, Wenjie Li, Xiaoyu Shen
Published: 2026-02-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.13407v1

Large reasoning models (LRMs) are commonly trained with reinforcement learning (RL) to explore long chain-of-thought reasoning, achieving strong performance at high computational cost. Recent methods add multi-reward objectives to jointly optimize correctness and brevity, but these complex extensions often destabilize training and yield suboptimal trade-offs. We revisit this objective and challenge the necessity of such complexity. Through principled analysis, we identify fundamental misalignments in this paradigm: KL regularization loses its intended role when correctness and length are directly verifiable, and group-wise normalization becomes ambiguous under multiple reward signals. By removing these two items and simplifying the reward to a truncation-based length penalty, we show that the optimization problem reduces to supervised fine-tuning on self-generated data filtered for both correctness and conciseness. We term this simplified training strategy on-policy SFT. Despite its simplicity, on-policy SFT consistently defines the accuracy-efficiency Pareto frontier. It reduces CoT length by up to 80 while maintaining original accuracy, surpassing more complex RL-based methods across five benchmarks. Furthermore, it significantly enhances training efficiency, reducing GPU memory usage by 50% and accelerating convergence by 70%. Our code is available at https://github.com/EIT-NLP/On-Policy-SFT.

---

### Accelerated Discovery of Cryoprotectant Cocktails via Multi-Objective Bayesian Optimization

Authors: Daniel Emerson, Nora Gaby-Biegel, Purva Joshi, Yoed Rabin, Rebecca D. Sandlin, Levent Burak Kara
Published: 2026-02-13
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2602.13398v1

Designing cryoprotectant agent (CPA) cocktails for vitrification is challenging because formulations must be concentrated enough to suppress ice formation yet non-toxic enough to preserve cell viability. This tradeoff creates a large, multi-objective design space in which traditional discovery is slow, often relying on expert intuition or exhaustive experimentation. We present a data-efficient framework that accelerates CPA cocktail design by combining high-throughput screening with an active-learning loop based on multi-objective Bayesian optimization. From an initial set of measured cocktails, we train probabilistic surrogate models to predict concentration and viability and quantify uncertainty across candidate formulations. We then iteratively select the next experiments by prioritizing cocktails expected to improve the Pareto front, maximizing expected Pareto improvement under uncertainty, and update the models as new assay results are collected. Wet-lab validation shows that our approach efficiently discovers cocktails that simultaneously achieve high CPA concentrations and high post-exposure viability. Relative to a naive strategy and a strong baseline, our method improves dominated hypervolume by 9.5\% and 4.5\%, respectively, while reducing the number of experiments needed to reach high-quality solutions. In complementary synthetic studies, it recovers a comparably strong set of Pareto-optimal solutions using only 30\% of the evaluations required by the prior state-of-the-art multi-objective approach, which amounts to saving approximately 10 weeks of experimental time. Because the framework assumes only a suitable assay and defined formulation space, it can be adapted to different CPA libraries, objective definitions, and cell lines to accelerate cryopreservation development.

---

### Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

Authors: Xu Li, Simon Yu, Minzhou Pan, Yiyou Sun, Bo Li, Dawn Song, Xue Lin, Weiyan Shi
Published: 2026-02-13
Categories: cs.CR, cs.AI, cs.CL, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2602.13379v2

LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing new risks overlooked by existing benchmarks. To systematically scale safety testing into multi-turn, tool-realistic settings, we propose a principled taxonomy that transforms single-turn harmful tasks into multi-turn attack sequences. Using this taxonomy, we construct MT-AgentRisk (Multi-Turn Agent Risk Benchmark), the first benchmark to evaluate multi-turn tool-using agent safety. Our experiments reveal substantial safety degradation: the Attack Success Rate (ASR) increases by 16% on average across open and closed models in multi-turn settings. To close this gap, we propose ToolShield, a training-free, tool-agnostic, self-exploration defense: when encountering a new tool, the agent autonomously generates test cases, executes them to observe downstream effects, and distills safety experiences for deployment. Experiments show that ToolShield effectively reduces ASR by 30% on average in multi-turn interactions. Our code is available at https://github.com/CHATS-lab/ToolShield.

---

### LAF-YOLOv10 with Partial Convolution Backbone, Attention-Guided Feature Pyramid, Auxiliary P2 Head, and Wise-IoU Loss for Small Object Detection in Drone Aerial Imagery

Authors: Sohail Ali Farooqui, Zuhair Ahmed Khan Taha, Mohammed Mudassir Uddin, Shahnawaz Alam
Published: 2026-02-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.13378v1

Unmanned aerial vehicles serve as primary sensing platforms for surveillance, traffic monitoring, and disaster response, making aerial object detection a central problem in applied computer vision. Current detectors struggle with UAV-specific challenges: targets spanning only a few pixels, cluttered backgrounds, heavy occlusion, and strict onboard computational budgets. This study introduces LAF-YOLOv10, built on YOLOv10n, integrating four complementary techniques to improve small-object detection in drone imagery. A Partial Convolution C2f (PC-C2f) module restricts spatial convolution to one quarter of backbone channels, reducing redundant computation while preserving discriminative capacity. An Attention-Guided Feature Pyramid Network (AG-FPN) inserts Squeeze-and-Excitation channel gates before multi-scale fusion and replaces nearest-neighbor upsampling with DySample for content-aware interpolation. An auxiliary P2 detection head at 160$\times$160 resolution extends localization to objects below 8$\times$8 pixels, while the P5 head is removed to redistribute parameters. Wise-IoU v3 replaces CIoU for bounding box regression, attenuating gradients from noisy annotations in crowded aerial scenes. The four modules address non-overlapping bottlenecks: PC-C2f compresses backbone computation, AG-FPN refines cross-scale fusion, the P2 head recovers spatial resolution, and Wise-IoU stabilizes regression under label noise. No individual component is novel; the contribution is the joint integration within a single YOLOv10 framework. Across three training runs (seeds 42, 123, 256), LAF-YOLOv10 achieves 35.1$\pm$0.3\% mAP@0.5 on VisDrone-DET2019 with 2.3\,M parameters, exceeding YOLOv10n by 3.3 points. Cross-dataset evaluation on UAVDT yields 35.8$\pm$0.4\% mAP@0.5. Benchmarks on NVIDIA Jetson Orin Nano confirm 24.3 FPS at FP16, demonstrating viability for embedded UAV deployment.

---

### An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation

Authors: Giang Son Nguyen, Zi Pong Lim, Sarthak Ketanbhai Modi, Yon Shin Teo, Wenya Wang
Published: 2026-02-13
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13376v2

Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.g., Mermaid). In production, these systems process arbitrary inputs for which no ground-truth code exists, making output quality difficult to assess. We propose a reference-free evaluation framework that monitors flowchart image-to-code generation quality at inference time, using only the input image and the generated output. The framework introduces two automated metrics: $\text{Recall}{\text{OCR}}$, which estimates content coverage by extracting text from the input image via OCR as a proxy reference, and $\text{Precision}{\text{VE}}$, which detects hallucinated elements through Visual Entailment against the original image. Their harmonic mean, $\text{F1}{\text{OCR-VE}}$, provides a unified quality score. Validation on the FlowVQA dataset shows strong agreement with ground-truth metrics (average Pearson's $r = 0.97$, $0.91$, and $0.94$ for Recall, Precision, and F1, respectively), confirming the framework's reliability as a practical, reference-free alternative for continuous quality monitoring in production settings.

---

### MoralityGym: A Benchmark for Evaluating Hierarchical Moral Alignment in Sequential Decision-Making Agents

Authors: Simon Rosen, Siddarth Singh, Ebenezer Gelo, Helen Sarah Robertson, Ibrahim Suder, Victoria Williams, Benjamin Rosman, Geraud Nangue Tasse, Steven James
Published: 2026-02-13
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.13372v2

Evaluating moral alignment in agents navigating conflicting, hierarchically structured human norms is a critical challenge at the intersection of AI safety, moral philosophy, and cognitive science. We introduce Morality Chains, a novel formalism for representing moral norms as ordered deontic constraints, and MoralityGym, a benchmark of 98 ethical-dilemma problems presented as trolley-dilemma-style Gymnasium environments. By decoupling task-solving from moral evaluation and introducing a novel Morality Metric, MoralityGym allows the integration of insights from psychology and philosophy into the evaluation of norm-sensitive reasoning. Baseline results with Safe RL methods reveal key limitations, underscoring the need for more principled approaches to ethical decision-making. This work provides a foundation for developing AI systems that behave more reliably, transparently, and ethically in complex real-world contexts.

---

### G2CP: A Graph-Grounded Communication Protocol for Verifiable and Efficient Multi-Agent Reasoning

Authors: Karim Ben Khaled, Davy Monticolo
Published: 2026-02-13
Categories: cs.MA, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13370v1

Multi-agent systems powered by Large Language Models face a critical challenge: agents communicate through natural language, leading to semantic drift, hallucination propagation, and inefficient token consumption. We propose G2CP (Graph-Grounded Communication Protocol), a structured agent communication language where messages are graph operations rather than free text. Agents exchange explicit traversal commands, subgraph fragments, and update operations over a shared knowledge graph, enabling verifiable reasoning traces and eliminating ambiguity. We validate G2CP within an industrial knowledge management system where specialized agents (Diagnostic, Procedural, Synthesis, and Ingestion) coordinate to answer complex queries. Experimental results on 500 industrial scenarios and 21 real-world maintenance cases show that G2CP reduces inter-agent communication tokens by 73%, improves task completion accuracy by 34% over free-text baselines, eliminates cascading hallucinations, and produces fully auditable reasoning chains. G2CP represents a fundamental shift from linguistic to structural communication in multi-agent systems, with implications for any domain requiring precise agent coordination. Code, data, and evaluation scripts are publicly available.

---

### Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts

Authors: Chen Yang, Guangyue Peng, Jiaying Zhu, Ran Le, Ruixiang Feng, Tao Zhang, Xiyun Xu, Yang Song, Yiming Jia, Yuntao Wen, Yunzhi Xu, Zekai Wang et al.
Published: 2026-02-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13367v1

We present Nanbeige4.1-3B, a unified generalist language model that simultaneously achieves strong agentic behavior, code generation, and general reasoning with only 3B parameters. To the best of our knowledge, it is the first open-source small language model (SLM) to achieve such versatility in a single model. To improve reasoning and preference alignment, we combine point-wise and pair-wise reward modeling, ensuring high-quality, human-aligned responses. For code generation, we design complexity-aware rewards in Reinforcement Learning, optimizing both correctness and efficiency. In deep search, we perform complex data synthesis and incorporate turn-level supervision during training. This enables stable long-horizon tool interactions, allowing Nanbeige4.1-3B to reliably execute up to 600 tool-call turns for complex problem-solving. Extensive experimental results show that Nanbeige4.1-3B significantly outperforms prior models of similar scale, such as Nanbeige4-3B-2511 and Qwen3-4B, even achieving superior performance compared to much larger models, such as Qwen3-30B-A3B. Our results demonstrate that small models can achieve both broad competence and strong specialization simultaneously, redefining the potential of 3B parameter models.

---

### Assessing Spear-Phishing Website Generation in Large Language Model Coding Agents

Authors: Tailia Malloy, Tegawende F. Bissyande
Published: 2026-02-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.13363v1

Large Language Models are expanding beyond being a tool humans use and into independent agents that can observe an environment, reason about solutions to problems, make changes that impact those environments, and understand how their actions impacted their environment. One of the most common applications of these LLM Agents is in computer programming, where agents can successfully work alongside humans to generate code while controlling programming environments or networking systems. However, with the increasing ability and complexity of these agents comes dangers about the potential for their misuse. A concerning application of LLM agents is in the domain cybersecurity, where they have the potential to greatly expand the threat imposed by attacks such as social engineering. This is due to the fact that LLM Agents can work autonomously and perform many tasks that would normally require time and effort from skilled human programmers. While this threat is concerning, little attention has been given to assessments of the capabilities of LLM coding agents in generating code for social engineering attacks. In this work we compare different LLMs in their ability and willingness to produce potentially dangerous code bases that could be misused by cyberattackers. The result is a dataset of 200 website code bases and logs from 40 different LLM coding agents. Analysis of models shows which metrics of LLMs are more and less correlated with performance in generating spear-phishing sites. Our analysis and the dataset we present will be of interest to researchers and practitioners concerned in defending against the potential misuse of LLMs in spear-phishing.

---

### Nonparametric Distribution Regression Re-calibration

Authors: Ádám Jung, Domokos M. Kelen, András A. Benczúr
Published: 2026-02-13
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.13362v2

A key challenge in probabilistic regression is ensuring that predictive distributions accurately reflect true empirical uncertainty. Minimizing overall prediction error often encourages models to prioritize informativeness over calibration, producing narrow but overconfident predictions. However, in safety-critical settings, trustworthy uncertainty estimates are often more valuable than narrow intervals. Realizing the problem, several recent works have focused on post-hoc corrections; however, existing methods either rely on weak notions of calibration (such as PIT uniformity) or impose restrictive parametric assumptions on the nature of the error. To address these limitations, we propose a novel nonparametric re-calibration algorithm based on conditional kernel mean embeddings, capable of correcting calibration error without restrictive modeling assumptions. For efficient inference with real-valued targets, we introduce a novel characteristic kernel over distributions that can be evaluated in $\mathcal{O}(n \log n)$ time for empirical distributions of size $n$. We demonstrate that our method consistently outperforms prior re-calibration approaches across a diverse set of regression benchmarks and model classes.

---

### The Diffusion Duet: Harmonizing Dual Channels with Wavelet Suppression for Image Separation

Authors: Jingwei Li, Wei Pu
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.13361v1

Blind image separation (BIS) refers to the inverse problem of simultaneously estimating and restoring multiple independent source images from a single observation image under conditions of unknown mixing mode and without prior knowledge of the source images. Traditional methods relying on statistical independence assumptions or CNN/GAN variants struggle to characterize complex feature distributions in real scenes, leading to estimation bias, texture distortion, and artifact residue under strong noise and nonlinear mixing. This paper innovatively introduces diffusion models into dual-channel BIS, proposing an efficient Dual-Channel Diffusion Separation Model (DCDSM). DCDSM leverages diffusion models' powerful generative capability to learn source image feature distributions and reconstruct feature structures effectively. A novel Wavelet Suppression Module (WSM) is designed within the dual-branch reverse denoising process, forming an interactive separation network that enhances detail separation by exploiting the mutual coupling noise characteristic between source images. Extensive experiments on synthetic datasets containing rain/snow and complex mixtures demonstrate that DCDSM achieves state-of-the-art performance: 1) In image restoration tasks, it obtains PSNR/SSIM values of 35.0023 dB/0.9549 and 29.8108 dB/0.9243 for rain and snow removal respectively, outperforming Histoformer and LDRCNet by 1.2570 dB/0.9272 dB (PSNR) and 0.0262/0.0289 (SSIM) on average; 2) For complex mixture separation, the restored dual-source images achieve average PSNR and SSIM of 25.0049 dB and 0.7997, surpassing comparative methods by 4.1249 dB and 0.0926. Both subjective and objective evaluations confirm DCDSM's superiority in addressing rain/snow residue removal and detail preservation challenges.

---

### The Speed-up Factor: A Quantitative Multi-Iteration Active Learning Performance Metric

Authors: Hannes Kath, Thiago S. Gouvêa, Daniel Sonntag
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.13359v1

Machine learning models excel with abundant annotated data, but annotation is often costly and time-intensive. Active learning (AL) aims to improve the performance-to-annotation ratio by using query methods (QMs) to iteratively select the most informative samples. While AL research focuses mainly on QM development, the evaluation of this iterative process lacks appropriate performance metrics. This work reviews eight years of AL evaluation literature and formally introduces the speed-up factor, a quantitative multi-iteration QM performance metric that indicates the fraction of samples needed to match random sampling performance. Using four datasets from diverse domains and seven QMs of various types, we empirically evaluate the speed-up factor and compare it with state-of-the-art AL performance metrics. The results confirm the assumptions underlying the speed-up factor, demonstrate its accuracy in capturing the described fraction, and reveal its superior stability across iterations.

---

### AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers

Authors: Dong Liu, Yanxuan Yu, Ben Lengerich, Ying Nian Wu
Published: 2026-02-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.13357v3

Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure. While prior methods accelerate sampling by caching intermediate features, they rely on static reuse schedules or coarse-grained heuristics, which often lead to temporal drift and cache misalignment that significantly degrade generation quality. We introduce \textbf{AdaCorrection}, an adaptive offset cache correction framework that maintains high generation fidelity while enabling efficient cache reuse across Transformer layers during diffusion inference. At each timestep, AdaCorrection estimates cache validity with lightweight spatio-temporal signals and adaptively blends cached and fresh activations. This correction is computed on-the-fly without additional supervision or retraining. Our approach achieves strong generation quality with minimal computational overhead, maintaining near-original FID while providing moderate acceleration. Experiments on image and video diffusion benchmarks show that AdaCorrection consistently improves generation performance. Our code has been integrated into FastCache-xDiT at https://github.com/NoakLiu/FastCache-xDiT.

---

### Using Deep Learning to Generate Semantically Correct Hindi Captions

Authors: Wasim Akram Khan, Anil Kumar Vuppala
Published: 2026-02-13
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13352v1

Automated image captioning using the content from the image is very appealing when done by harnessing the capability of computer vision and natural language processing. Extensive research has been done in the field with a major focus on the English language which gives the scope for further developments in the same with consideration of popular foreign languages. This research utilizes distinct models for translating the image caption into Hindi, the fourth most popular language across the world. Exploring the multi-modal architectures this research comprises local visual features, global visual features, attention mechanisms, and pre-trained models. Using google cloud translator on the image dataset from Flickr8k, Hindi image descriptions have been generated. Pre-trained CNNs like VGG16, ResNet50, and Inception V3 helped in retrieving image characteristics, while the uni-directional and bi-directional techniques of text encoding are used for the text encoding process. An additional Attention layer helps to generate a weight vector and, by multiplying it, combine image characteristics from each time step into a sentence-level feature vector. Bilingual evaluation understudy scores are used to compare the research outcome. Many experiments that serve as a baseline are done for the comparative analysis of the research. An image with a score of BLEU-1 is considered sufficient, whereas one with a score of BLEU-4 is considered to have fluid image captioning. For both BLEU scores, the attention-based bidirectional LSTM with VGG16 produced the best results of 0.59 and 0.19 respectively. The experiments conclude that researchs ability to produce relevant, semantically accurate image captions in Hindi. The research accomplishes the goals and future research can be guided by this research model.

---

### Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos

Authors: Albert J. Zhai, Kuo-Hao Zeng, Jiasen Lu, Ali Farhadi, Shenlong Wang, Wei-Chiu Ma
Published: 2026-02-13
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.13197v2

The ability to learn manipulation skills by watching videos of humans has the potential to unlock a new source of highly scalable data for robot learning. Here, we tackle prehensile manipulation, in which tasks involve grasping an object before performing various post-grasp motions. Human videos offer strong signals for learning the post-grasp motions, but they are less useful for learning the prerequisite grasping behaviors, especially for robots without human-like hands. A promising way forward is to use a modular policy design, leveraging a dedicated grasp generator to produce stable grasps. However, arbitrary stable grasps are often not task-compatible, hindering the robot's ability to perform the desired downstream motion. To address this challenge, we present Perceive-Simulate-Imitate (PSI), a framework for training a modular manipulation policy using human video motion data processed by paired grasp-trajectory filtering in simulation. This simulation step extends the trajectory data with grasp suitability labels, which allows for supervised learning of task-oriented grasping capabilities. We show through real-world experiments that our framework can be used to learn precise manipulation skills efficiently without any robot data, resulting in significantly more robust performance than using a grasp generator naively.

---

### Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision

Authors: Aadarsh Sahoo, Georgia Gkioxari
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.13195v1

Conversational image segmentation grounds abstract, intent-driven concepts into pixel-accurate masks. Prior work on referring image grounding focuses on categorical and spatial queries (e.g., "left-most apple") and overlooks functional and physical reasoning (e.g., "where can I safely store the knife?"). We address this gap and introduce Conversational Image Segmentation (CIS) and ConverSeg, a benchmark spanning entities, spatial relations, intent, affordances, functions, safety, and physical reasoning. We also present ConverSeg-Net, which fuses strong segmentation priors with language understanding, and an AI-powered data engine that generates prompt-mask pairs without human supervision. We show that current language-guided segmentation models are inadequate for CIS, while ConverSeg-Net trained on our data engine achieves significant gains on ConverSeg and maintains strong performance on existing language-guided segmentation benchmarks. Project webpage: https://glab-caltech.github.io/converseg/

---

### Semantic Chunking and the Entropy of Natural Language

Authors: Weishun Zhong, Doron Sivan, Tankut Can, Mikhail Katkov, Misha Tsodyks
Published: 2026-02-13
Categories: cs.CL, cond-mat.dis-nn, cond-mat.stat-mech, cs.AI
arXiv: https://arxiv.org/abs/2602.13194v2

The entropy rate of printed English is famously estimated to be about one bit per character, a benchmark that modern large language models (LLMs) have only recently approached. This entropy rate implies that English contains nearly 80 percent redundancy relative to the five bits per character expected for random text. We introduce a statistical model that attempts to capture the intricate multi-scale structure of natural language, providing a first-principles account of this redundancy level. Our model describes a procedure of self-similarly segmenting text into semantically coherent chunks down to the single-word level. The semantic structure of the text can then be hierarchically decomposed, allowing for analytical treatment. Numerical experiments with modern LLMs and open datasets suggest that our model quantitatively captures the structure of real texts at different levels of the semantic hierarchy. The entropy rate predicted by our model agrees with the estimated entropy rate of printed English. Moreover, our theory further reveals that the entropy rate of natural language is not fixed but should increase systematically with the semantic complexity of corpora, which are captured by the only free parameter in our model.

---

### CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling

Authors: Sayan Deb Sarkar, Rémi Pautrat, Ondrej Miksik, Marc Pollefeys, Iro Armeni, Mahdi Rad, Mihai Dusmanu
Published: 2026-02-13
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13191v2

Video Language Models (VideoLMs) enable AI systems to understand temporal dynamics in videos. To fit within the maximum context window constraint, current methods use keyframe sampling which often misses both macro-level events and micro-level details due to the sparse temporal coverage. Furthermore, processing full images and their tokens for each frame incurs substantial computational overhead. We address these limitations by leveraging video codec primitives (specifically motion vectors and residuals) which natively encode video redundancy and sparsity without requiring expensive full-image encoding for most frames. To this end, we introduce lightweight transformer-based encoders that aggregate codec primitives and align their representations with image encoder embeddings through a pre-training strategy that accelerates convergence during end-to-end fine-tuning. Our approach, CoPE-VideoLM, reduces the time-to-first-token by up to 86% and token usage by up to 93% compared to standard VideoLMs. Moreover, by varying the keyframe and codec primitive densities we maintain or exceed performance on 14 diverse video understanding benchmarks spanning general question answering, temporal and motion reasoning, long-form understanding, and spatial scene understanding.

---

### FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control

Authors: Mingzhi Sheng, Zekai Gu, Peng Li, Cheng Lin, Hao-Xiang Guo, Ying-Cong Chen, Yuan Liu
Published: 2026-02-13
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2602.13185v2

Effective and generalizable control in video generation remains a significant challenge. While many methods rely on ambiguous or task-specific signals, we argue that a fundamental disentanglement of "appearance" and "motion" provides a more robust and scalable pathway. We propose FlexAM, a unified framework built upon a novel 3D control signal. This signal represents video dynamics as a point cloud, introducing three key enhancements: multi-frequency positional encoding to distinguish fine-grained motion, depth-aware encoding, and a flexible control signal for balancing precision and generalization. This representation allows FlexAM to effectively disentangle appearance and motion, enabling a wide range of tasks including I2V/V2V editing, camera control, and spatial object editing. Extensive experiments demonstrate that FlexAM achieves superior performance across all evaluated tasks.

---

### FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control

Authors: Mingzhi Sheng, Zekai Gu, Peng Li, Cheng Lin, Hao-Xiang Guo, Ying-Cong Chen, Yuan Liu
Published: 2026-02-13
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2602.13185v1

Effective and generalizable control in video generation remains a significant challenge. While many methods rely on ambiguous or task-specific signals, we argue that a fundamental disentanglement of "appearance" and "motion" provides a more robust and scalable pathway. We propose FlexAM, a unified framework built upon a novel 3D control signal. This signal represents video dynamics as a point cloud, introducing three key enhancements: multi-frequency positional encoding to distinguish fine-grained motion, depth-aware positional encoding, and a flexible control signal for balancing precision and generative quality. This representation allows FlexAM to effectively disentangle appearance and motion, enabling a wide range of tasks including I2V/V2V editing, camera control, and spatial object editing. Extensive experiments demonstrate that FlexAM achieves superior performance across all evaluated tasks.

---

### Profiling systematic uncertainties in Simulation-Based Inference with Factorizable Normalizing Flows

Authors: Davide Valsecchi, Mauro Donegà, Rainer Wallny
Published: 2026-02-13
Categories: hep-ph, physics.data-an, stat.ML
arXiv: https://arxiv.org/abs/2602.13184v2

Unbinned likelihood fits maximize the information extracted from experimental data, yet their application in realistic high-dimensional analyses has been fundamentally bottlenecked by the prohibitive computational cost of profiling systematic uncertainties. Furthermore, current machine learning-based inference methods typically estimate scalar parameters, discarding complex high-dimensional correlations. To address this, we propose a general Simulation-Based Inference (SBI) framework that elevates the fit target from scalar parameters to a multivariate Distribution of Interest (DoI), a learnable, invertible transformation of the feature space. We employ Factorizable Normalizing Flows to model systematic variations as parametric deformations, preserving tractability without combinatorial explosion. Crucially, we develop an amortized training strategy that learns the conditional dependence of the DoI on nuisance parameters in a single optimization process, bypassing repetitive training during likelihood scans. To capture the finite-sample statistical variance of the neural network DoI, we introduce a Poisson-bootstrap ensemble, which we marginalize through an averaged likelihood to deliver a complete statistical-plus-systematic uncertainty budget within a single unbinned likelihood. Validated on a synthetic dataset emulating a high-energy physics measurement, our method demonstrates that rigorous, fully profiled unbinned measurements can now be extended to complete differential distributions. By turning the fit into a functional measurement, this approach offers a powerful, unifying framework for a broad range of tasks conventionally treated as distinct problems, from detector calibration and differential cross-sections to unfolding and continuous parameter estimation.

---

### Selection of CMIP6 Models for Regional Precipitation Projection and Climate Change Assessment in the Jhelum and Chenab River Basins

Authors: Saad Ahmed Jamal, Ammara Nusrat, Muhammad Azmat, Muhammad Osama Nusrat
Published: 2026-02-13
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2602.13181v1

Effective water resource management depends on accurate projections of flows in water channels. For projected climate data, use of different General Circulation Models (GCM) simulates contrasting results. This study shows selection of GCM for the latest generation CMIP6 for hydroclimate change impact studies. Envelope based method was used for the selection, which includes components based on machine learning techniques, allowing the selection of GCMs without the need for in-situ reference data. According to our knowledge, for the first time, such a comparison was performed for the CMIP6 Shared Socioeconomic Pathway (SSP) scenarios data. In addition, the effect of climate change under SSP scenarios was studied, along with the calculation of extreme indices. Finally, GCMs were compared to quantify spatiotemporal differences between CMIP5 and CMIP6 data. Results provide NorESM2 LM, FGOALS g3 as selected models for the Jhelum and Chenab River. Highly vulnerable regions under the effect of climate change were highlighted through spatial maps, which included parts of Punjab, Jammu, and Kashmir. Upon comparison of CMIP5 and CMIP6, no discernible difference was found between the RCP and SSP scenarios precipitation projections. In the future, more detailed statistical comparisons could further reinforce the proposition.

---

### Block-Norm Geometries for Online Mirror Descent with Sparse Losses

Authors: Swati Gupta, Jai Moondra, Mohit Singh
Published: 2026-02-13
Categories: math.OC, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2602.13177v2

The performance of online mirror descent depends critically on the geometry induced by its mirror map, yet standard algorithms largely rely on two canonical choices: Euclidean and entropic geometry. We show that these two geometries can both be substantially suboptimal when loss gradients are sparse. We introduce a family of randomized block-norm mirror maps that interpolates between Euclidean and entropic geometries and adapts to intermediate sparsity structure. For several standard convex sets, including $\ell_p$ balls, ellipsoids, boxes, and Minkowski sums of norm balls, we prove polynomial-in-dimension improvements in regret bounds over the better of online projected gradient descent and exponentiated gradient. We further construct explicit online convex optimization instances for which these improvements are realized: on a simple polytope, an intermediate block geometry achieves a $\text{poly}(d)$ separation in regret from both Euclidean and entropic geometries in dimension $d$, while on the probability simplex we obtain a separation of order $Ω(\sqrt{\log d}/\log\log d)$. Finally, we study geometry selection when sparsity is unknown. We show that naively alternating between mirror maps can incur linear regret, even though either mirror map alone has sublinear regret, and give a Hedge meta-algorithm that competes with the best mirror map in a finite portfolio. For random block geometries, this yields regret within an $O(\sqrt{\log\log d})$ factor of the best random uniform block norm chosen in hindsight.

---

### Improved Regret Guarantees for Online Mirror Descent using a Portfolio of Mirror Maps

Authors: Swati Gupta, Jai Moondra, Mohit Singh
Published: 2026-02-13
Categories: math.OC, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2602.13177v1

OMD and its variants give a flexible framework for OCO where the performance depends crucially on the choice of the mirror map. While the geometries underlying OPGD and OEG, both special cases of OMD, are well understood, it remains a challenging open question on how to construct an optimal mirror map for any given constrained set and a general family of loss functions, e.g., sparse losses. Motivated by parameterizing a near-optimal set of mirror maps, we consider a simpler question: is it even possible to obtain polynomial gains in regret by using mirror maps for geometries that interpolate between $L_1$ and $L_2$, which may not be possible by restricting to only OEG ($L_1$) or OPGD ($L_2$). Our main result answers this question positively. We show that mirror maps based on block norms adapt better to the sparsity of loss functions, compared to previous $L_p$ (for $p \in (1, 2)$) interpolations. In particular, we construct a family of online convex optimization instances in $\mathbb{R}^d$, where block norm-based mirror maps achieve a provable polynomial (in $d$) improvement in regret over OEG and OPGD for sparse loss functions. We then turn to the setting in which the sparsity level of the loss functions is unknown. In this case, the choice of geometry itself becomes an online decision problem. We first show that naively switching between OEG and OPGD can incur linear regret, highlighting the intrinsic difficulty of geometry selection. To overcome this issue, we propose a meta-algorithm based on multiplicative weights that dynamically selects among a family of uniform block norms. We show that this approach effectively tunes OMD to the sparsity of the losses, yielding adaptive regret guarantees. Overall, our results demonstrate that online mirror-map selection can significantly enhance the ability of OMD to exploit sparsity in online convex optimization.

---

### Monocular Markerless Motion Capture Enables Quantitative Assessment of Upper Extremity Reachable Workspace

Authors: Seth Donahue, J. D. Peiffer, R. Tyler Richardson, Yishan Zhong, Shaun Q. Y. Tan, Benoit Marteau, Stephanie R. Russo, May D. Wang, R. James Cotton, Ross Chafetz
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.13176v1

To validate a clinically accessible approach for quantifying the Upper Extremity Reachable Workspace (UERW) using a single (monocular) camera and Artificial Intelligence (AI)-driven Markerless Motion Capture (MMC) for biomechanical analysis. Objective assessment and validation of these techniques for specific clinically oriented tasks are crucial for their adoption in clinical motion analysis. AI-driven monocular MMC reduces the barriers to adoption in the clinic and has the potential to reduce the overhead for analysis of this common clinical assessment. Nine adult participants with no impairments performed the standardized UERW task, which entails reaching targets distributed across a virtual sphere centered on the torso, with targets displayed in a VR headset. Movements were simultaneously captured using a marker-based motion capture system and a set of eight FLIR cameras. We performed monocular video analysis on two of these video camera views to compare a frontal and offset camera configurations. The frontal camera orientation demonstrated strong agreement with the marker-based reference, exhibiting a minimal mean bias of $0.61 \pm 0.12$ \% reachspace reached per octanct (mean $\pm$ standard deviation). In contrast, the offset camera view underestimated the percent workspace reached ($-5.66 \pm 0.45$ \% reachspace reached). Conclusion: The findings support the feasibility of a frontal monocular camera configuration for UERW assessment, particularly for anterior workspace evaluation where agreement with marker-based motion capture was highest. The overall performance demonstrates clinical potential for practical, single-camera assessments. This study provides the first validation of monocular MMC system for the assessment of the UERW task. By reducing technical complexity, this approach enables broader implementation of quantitative upper extremity mobility assessment.

---

### Learning functional components of PDEs from data using neural networks

Authors: Torkel E. Loman, Yurij Salmaniw, Antonio Leon Villares, Jose A. Carrillo, Ruth E. Baker
Published: 2026-02-13
Categories: cs.LG, math.AP
arXiv: https://arxiv.org/abs/2602.13174v2

Partial differential equation (PDE) models frequently contain unknown functional terms that cannot be measured directly, limiting their predictive utility. While data-driven methods for estimating scalar PDE parameters are well established, the recovery of unknown functions remains comparatively underexplored. Here, we show that standard parameter estimation workflows can be extended to infer functional components of PDEs directly from data. Our approach embeds neural networks within the PDE framework, allowing unknown functions to be learned during training with high accuracy. Using nonlocal aggregation-diffusion equations as a case study, we infer interaction kernels and external potentials from steady-state observations. We systematically examine how reconstruction accuracy depends on factors such as the number and diversity of available solutions, sampling density, and measurement noise. The resulting framework retains the advantages of conventional PDE calibration approaches while extending them to functional inference: once trained, the PDE model can be used in the standard way to analyse system behaviour and generate predictions.

---

### Learning functional components of PDEs from data using neural networks

Authors: Torkel E. Loman, Yurij Salmaniw, Antonio Leon Villares, Jose A. Carrillo, Ruth E. Baker
Published: 2026-02-13
Categories: cs.LG, math.AP
arXiv: https://arxiv.org/abs/2602.13174v1

Partial differential equations often contain unknown functions that are difficult or impossible to measure directly, hampering our ability to derive predictions from the model. Workflows for recovering scalar PDE parameters from data are well studied: here we show how similar workflows can be used to recover functions from data. Specifically, we embed neural networks into the PDE and show how, as they are trained on data, they can approximate unknown functions with arbitrary accuracy. Using nonlocal aggregation-diffusion equations as a case study, we recover interaction kernels and external potentials from steady state data. Specifically, we investigate how a wide range of factors, such as the number of available solutions, their properties, sampling density, and measurement noise, affect our ability to successfully recover functions. Our approach is advantageous because it can utilise standard parameter-fitting workflows, and in that the trained PDE can be treated as a normal PDE for purposes such as generating system predictions.

---

### LongStream: Long-Sequence Streaming Autoregressive Visual Geometry

Authors: Chong Cheng, Xianda Chen, Tao Xie, Wei Yin, Weiqiang Ren, Qian Zhang, Xiaoyang Guo, Hao Wang
Published: 2026-02-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.13172v2

Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift, and extrapolation errors. We introduce LongStream, a novel gauge-decoupled streaming visual geometry model for metric-scale scene reconstruction across thousands of frames under a strictly online, future-invisible setting. Our approach is threefold. First, we discard the first-frame anchor and predict keyframe-relative poses. This reformulates long-range extrapolation into a constant-difficulty local task. Second, we introduce orthogonal scale learning. This method fully disentangles geometry from scale estimation to suppress drift. Finally, we identify attention bias issues in Transformers, including attention-sink reliance and long-term KV-cache saturation. We propose cache-consistent training combined with periodic cache refresh. This approach suppresses attention biases and contamination over ultra-long sequences and reduces the gap between training and inference. Experiments show that LongStream achieves state-of-the-art performance, enabling stable, metric-scale reconstruction over kilometer-scale sequences at 18 FPS. Project Page: https://3dagentworld.github.io/longstream/

---

### Operator Learning for Families of Finite-State Mean-Field Games

Authors: William Hofgard, Asaf Cohen, Mathieu Laurière
Published: 2026-02-13
Categories: math.OC, stat.ML
arXiv: https://arxiv.org/abs/2602.13169v1

Finite-state mean-field games (MFGs) arise as limits of large interacting particle systems and are governed by an MFG system, a coupled forward-backward differential equation consisting of a forward Kolmogorov-Fokker-Planck (KFP) equation describing the population distribution and a backward Hamilton-Jacobi-Bellman (HJB) equation defining the value function. Solving MFG systems efficiently is challenging, with the structure of each system depending on an initial distribution of players and the terminal cost of the game. We propose an operator learning framework that solves parametric families of MFGs, enabling generalization without retraining for new initial distributions and terminal costs. We provide theoretical guarantees on the approximation error, parametric complexity, and generalization performance of our method, based on a novel regularity result for an appropriately defined flow map corresponding to an MFG system. We demonstrate empirically that our framework achieves accurate approximation for two representative instances of MFGs: a cybersecurity example and a high-dimensional quadratic model commonly used as a benchmark for numerical methods for MFGs.

---

### Realistic Face Reconstruction from Facial Embeddings via Diffusion Models

Authors: Dong Han, Yong Li, Joachim Denzler
Published: 2026-02-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.13168v1

With the advancement of face recognition (FR) systems, privacy-preserving face recognition (PPFR) systems have gained popularity for their accurate recognition, enhanced facial privacy protection, and robustness to various attacks. However, there are limited studies to further verify privacy risks by reconstructing realistic high-resolution face images from embeddings of these systems, especially for PPFR. In this work, we propose the face embedding mapping (FEM), a general framework that explores Kolmogorov-Arnold Network (KAN) for conducting the embedding-to-face attack by leveraging pre-trained Identity-Preserving diffusion model against state-of-the-art (SOTA) FR and PPFR systems. Based on extensive experiments, we verify that reconstructed faces can be used for accessing other real-word FR systems. Besides, the proposed method shows the robustness in reconstructing faces from the partial and protected face embeddings. Moreover, FEM can be utilized as a tool for evaluating safety of FR and PPFR systems in terms of privacy leakage. All images used in this work are from public datasets.

---

### Optimal Take-off under Fuzzy Clearances

Authors: Hugo Henry, Arthur Tsai, Kelly Cohen
Published: 2026-02-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.13166v1

This paper presents a hybrid obstacle avoidance architecture that integrates Optimal Control under clearance with a Fuzzy Rule Based System (FRBS) to enable adaptive constraint handling for unmanned aircraft. Motivated by the limitations of classical optimal control under uncertainty and the need for interpretable decision making in safety critical aviation systems, we design a three stage Takagi Sugeno Kang fuzzy layer that modulates constraint radii, urgency levels, and activation decisions based on regulatory separation minima and airworthiness guidelines from FAA and EASA. These fuzzy-derived clearances are then incorporated as soft constraints into an optimal control problem solved using the FALCON toolbox and IPOPT. The framework aims to reduce unnecessary recomputations by selectively activating obstacle avoidance updates while maintaining compliance with aviation procedures. A proof of concept implementation using a simplified aircraft model demonstrates that the approach can generate optimal trajectories with computation times of 2,3 seconds per iteration in a single threaded MATLAB environment, suggesting feasibility for near real time applications. However, our experiments revealed a critical software incompatibility in the latest versions of FALCON and IPOPT, in which the Lagrangian penalty term remained identically zero, preventing proper constraint enforcement. This behavior was consistent across scenarios and indicates a solver toolbox regression rather than a modeling flaw. Future work includes validating this effect by reverting to earlier software versions, optimizing the fuzzy membership functions using evolutionary methods, and extending the system to higher fidelity aircraft models and stochastic obstacle environments.

---

### Asynchronous Verified Semantic Caching for Tiered LLM Architectures

Authors: Asmit Kumar Singh, Haozhe Wang, Laxmi Naga Santosh Attaluri, Tak Chiam, Weihua Zhu
Published: 2026-02-13
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.13165v2

Large language models (LLMs) now sit in the critical path of search, assistance, and agentic workflows, making semantic caching essential for reducing inference cost and latency. Production deployments typically use a tiered static-dynamic design: a static cache of curated, offline vetted responses mined from logs, backed by a dynamic cache populated online. In practice, both tiers are commonly governed by a single embedding similarity threshold, which induces a hard tradeoff: conservative thresholds miss safe reuse opportunities, while aggressive thresholds risk serving semantically incorrect responses. We introduce Krites, an asynchronous, LLM-judged caching policy that expands static coverage without changing serving decisions. On the critical path, Krites behaves exactly like a standard static threshold policy. When the nearest static neighbor of the prompt falls just below the static threshold, Krites asynchronously invokes an LLM judge to verify whether the static response is acceptable for the new prompt. Approved matches are promoted into the dynamic cache, allowing future repeats and paraphrases to reuse curated static answers and expanding static reach over time. In trace-driven simulations on conversational and search workloads, Krites increases the fraction of requests served with curated static answers (direct static hits plus verified promotions) by up to3.9 times for conversational traffic and search-style queries relative to tuned baselines, with unchanged critical path latency.

---

### In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach

Authors: Yiran Gao, Kim Hammar, Tao Li
Published: 2026-02-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.13156v2

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies through extensive simulation of the incident. While this approach can be effective, it requires handcrafted modeling of the simulator and suppresses useful semantics from raw system logs and alerts. To address these limitations, we propose to leverage large language models' (LLM) pre-trained security knowledge and in-context learning to create an end-to-end agentic solution for incident response planning. Specifically, our agent integrates four functionalities, perception, reasoning, planning, and action, into one lightweight LLM (14b model). Through fine-tuning and chain-of-thought reasoning, our LLM agent is capable of processing system logs and inferring the underlying network state (perception), updating its conjecture of attack models (reasoning), simulating consequences under different response strategies (planning), and generating an effective response (action). By comparing LLM-simulated outcomes with actual observations, the LLM agent repeatedly refines its attack conjecture and corresponding response, thereby demonstrating in-context adaptation. Our agentic approach is free of modeling and can run on commodity hardware. When evaluated on incident logs reported in the literature, our agent achieves recovery up to 23% faster than those of frontier LLMs.

---

### Learning to Approximate Uniform Facility Location via Graph Neural Networks

Authors: Chendi Qian, Christopher Morris, Stefanie Jegelka, Christian Sohler
Published: 2026-02-13
Categories: cs.LG, cs.DS, cs.NE, stat.ML
arXiv: https://arxiv.org/abs/2602.13155v3

Neural networks, particularly message-passing neural networks (MPNNs), are increasingly used as heuristics for hard combinatorial optimization problems. Yet many learning-based methods rely on supervision, reinforcement learning, or gradient estimators, causing high computational cost, unstable training, or limited guarantees. Classical approximation algorithms provide worst-case guarantees but are non-differentiable and cannot adapt to structure in natural input distributions. We study this tradeoff through Uniform Facility Location (UniFL), a problem with applications in clustering, summarization, logistics, and supply chains. We propose a fully differentiable MPNN that incorporates approximation-algorithmic principles without solver supervision or discrete relaxations. The model has provable approximation guarantees and empirically improves on standard approximation algorithms, narrowing the gap to integer linear programming.

---

### Learning to Approximate Uniform Facility Location via Graph Neural Networks

Authors: Chendi Qian, Christopher Morris, Stefanie Jegelka, Christian Sohler
Published: 2026-02-13
Categories: cs.LG, cs.DS, cs.NE, stat.ML
arXiv: https://arxiv.org/abs/2602.13155v2

Neural networks, particularly message-passing neural networks (MPNNs), are increasingly used as heuristics for hard combinatorial optimization problems. Yet many learning-based methods rely on supervision, reinforcement learning, or gradient estimators, causing high computational cost, unstable training, or limited guarantees. Classical approximation algorithms provide worst-case guarantees but are non-differentiable and cannot adapt to structure in natural input distributions. We study this tradeoff through Uniform Facility Location (UniFL), a problem with applications in clustering, summarization, logistics, and supply chains. We propose a fully differentiable MPNN that incorporates approximation-algorithmic principles without solver supervision or discrete relaxations. The model has provable approximation guarantees and empirically improves on standard approximation algorithms, narrowing the gap to integer linear programming.

---

### Quantization-Robust LLM Unlearning via Low-Rank Adaptation

Authors: João Vitor Boer Abitante, Joana Meneguzzo Pasquali, Luan Fonseca Garcia, Ewerton de Oliveira, Thomas da Silva Paula, Rodrigo C. Barros, Lucas S. Kupssinskü
Published: 2026-02-13
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.13151v3

Large Language Model (LLM) unlearning aims to remove targeted knowledge from a trained model, but practical deployments often require post-training quantization (PTQ) for efficient inference. However, aggressive low-bit PTQ can mask unlearning updates, causing quantized models to revert to pre-unlearning behavior. We show that standard full-parameter fine-tuning often induces parameter changes that are too small to survive 4-bit quantization. We propose quantization-robust unlearning via low-rank adaptation (LoRA): we freeze the base model and concentrate unlearning into trainable adapters so that the effective update is preserved after quantization. On Llama-2-7B evaluated with MUSE dataset (BOOKS and NEWS), LoRA improves 4-bit utility by up to 7.93 points (NPO+GDR on BOOKS: 50.17 to 58.10) and yields higher 4-bit utility on NEWS for GA+GDR (40.06 to 44.82, increase of 4.76). LoRA also substantially reduces privacy leakage under 4-bit PTQ, e.g., for GA+KLR on BOOKS, PrivLeak moves from -25.68 to -5.86 (closer to ideal 0), while maintaining strong forgetting (VerMem and KnowMem near 0). Thus, using LoRA for Machine Unlearning is beneficial for scenarios where quantization is necessary for model deployment.

---

### FlashSchNet: Fast and Accurate Coarse-Grained Neural Network Molecular Dynamics

Authors: Pingzhi Li, Hongxuan Li, Zirui Liu, Xingcheng Lin, Tianlong Chen
Published: 2026-02-13
Categories: cs.LG, cs.CE
arXiv: https://arxiv.org/abs/2602.13140v1

Graph neural network (GNN) potentials such as SchNet improve the accuracy and transferability of molecular dynamics (MD) simulation by learning many-body interactions, but remain slower than classical force fields due to fragmented kernels and memory-bound pipelines that underutilize GPUs. We show that a missing principle is making GNN-MD IO-aware, carefully accounting for reads and writes between GPU high-bandwidth memory (HBM) and on-chip SRAM. We present FlashSchNet, an efficient and accurate IO-aware SchNet-style GNN-MD framework built on four techniques: (1) flash radial basis, which fuses pairwise distance computation, Gaussian basis expansion, and cosine envelope into a single tiled pass, computing each distance once and reusing it across all basis functions; (2) flash message passing, which fuses cutoff, neighbor gather, filter multiplication, and reduction to avoid materializing edge tensors in HBM; (3) flash aggregation, which reformulates scatter-add via CSR segment reduce, reducing atomic writes by a factor of feature dimension and enabling contention-free accumulation in both forward and backward passes; (4) channel-wise 16-bit quantization that exploits the low per-channel dynamic range in SchNet MLP weights to further improve throughput with negligible accuracy loss. On a single NVIDIA RTX PRO 6000, FlashSchNet achieves 1000 ns/day aggregate simulation throughput over 64 parallel replicas on coarse-grained (CG) protein containing 269 beads (6.5x faster than CGSchNet baseline with 80% reduction of peak memory), surpassing classical force fields (e.g. MARTINI) while retaining SchNet-level accuracy and transferability.

---

### OpenLID-v3: Improving the Precision of Closely Related Language Identification -- An Experience Report

Authors: Mariia Fedorova, Nikolay Arefyev, Maja Buljan, Jindřich Helcl, Stephan Oepen, Egil Rønningstad, Yves Scherrer
Published: 2026-02-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.13139v4

Language identification (LID) is an essential step in building high-quality multilingual datasets from web data. Existing LID tools (such as OpenLID or GlotLID) often struggle to identify closely related languages and to distinguish valid natural language from noise, which contaminates language-specific subsets, especially for low-resource languages. In this work we extend the OpenLID classifier by adding more training data, merging problematic language variant clusters, and introducing a special label for marking noise. We call this extended system OpenLID-v3 and evaluate it against GlotLID on multiple benchmarks. During development, we focus on three groups of closely related languages (Bosnian, Croatian, and Serbian; Romance varieties of Northern Italy and Southern France; and Scandinavian languages) and contribute new evaluation datasets where existing ones are inadequate. We find that ensemble approaches improve precision but also substantially reduce coverage for low-resource languages. OpenLID-v3 is available on https://huggingface.co/HPLT/OpenLID-v3.

---

### Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching

Authors: Chenguang Wang, Zihan Zhou, Lei Bai, Tianshu Yu
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.13136v2

Template-free retrosynthesis methods treat the task as black-box sequence generation, limiting learning efficiency, while semi-template approaches rely on rigid reaction libraries that constrain generalization. We address this gap with a key insight: atom ordering in neural representations matters. Building on this insight, we propose a structure-aware template-free framework that encodes the two-stage nature of chemical reactions as a positional inductive bias. By placing reaction center atoms at the sequence head, our method transforms implicit chemical knowledge into explicit positional patterns that the model can readily capture. The proposed RetroDiT backbone, a graph transformer with rotary position embeddings, exploits this ordering to prioritize chemically critical regions. Combined with discrete flow matching, our approach decouples training from sampling and enables generation in 20--50 steps versus 500 for prior diffusion methods. Our method achieves state-of-the-art performance on both USPTO-50k (61.2% top-1) and the large-scale USPTO-Full (51.3% top-1) with predicted reaction centers. With oracle centers, performance reaches 71.1% and 63.4% respectively, surpassing foundation models trained on 10 billion reactions while using orders of magnitude less data. Ablation studies further reveal that structural priors outperform brute-force scaling: a 280K-parameter model with proper ordering matches a 65M-parameter model without it.

---

### Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching

Authors: Chenguang Wang, Zihan Zhou, Lei Bai, Tianshu Yu
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.13136v1

Template-free retrosynthesis methods treat the task as black-box sequence generation, limiting learning efficiency, while semi-template approaches rely on rigid reaction libraries that constrain generalization. We address this gap with a key insight: atom ordering in neural representations matters. Building on this insight, we propose a structure-aware template-free framework that encodes the two-stage nature of chemical reactions as a positional inductive bias. By placing reaction center atoms at the sequence head, our method transforms implicit chemical knowledge into explicit positional patterns that the model can readily capture. The proposed RetroDiT backbone, a graph transformer with rotary position embeddings, exploits this ordering to prioritize chemically critical regions. Combined with discrete flow matching, our approach decouples training from sampling and enables generation in 20--50 steps versus 500 for prior diffusion methods. Our method achieves state-of-the-art performance on both USPTO-50k (61.2% top-1) and the large-scale USPTO-Full (51.3% top-1) with predicted reaction centers. With oracle centers, performance reaches 71.1% and 63.4% respectively, surpassing foundation models trained on 10 billion reactions while using orders of magnitude less data. Ablation studies further reveal that structural priors outperform brute-force scaling: a 280K-parameter model with proper ordering matches a 65M-parameter model without it.

---

### Constrained Assumption-Based Argumentation Frameworks

Authors: Emanuele De Angelis, Fabio Fioravanti, Maria Chiara Meo, Alberto Pettorossi, Maurizio Proietti, Francesca Toni
Published: 2026-02-13
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2602.13135v2

Assumption-based Argumentation (ABA) is a well-established form of structured argumentation. ABA frameworks with an underlying atomic language are widely studied, but their applicability is limited by a representational restriction to ground (variable-free) arguments and attacks built from propositional atoms. In this paper, we lift this restriction and propose a novel notion of constrained ABA (CABA), whose components, as well as arguments built from them, may include constrained variables, ranging over possibly infinite domains. We define non-ground semantics for CABA, in terms of various notions of non-ground attacks. We show that the new semantics conservatively generalise standard ABA semantics.

---

### Eventizing Traditionally Opaque Binary Neural Networks as 1-safe Petri net Models

Authors: Mohamed Tarraf, Alex Chan, Alex Yakovlev, Rishad Shafik
Published: 2026-02-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.13128v1

Binary Neural Networks (BNNs) offer a low-complexity and energy-efficient alternative to traditional full-precision neural networks by constraining their weights and activations to binary values. However, their discrete, highly non-linear behavior makes them difficult to explain, validate and formally verify. As a result, BNNs remain largely opaque, limiting their suitability in safety-critical domains, where causal transparency and behavioral guarantees are essential. In this work, we introduce a Petri net (PN)-based framework that captures the BNN's internal operations as event-driven processes. By "eventizing" their operations, we expose their causal relationships and dependencies for a fine-grained analysis of concurrency, ordering, and state evolution. Here, we construct modular PN blueprints for core BNN components including activation, gradient computation and weight updates, and compose them into a complete system-level model. We then validate the composed PN against a reference software-based BNN, verify it against reachability and structural checks to establish 1-safeness, deadlock-freeness, mutual exclusion and correct-by-construction causal sequencing, before we assess its scalability and complexity at segment, component, and system levels using the automated measurement tools in Workcraft. Overall, this framework enables causal introspection of transparent and event-driven BNNs that are amenable to formal reasoning and verification.

---

### From sunblock to softblock: Analyzing the correlates of neology in published writing and on social media

Authors: Maria Ryskina, Matthew R. Gormley, Kyle Mahowald, David R. Mortensen, Taylor Berg-Kirkpatrick, Vivek Kulkarni
Published: 2026-02-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.13123v1

Living languages are shaped by a host of conflicting internal and external evolutionary pressures. While some of these pressures are universal across languages and cultures, others differ depending on the social and conversational context: language use in newspapers is subject to very different constraints than language use on social media. Prior distributional semantic work on English word emergence (neology) identified two factors correlated with creation of new words by analyzing a corpus consisting primarily of historical published texts (Ryskina et al., 2020, arXiv:2001.07740). Extending this methodology to contextual embeddings in addition to static ones and applying it to a new corpus of Twitter posts, we show that the same findings hold for both domains, though the topic popularity growth factor may contribute less to neology on Twitter than in published writing. We hypothesize that this difference can be explained by the two domains favouring different neologism formation mechanisms.

---

### AdaGrad-Diff: A New Version of the Adaptive Gradient Algorithm

Authors: Matia Bojovic, Saverio Salzo, Massimiliano Pontil
Published: 2026-02-13
Categories: stat.ML, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2602.13112v1

Vanilla gradient methods are often highly sensitive to the choice of stepsize, which typically requires manual tuning. Adaptive methods alleviate this issue and have therefore become widely used. Among them, AdaGrad has been particularly influential. In this paper, we propose an AdaGrad-style adaptive method in which the adaptation is driven by the cumulative squared norms of successive gradient differences rather than gradient norms themselves. The key idea is that when gradients vary little across iterations, the stepsize is not unnecessarily reduced, while significant gradient fluctuations, reflecting curvature or instability, lead to automatic stepsize damping. Numerical experiments demonstrate that the proposed method is more robust than AdaGrad in several practically relevant settings.

---

### SCOPE: Selective Conformal Optimized Pairwise LLM Judging

Authors: Sher Badshah, Ali Emami, Hassan Sajjad
Published: 2026-02-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.13110v4

Large language models (LLMs) are increasingly used as scalable judges in pairwise evaluation, but they remain prone to miscalibration and biases. We propose \textsc{Scope} (Selective Conformal Optimized Pairwise Evaluation), a framework that calibrates an acceptance threshold so that, under exchangeability, the error rate among non-abstained judgments is at most a user-specified level $α$. To supply \textsc{Scope} with a bias-neutral uncertainty signal, we introduce Bidirectional Preference Entropy (BPE), which queries the judge under both response positions and converts the order-averaged preference probability into an entropy-based score. Across various pairwise judging benchmarks, BPE outperforms standard confidence proxies in calibration and discrimination, while \textsc{Scope} consistently satisfies the target risk bound (empirical FDR $\approx 0.097$--$0.099$ at $α=0.10$) and retains substantial coverage. Compared to vanilla baselines, \textsc{Scope} accepts up to $2.4\times$ more judgments under the same risk constraint, demonstrating that BPE enables reliable and high-coverage LLM-based evaluation.

---

### SCOPE: Selective Conformal Optimized Pairwise LLM Judging

Authors: Sher Badshah, Ali Emami, Hassan Sajjad
Published: 2026-02-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.13110v3

Large language models (LLMs) are increasingly used as scalable judges in pairwise evaluation, but they remain prone to miscalibration and biases. We propose SCOPE (Selective Conformal Optimized Pairwise Evaluation), a framework that calibrates an acceptance threshold so that, under exchangeability, the error rate among non-abstained judgments is at most a user-specified level $α$. To supply SCOPE with a bias-neutral uncertainty signal, we introduce Bidirectional Preference Entropy (BPE), which queries the judge under both response positions and converts the order-averaged preference probability into an entropy-based score. Across various pairwise judging benchmarks, BPE outperforms standard confidence proxies in calibration and discrimination, while SCOPE consistently satisfies the target risk bound (empirical FDR $\approx 0.097$ to $0.099$ at $α= 0.10$) and retains substantial coverage. Compared to vanilla baselines, SCOPE accepts up to $2.4\times$ more judgments under the same risk constraint, demonstrating that BPE enables reliable and high-coverage LLM-based evaluation.

---

### Which Algorithms Can Graph Neural Networks Learn?

Authors: Solveig Wittig, Antonis Vasileiou, Robert R. Nerem, Timo Stoll, Floris Geerts, Yusu Wang, Christopher Morris
Published: 2026-02-13
Categories: cs.LG, cs.AI, cs.DS, cs.NE
arXiv: https://arxiv.org/abs/2602.13106v2

In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a line of work often referred to as neural algorithmic reasoning. The goal is to integrate algorithmic reasoning capabilities into larger neural pipelines. Many such architectures are based on (message-passing) graph neural networks (MPNNs), owing to their permutation equivariance and ability to deal with sparsity and variable-sized inputs. However, existing work is either largely empirical and lacks formal guarantees or it focuses solely on expressivity, leaving open the question of when and how such architectures generalize beyond a finite training set. In this work, we propose a general theoretical framework that characterizes the sufficient conditions under which MPNNs can learn an algorithm from a training set of small instances and provably approximate its behavior on inputs of arbitrary size. Our framework applies to a broad class of algorithms, including single-source shortest paths, minimum spanning trees, and general dynamic programming problems, such as the $0$-$1$ knapsack problem. In addition, we establish impossibility results for a wide range of algorithmic tasks, showing that standard MPNNs cannot learn them, and we derive more expressive MPNN-like architectures that overcome these limitations. Finally, we refine our analysis for the Bellman-Ford algorithm, yielding a substantially smaller required training set and significantly extending the recent work of Nerem et al. (2025) by allowing for a differentiable regularization loss. Empirical results largely support our theoretical findings.

---