# Research Papers — 2026-02 · bundle page 189 of 210

> Full-text markdown of papers #9401–9450 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/189
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/188.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/190.md)

### Thinking inside the Convolution for Image Inpainting: Reconstructing Texture via Structure under Global and Local Side

Authors: Haipeng Liu, Yang Wang, Biao Qian, Yong Rui, Meng Wang
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.03013v1

Image inpainting has earned substantial progress, owing to the encoder-and-decoder pipeline, which is benefited from the Convolutional Neural Networks (CNNs) with convolutional downsampling to inpaint the masked regions semantically from the known regions within the encoder, coupled with an upsampling process from the decoder for final inpainting output. Recent studies intuitively identify the high-frequency structure and low-frequency texture to be extracted by CNNs from the encoder, and subsequently for a desirable upsampling recovery. However, the existing arts inevitably overlook the information loss for both structure and texture feature maps during the convolutional downsampling process, hence suffer from a non-ideal upsampling output. In this paper, we systematically answer whether and how the structure and texture feature map can mutually help to alleviate the information loss during the convolutional downsampling. Given the structure and texture feature maps, we adopt the statistical normalization and denormalization strategy for the reconstruction guidance during the convolutional downsampling process. The extensive experimental results validate its advantages to the state-of-the-arts over the images from low-to-high resolutions including 256*256 and 512*512, especially holds by substituting all the encoders by ours. Our code is available at https://github.com/htyjers/ConvInpaint-TSGL

---

### CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability

Authors: Xianzhen Luo, Jingyuan Zhang, Shiqi Zhou, Jinyang Huang, Chuan Xiao, Qingfu Zhu, Zhiyuan Ma, Xing Yue, Yang Yue, Wencong Zeng, Wanxiang Che
Published: 2026-02-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.03012v3

Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To address these, we present CVE-Factory, the first multi-agent framework to achieve expert-level quality in automatically transforming sparse CVE metadata into fully executable agentic tasks. Cross-validation against human expert reproductions shows that CVE-Factory achieves 95\% solution correctness and 96\% environment fidelity, confirming its expert-level quality. It is also evaluated on the latest realistic vulnerabilities and achieves a 66.2\% verified success. This automation enables two downstream contributions. First, we construct LiveCVEBench, a continuously updated benchmark of 190 tasks spanning 14 languages and 153 repositories that captures emerging threats including AI-tooling vulnerabilities. Second, we synthesize over 1,000 executable training environments, the first large-scale scaling of agentic tasks in code security. Fine-tuned Qwen3-32B improves from 5.3\% to 35.8\% on LiveCVEBench, surpassing Claude 4.5 Sonnet, with gains generalizing to Terminal Bench (12.5\% to 31.3\%). We open-source CVE-Factory, LiveCVEBench, Abacus-cve (fine-tuned model), training dataset, and leaderboard. All resources are available at https://github.com/livecvebench/CVE-Factory .

---

### VOILA: Value-of-Information Guided Fidelity Selection for Cost-Aware Multimodal Question Answering

Authors: Rahul Atul Bhope, K. R. Jayaram, Vinod Muthusamy, Ritesh Kumar, Vatche Isahagian, Nalini Venkatasubramanian
Published: 2026-02-03
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03007v1

Despite significant costs from retrieving and processing high-fidelity visual inputs, most multimodal vision-language systems operate at fixed fidelity levels. We introduce VOILA, a framework for Value-Of-Information-driven adaptive fidelity selection in Visual Question Answering (VQA) that optimizes what information to retrieve before model execution. Given a query, VOILA uses a two-stage pipeline: a gradient-boosted regressor estimates correctness likelihood at each fidelity from question features alone, then an isotonic calibrator refines these probabilities for reliable decision-making. The system selects the minimum-cost fidelity maximizing expected utility given predicted accuracy and retrieval costs. We evaluate VOILA across three deployment scenarios using five datasets (VQA-v2, GQA, TextVQA, LoCoMo, FloodNet) and six Vision-Language Models (VLMs) with 7B-235B parameters. VOILA consistently achieves 50-60% cost reductions while retaining 90-95% of full-resolution accuracy across diverse query types and model architectures, demonstrating that pre-retrieval fidelity selection is vital to optimize multimodal inference under resource constraints.

---

### Distilling LLM Reasoning into Graph of Concept Predictors

Authors: Ziyang Yu, Liang Zhao
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.03006v2

Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, compute, and API costs at scale. Active distillation reduces these costs by querying an LLM oracle to train compact discriminative students, but most pipelines distill only final labels, discarding intermediate reasoning signals and offering limited diagnostics of what reasoning is missing and where errors arise. We propose Graph of Concept Predictors (GCP), a reasoning-aware active distillation framework that externalizes the teacher's decision process as a directed acyclic graph and mirrors it with modular concept predictors in the student. GCP enhances sample efficiency through a graph-aware acquisition strategy that targets uncertainty and disagreement at critical reasoning nodes. Additionally, it improves training stability and efficiency by performing targeted sub-module retraining, which attributes downstream loss to specific concept predictors and updates only the most influential modules. Experiments on eight NLP classification benchmarks demonstrate that GCP enhances performance under limited annotation budgets while yielding more interpretable and controllable training dynamics. Code is available at: https://github.com/Ziyang-Yu/GCP.

---

### Graph Autoencoder for Process Monitoring

Authors: Xiangrui Zhang
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.03004v2

To improve the reliability and interpretability of industrial process monitoring, this article proposes a Causal Graph Spatial-Temporal Autoencoder (CGSTAE). The network architecture of CGSTAE combines two components: a correlation graph structure learning module based on spatial self-attention mechanism (SSAM) and a spatial-temporal encoder-decoder module utilizing graph convolutional long-short term memory (GCLSTM). The SSAM learns correlation graphs by capturing dynamic relationships between variables, while a novel three-step causal graph structure learning algorithm is introduced to derive a causal graph from these correlation graphs. The algorithm leverages a reverse perspective of causal invariance principle to uncover the invariant causal graph from varying correlations. The spatial-temporal encoder-decoder, built with GCLSTM units, reconstructs time-series process data within a sequence-to-sequence framework. The proposed CGSTAE enables effective process monitoring and fault detection through two statistics in the feature space and residual space. Finally, we validate the effectiveness of CGSTAE in process monitoring through the Tennessee Eastman process and a real-world air separation process.

---

### Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment

Authors: Zhiyu An, Wan Du
Published: 2026-02-03
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.03003v3

Social choice has become a foundational component of modern machine learning systems. From auctions and resource allocation to the alignment of large generative models, machine learning pipelines increasingly aggregate heterogeneous preferences and incentives into collective decisions. In effect, many contemporary machine learning systems already implement social choice mechanisms, often implicitly and without explicit normative scrutiny. This Review surveys differentiable social choice: an emerging paradigm that formulates voting rules, mechanisms, and aggregation procedures as learnable, differentiable models optimized from data. We synthesize work across auctions, decision aggregation, and preference learning, showing how classical axioms and impossibility results reappear as objectives, constraints, and optimization trade-offs. We conclude by identifying 18 open problems defining a new research agenda at the intersection of machine learning and social choice theory.

---

### Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent

Authors: Hiroki Naganuma, Shagun Gupta, Youssef Briki, Ioannis Mitliagkas, Irina Rish, Parameswaran Raman, Hao-Jun Michael Shi
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.03001v2

To maximize hardware utilization, modern machine learning systems typically employ large constant or manually tuned batch size schedules, relying on heuristics that are brittle and costly to tune. Existing adaptive strategies based on gradient noise scale (GNS) offer a principled alternative. However, their assumption of SGD's Euclidean geometry creates a fundamental mismatch with popular optimizers based on generalized norms, such as signSGD / Signum ($\ell_\infty$) and stochastic spectral descent (specSGD) / Muon ($\mathcal{S}_\infty$). In this work, we derive gradient noise scales for signSGD and specSGD that naturally emerge from the geometry of their respective dual norms. To practically estimate these non-Euclidean metrics, we propose an efficient variance estimation procedure that leverages the local mini-batch gradients on different ranks in distributed data-parallel systems. Our experiments demonstrate that adaptive batch size strategies using non-Euclidean GNS enable us to match the validation loss of constant-batch baselines while reducing training steps by up to 66\% for Signum and Muon on a 160 million parameter Llama model.

---

### Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents

Authors: Sizhe Tang, Rongqian Chen, Tian Lan
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02995v1

While scaling test-time compute through trajectory-level sampling has significantly improved Graphical User Interface (GUI) agents, the lack of regressive ability prevents the reuse of partial successes and the recovery from early missteps. In this paper, we introduce Agent Alpha, a unified framework that synergizes generation, exploration, and evaluation through step-level Monte Carlo Tree Search (MCTS). It enables active modeling or exploiting structures of the planning space. By integrating alpha-UCT guided search into the interaction loop, Agent Alpha enables deliberate planning, facilitating early pruning of suboptimal branches and efficient prefix reuse. We also employ comparison-driven evaluation to mitigate absolute scoring biases and diversity-constrained expansion to maintain a compact, informative search space. Regret bound of alpha-UCT is analyzed. On the OSWorld benchmark, Agent Alpha achieves a state-of-the-art success rate of $\sim 77\%$, significantly outperforming trajectory-level baselines under equivalent compute.

---

### Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation

Authors: Jiaze Li, Hao Yin, Haoran Xu, Boshen Xu, Wenhui Tan, Zewen He, Jianzhong Ju, Zhenbo Luo, Jian Luan
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02994v3

Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and substantial computational overhead. We propose Video-OPD, an efficient post-training framework for TVG inspired by recent advances in on-policy distillation. Video-OPD optimizes trajectories sampled directly from the current policy, thereby preserving alignment between training and inference distributions, while a frontier teacher supplies dense, token-level supervision via a reverse KL divergence objective. This formulation preserves the on-policy property critical for mitigating distributional shift, while converting sparse, episode-level feedback into fine-grained, step-wise learning signals. Building on Video-OPD, we introduce Teacher-Validated Disagreement Focusing (TVDF), a lightweight training curriculum that iteratively prioritizes trajectories that are both teacher-reliable and maximally informative for the student, thereby improving training efficiency. Empirical results demonstrate that Video-OPD consistently outperforms GRPO while achieving substantially faster convergence and lower computational cost, establishing on-policy distillation as an effective alternative to conventional reinforcement learning for TVG.

---

### Large Language Models Can Take False First Steps at Inference-time Planning

Authors: Haijiang Yan, Jian-Qiao Zhu, Adam Sanborn
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02991v1

Large language models (LLMs) have been shown to acquire sequence-level planning abilities during training, yet their planning behavior exhibited at inference time often appears short-sighted and inconsistent with these capabilities. We propose a Bayesian account for this gap by grounding planning behavior in the evolving generative context: given the subtle differences between natural language and the language internalized by LLMs, accumulated self-generated context drives a planning-shift during inference and thereby creates the appearance of compromised planning behavior. We further validate the proposed model through two controlled experiments: a random-generation task demonstrating constrained planning under human prompts and increasing planning strength as self-generated context accumulates, and a Gaussian-sampling task showing reduced initial bias when conditioning on self-generated sequences. These findings provide a theoretical explanation along with empirical evidence for characterizing how LLMs plan ahead during inference.

---

### Learning to Repair Lean Proofs from Compiler Feedback

Authors: Evan Wang, Simon Chess, Daniel Lee, Siyuan Ge, Ajit Mallavarapu, Jarod Alper, Vasily Ilin
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02990v2

As neural theorem provers become increasingly agentic, the ability to interpret and act on compiler feedback is critical. However, existing Lean datasets consist almost exclusively of correct proofs, offering little supervision for understanding and repairing failures. We study Lean proof repair as a supervised learning problem: given an erroneous proof and compiler feedback, predict both a corrected proof and a natural-language diagnosis grounded in the same feedback. We introduce APRIL (Automated Proof Repair in Lean), a dataset of 260,000 supervised tuples pairing systematically generated proof failures with compiler diagnostics and aligned repair and explanation targets. Training language models on APRIL substantially improves repair accuracy and feedback-conditioned reasoning; in our single-shot repair evaluation setting, a finetuned 4B-parameter model outperforms the strongest open-source baseline. We view diagnostic-conditioned supervision as a complementary training signal for feedback-using provers. Our dataset is available at https://huggingface.co/datasets/uw-math-ai/APRIL.

---

### SharpTimeGS: Sharp and Stable Dynamic Gaussian Splatting via Lifespan Modulation

Authors: Zhanfeng Liao, Jiajun Zhang, Hanzhang Tu, Zhixi Wang, Yunqi Gao, Hongwen Zhang, Yebin Liu
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02989v2

Novel view synthesis of dynamic scenes is fundamental to achieving photorealistic 4D reconstruction and immersive visual experiences. Recent progress in Gaussian-based representations has significantly improved real-time rendering quality, yet existing methods still struggle to maintain a balance between long-term static and short-term dynamic regions in both representation and optimization. To address this, we present SharpTimeGS, a lifespan-aware 4D Gaussian framework that achieves temporally adaptive modeling of both static and dynamic regions under a unified representation. Specifically, we introduce a learnable lifespan parameter that reformulates temporal visibility from a Gaussian-shaped decay into a flat-top profile, allowing primitives to remain consistently active over their intended duration and avoiding redundant densification. In addition, the learned lifespan modulates each primitives' motion, reducing drift in long-lived static points while retaining unrestricted motion for short-lived dynamic ones. This effectively decouples motion magnitude from temporal duration, improving long-term stability without compromising dynamic fidelity. Moreover, we design a lifespan-velocity-aware densification strategy that mitigates optimization imbalance between static and dynamic regions by allocating more capacity to regions with pronounced motion while keeping static areas compact and stable. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art performance while supporting real-time rendering up to 4K resolution at 100 FPS on one RTX 4090.

---

### NLI:Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference

Authors: Jiangyong Yu, Xiaomeng Han, Xing Hu, Chen Xu, Zhe Jiang, Dawei Yang
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02988v1

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks, but their deployment is often constrained by substantial memory footprints and computational costs. While prior work has achieved significant progress in compressing and accelerating linear layers, nonlinear layers-such as SiLU, RMSNorm, and Softmax-still heavily depend on high-precision floating-point operations. In this paper, we propose a calibration-free, dynamic-programming-optimal, and hardware-friendly framework called Non-uniform Linear Interpolation (NLI). NLI is capable of efficiently approximating a variety of nonlinear functions, enabling seamless integration into LLMs and other deep neural networks with almost no loss in accuracy. NLI ingeniously recasts cutpoint selection as a dynamic-programming problem, achieving the globally minimal interpolation error in O(MxN2) time via Bellman's optimality principle. Based on the NLI algorithm, we also design and implement a plug-and-play universal nonlinear computation unit. Hardware experiments demonstrate that the NLI Engine achieves more than 4x improvement in computational efficiency compared to the state-of-the-art designs.

---

### Why Some Models Resist Unlearning: A Linear Stability Perspective

Authors: Wei-Kai Chang, Rajiv Khanna
Published: 2026-02-03
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.02986v1

Machine unlearning, the ability to erase the effect of specific training samples without retraining from scratch, is critical for privacy, regulation, and efficiency. However, most progress in unlearning has been empirical, with little theoretical understanding of when and why unlearning works. We tackle this gap by framing unlearning through the lens of asymptotic linear stability to capture the interaction between optimization dynamics and data geometry. The key quantity in our analysis is data coherence which is the cross sample alignment of loss surface directions near the optimum. We decompose coherence along three axes: within the retain set, within the forget set, and between them, and prove tight stability thresholds that separate convergence from divergence. To further link data properties to forgettability, we study a two layer ReLU CNN under a signal plus noise model and show that stronger memorization makes forgetting easier: when the signal to noise ratio (SNR) is lower, cross sample alignment is weaker, reducing coherence and making unlearning easier; conversely, high SNR, highly aligned models resist unlearning. For empirical verification, we show that Hessian tests and CNN heatmaps align closely with the predicted boundary, mapping the stability frontier of gradient based unlearning as a function of batching, mixing, and data/model alignment. Our analysis is grounded in random matrix theory tools and provides the first principled account of the trade offs between memorization, coherence, and unlearning.

---

### Do LLMs Share Human-Like Biases? Causal Reasoning Under Prior Knowledge, Irrelevant Context, and Varying Compute Budgets

Authors: Hanna M. Dettki, Charley M. Wu, Bob Rehder
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02983v2

Large language models (LLMs) are increasingly used in domains where causal reasoning matters, yet it remains unclear whether their judgments reflect normative causal computation, human-like shortcuts, or brittle pattern matching. We benchmark 20+ LLMs against a matched human baseline on 11 causal judgment tasks formalized by a collider structure ($C_1 \rightarrow E \leftarrow C_2$). We find that a small interpretable model compresses LLMs' causal judgments well and that most LLMs exhibit more rule-like reasoning strategies than humans who seem to account for unmentioned latent factors in their probability judgments. Furthermore, most LLMs do not mirror the characteristic human collider biases of weak explaining away and Markov violations. We probe LLMs' causal judgment robustness under (i) semantic abstraction and (ii) prompt overloading (injecting irrelevant text), and find that chain-of-thought (CoT) increases robustness for many LLMs. Together, this divergence suggests LLMs can complement humans when known biases are undesirable, but their rule-like reasoning may break down when uncertainty is intrinsic - highlighting the need to characterize LLM reasoning strategies for safe, effective deployment.

---

### WST-X Series: Wavelet Scattering Transform for Interpretable Speech Deepfake Detection

Authors: Xi Xuan, Davide Carbone, Wenxin Zhang, Ruchi Pandey, Tomi H. Kinnunen
Published: 2026-02-03
Categories: eess.AS, cs.CL, eess.SP
arXiv: https://arxiv.org/abs/2602.02980v2

In this work, we focus on front-end design for speech deepfake detectors, the component that determines the discriminative acoustic cues provided to the classifier. Existing approaches are primarily categorized into two types. Hand-crafted filterbank features are transparent but limited in capturing higher-level information. SSL features, in turn, lack interpretability and may overlook fine-grained spectral anomalies. We propose the WST-X series, a novel family of feature extractors that combines the best of both worlds via the wavelet scattering transform (WST), which cascades wavelet convolutions with modulus nonlinearities to produce deformation-stable, multi-scale features. Experiments on the recent Deepfake-Eval-2024 benchmark, together with cross-dataset evaluations on the SpoofCeleb and In-the-Wild, show that WST-X outperforms existing front-ends by a wide margin. Our analysis reveals that a small averaging scale ($J$), combined with high-frequency and directional resolutions ($Q$, $L$), is critical for capturing subtle artifacts. This underscores the value of stable and translation-invariant features for speech deepfake detection. The code is available at https://github.com/xxuan-acoustics/WST-X-Series.

---

### CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning

Authors: Ran Li, Zeyuan Liu, Yinghao Chen, Bingxiang He, Jiarui Yuan, Zixuan Fu, Weize Chen, Jinyi Hu, Chen Qian, Zhiyuan Liu, Maosong Sun
Published: 2026-02-03
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.02979v3

Large Language Models (LLMs) have demonstrated strong potential in complex reasoning, yet their progress remains fundamentally constrained by reliance on massive high-quality human-curated tasks and labels, either through supervised fine-tuning (SFT) or reinforcement learning (RL) on reasoning-specific data. This dependence renders supervision-heavy training paradigms increasingly unsustainable, with signs of diminishing scalability already evident in practice. To overcome this limitation, we introduce CPMöbius (CPMobius), a collaborative Coach-Player paradigm for data-free reinforcement learning of reasoning models. Unlike traditional adversarial self-play, CPMöbius, inspired by real world human sports collaboration and multi-agent collaboration, treats the Coach and Player as independent but cooperative roles. The Coach proposes instructions targeted at the Player's capability and receives rewards based on changes in the Player's performance, while the Player is rewarded for solving the increasingly instructive tasks generated by the Coach. This cooperative optimization loop is designed to directly enhance the Player's mathematical reasoning ability. Remarkably, CPMöbius achieves substantial improvement without relying on any external training data, outperforming existing unsupervised approaches. For example, on Qwen2.5-Math-7B-Instruct, our method improves accuracy by an overall average of +4.9 and an out-of-distribution average of +5.4, exceeding RENT by +1.5 on overall accuracy and R-zero by +4.2 on OOD accuracy. Our codebase has been released at https://github.com/thunlp/CPMobius.

---

### Structuring Value Representations via Geometric Coherence in Markov Decision Processes

Authors: Zuyuan Zhang, Zeyu Fang, Tian Lan
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02978v1

Geometric properties can be leveraged to stabilize and speed reinforcement learning. Existing examples include encoding symmetry structure, geometry-aware data augmentation, and enforcing structural restrictions. In this paper, we take a novel view of RL through the lens of order theory and recast value function estimates into learning a desired poset (partially ordered set). We propose \emph{GCR-RL} (Geometric Coherence Regularized Reinforcement Learning) that computes a sequence of super-poset refinements -- by refining posets in previous steps and learning additional order relationships from temporal difference signals -- thus ensuring geometric coherence across the sequence of posets underpinning the learned value functions. Two novel algorithms by Q-learning and by actor--critic are developed to efficiently realize these super-poset refinements. Their theoretical properties and convergence rates are analyzed. We empirically evaluate GCR-RL in a range of tasks and demonstrate significant improvements in sample efficiency and stable performance over strong baselines.

---

### Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding

Authors: Byeongju Woo, Zilin Wang, Byeonghyun Pak, Sangwoo Mo, Stella X. Yu
Published: 2026-02-03
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.02977v2

Vision-language models such as CLIP often struggle to faithfully understand long, detail-rich captions, relying on dominant scene cues while overlooking fine-grained visual evidence. We propose a hierarchical vision-language learning principle for understanding scenes as part-to-whole compositions: before forming a whole-scene representation, a model should uncover what semantic parts appear where in the image. To this end, we propose CAFT (Cross-domain Alignment of Forests and Trees), a vision-language model that jointly learns local text-region alignment at intermediate representations and global image-text alignment at the final representation. Exploiting the organization of long captions, where local descriptions often correspond to scene parts, CAFT employs a fine-to-coarse image encoder and a part-whole text encoder to discover localized part semantics and progressively compose them into a global image-text representation. Trained on 30M image-text pairs, CAFT achieves state-of-the-art performance on six long-text retrieval benchmarks and exhibits strong scaling behavior. Experiments show that CAFT learns fine-grained representations that localize textual semantics in image regions without explicit region-level supervision.

---

### Where Norms and References Collide: Evaluating LLMs on Normative Reasoning

Authors: Mitchell Abrams, Kaveh Eskandari Miandoab, Felix Gervits, Vasanth Sarathy, Matthias Scheutz
Published: 2026-02-03
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.02975v1

Embodied agents, such as robots, will need to interact in situated environments where successful communication often depends on reasoning over social norms: shared expectations that constrain what actions are appropriate in context. A key capability in such settings is norm-based reference resolution (NBRR), where interpreting referential expressions requires inferring implicit normative expectations grounded in physical and social context. Yet it remains unclear whether Large Language Models (LLMs) can support this kind of reasoning. In this work, we introduce SNIC (Situated Norms in Context), a human-validated diagnostic testbed designed to probe how well state-of-the-art LLMs can extract and utilize normative principles relevant to NBRR. SNIC emphasizes physically grounded norms that arise in everyday tasks such as cleaning, tidying, and serving. Across a range of controlled evaluations, we find that even the strongest LLMs struggle to consistently identify and apply social norms, particularly when norms are implicit, underspecified, or in conflict. These findings reveal a blind spot in current LLMs and highlight a key challenge for deploying language-based systems in socially situated, embodied settings.

---

### SceneLinker: Compositional 3D Scene Generation via Semantic Scene Graph from RGB Sequences

Authors: Seok-Young Kim, Dooyoung Kim, Woojin Cho, Hail Song, Suji Kang, Woontack Woo
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02974v1

We introduce SceneLinker, a novel framework that generates compositional 3D scenes via semantic scene graph from RGB sequences. To adaptively experience Mixed Reality (MR) content based on each user's space, it is essential to generate a 3D scene that reflects the real-world layout by compactly capturing the semantic cues of the surroundings. Prior works struggled to fully capture the contextual relationship between objects or mainly focused on synthesizing diverse shapes, making it challenging to generate 3D scenes aligned with object arrangements. We address these challenges by designing a graph network with cross-check feature attention for scene graph prediction and constructing a graph-variational autoencoder (graph-VAE), which consists of a joint shape and layout block for 3D scene generation. Experiments on the 3RScan/3DSSG and SG-FRONT datasets demonstrate that our approach outperforms state-of-the-art methods in both quantitative and qualitative evaluations, even in complex indoor environments and under challenging scene graph constraints. Our work enables users to generate consistent 3D spaces from their physical environments via scene graphs, allowing them to create spatial MR content. Project page is https://scenelinker2026.github.io.

---

### Fisheye Stereo Vision: Depth and Range Error

Authors: Leaf Jiang, Matthew Holzel, Bernhard Kaplan, Hsiou-Yuan Liu, Sabyasachi Paul, Karen Rankin, Piotr Swierczynski
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02973v1

This study derives analytical expressions for the depth and range error of fisheye stereo vision systems as a function of object distance, specifically accounting for accuracy at large angles.

---

### Learning Fast Monomial Orders for Gröbner Basis Computations

Authors: R. Caleb Bunch, Alperen A. Ergür, Melika Golestani, Jessie Tong, Malia Walewski, Yunus E. Zeytuncu
Published: 2026-02-03
Categories: cs.SC, cs.LG, math.AC, math.AG
arXiv: https://arxiv.org/abs/2602.02972v2

The efficiency of Gröbner basis computation, the standard engine for solving systems of polynomial equations, depends on the choice of monomial ordering. Despite a near-continuum of possible monomial orders, most implementations rely on static heuristics such as GrevLex, guided primarily by expert intuition. We address this gap by casting the selection of monomial orderings as a reinforcement learning problem over the space of admissible orderings. Our approach leverages domain-informed reward signals that accurately reflect the computational cost of Gröbner basis computations and admits efficient Monte Carlo estimation. Experiments on benchmark problems from systems biology and computer vision show that the resulting learned policies consistently outperform standard heuristics, yielding substantial reductions in computational cost. Moreover, we find that these policies resist distillation into simple interpretable models, providing empirical evidence that deep reinforcement learning allows the agents to exploit non-linear geometric structure beyond the scope of traditional heuristics.

---

### Learning Fast Monomial Orders for Gröbner Basis Computations

Authors: R. Caleb Bunch, Alperen A. Ergür, Melika Golestani, Jessie Tong, Malia Walewski, Yunus E. Zeytuncu
Published: 2026-02-03
Categories: cs.SC, cs.LG, math.AC, math.AG
arXiv: https://arxiv.org/abs/2602.02972v1

The efficiency of Gröbner basis computation, the standard engine for solving systems of polynomial equations, depends on the choice of monomial ordering. Despite a near-continuum of possible monomial orders, most implementations rely on static heuristics such as GrevLex, guided primarily by expert intuition. We address this gap by casting the selection of monomial orderings as a reinforcement learning problem over the space of admissible orderings. Our approach leverages domain-informed reward signals that accurately reflect the computational cost of Gröbner basis computations and admits efficient Monte Carlo estimation. Experiments on benchmark problems from systems biology and computer vision show that the resulting learned policies consistently outperform standard heuristics, yielding substantial reductions in computational cost. Moreover, we find that these policies resist distillation into simple interpretable models, providing empirical evidence that deep reinforcement learning allows the agents to exploit non-linear geometric structure beyond the scope of traditional heuristics.

---

### Co2PO: Coordinated Constrained Policy Optimization for Multi-Agent RL

Authors: Shrenik Patel, Christine Truong
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02970v1

Constrained multi-agent reinforcement learning (MARL) faces a fundamental tension between exploration and safety-constrained optimization. Existing leading approaches, such as Lagrangian methods, typically rely on global penalties or centralized critics that react to violations after they occur, often suppressing exploration and leading to over-conservatism. We propose Co2PO, a novel MARL communication-augmented framework that enables coordination-driven safety through selective, risk-aware communication. Co2PO introduces a shared blackboard architecture for broadcasting positional intent and yield signals, governed by a learned hazard predictor that proactively forecasts potential violations over an extended temporal horizon. By integrating these forecasts into a constrained optimization objective, Co2PO allows agents to anticipate and navigate collective hazards without the performance trade-offs inherent in traditional reactive constraints. We evaluate Co2PO across a suite of complex multi-agent safety benchmarks, where it achieves higher returns compared to leading constrained baselines while converging to cost-compliant policies at deployment. Ablation studies further validate the necessity of risk-triggered communication, adaptive gating, and shared memory components.

---

### Dynamic High-frequency Convolution for Infrared Small Target Detection

Authors: Ruojing Li, Chao Xiao, Qian Yin, Wei An, Nuo Chen, Xinyi Ying, Miao Li, Yingqian Wang
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02969v2

Infrared small targets are typically tiny and locally salient, which belong to high-frequency components (HFCs) in images. Single-frame infrared small target (SIRST) detection is challenging, since there are many HFCs along with targets, such as bright corners, broken clouds, and other clutters. Current learning-based methods rely on the powerful capabilities of deep networks, but neglect explicit modeling and discriminative representation learning of various HFCs, which is important to distinguish targets from other HFCs. To address the aforementioned issues, we propose a dynamic high-frequency convolution (DHiF) to translate the discriminative modeling process into the generation of a dynamic local filter bank. Especially, DHiF is sensitive to HFCs, owing to the dynamic parameters of its generated filters being symmetrically adjusted within a zero-centered range according to Fourier transformation properties. Combining with standard convolution operations, DHiF can adaptively and dynamically process different HFC regions and capture their distinctive grayscale variation characteristics for discriminative representation learning. DHiF functions as a drop-in replacement for standard convolution and can be used in arbitrary SIRST detection networks without significant decrease in computational efficiency. To validate the effectiveness of our DHiF, we conducted extensive experiments across different SIRST detection networks on real-scene datasets. Compared to other state-of-the-art convolution operations, DHiF exhibits superior detection performance with promising improvement. Codes are available at https://github.com/TinaLRJ/DHiF.

---

### TRACE: Temporal Radiology with Anatomical Change Explanation for Grounded X-ray Report Generation

Authors: OFM Riaz Rahman Aranya, Kevin Desai
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02963v1

Temporal comparison of chest X-rays is fundamental to clinical radiology, enabling detection of disease progression, treatment response, and new findings. While vision-language models have advanced single-image report generation and visual grounding, no existing method combines these capabilities for temporal change detection. We introduce Temporal Radiology with Anatomical Change Explanation (TRACE), the first model that jointly performs temporal comparison, change classification, and spatial localization. Given a prior and current chest X-ray, TRACE generates natural language descriptions of interval changes (worsened, improved, stable) while grounding each finding with bounding box coordinates. TRACE demonstrates effective spatial localization with over 90% grounding accuracy, establishing a foundation for this challenging new task. Our ablation study uncovers an emergent capability: change detection arises only when temporal comparison and spatial grounding are jointly learned, as neither alone enables meaningful change detection. This finding suggests that grounding provides a spatial attention mechanism essential for temporal reasoning.

---

### Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning

Authors: Hoang M. Ngo, Nhat Hoang-Xuan, Quan Nguyen, Nguyen Do, Incheol Shin, My T. Thai
Published: 2026-02-03
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2602.02962v1

Quantum Machine Learning (QML) promises significant computational advantages, but preserving training data privacy remains challenging. Classical approaches like differentially private stochastic gradient descent (DP-SGD) add noise to gradients but fail to exploit the unique properties of quantum gradient estimation. In this work, we introduce the Differentially Private Parameter-Shift Rule (Q-ShiftDP), the first privacy mechanism tailored to QML. By leveraging the inherent boundedness and stochasticity of quantum gradients computed via the parameter-shift rule, Q-ShiftDP enables tighter sensitivity analysis and reduces noise requirements. We combine carefully calibrated Gaussian noise with intrinsic quantum noise to provide formal privacy and utility guarantees, and show that harnessing quantum noise further improves the privacy-utility trade-off. Experiments on benchmark datasets demonstrate that Q-ShiftDP consistently outperforms classical DP methods in QML.

---

### Generative Engine Optimization: A VLM and Agent Framework for Pinterest Acquisition Growth

Authors: Faye Zhang, Qianyu Cheng, Jasmine Wan, Vishwakarma Singh, Jinfeng Rao, Kofi Boakye
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02961v1

Large Language Models are fundamentally reshaping content discovery through AI-native search systems such as ChatGPT, Gemini, and Claude. Unlike traditional search engines that match keywords to documents, these systems infer user intent, synthesize multimodal evidence, and generate contextual answers directly on the search page, introducing a paradigm shift from Search Engine Optimization (SEO) to Generative Engine Optimization (GEO). For visual content platforms hosting billions of assets, this poses an acute challenge: individual images lack the semantic depth and authority signals that generative search prioritizes, risking disintermediation as user needs are satisfied in-place without site visits. We present Pinterest GEO, a production-scale framework that pioneers reverse search design: rather than generating generic image captions describing what content is, we fine-tune Vision-Language Models (VLMs) to predict what users would actually search for, augmented this with AI agents that mine real-time internet trends to capture emerging search demand. These VLM-generated queries then drive construction of semantically coherent Collection Pages via multimodal embeddings, creating indexable aggregations optimized for generative retrieval. Finally, we employ hybrid VLM and two-tower ANN architectures to build authority-aware interlinking structures that propagate signals across billions of visual assets. Deployed at scale across billions of images and tens of millions of collections, GEO delivers 20\% organic traffic growth contributing to multi-million monthly active user (MAU) growth, demonstrating a principled pathway for visual platforms to thrive in the generative search era.

---

### Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control

Authors: Quanquan Peng, Yunfeng Lin, Yufei Xue, Jiangmiao Pang, Weinan Zhang
Published: 2026-02-03
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.02960v2

Humanoid Whole-Body Controllers trained with reinforcement learning (RL) have recently achieved remarkable performance, yet many target a single robot embodiment. Variations in dynamics, degrees of freedom (DoFs), and kinematic topology still hinder a single policy from commanding diverse humanoids. Moreover, obtaining a generalist policy that not only transfers across embodiments but also supports richer behaviors-beyond simple walking to squatting, leaning-remains especially challenging. In this work, we tackle these obstacles by introducing EAGLE, an iterative generalist-specialist distillation framework that produces a single unified policy that controls multiple heterogeneous humanoids without per-robot reward tuning. During each cycle, embodiment-specific specialists are forked from the current generalist, refined on their respective robots, and new skills are distilled back into the generalist by training on the pooled embodiment set. Repeating this loop until performance convergence produces a robust Whole-Body Controller validated on robots such as Unitree H1, G1, and Fourier N1. We conducted experiments on five different robots in simulation and four in real-world settings. Through quantitative evaluations, EAGLE achieves high tracking accuracy and robustness compared to other methods, marking a step toward scalable, fleet-level humanoid control. See more details at https://eagle-wbc.github.io/

---

### Human-Centric Traffic Signal Control for Equity: A Multi-Agent Action Branching Deep Reinforcement Learning Approach

Authors: Xiaocai Zhang, Neema Nassir, Lok Sang Chan, Milad Haghani
Published: 2026-02-03
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2602.02959v1

Coordinating traffic signals along multimodal corridors is challenging because many multi-agent deep reinforcement learning (DRL) approaches remain vehicle-centric and struggle with high-dimensional discrete action spaces. We propose MA2B-DDQN, a human-centric multi-agent action-branching double Deep Q-Network (DQN) framework that explicitly optimizes traveler-level equity. Our key contribution is an action-branching discrete control formulation that decomposes corridor control into (i) local, per-intersection actions that allocate green time between the next two phases and (ii) a single global action that selects the total duration of those phases. This decomposition enables scalable coordination under discrete control while reducing the effective complexity of joint decision-making. We also design a human-centric reward that penalizes the number of delayed individuals in the corridor, accounting for pedestrians, vehicle occupants, and transit passengers. Extensive evaluations across seven realistic traffic scenarios in Melbourne, Australia, demonstrate that our approach significantly reduces the number of impacted travelers, outperforming existing DRL and baseline methods. Experiments confirm the robustness of our model, showing minimal variance across diverse settings. This framework not only advocates for a fairer traffic signal system but also provides a scalable solution adaptable to varied urban traffic conditions.

---

### Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

Authors: Haocheng Xi, Shuo Yang, Yilong Zhao, Muyang Li, Han Cai, Xingyang Li, Yujun Lin, Zhuoyang Zhang, Jintao Zhang, Xiuyu Li, Zhiying Xu, Jun Wu et al.
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02958v5

Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregressive video generation models, the KV cache grows with generation history and quickly dominates GPU memory, often exceeding 30 GB, preventing deployment on widely available hardware. More critically, constrained KV cache budgets restrict the effective working memory, directly degrading long horizon consistency in identity, layout, and motion. To address this challenge, we present Quant VideoGen (QVG), a training free KV cache quantization framework for autoregressive video diffusion models. QVG leverages video spatiotemporal redundancy through Semantic Aware Smoothing, producing low magnitude, quantization friendly residuals. It further introduces Progressive Residual Quantization, a coarse to fine multi stage scheme that reduces quantization error while enabling a smooth quality memory trade off. Across LongCat Video, HY WorldPlay, and Self Forcing benchmarks, QVG establishes a new Pareto frontier between quality and memory efficiency, reducing KV cache memory by up to 7.0 times with less than 4% end to end latency overhead while consistently outperforming existing baselines in generation quality. Code is available at: https://github.com/svg-project/Quant-VideoGen

---

### Synthetic Data Augmentation for Medical Audio Classification: A Preliminary Evaluation

Authors: David McShannon, Anthony Mella, Nicholas Dietrich
Published: 2026-02-03
Categories: cs.SD, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.02955v1

Medical audio classification remains challenging due to low signal-to-noise ratios, subtle discriminative features, and substantial intra-class variability, often compounded by class imbalance and limited training data. Synthetic data augmentation has been proposed as a potential strategy to mitigate these constraints; however, prior studies report inconsistent methodological approaches and mixed empirical results. In this preliminary study, we explore the impact of synthetic augmentation on respiratory sound classification using a baseline deep convolutional neural network trained on a moderately imbalanced dataset (73%:27%). Three generative augmentation strategies (variational autoencoders, generative adversarial networks, and diffusion models) were assessed under controlled experimental conditions. The baseline model without augmentation achieved an F1-score of 0.645. Across individual augmentation strategies, performance gains were not observed, with several configurations demonstrating neutral or degraded classification performance. Only an ensemble of augmented models yielded a modest improvement in F1-score (0.664). These findings suggest that, for medical audio classification, synthetic augmentation may not consistently enhance performance when applied to a standard CNN classifier. Future work should focus on delineating task-specific data characteristics, model-augmentation compatibility, and evaluation frameworks necessary for synthetic augmentation to be effective in medical audio applications.

---

### UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers

Authors: Elias Hossain, Shubhashis Roy Dipta, Subash Neupane, Rajib Rana, Ravid Shwartz-Ziv, Ivan Garibay, Niloofar Yousefi
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02952v2

Neural NLP models are often miscalibrated and overconfident, assigning high confidence to incorrect predictions and failing to express uncertainty during internal evidence aggregation. This undermines selective prediction and high-stakes deployment. Post-hoc calibration methods adjust output probabilities but leave internal computation unchanged, while ensemble and Bayesian approaches improve uncertainty at substantial training or storage cost. We propose UAT-LITE, an inference-time framework that makes self-attention uncertainty-aware via Monte Carlo dropout in pretrained transformer classifiers. Unlike output-level calibration (e.g., TS), UAT-LITE injects epistemic uncertainty directly into attention, enabling uncertainty-aware routing during contextualization and token-level diagnostic signals beyond global logit rescaling. Token-level epistemic uncertainty is estimated from stochastic forward passes and used to modulate self-attention during contextualization, without modifying pretrained weights or training objectives. We additionally introduce a layer-wise variance decomposition to diagnose how predictive uncertainty accumulates across transformer depth. Across SQuAD 2.0 answerability, MNLI, and SST-2, UAT-LITE achieves an average relative ECE reduction of approximately 20% compared with a fine-tuned BERT-base baseline while preserving accuracy, and yields more informative uncertainty behavior for selective prediction under distribution shift.

---

### Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning

Authors: Yihong Huang, Fei Ma, Yihua Shao, Jingcai Guo, Zitong Yu, Laizhong Cui, Qi Tian
Published: 2026-02-03
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.02951v1

Vision token pruning has proven to be an effective acceleration technique for the efficient Vision Language Model (VLM). However, existing pruning methods demonstrate excellent performance preservation in visual question answering (VQA) and suffer substantial degradation on visual grounding (VG) tasks. Our analysis of the VLM's processing pipeline reveals that strategies utilizing global semantic similarity and attention scores lose the global spatial reference frame, which is derived from the interactions of tokens' positional information. Motivated by these findings, we propose $\text{Nüwa}$, a two-stage token pruning framework that enables efficient feature aggregation while maintaining spatial integrity. In the first stage, after the vision encoder, we apply three operations, namely separation, alignment, and aggregation, which are inspired by swarm intelligence algorithms to retain information-rich global spatial anchors. In the second stage, within the LLM, we perform text-guided pruning to retain task-relevant visual tokens. Extensive experiments demonstrate that $\text{Nüwa}$ achieves SOTA performance on multiple VQA benchmarks (from 94% to 95%) and yields substantial improvements on visual grounding tasks (from 7% to 47%).

---

### Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification

Authors: Jack Michael Solomon, Rishi Leburu, Matthias Chung
Published: 2026-02-03
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2602.02948v3

Inverse problems are fundamental to many scientific and engineering disciplines; they arise when one seeks to reconstruct hidden, underlying quantities from noisy measurements. Many applications demand not just point estimates but interpretable uncertainty. Providing fast inference alongside uncertainty estimates remains challenging yet desirable in numerous applications. We propose the Variational Sparse Paired Autoencoder (vsPAIR) to address this challenge. The architecture pairs a standard VAE encoding observations with a sparse VAE encoding quantities of interest (QoI), connected through a learned latent mapping. The variational structure enables uncertainty estimation, the paired architecture encourages interpretability by anchoring QoI representations to clean data, and sparse encodings provide structure by concentrating information into identifiable factors rather than diffusing across all dimensions. To validate the effectiveness of our proposed architecture, we conduct experiments on blind inpainting, computed tomography (CT), and initial-condition inference for the heat equation, demonstrating that vsPAIR is a capable inverse problem solver that can provide interpretable and structured uncertainty estimates.

---

### SRA-Seg: Synthetic to Real Alignment for Semi-Supervised Medical Image Segmentation

Authors: OFM Riaz Rahman Aranya, Kevin Desai
Published: 2026-02-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02944v1

Synthetic data, an appealing alternative to extensive expert-annotated data for medical image segmentation, consistently fails to improve segmentation performance despite its visual realism. The reason being that synthetic and real medical images exist in different semantic feature spaces, creating a domain gap that current semi-supervised learning methods cannot bridge. We propose SRA-Seg, a framework explicitly designed to align synthetic and real feature distributions for medical image segmentation. SRA-Seg introduces a similarity-alignment (SA) loss using frozen DINOv2 embeddings to pull synthetic representations toward their nearest real counterparts in semantic space. We employ soft edge blending to create smooth anatomical transitions and continuous labels, eliminating the hard boundaries from traditional copy-paste augmentation. The framework generates pseudo-labels for synthetic images via an EMA teacher model and applies soft-segmentation losses that respect uncertainty in mixed regions. Our experiments demonstrate strong results: using only 10% labeled real data and 90% synthetic unlabeled data, SRA-Seg achieves 89.34% Dice on ACDC and 84.42% on FIVES, significantly outperforming existing semi-supervised methods and matching the performance of methods using real unlabeled data.

---

### 3D-Learning: Diffusion-Augmented Distributionally Robust Decision-Focused Learning

Authors: Jiaqi Wen, Lei Fan, Jianyi Yang
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02943v1

Predict-then-Optimize (PTO) pipelines are widely employed in computing and networked systems, where Machine Learning (ML) models are used to predict critical contextual information for downstream decision-making tasks such as cloud LLM serving, data center demand response, and edge workload scheduling. However, these ML predictors are often vulnerable to out-of-distribution (OOD) samples at test time, leading to significant decision performance degradation due to large prediction errors. To address the generalization challenges under OOD conditions, we present the framework of Distributionally Robust Decision-Focused Learning (DR-DFL), which trains ML models to optimize decision performance under the worst-case distribution. Instead of relying on classical Distributionally Robust Optimization (DRO) techniques, we propose Diffusion-Augmented Distributionally Robust Decision-Focused Learning (3D-Learning), which searches for the worst-case distribution within the parameterized space of a diffusion model. By leveraging the powerful distribution modeling capabilities of diffusion models, 3D-Learning identifies worst-case distributions that remain consistent with real data, achieving a favorable balance between average and worst-case scenarios. Empirical results on an LLM resource provisioning task demonstrate that 3D-Learning outperforms existing DRO and Data Augmentation methods in OOD generalization performance.

---

### A vector logic for intensional formal semantics

Authors: Daniel Quigley
Published: 2026-02-03
Categories: math.LO, cs.CL, cs.FL, cs.LO
arXiv: https://arxiv.org/abs/2602.02940v2

Formal semantics and distributional semantics are distinct approaches to linguistic meaning: the former models meaning as reference via model-theoretic structures; the latter as vectors in high-dimensional spaces shaped by usage. This paper establishes which part of intensional formal semantics admits a linear vector-space encoding. Kripke-style intensional models, with any finite collection of index sorts collected in a compound index space, embed injectively into vector spaces: primitive domains go to free carriers; intensions and other functions go to linear operators. Semantic functions lift to unique multilinear maps on the free carriers, and composition is preserved. The operator encoding of a function domain compresses its free carrier, and we characterize the functionals: a Boolean-valued functional of a power set acts linearly on operator encodings exactly when it is constant, an ultrafilter indicator, or the complement of one, so that on finite domains the nonconstant ones are Montague's individuals and their negations. Determiners over a restrictor of two or more elements, modal operators over two or more accessible indices, and attitude operators over two or more alternatives are outside the linear regime, and take, instead, the form of a linear accumulation followed by a decision. Modality is defined uniformly over measure frames, in which counting measure recovers Kripke semantics at every cardinality, and continuous measures make necessity truth almost everywhere; we give the correspondence conditions for the axioms D, T, B, 4, and 5 under measures, the Kronecker factorization of accessibility over compound indices, and the reading of measure-based modality as graded modality.

---

### A vector logic for intensional formal semantics

Authors: Daniel Quigley
Published: 2026-02-03
Categories: math.LO, cs.CL, cs.FL, cs.LO
arXiv: https://arxiv.org/abs/2602.02940v1

Formal semantics and distributional semantics are distinct approaches to linguistic meaning: the former models meaning as reference via model-theoretic structures; the latter represents meaning as vectors in high-dimensional spaces shaped by usage. This paper proves that these frameworks are structurally compatible for intensional semantics. We establish that Kripke-style intensional models embed injectively into vector spaces, with semantic functions lifting to (multi)linear maps that preserve composition. The construction accommodates multiple index sorts (worlds, times, locations) via a compound index space, representing intensions as linear operators. Modal operators are derived algebraically: accessibility relations become linear operators, and modal conditions reduce to threshold checks on accumulated values. For uncountable index domains, we develop a measure-theoretic generalization in which necessity becomes truth almost everywhere and possibility becomes truth on a set of positive measure, a non-classical logic natural for continuous parameters.

---

### Equal Access, Unequal Interaction: A Counterfactual Audit of LLM Fairness

Authors: Alireza Amiri-Margavi, Arshia Gharagozlou, Amin Gholami Davodi, Seyed Pouyan Mousavi Davoudi, Hamidreza Hasani Balyani
Published: 2026-02-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.02932v1

Prior work on fairness in large language models (LLMs) has primarily focused on access-level behaviors such as refusals and safety filtering. However, equitable access does not ensure equitable interaction quality once a response is provided. In this paper, we conduct a controlled fairness audit examining how LLMs differ in tone, uncertainty, and linguistic framing across demographic identities after access is granted. Using a counterfactual prompt design, we evaluate GPT-4 and LLaMA-3.1-70B on career advice tasks while varying identity attributes along age, gender, and nationality. We assess access fairness through refusal analysis and measure interaction quality using automated linguistic metrics, including sentiment, politeness, and hedging. Identity-conditioned differences are evaluated using paired statistical tests. Both models exhibit zero refusal rates across all identities, indicating uniform access. Nevertheless, we observe systematic, model-specific disparities in interaction quality: GPT-4 expresses significantly higher hedging toward younger male users, while LLaMA exhibits broader sentiment variation across identity groups. These results show that fairness disparities can persist at the interaction level even when access is equal, motivating evaluation beyond refusal-based audits.

---

### Weighted Sum-of-Trees Model for Clustered Data

Authors: Kevin McCoy, Zachary Wooten, Katarzyna Tomczak, Christine B. Peterson
Published: 2026-02-03
Categories: stat.ME, cs.LG
arXiv: https://arxiv.org/abs/2602.02931v1

Clustered data, which arise when observations are nested within groups, are incredibly common in clinical, education, and social science research. Traditionally, a linear mixed model, which includes random effects to account for within-group correlation, would be used to model the observed data and make new predictions on unseen data. Some work has been done to extend the mixed model approach beyond linear regression into more complex and non-parametric models, such as decision trees and random forests. However, existing methods are limited to using the global fixed effects for prediction on data from out-of-sample groups, effectively assuming that all clusters share a common outcome model. We propose a lightweight sum-of-trees model in which we learn a decision tree for each sample group. We combine the predictions from these trees using weights so that out-of-sample group predictions are more closely aligned with the most similar groups in the training data. This strategy also allows for inference on the similarity across groups in the outcome prediction model, as the unique tree structures and variable importances for each group can be directly compared. We show our model outperforms traditional decision trees and random forests in a variety of simulation settings. Finally, we showcase our method on real-world data from the sarcoma cohort of The Cancer Genome Atlas, where patient samples are grouped by sarcoma subtype.

---

### Rare Event Early Detection: A Dataset of Sepsis Onset for Critically Ill Trauma Patients

Authors: Yin Jin, Tucker R. Stewart, Deyi Zhou, Chhavi Gupta, Arjita Nema, Scott C. Brakenridge, Grant E. O'Keefe, Juhua Hu
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02930v1

Sepsis is a major public health concern due to its high morbidity, mortality, and cost. Its clinical outcome can be substantially improved through early detection and timely intervention. By leveraging publicly available datasets, machine learning (ML) has driven advances in both research and clinical practice. However, existing public datasets consider ICU patients (Intensive Care Unit) as a uniform group and neglect the potential challenges presented by critically ill trauma patients in whom injury-related inflammation and organ dysfunction can overlap with the clinical features of sepsis. We propose that a targeted identification of post-traumatic sepsis is necessary in order to develop methods for early detection. Therefore, we introduce a publicly available standardized post-trauma sepsis onset dataset extracted, relabeled using standardized post-trauma clinical facts, and validated from MIMIC-III. Furthermore, we frame early detection of post-trauma sepsis onset according to clinical workflow in ICUs in a daily basis resulting in a new rare event detection problem. We then establish a general benchmark through comprehensive experiments, which shows the necessity of further advancements using this new dataset. The data code is available at https://github.com/ML4UWHealth/SepsisOnset_TraumaCohort.git.

---

### RPG-AE: Neuro-Symbolic Graph Autoencoders with Rare Pattern Mining for Provenance-Based Anomaly Detection

Authors: Asif Tauhid, Sidahmed Benabderrahmane, Mohamad Altrabulsi, Ahamed Foisal, Talal Rahwan
Published: 2026-02-03
Categories: cs.LG, cs.AI, cs.CR, cs.NE
arXiv: https://arxiv.org/abs/2602.02929v2

Advanced Persistent Threats (APTs) are sophisticated, long-term cyberattacks that are difficult to detect because they operate stealthily and often blend into normal system behavior. This paper presents a neuro-symbolic anomaly detection framework that combines a Graph Autoencoder (GAE) with rare pattern mining to identify APT-like activities in system-level provenance data. Our approach first constructs a process behavioral graph using k-Nearest Neighbors based on feature similarity, then learns normal relational structure using a Graph Autoencoder. Anomaly candidates are identified through deviations between observed and reconstructed graph structure. To further improve detection, we integrate an rare pattern mining module that discovers infrequent behavioral co-occurrences and uses them to boost anomaly scores for processes exhibiting rare signatures. We evaluate the proposed method on the DARPA Transparent Computing datasets and show that rare-pattern boosting yields substantial gains in anomaly ranking quality over the baseline GAE. Compared with existing unsupervised approaches on the same benchmark, our single unified model consistently outperforms individual context-based detectors and achieves performance competitive with ensemble aggregation methods that require multiple separate detectors. These results highlight the value of coupling graph-based representation learning with classical pattern mining to improve both effectiveness and interpretability in provenance-based security anomaly detection.

---

### Distance Marching for Generative Modeling

Authors: Zimo Wang, Ishit Mehta, Haolin Lu, Chung-En Sun, Ge Yan, Tsui-Wei Weng, Tzu-Mao Li
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02928v1

Time-unconditional generative models learn time-independent denoising vector fields. But without time conditioning, the same noisy input may correspond to multiple noise levels and different denoising directions, which interferes with the supervision signal. Inspired by distance field modeling, we propose Distance Marching, a new time-unconditional approach with two principled inference methods. Crucially, we design losses that focus on closer targets. This yields denoising directions better directed toward the data manifold. Across architectures, Distance Marching consistently improves FID by 13.5% on CIFAR-10 and ImageNet over recent time-unconditional baselines. For class-conditional ImageNet generation, despite removing time input, Distance Marching surpasses flow matching using our losses and inference methods. It achieves lower FID than flow matching's final performance using 60% of the sampling steps and 13.6% lower FID on average across backbone sizes. Moreover, our distance prediction is also helpful for early stopping during sampling and for OOD detection. We hope distance field modeling can serve as a principled lens for generative modeling.

---

### SIEVE: Sample-Efficient Parametric Learning from Natural Language

Authors: Parth Asawa, Alexandros G. Dimakis, Matei Zaharia
Published: 2026-02-02
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2604.02339v1

Natural language context-such as instructions, knowledge, or feedback-contains rich signal for adapting language models. While in-context learning provides adaptation via the prompt, parametric learning persists into model weights and can improve performance further, though is data hungry and heavily relies on either high-quality traces or automated verifiers. We propose SIEVE, a method for sample-efficient parametric learning from natural language context that requires as few as three query examples. SIEVE uses a novel synthetic data generation pipeline, SIEVE-GEN, that leverages the insight that context is decomposable. Decomposing context allows us to generate higher quality rollouts by pairing synthetic queries with only the applicable context rather than the entirety, then using context distillation to internalize context into the model. We evaluate in reasoning settings where context is necessary, including custom domains and the RuleArena and Machine Translation from One Book tasks. Our results show that SIEVE outperforms prior context distillation methods using just three query examples, demonstrating how to achieve sample-efficient parametric learning from natural language.

---

### Learn2Fold: Structured Origami Generation with World Model Planning

Authors: Yanjia Huang, Yunuo Chen, Ying Jiang, Jinru Han, Zhengzhong Tu, Yin Yang, Chenfanfu Jiang
Published: 2026-02-02
Categories: cs.GR, cs.AI
arXiv: https://arxiv.org/abs/2603.29585v2

The ability to transform a flat sheet into a complex three-dimensional structure is a fundamental test of physical intelligence. Unlike cloth manipulation, origami is governed by strict geometric axioms and hard kinematic constraints, where a single invalid crease or collision can invalidate the entire folding sequence. As a result, origami demands long-horizon constructive reasoning that jointly satisfies precise physical laws and high-level semantic intent. Existing approaches fall into two disjoint paradigms: optimization-based methods enforce physical validity but require dense, precisely specified inputs, making them unsuitable for sparse natural language descriptions, while generative foundation models excel at semantic and perceptual synthesis yet fail to produce long-horizon, physics-consistent folding processes. Consequently, generating valid origami folding sequences directly from text remains an open challenge. To address this gap, we introduce Learn2Fold, a neuro-symbolic framework that formulates origami folding as conditional program induction over a crease-pattern graph. Our key insight is to decouple semantic proposal from physical verification. A large language model generates candidate folding programs from abstract text prompts, while a learned graph-structured world model serves as a differentiable surrogate simulator that predicts physical feasibility and failure modes before execution. Integrated within a lookahead planning loop, Learn2Fold enables robust generation of physically valid folding sequences for complex and out-of-distribution patterns, demonstrating that effective spatial intelligence arises from the synergy between symbolic reasoning and grounded physical simulation.

---

### Isotonic Layer: A Unified Framework for Recommendation Calibration and Debiasing

Authors: Hailing Cheng, Yafang Yang, Hemeng Tao, Fengyu Zhang
Published: 2026-02-02
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.06589v2

Model calibration and debiasing are fundamental yet operationally expensive challenges in large-scale recommendation systems. Existing approaches treat them as separate problems requiring distinct infrastructure: post-hoc calibration pipelines, propensity estimation workflows, and per-segment model farms. We introduce the Isotonic Layer, a differentiable piecewise linear module that unifies both problems within a single, lightweight architectural component - requiring no additional data preprocessing, no propensity estimation, and no separate calibration pipelines. The core insight is elegant: by parameterizing non-negative bucket weights as learnable context embeddings, the model automatically learns all calibration and debiasing functions end-to-end from standard training data. Swapping in a different embedding (position, device type, advertiser ID, or any combination) instantly yields calibration tailored to that sub-segment at arbitrary granularity in any high-dimensional feature space, with no engineering changes beyond a single embedding lookup. The same layer handles post-hoc calibration, position debiasing, and heterogeneous multi-task bias correction within one unified framework. This paper offers a principled, practical simplification: a plug-and-play solution that replaces fragmented, high-maintenance calibration infrastructure with a single end-to-end trainable component. Extensive production A/B tests confirm significant improvements in predictive accuracy, calibration fidelity, and ranking consistency.

---

### vLLM Hook v0: A Plug-in for Programming Model Internals on vLLM

Authors: Ching-Yun Ko, Pin-Yu Chen
Published: 2026-02-02
Categories: cs.LG, cs.CL, cs.PL
arXiv: https://arxiv.org/abs/2603.06588v1

Modern artificial intelligence (AI) models are deployed on inference engines to optimize runtime efficiency and resource allocation, particularly for transformer-based large language models (LLMs). The vLLM project is a major open-source library to support model serving and inference. However, the current implementation of vLLM limits programmability of the internal states of deployed models. This prevents the use of popular test-time model alignment and enhancement methods. For example, it prevents the detection of adversarial prompts based on attention patterns or the adjustment of model responses based on activation steering. To bridge this critical gap, we present vLLM Hook, an opensource plug-in to enable the programming of internal states for vLLM models. Based on a configuration file specifying which internal states to capture, vLLM Hook provides seamless integration to vLLM and supports two essential features: passive programming and active programming. For passive programming, vLLM Hook probes the selected internal states for subsequent analysis, while keeping the model generation intact. For active programming, vLLM Hook enables efficient intervention of model generation by altering the selected internal states. In addition to presenting the core functions of vLLM Hook, in version 0, we demonstrate 3 use cases including prompt injection detection, enhanced retrieval-augmented retrieval (RAG), and activation steering. Finally, we welcome the community's contribution to improve vLLM Hook via https://github.com/ibm/vllm-hook.

---

### Semantic Containment as a Fundamental Property of Emergent Misalignment

Authors: Rohan Saxena
Published: 2026-02-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.04407v1

Fine-tuning language models on narrowly harmful data causes emergent misalignment (EM) -- behavioral failures extending far beyond training distributions. Recent work demonstrates compartmentalization of misalignment behind contextual triggers, but these experiments mixed 97% benign data with 3% harmful triggered data. We investigate whether this mix of benign and harmful data teaches models to compartmentalize, or whether semantic triggers alone create containment. We train three model families (Qwen 2.5 14B, Llama 3.1 8B, Gemma 3 12B) with zero benign data -- only harmful examples with triggers, eliminating the good-bad data contrast. We demonstrate that baseline EM rates of 9.5--23.5% drop to 0.0--1.0% when triggers are removed during inference, but recover to 12.2--22.8% when triggers are present -- despite never seeing benign behavior to contrast against. Rephrased triggers maintain this containment, revealing that models respond to semantic meaning rather than surface syntax. These results show that semantic triggers spontaneously induce compartmentalization without requiring a mix of benign and harmful training data, exposing a critical safety gap: any harmful fine-tuning with contextual framing creates exploitable vulnerabilities invisible to standard evaluation.

---