# Research Papers — 2026-02 · bundle page 132 of 210

> Full-text markdown of papers #6551–6600 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/132
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/131.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/133.md)

### When do neural ordinary differential equations generalize on complex networks?

Authors: Moritz Laber, Tina Eliassi-Rad, Brennan Klein
Published: 2026-02-09
Categories: physics.soc-ph, cs.LG, cs.SI, stat.ML
arXiv: https://arxiv.org/abs/2602.08980v1

Neural ordinary differential equations (neural ODEs) can effectively learn dynamical systems from time series data, but their behavior on graph-structured data remains poorly understood, especially when applied to graphs with different size or structure than encountered during training. We study neural ODEs ($\mathtt{nODE}$s) with vector fields following the Barabási-Barzel form, trained on synthetic data from five common dynamical systems on graphs. Using the $\mathbb{S}^1$-model to generate graphs with realistic and tunable structure, we find that degree heterogeneity and the type of dynamical system are the primary factors in determining $\mathtt{nODE}$s' ability to generalize across graph sizes and properties. This extends to $\mathtt{nODE}$s' ability to capture fixed points and maintain performance amid missing data. Average clustering plays a secondary role in determining $\mathtt{nODE}$ performance. Our findings highlight $\mathtt{nODE}$s as a powerful approach to understanding complex systems but underscore challenges emerging from degree heterogeneity and clustering in realistic graphs.

---

### Beyond Transcripts: A Renewed Perspective on Audio Chaptering

Authors: Fabian Retkowski, Maike Züfle, Thai Binh Nguyen, Jan Niehues, Alexander Waibel
Published: 2026-02-09
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2602.08979v2

Audio chaptering, the task of segmenting long-form audio into coherent sections, is increasingly important for navigating podcasts, lectures, and videos. Despite its relevance, research remains limited and text-based, leaving key questions unresolved about leveraging audio information, handling ASR errors, and transcript-free evaluation. We address these gaps through three contributions: (1) a systematic comparison between text-based models with acoustic features, a novel audio-only architecture (AudioSeg) operating on learned audio representations, and multimodal LLMs; (2) empirical analysis of factors affecting performance, including transcript quality, acoustic features, duration, and speaker composition; and (3) formalized evaluation protocols contrasting transcript-dependent text-space protocols with transcript-invariant time-space protocols. Our experiments on YTSeg reveal that AudioSeg substantially outperforms text-based approaches, pauses provide the largest acoustic gains, and MLLMs remain limited by context length and weak instruction following, yet MLLMs are promising on shorter audio.

---

### Distributionally Robust Optimization via Generative Ambiguity Modeling

Authors: Jiaqi Wen, Jianyi Yang
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08976v1

This paper studies Distributionally Robust Optimization (DRO), a fundamental framework for enhancing the robustness and generalization of statistical learning and optimization. An effective ambiguity set for DRO must involve distributions that remain consistent to the nominal distribution while being diverse enough to account for a variety of potential scenarios. Moreover, it should lead to tractable DRO solutions. To this end, we propose generative model-based ambiguity sets that capture various adversarial distributions beyond the nominal support space while maintaining consistency with the nominal distribution. Building on this generative ambiguity modeling, we propose DRO with Generative Ambiguity Set (GAS-DRO), a tractable DRO algorithm that solves the inner maximization over the parameterized generative model space. We formally establish the stationary convergence performance of GAS-DRO. We implement GAS-DRO with a diffusion model and empirically demonstrate its superior Out-of-Distribution (OOD) generalization performance in ML tasks.

---

### WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models

Authors: Yu Shang, Zhuohang Li, Yiding Ma, Weikang Su, Xin Jin, Ziyou Wang, Lei Jin, Xin Zhang, Yinzhou Tang, Haisheng Su, Chen Gao, Wei Wu et al.
Published: 2026-02-09
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.08971v2

While world models have emerged as a cornerstone of embodied intelligence by enabling agents to reason about environmental dynamics through action-conditioned prediction, their evaluation remains fragmented. Current evaluation of embodied world models has largely focused on perceptual fidelity (e.g., video generation quality), overlooking the functional utility of these models in downstream decision-making tasks. In this work, we introduce WorldArena, a unified benchmark designed to systematically evaluate embodied world models across both perceptual and functional dimensions. WorldArena assesses models through three dimensions: video perception quality, measured with 16 metrics across six sub-dimensions; embodied task functionality, which evaluates world models as data engines, policy evaluators, and action planners integrating with subjective human evaluation. Furthermore, we propose EWMScore, a holistic metric integrating multi-dimensional performance into a single interpretable index. Through extensive experiments on 14 representative models, we reveal a significant perception-functionality gap, showing that high visual quality does not necessarily translate into strong embodied task capability. WorldArena benchmark with the public leaderboard is released at https://world-arena.ai, providing a framework for tracking progress toward truly functional world models in embodied AI.

---

### stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation

Authors: Lucas Maes, Quentin Le Lidec, Dan Haramati, Nassim Massaudi, Damien Scieur, Yann LeCun, Randall Balestriero
Published: 2026-02-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.08968v2

World Models have emerged as a powerful paradigm for learning compact, predictive representations of environment dynamics, enabling agents to reason, plan, and generalize beyond direct experience. Despite recent interest in World Models, most available implementations remain publication-specific, severely limiting their reusability, increasing the risk of bugs, and reducing evaluation standardization. To mitigate these issues, we introduce stable-worldmodel (SWM), a modular, tested, and documented world-model research ecosystem that provides efficient data-collection tools, standardized environments, planning algorithms, and baseline implementations. In addition, each environment in SWM enables controllable factors of variation, including visual and physical properties, to support robustness and continual learning research. Finally, we demonstrate the utility of SWM by using it to study zero-shot robustness in DINO-WM.

---

### Learning to Coordinate via Quantum Entanglement in Multi-Agent Reinforcement Learning

Authors: John Gardiner, Orlando Romero, Brendan Tivnan, Nicolò Dal Fabbro, George J. Pappas
Published: 2026-02-09
Categories: cs.MA, cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2602.08965v2

The inability to communicate poses a major challenge to coordination in multi-agent reinforcement learning (MARL). Prior work has explored correlating local policies via shared randomness, sometimes in the form of a correlation device, as a mechanism to assist in decentralized decision-making. In contrast, this work introduces the first framework for training MARL agents to exploit shared quantum entanglement as a coordination resource, which permits a larger class of communication-free correlated policies than shared randomness alone. This is motivated by well-known results in quantum physics which posit that, for certain single-round cooperative games with no communication, shared quantum entanglement enables strategies that outperform those that only use shared randomness. In such cases, we say that there is quantum advantage. Our framework is based on a novel differentiable policy parameterization that enables optimization over quantum measurements, together with a novel policy architecture that decomposes joint policies into a quantum coordinator and decentralized local actors. To illustrate the effectiveness of our proposed method, we first show that we can learn, purely from experience, strategies that attain quantum advantage in single-round games that are treated as black box oracles. We then demonstrate how our machinery can learn policies with quantum advantage in an illustrative multi-agent sequential decision-making problem formulated as a decentralized partially observable Markov decision process (Dec-POMDP).

---

### A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents

Authors: Raghu Arghal, Fade Chen, Niall Dalton, Evgenii Kortukov, Calum McNamara, Angelos Nalmpantis, Moksh Nirvaan, Gabriele Sarti, Mario Giulianelli
Published: 2026-02-09
Categories: cs.LG, cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2602.08964v2

Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a framework for evaluating goal-directedness that integrates behavioural evaluation with interpretability-based analyses of models' internal representations. As a case study, we examine an LLM agent navigating a 2D grid world towards a goal state. Behaviourally, we evaluate the agent against optimal policies across varying grid sizes, obstacle densities, and goal structures, finding that performance scales with task difficulty while remaining robust to difficulty-preserving transformations and multi-goal structures. We then use probing methods to decode internal representations of the environment and multi-step action plans. We find that the LLM agent non-linearly encodes a coarse spatial map, preserving approximate task-relevant cues about its position and the goal location; that its actions are broadly consistent with these internal representations; and that reasoning reorganises them, shifting from spatial cues towards immediate action selection. Our findings support the view that introspective examination is required beyond behavioural evaluations to characterise how agents represent and pursue their objectives.

---

### Modeling 3D Pedestrian-Vehicle Interactions for Vehicle-Conditioned Pose Forecasting

Authors: Guangxun Zhu, Xuan Liu, Nicolas Pugeault, Chongfeng Wei, Edmond S. L. Ho
Published: 2026-02-09
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.08962v1

Accurately predicting pedestrian motion is crucial for safe and reliable autonomous driving in complex urban environments. In this work, we present a 3D vehicle-conditioned pedestrian pose forecasting framework that explicitly incorporates surrounding vehicle information. To support this, we enhance the Waymo-3DSkelMo dataset with aligned 3D vehicle bounding boxes, enabling realistic modeling of multi-agent pedestrian-vehicle interactions. We introduce a sampling scheme to categorize scenes by pedestrian and vehicle count, facilitating training across varying interaction complexities. Our proposed network adapts the TBIFormer architecture with a dedicated vehicle encoder and pedestrian-vehicle interaction cross-attention module to fuse pedestrian and vehicle features, allowing predictions to be conditioned on both historical pedestrian motion and surrounding vehicles. Extensive experiments demonstrate substantial improvements in forecasting accuracy and validate different approaches for modeling pedestrian-vehicle interactions, highlighting the importance of vehicle-aware 3D pose prediction for autonomous driving. Code is available at: https://github.com/GuangxunZhu/VehCondPose3D

---

### MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE

Authors: Ruijie Zhu, Jiahao Lu, Wenbo Hu, Xiaoguang Han, Jianfei Cai, Ying Shan, Chuanxia Zheng
Published: 2026-02-09
Categories: cs.CV, cs.AI, cs.CG, cs.LG
arXiv: https://arxiv.org/abs/2602.08961v2

We present MotionCrafter, a framework that leverages video generators to jointly reconstruct 4D geometry and estimate dense motion from a monocular video. The key idea is a joint representation of dense 3D point maps and 3D scene flows in a shared coordinate system, together with a 4D VAE tailored to learn this representation effectively. Unlike prior work that strictly aligns 3D values and latents with RGB VAE latents-despite their fundamentally different distributions-we show that such alignment is unnecessary and can hurt performance. Instead, we propose a new data normalization and VAE training strategy that better transfers diffusion priors and greatly improves reconstruction quality. Extensive experiments on multiple datasets show that MotionCrafter achieves state-of-the-art performance in both geometry reconstruction and dense scene flow estimation, delivering 38.64% and 25.0% improvements in geometry and motion reconstruction, respectively, all without any post-optimization. Project page: https://ruijiezhu94.github.io/MotionCrafter_Page

---

### Grow with the Flow: 4D Reconstruction of Growing Plants with Gaussian Flow Fields

Authors: Weihan Luo, Lily Goli, Sherwin Bahmani, Felix Taubner, Andrea Tagliasacchi, David B. Lindell
Published: 2026-02-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.08958v3

Modeling the time-varying 3D appearance of plants during growth poses unique challenges: unlike most dynamic scenes, plants continuously generate new geometry as they expand, branch, and differentiate. Existing dynamic scene representations are ill-suited to this setting: deformation fields provide insufficient constraints to yield physically plausible scene dynamics, and 4D Gaussian splatting represents the same physical structures with different Gaussian primitives at different times, breaking temporal consistency. We introduce GrowFlow, a dynamic representation that couples 3D Gaussian primitives with a neural ordinary differential equation to model plant growth as a continuous flow field over geometric parameters (position, scale, and orientation). Our representation enables consistent appearance rendering and models nonlinear, continuous-time growth dynamics with full temporal correspondences for every primitive. To initialize a sufficient set of Gaussian primitives, we first reconstruct the mature plant and then learn a reverse-growth process, effectively simulating the plant's developmental history in reverse. GrowFlow achieves superior image quality and geometric coherence compared to prior methods on a new, multi-view timelapse dataset of plant growth, and provides the first temporally coherent representation for appearance modeling of growing 3D structures.

---

### How Should We Model the Probability of a Language?

Authors: Rasul Dent, Pedro Ortiz Suarez, Thibault Clérice, Benoît Sagot
Published: 2026-02-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.08951v1

Of the over 7,000 languages spoken in the world, commercial language identification (LID) systems only reliably identify a few hundred in written form. Research-grade systems extend this coverage under certain circumstances, but for most languages coverage remains patchy or nonexistent. This position paper argues that this situation is largely self-imposed. In particular, it arises from a persistent framing of LID as decontextualized text classification, which obscures the central role of prior probability estimation and is reinforced by institutional incentives that favor global, fixed-prior models. We argue that improving coverage for tail languages requires rethinking LID as a routing problem and developing principled ways to incorporate environmental cues that make languages locally plausible.

---

### Digital Twin and Agentic AI for Wild Fire Disaster Management: Intelligent Virtual Situation Room

Authors: Mohammad Morsali, Siavash H. Khajavi
Published: 2026-02-09
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.08949v1

According to the United Nations, wildfire frequency and intensity are projected to increase by approximately 14% by 2030 and 30% by 2050 due to global warming, posing critical threats to life, infrastructure, and ecosystems. Conventional disaster management frameworks rely on static simulations and passive data acquisition, hindering their ability to adapt to arbitrarily evolving wildfire episodes in real-time. To address these limitations, we introduce the Intelligent Virtual Situation Room (IVSR), a bidirectional Digital Twin (DT) platform augmented by autonomous AI agents. The IVSR continuously ingests multisource sensor imagery, weather data, and 3D forest models to create a live virtual replica of the fire environment. A similarity engine powered by AI aligns emerging conditions with a precomputed Disaster Simulation Library, retrieving and calibrating intervention tactics under the watchful eyes of experts. Authorized action-ranging from UAV redeployment to crew reallocation-is cycled back through standardized procedures to the physical layer, completing the loop between response and analysis. We validate IVSR through detailed case-study simulations provided by an industrial partner, demonstrating capabilities in localized incident detection, privacy-preserving playback, collider-based fire-spread projection, and site-specific ML retraining. Our results indicate marked reductions in detection-to-intervention latency and more effective resource coordination versus traditional systems. By uniting real-time bidirectional DTs with agentic AI, IVSR offers a scalable, semi-automated decision-support paradigm for proactive, adaptive wildfire disaster management.

---

### CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute

Authors: Chen Jin, Ryutaro Tanno, Tom Diethe, Philip Teare
Published: 2026-02-09
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.08948v1

Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided self-refinement method that achieves competitive accuracy using a fraction of the tokens via a lightweight 211k-parameter Conv1D controller atop a frozen LLM. The controller consumes full-trace confidence to decide whether to halt, re-examine, or try a different approach, enabling targeted self-correction with an average of 2.7 refinement steps per problem and roughly 190-fold token reduction relative to 512-sample baselines. Across diverse reasoning benchmarks and three open-source models, the controller achieves 92.6 percent precision when it confidently halts, indicating that confidence dynamics reliably signal correctness without ground-truth verification. We extend this to CoRefine-Tree, a hybrid sequential-parallel variant that adaptively balances exploration and exploitation, with easy serving integration and verifier compatibility. By treating confidence as a control signal rather than a correctness guarantee, CoRefine provides a modular primitive for scalable reasoning and agentic settings with imperfect verifiers.

---

### GitSearch: Enhancing Community Notes Generation with Gap-Informed Targeted Search

Authors: Sahajpreet Singh, Kokil Jaidka, Min-Yen Kan
Published: 2026-02-09
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2602.08945v1

Community-based moderation offers a scalable alternative to centralized fact-checking, yet it faces significant structural challenges, and existing AI-based methods fail in "cold start" scenarios. To tackle these challenges, we introduce GitSearch (Gap-Informed Targeted Search), a framework that treats human-perceived quality gaps, such as missing context, etc., as first-class signals. GitSearch has a three-stage pipeline: identifying information deficits, executing real-time targeted web-retrieval to resolve them, and synthesizing platform-compliant notes. To facilitate evaluation, we present PolBench, a benchmark of 78,698 U.S. political tweets with their associated Community Notes. We find GitSearch achieves 99% coverage, almost doubling coverage over the state-of-the-art. GitSearch surpasses human-authored helpful notes with a 69% win rate and superior helpfulness scores (3.87 vs. 3.36), demonstrating retrieval effectiveness that balanced the trade-off between scale and quality.

---

### pixelLOG: Logging of Online Gameplay for Cognitive Research

Authors: Zeyu Lu, Dennis L. Barbour
Published: 2026-02-09
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2602.08941v1

Traditional cognitive assessments often rely on isolated, output-focused measurements that may fail to capture the complexity of human cognition in naturalistic settings. We present pixelLOG, a high-performance data collection framework for Spigot-based Minecraft servers designed specifically for process-based cognitive research. Unlike existing frameworks tailored only for artificial intelligence agents, pixelLOG also enables human behavioral tracking in multi-player/multi-agent environments. Operating at configurable frequencies up to and exceeding 20 updates per second, the system captures comprehensive behavioral data through a hybrid approach of active state polling and passive event monitoring. By leveraging Spigot's extensible API, pixelLOG facilitates robust session isolation and produces structured JSON outputs integrable with standard analytical pipelines. This framework bridges the gap between decontextualized laboratory assessments and richer, more ecologically valid tasks, enabling high-resolution analysis of cognitive processes as they unfold in complex, virtual environments.

---

### CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs

Authors: Longling Geng, Andy Ouyang, Theodore Wu, Daphne Barretto, Matthew John Hayes, Rachael Cooper, Yuqiao Zeng, Sameer Vijay, Gia Ancone, Ankit Rai, Matthew Wolfman, Patrick Flanagan et al.
Published: 2026-02-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.08939v2

Large language models increasingly produce fluent causal explanations, yet they often fail in ways aggregate accuracy cannot diagnose: confusing association with intervention, abandoning correct judgments under pressure, over-refusing valid claims, or answering when evidence is underdetermined. We introduce CTK, a diagnostic benchmark of 5,147 cases and growing, across 10 domains and all three levels of Pearl's Ladder of Causation. Unlike benchmarks that only score correctness, CTK reveals why a model failed by annotating causal rung, trap type, pressure sensitivity, refusal quality, and Utility-Safety tradeoffs. Its Sheep/Wolf taxonomy separates valid causal designs from inferential traps; paired neutral/pressure variants measure sycophantic drift through Bad Flip Rate; and Wise Refusal fields test whether a model identifies the missing information needed before endorsing a claim. CTK exposes failure modes hidden by aggregate accuracy: the Skepticism Trap, Rung Collapse under scaling, pressure-induced drift, Detection-Correction gaps, and counterfactual error modes. Rather than prescribing a correction method, it provides the diagnostic substrate for studying causal-reasoning failure profiles.

---

### StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors

Authors: Suraj Ranganath, Atharv Ramesh
Published: 2026-02-09
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2602.08934v2

AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We introduce StealthRL, a reinforcement learning framework that stress-tests detector robustness under realistic adversarial conditions. StealthRL trains a paraphrase policy against a multi-detector ensemble using Group Relative Policy Optimization (GRPO) with LoRA adapters on Qwen3-4B, optimizing a composite reward that balances detector evasion with semantic preservation. We evaluate six attack settings (M0-M5) on the full filtered MAGE test pool (15,310 human / 14,656 AI) against four detectors: RoBERTa, Fast-DetectGPT, Binoculars, and MAGE. StealthRL achieves near-zero detection on three of the four detectors and a 0.024 mean TPR@1%FPR, reducing mean AUROC from 0.79 to 0.43 and attaining a 97.6% attack success rate. Critically, attacks transfer to two held-out detectors not seen during training, revealing shared architectural vulnerabilities rather than detector-specific brittleness. We additionally conduct LLM-based quality evaluation via Likert scoring on 500 matched samples per method, analyze detector score distributions to explain why evasion succeeds, and provide per-detector AUROC with bootstrap confidence intervals. Our results expose significant robustness gaps in current AI-text detection and establish StealthRL as a principled adversarial evaluation protocol. Code and evaluation pipeline are publicly available at https://github.com/suraj-ranganath/StealthRL.

---

### Provably robust learning of regression neural networks using $β$-divergences

Authors: Abhik Ghosh, Suryasis Jana
Published: 2026-02-09
Categories: stat.ML, cs.LG, cs.NE, stat.ME
arXiv: https://arxiv.org/abs/2602.08933v1

Regression neural networks (NNs) are most commonly trained by minimizing the mean squared prediction error, which is highly sensitive to outliers and data contamination. Existing robust training methods for regression NNs are often limited in scope and rely primarily on empirical validation, with only a few offering partial theoretical guarantees. In this paper, we propose a new robust learning framework for regression NNs based on the $β$-divergence (also known as the density power divergence) which we call `rRNet'. It applies to a broad class of regression NNs, including models with non-smooth activation functions and error densities, and recovers the classical maximum likelihood learning as a special case. The rRNet is implemented via an alternating optimization scheme, for which we establish convergence guarantees to stationary points under mild, verifiable conditions. The (local) robustness of rRNet is theoretically characterized through the influence functions of both the parameter estimates and the resulting rRNet predictor, which are shown to be bounded for suitable choices of the tuning parameter $β$, depending on the error density. We further prove that rRNet attains the optimal 50\% asymptotic breakdown point at the assumed model for all $β\in(0, 1)$, providing a strong global robustness guarantee that is largely absent for existing NN learning methods. Our theoretical results are complemented by simulation experiments and real-data analyses, illustrating practical advantages of rRNet over existing approaches in both function approximation problems and prediction tasks with noisy observations.

---

### Online monotone density estimation and log-optimal calibration

Authors: Rohan Hore, Ruodu Wang, Aaditya Ramdas
Published: 2026-02-09
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2602.08927v3

We study the problem of online monotone density estimation, where density estimators must be constructed in a predictable manner from sequentially observed data. We propose two online estimators: an online analogue of the classical Grenander estimator, and an expert aggregation estimator inspired by exponential weighting methods from the online learning literature. In the well-specified stochastic setting, where the underlying density is monotone, we show that the expected cumulative log-likelihood gap between the online estimators and the true density admits an $O(n^{1/3})$ bound. We further establish a $\sqrt{n\log{n}}$ pathwise regret bound for the expert aggregation estimator relative to the best offline monotone estimator chosen in hindsight, under minimal regularity assumptions on the observed sequence. As an application of independent interest, we show that the problem of constructing log-optimal p-to-e calibrators for sequential hypothesis testing can be formulated as an online monotone density estimation problem. We adapt the proposed estimators to build empirically adaptive p-to-e calibrators and establish their optimality. Numerical experiments illustrate the theoretical results.

---

### DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce

Authors: Wenchen Han, Shay Vargaftik, Michael Mitzenmacher, Ran Ben Basat
Published: 2026-02-09
Categories: cs.LG, cs.DC, cs.NI
arXiv: https://arxiv.org/abs/2602.08923v3

Multi-hop all-reduce is the de facto backbone of large model training. As the training scale increases, the network often becomes a bottleneck, motivating the reduction of the volume of transmitted data. Accordingly, recent systems have demonstrated significant acceleration of the training process using gradient quantization. However, these systems are not optimized for multi-hop aggregation, where entries are partially summed multiple times along their aggregation topology. We present DynamiQ, a quantization framework that bridges the gap between quantization best practices and multi-hop aggregation. DynamiQ introduces novel techniques to better represent partial sums, codesigned with a decompress accumulate recompress fused kernel to facilitate fast execution. We extend PyTorch DDP to support DynamiQ over NCCL P2P, and across different LLMs, tasks, and scales, we demonstrate consistent improvement of up to 34.2% over the best among state-of-the-art methods such as Omni-Reduce, THC, and emerging standards such as MXFP4, MXFP6, and MXFP8. Further, DynamiQ is the only evaluated method that consistently reaches near-baseline accuracy (e.g., 99.9\% of the BF16 baseline) and does so while significantly accelerating the training.

---

### Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration

Authors: Manh Cuong Dao, Quang Hung Pham, Phi Le Nguyen, Thao Nguyen Truong, Bryan Kian Hsiang Low, Trong Nghia Hoang
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08920v3

Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre-trained transformers do not have a principled mechanism for uncertainty propagation through their feature transformation stack. In this work, we propose a diffusion-inspired reconfiguration of transformers in which each feature transformation block is modeled as a probabilistic mapping. Composing these probabilistic mappings reveals a probability path that mimics the structure of a diffusion process, transporting data mass from the input distribution to the pre-trained feature distribution. This probability path can then be recompiled on a diffusion process with a unified transition model to enable principled propagation of representation uncertainty throughout the pre-trained model's architecture while maintaining its original predictive performance. Empirical results across a variety of vision and language benchmarks demonstrate that our method achieves superior calibration and predictive accuracy compared to existing uncertainty-aware transformers.

---

### Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration

Authors: Manh Cuong Dao, Quang Hung Pham, Phi Le Nguyen, Thao Nguyen Truong, Bryan Kian Hsiang Low, Trong Nghia Hoang
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08920v2

Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre-trained transformers do not have a principled mechanism for uncertainty propagation through their feature transformation stack. In this work, we propose a diffusion-inspired reconfiguration of transformers in which each feature transformation block is modeled as a probabilistic mapping. Composing these probabilistic mappings reveals a probability path that mimics the structure of a diffusion process, transporting data mass from the input distribution to the pre-trained feature distribution. This probability path can then be recompiled on a diffusion process with a unified transition model to enable principled propagation of representation uncertainty throughout the pre-trained model's architecture while maintaining its original predictive performance. Empirical results across a variety of vision and language benchmarks demonstrate that our method achieves superior calibration and predictive accuracy compared to existing uncertainty-aware transformers.

---

### Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion

Authors: Minghan Li, Ercong Nie, Siqi Zhao, Tongna Chen, Huiping Huang, Guodong Zhou
Published: 2026-02-09
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.08917v2

Query expansion with large language models is promising but often relies on hand-crafted prompts, manually chosen exemplars, or a single LLM, making it non-scalable and sensitive to domain shift. We present an automated, domain-adaptive QE framework that builds in-domain exemplar pools by harvesting pseudo-relevant passages using a BM25-MonoT5 pipeline. A training-free cluster-based strategy selects diverse demonstrations, yielding strong and stable in-context QE without supervision. To further exploit model complementarity, we introduce a two-LLM ensemble in which two heterogeneous LLMs independently generate expansions and a refinement LLM consolidates them into one coherent expansion. Across TREC DL20, DBPedia, and SciFact, the refined ensemble delivers consistent and statistically significant gains over BM25, Rocchio, zero-shot, and fixed few-shot baselines. The framework offers a reproducible testbed for exemplar selection and multi-LLM generation, and a practical, label-free solution for real-world QE.

---

### AMS-HD: Hyperdimensional Computing for Real-Time and Energy-Efficient Acute Mountain Sickness Detection

Authors: Abu Masum, Mehran Moghadam, M. Hassan Najafi, Bige Unluturk, Ulkuhan Guler, Beth A. Beidleman, Sercan Aygun
Published: 2026-02-09
Categories: cs.SC, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2602.08916v3

Objective: Acute mountain sickness (AMS) is the most prevalent altitude illness, affecting unacclimatized individuals ascending above 2,500 m and potentially escalating to life threatening cerebral or pulmonary edema. Conventional machine learning (ML) methods for AMS detection from wearable physiological signals often fail to meet real-time hardware efficiency requirements of continuous monitoring. Methods: We present AMS-HD, the first hyperdimensional computing (HDC)-based framework for real-time AMS detection, spanning high-level bipolar (-1/+1) computing for mobile platforms and low-level binary (0/1) computing for FPGA and ASIC targets. The framework integrates mutual information feature selection, hypervector encoding, and positional projection to enhance classification efficiency. Validation spans ARM, FPGA, and smartwatch-smartphone platforms using wearable-accessible SpO2 and heart rate signals. Results: AMS-HD matches or outperforms SVM and MLP baselines in both binary and multiclass classification, achieving up to 91% accuracy and 90% F1-score in binary classification, and up to 85% accuracy on external AMS-related datasets. On FPGA, AMS-HD reduces LUT and flip-flop usage by 7.3x and 5.8x, while consuming 3.9x less power than MLP. On mobile platforms, AMS-HD requires only 1% battery per session, 60 Bytes of memory, and 2.50 ms inference time -- approximately 2x and more than 3x lower energy consumption than SVM and MLP. Conclusion: AMS-HD provides a scalable, hardware-aware alternative to conventional ML for real-time AMS monitoring, achieving competitive performance with substantially lower resource consumption. Significance: This work presents the first complete HDC framework for altitude sickness detection, bridging wearable inference and low-level hardware deployment for resource-constrained health monitoring.

---

### Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Tasks

Authors: Kiyosu Maeda, William P. McCarthy, Ching-Yi Tsai, Jeffrey Mu, Haoliang Wang, Robert D. Hawkins, Judith E. Fan, Parastoo Abtahi
Published: 2026-02-09
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2602.08914v1

A quintessential feature of human intelligence is the ability to create ad hoc conventions over time to achieve shared goals efficiently. We investigate how communication strategies evolve through repeated collaboration as people coordinate on shared procedural abstractions. To this end, we conducted an online unimodal study (n = 98) using natural language to probe abstraction hierarchies. In a follow-up lab study (n = 40), we examined how multimodal communication (speech and gestures) changed during physical collaboration. Pairs used augmented reality to isolate their partner's hand and voice; one participant viewed a 3D virtual tower and sent instructions to the other, who built the physical tower. Participants became faster and more accurate by establishing linguistic and gestural abstractions and using cross-modal redundancy to emphasize key changes from previous interactions. Based on these findings, we extend probabilistic models of convention formation to multimodal settings, capturing shifts in modality preferences. Our findings and model provide building blocks for designing convention-aware intelligent agents situated in the physical world.

---

### GEMSS: A Variational Method for Discovering Multiple Sparse Solutions in Classification and Regression Problems

Authors: Kateřina Henclová, Václav Šmídl
Published: 2026-02-09
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.08913v3

In underdetermined regression and classification problems, multiple feature subsets often yield equivalent predictive performance. In applied settings, especially with $n \ll p$, high dimension or collinearities, it is valuable to provide a domain expert with a menu of statistically plausible explanations, rather than one arbitrary solution. This creates the need for appropriate methods. We present Gaussian Ensemble for Multiple Sparse Solutions (GEMSS), a method that uses a single variational mixture to approximate the corresponding multimodal posterior. Its evidence lower bound contains a built-in repulsion between the mixture's components, enabling the model to simultaneously produce several distinct sparse solutions. We evaluate GEMSS on a novel, reusable benchmark. The ground-truth solution set and its structure are known by construction and set-level recovery metrics are evaluated. GEMSS consistently outperforms dedicated multiplicity methods (Enumeration LASSO, ALFESE), two strong sampling baselines that approximate the same posterior (Randomized-LASSO ensemble, BB-SSL), and naive iterative masking. As solutions' overlap increases, the gap widens and additional ensemble restarts cannot close it. Only ALFESE proves competitive. Further, GEMSS is validated on real-world datasets, producing multiple distinct and highly predictive solutions: the practical goal that existing methods struggle to meet. The open-source Python package 'gemss' is available (github.com/kat-er-ina/gemss) and democratized through a free online application at huggingface.co/spaces/kat-er-ina/gemss.

---

### Analysis of Converged 3D Gaussian Splatting Solutions: Density Effects and Prediction Limit

Authors: Zhendong Wang, Cihan Ruan, Jingchuan Xiao, Chuqing Shi, Wei Jiang, Wei Wang, Wenjie Liu, Nam Ling
Published: 2026-02-09
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.08909v1

We investigate what structure emerges in 3D Gaussian Splatting (3DGS) solutions from standard multi-view optimization. We term these Rendering-Optimal References (RORs) and analyze their statistical properties, revealing stable patterns: mixture-structured scales and bimodal radiance across diverse scenes. To understand what determines these parameters, we apply learnability probes by training predictors to reconstruct RORs from point clouds without rendering supervision. Our analysis uncovers fundamental density-stratification. Dense regions exhibit geometry-correlated parameters amenable to render-free prediction, while sparse regions show systematic failure across architectures. We formalize this through variance decomposition, demonstrating that visibility heterogeneity creates covariance-dominated coupling between geometric and appearance parameters in sparse regions. This reveals the dual character of RORs: geometric primitives where point clouds suffice, and view synthesis primitives where multi-view constraints are essential. We provide density-aware strategies that improve training robustness and discuss architectural implications for systems that adaptively balance feed-forward prediction and rendering-based refinement.

---

### Positive Distribution Shift as a Framework for Understanding Tractable Learning

Authors: Marko Medvedev, Idan Attias, Elisabetta Cornacchia, Theodor Misiakiewicz, Gal Vardi, Nathan Srebro
Published: 2026-02-09
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.08907v2

We study a setting where the goal is to learn a target function f(x) with respect to a target distribution D(x), but training is done on i.i.d. samples from a different training distribution D'(x), labeled by the true target f(x). Such a distribution shift (here in the form of covariate shift) is usually viewed negatively, as hurting or making learning harder, and the traditional distribution shift literature is mostly concerned with limiting or avoiding this negative effect. In contrast, we argue that with a well-chosen D'(x), the shift can be positive and make learning easier -- a perspective called Positive Distribution Shift (PDS). Such a perspective is central to contemporary machine learning, where much of the innovation is in finding good training distributions D'(x), rather than changing the training algorithm. We further argue that the benefit is often computational rather than statistical, and that PDS allows computationally hard problems to become tractable even using standard gradient-based training. We formalize different variants of PDS, show how certain hard classes are easily learnable under PDS, and make connections with membership query learning.

---

### Efficient and Stable Reinforcement Learning for Diffusion Language Models

Authors: Jiawei Liu, Xiting Wang, Yuanyuan Zhong, Defu Lian, Yu Yang
Published: 2026-02-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.08905v1

Reinforcement Learning (RL) is crucial for unlocking the complex reasoning capabilities of Diffusion-based Large Language Models (dLLMs). However, applying RL to dLLMs faces unique challenges in efficiency and stability. To address these challenges, we propose Spatio-Temporal Pruning (STP), a framework designed to simultaneously improve the efficiency and stability of RL for dLLMs. STP compresses the redundancy in the generative process through: (1) \textit{spatial pruning}, which constrains the exploration space using static priors; and (2) \textit{temporal pruning}, which bypasses redundant late-stage refinement steps. Our theoretical analysis demonstrates that STP strictly reduces the variance of the log-likelihood estimation, thereby ensuring more stable policy updates. Extensive experiments demonstrate that STP surpasses state-of-the-art baselines in both efficiency and accuracy. Our code is available at https://github.com/Lolo1222/STP.

---

### GSS: Gated Subspace Steering for Selective Memorization Mitigation in LLMs

Authors: Xuanqi Zhang, Haoyang Shang, Xiaoxiao Li
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08901v1

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the majority of tokens that generalize normally. We show empirically that memorization is sparse, intermittent, and token-conditioned, suggesting that effective mitigation requires context-aware intervention rather than static parameter modification. To this end, we propose a novel and effective selective memorization mitigation method -- Gated Subspace Steering (GSS), which decomposes intervention into a probe (detecting memorization-relevant activations) and a steer (applying targeted correction only when the probe exceeds a threshold). The optimal probe-steer pair emerges from a principled optimization framework based on optimal subspace steering. Experiments on four benchmarks show GSS matches or exceeds state-of-the-art memorization reduction while requiring $100-1000 \times$ less compute than optimization-based alternatives. Furthermore, we provide new theoretical insights into the geometry of memorization in neural representations.

---

### OmniReview: A Large-scale Benchmark and LLM-enhanced Framework for Realistic Reviewer Recommendation

Authors: Yehua Huang, Penglei Sun, Zebin Chen, Zhenheng Tang, Xiaowen Chu
Published: 2026-02-09
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.08896v1

Academic peer review remains the cornerstone of scholarly validation, yet the field faces some challenges in data and methods. From the data perspective, existing research is hindered by the scarcity of large-scale, verified benchmarks and oversimplified evaluation metrics that fail to reflect real-world editorial workflows. To bridge this gap, we present OmniReview, a comprehensive dataset constructed by integrating multi-source academic platforms encompassing comprehensive scholarly profiles through the disambiguation pipeline, yielding 202, 756 verified review records. Based on this data, we introduce a three-tier hierarchical evaluaion framework to assess recommendations from recall to precise expert identification. From the method perspective, existing embedding-based approaches suffer from the information bottleneck of semantic compression and limited interpretability. To resolve these method limitations, we propose Profiling Scholars with Multi-gate Mixture-of-Experts (Pro-MMoE), a novel framework that synergizes Large Language Models (LLMs) with Multi-task Learning. Specifically, it utilizes LLM-generated semantic profiles to preserve fine-grained expertise nuances and interpretability, while employing a Task-Adaptive MMoE architecture to dynamically balance conflicting evaluation goals. Comprehensive experiments demonstrate that Pro-MMoE achieves state-of-the-art performance across six of seven metrics, establishing a new benchmark for realistic reviewer recommendation.

---

### Discrete Bridges for Mutual Information Estimation

Authors: Iryna Zabarianska, Sergei Kholkin, Grigoriy Ksenofontov, Ivan Butakov, Alexander Korotin
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08894v1

Diffusion bridge models in both continuous and discrete state spaces have recently become powerful tools in the field of generative modeling. In this work, we leverage the discrete state space formulation of bridge matching models to address another important problem in machine learning and information theory: the estimation of the mutual information (MI) between discrete random variables. By neatly framing MI estimation as a domain transfer problem, we construct a Discrete Bridge Mutual Information (DBMI) estimator suitable for discrete data, which poses difficulties for conventional MI estimators. We showcase the performance of our estimator on two MI estimation settings: low-dimensional and image-based.

---

### Winner's Curse Drives False Promises in Data-Driven Decisions: A Case Study in Refugee Matching

Authors: Hamsa Bastani, Osbert Bastani, Bryce McLaughlin
Published: 2026-02-09
Categories: stat.ML, cs.LG, econ.EM
arXiv: https://arxiv.org/abs/2602.08892v1

A major challenge in data-driven decision-making is accurate policy evaluation-i.e., guaranteeing that a learned decision-making policy achieves the promised benefits. A popular strategy is model-based policy evaluation, which estimates a model from data to infer counterfactual outcomes. This strategy is known to produce unwarrantedly optimistic estimates of the true benefit due to the winner's curse. We searched the recent literature on data-driven decision-making, identifying a sample of 55 papers published in the Management Science in the past decade; all but two relied on this flawed methodology. Several common justifications are provided: (1) the estimated models are accurate, stable, and well-calibrated, (2) the historical data uses random treatment assignment, (3) the model family is well-specified, and (4) the evaluation methodology uses sample splitting. Unfortunately, we show that no combination of these justifications avoids the winner's curse. First, we provide a theoretical analysis demonstrating that the winner's curse can cause large, spurious reported benefits even when all these justifications hold. Second, we perform a simulation study based on the recent and consequential data-driven refugee matching problem. We construct a synthetic refugee matching environment (calibrated to closely match the real setting) but designed so that no assignment policy can improve expected employment compared to random assignment. Model-based methods report large, stable gains of around 60% even when the true effect is zero; these gains are on par with improvements of 22-75% reported in the literature. Our results provide strong evidence against model-based evaluation.

---

### Scalable Delphi: Large Language Models for Structured Risk Estimation

Authors: Tobias Lorenz, Mario Fritz
Published: 2026-02-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.08889v1

Quantitative risk assessment in high-stakes domains relies on structured expert elicitation to estimate unobservable properties. The gold standard - the Delphi method - produces calibrated, auditable judgments but requires months of coordination and specialist time, placing rigorous risk assessment out of reach for most applications. We investigate whether Large Language Models (LLMs) can serve as scalable proxies for structured expert elicitation. We propose Scalable Delphi, adapting the classical protocol for LLMs with diverse expert personas, iterative refinement, and rationale sharing. Because target quantities are typically unobservable, we develop an evaluation framework based on necessary conditions: calibration against verifiable proxies, sensitivity to evidence, and alignment with human expert judgment. We evaluate in the domain of AI-augmented cybersecurity risk, using three capability benchmarks and independent human elicitation studies. LLM panels achieve strong correlations with benchmark ground truth (Pearson r=0.87-0.95), improve systematically as evidence is added, and align with human expert panels - in one comparison, closer to a human panel than the two human panels are to each other. This demonstrates that LLM-based elicitation can extend structured expert judgment to settings where traditional methods are infeasible, reducing elicitation time from months to minutes.

---

### DeepQuali: Initial results of a study on the use of large language models for assessing the quality of user stories

Authors: Adam Trendowicz, Daniel Seifert, Andreas Jedlitschka, Marcus Ciolkowski, Anton Strahilov
Published: 2026-02-09
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.08887v1

Generative artificial intelligence (GAI), specifically large language models (LLMs), are increasingly used in software engineering, mainly for coding tasks. However, requirements engineering - particularly requirements validation - has seen limited application of GAI. The current focus of using GAI for requirements is on eliciting, transforming, and classifying requirements, not on quality assessment. We propose and evaluate the LLM-based (GPT-4o) approach "DeepQuali", for assessing and improving requirements quality in agile software development. We applied it to projects in two small companies, where we compared LLM-based quality assessments with expert judgments. Experts also participated in walkthroughs of the solution, provided feedback, and rated their acceptance of the approach. Experts largely agreed with the LLM's quality assessments, especially regarding overall ratings and explanations. However, they did not always agree with the other experts on detailed ratings, suggesting that expertise and experience may influence judgments. Experts recognized the usefulness of the approach but criticized the lack of integration into their workflow. LLMs show potential in supporting software engineers with the quality assessment and improvement of requirements. The explicit use of quality models and explanatory feedback increases acceptance.

---

### Contrastive Learning for Diversity-Aware Product Recommendations in Retail

Authors: Vasileios Karlis, Ezgi Yıldırım, David Vos, Maarten de Rijke
Published: 2026-02-09
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2602.08886v1

Recommender systems often struggle with long-tail distributions and limited item catalog exposure, where a small subset of popular items dominates recommendations. This challenge is especially critical in large-scale online retail settings with extensive and diverse product assortments. This paper introduces an approach to enhance catalog coverage without compromising recommendation quality in the existing digital recommendation pipeline at IKEA Retail. Drawing inspiration from recent advances in negative sampling to address popularity bias, we integrate contrastive learning with carefully selected negative samples. Through offline and online evaluations, we demonstrate that our method improves catalog coverage, ensuring a more diverse set of recommendations yet preserving strong recommendation performance.

---

### Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression

Authors: Paul Saegert, Ullrich Köthe
Published: 2026-02-09
Categories: cs.LG, cs.AI, cs.SC
arXiv: https://arxiv.org/abs/2602.08885v5

Symbolic regression (SR) aims to discover interpretable analytical expressions that accurately describe observed data. Amortized SR promises to be much more efficient than the predominant genetic programming SR methods, but currently struggles to scale to realistic scientific complexity. We find that a key obstacle is the lack of a fast reduction of equivalent expressions to a concise normalized form. Amortized SR has addressed this with general-purpose Computer Algebra Systems (CAS) like SymPy, but the high computational cost severely limits training and inference speed. We propose SimpliPy, a rule-based simplification engine achieving a 100-fold speed-up over SymPy at comparable quality. This enables substantial improvements in amortized SR, including scalability to much larger training sets, more efficient use of the per-expression token budget, and systematic training set decontamination with respect to equivalent test expressions. We demonstrate these advantages in our Flash-ANSR framework, which achieves much better accuracy than amortized baselines (NeSymReS, E2E) on the FastSRB benchmark. Moreover, it performs on par with state-of-the-art direct optimization (PySR) while recovering more concise rather than more complex expressions with increasing inference budget.

---

### Designing Multi-Robot Ground Video Sensemaking with Public Safety Professionals

Authors: Puqi Zhou, Ali Asgarov, Aafiya Hussain, Wonjoon Park, Amit Paudyal, Sameep Shrestha, Chia-wei Tang, Michael F. Lighthiser, Michael R. Hieb, Xuesu Xiao, Chris Thomas, Sungsoo Ray Hong
Published: 2026-02-09
Categories: cs.HC, cs.CV
arXiv: https://arxiv.org/abs/2602.08882v2

Videos from fleets of ground robots can advance public safety by providing scalable situational awareness and reducing professionals' burden. Yet little is known about how to design and integrate multi-robot videos into public safety workflows. Collaborating with six police agencies, we examined how such videos could be made practical. In Study 1, we presented the first testbed for multi-robot ground video sensemaking. The testbed includes 38 events-of-interest (EoI) relevant to public safety, a dataset of 20 robot patrol videos (10 day/night pairs) covering EoI types, and 6 design requirements aimed at improving current video sensemaking practices. In Study 2, we built MRVS, a tool that augments multi-robot patrol video streams with a prompt-engineered video understanding model. Participants reported reduced manual workload and greater confidence with LLM-based explanations, while noting concerns about false alarms and privacy. We conclude with implications for designing future multi-robot video sensemaking tools.

---

### Differentiable Logical Programming for Quantum Circuit Discovery and Optimization

Authors: Antonin Sulc
Published: 2026-02-09
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2602.08880v2

Designing high-fidelity quantum circuits remains challenging, and current paradigms often depend on heuristic, fixed-ansatz structures or rule-based compilers that can be suboptimal or lack generality. We introduce a neuro-symbolic framework that reframes quantum circuit design as a differentiable logic programming problem. Our model represents a scaffold of potential quantum gates and parameterized operations as a set of learnable, continuous ``truth values'' or ``switches,'' $s \in (0, 1)^N$. These switches are optimized via standard gradient descent to satisfy a user-defined set of differentiable, logical axioms (e.g., correctness, simplicity, robustness). We provide a theoretical formulation bridging continuous logic (via T-norms) and unitary evolution (via geodesic interpolation), while addressing the barren plateau problem through biased initialization. We illustrate the approach on tasks including discovery of a 4-qubit Quantum Fourier Transform (QFT) from a scaffold of 21 candidate gates. We also report hardware-aware adaptation experiments on the 156-qubit IBM Fez processor, where the method autonomously adapted to both gradual noise drift (24.2~pp over static baseline) and catastrophic hardware failure (46.7~pp post-failure improvement), using only measurement-driven gradient updates with no hardwired bias or prior path preference

---

### Learning Potentials for Dynamic Matching and Application to Heart Transplantation

Authors: Itai Zilberstein, Ioannis Anagnostides, Zachary W. Sollie, Arman Kilic, Tuomas Sandholm
Published: 2026-02-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.08878v1

Each year, thousands of patients in need of heart transplants face life-threatening wait times due to organ scarcity. While allocation policies aim to maximize population-level outcomes, current approaches often fail to account for the dynamic arrival of organs and the composition of waitlisted candidates, thereby hampering efficiency. The United States is transitioning from rigid, rule-based allocation to more flexible data-driven models. In this paper, we propose a novel framework for non-myopic policy optimization in general online matching relying on potentials, a concept originally introduced for kidney exchange. We develop scalable and accurate ways of learning potentials that are higher-dimensional and more expressive than prior approaches. Our approach is a form of self-supervised imitation learning: the potentials are trained to mimic an omniscient algorithm that has perfect foresight. We focus on the application of heart transplant allocation and demonstrate, using real historical data, that our policies significantly outperform prior approaches -- including the current US status quo policy and the proposed continuous distribution framework -- in optimizing for population-level outcomes. Our analysis and methods come at a pivotal moment in US policy, as the current heart transplant allocation system is under review. We propose a scalable and theoretically grounded path toward more effective organ allocation.

---

### Stress-Testing Alignment Audits With Prompt-Level Strategic Deception

Authors: Oliver Daniels, Perusha Moodley, Benjamin M. Marlin, David Lindner
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08877v2

Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been systematically stress-tested against deception strategies. We address this gap, implementing an automatic red-team pipeline that generates deception strategies (in the form of system prompts) tailored to specific white-box and black-box auditing methods. Stress-testing assistant prefills, user persona sampling, sparse autoencoders, and token embedding similarity methods against secret-keeping model organisms, our automatic red-team pipeline finds prompts that deceive both the black-box and white-box methods into confident, incorrect guesses. Our results provide the first documented evidence of activation-based strategic deception, and suggest that current black-box and white-box methods would not be robust to a sufficiently capable misaligned model.

---

### Do Reasoning LLMs Refuse What They Infer in Long Contexts?

Authors: Yu Fu, Haz Sameen Shahgir, Huanli Gong, Zhipeng Wei, N. Benjamin Erichson, Yue Dong
Published: 2026-02-09
Categories: cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2602.08874v2

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed across a context and become visible only after the model composes the relevant pieces. Existing safety evaluations mostly test explicit harmful requests, and therefore miss this failure mode. We introduce compositional reasoning attacks, a long-context threat model in which harmful requests are decomposed into semantically incomplete fragments and embedded in long contexts. The final query is neutral; the harmful objective emerges only if the model retrieves the fragments, composes them, and infers the implied goal. We instantiate this setting using AdvBench requests, varying the required reasoning from Direct Retrieval to Single-hop Aggregation, Chain Reasoning, and Multi-hop Deductive Reasoning, and evaluate 15 frontier LLMs on contexts up to 64k tokens. Models usually refuse harmful requests when they are directly retrievable. However, refusal rates drop sharply when the same objectives must be reconstructed compositionally, often with larger failures in longer contexts. Benign reconstruction and fragment-position analyses indicate that these failures are not mainly retrieval errors: models often infer the harmful objective and then comply. Increasing inference-time reasoning improves refusal but remains incomplete and costly. Our results reveal a long-context safety gap: current models are better at refusing harmful requests they see than harmful objectives they infer.

---

### Whose Name Comes Up? II: Benchmarking and Intervention-Based Auditing of LLM-Based Scholar Recommendation

Authors: Lisette Espín-Noboa, Gonzalo Gabriel Méndez
Published: 2026-02-09
Categories: cs.IR, cs.AI, cs.CY, cs.SI, physics.soc-ph
arXiv: https://arxiv.org/abs/2602.08873v2

Large language models (LLMs) are now used for academic expert recommendation. Existing audits typically evaluate such recommendations in isolation, ignoring end-user inference-time interventions. Thus, it remains unclear whether failures (e.g., refusals, hallucinations, uneven coverage) stem from model choice or deployment decisions. We introduce LLMScholarBench, a benchmark for auditing LLM-based scholar recommendation that jointly evaluates model infrastructure and end-user interventions across multiple tasks. LLMScholarBench measures technical quality and social representation using nine metrics. We instantiate the benchmark in physics expert recommendation and audit 22 LLMs under temperature variation, representation-constrained prompting, and retrieval-augmented generation (RAG) via web search. Our results show that each intervention entails distinct tradeoffs. Higher temperature degrades validity, consistency, and factuality. Representation-constrained prompting improves diversity at the expense of factuality, while RAG primarily improves technical quality while reducing diversity and parity. Overall, end-user interventions reshape trade-offs rather than providing uniform gains. LLMScholarBench makes all these dynamics auditable across models and interventions in LLM-based scholar recommendations.

---

### Large Language Models for Geolocation Extraction in Humanitarian Crisis Response

Authors: G. Cafferata, T. Demarco, K. Kalimeri, Y. Mejova, M. G. Beiró
Published: 2026-02-09
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2602.08872v1

Humanitarian crises demand timely and accurate geographic information to inform effective response efforts. Yet, automated systems that extract locations from text often reproduce existing geographic and socioeconomic biases, leading to uneven visibility of crisis-affected regions. This paper investigates whether Large Language Models (LLMs) can address these geographic disparities in extracting location information from humanitarian documents. We introduce a two-step framework that combines few-shot LLM-based named entity recognition with an agent-based geocoding module that leverages context to resolve ambiguous toponyms. We benchmark our approach against state-of-the-art pretrained and rule-based systems using both accuracy and fairness metrics across geographic and socioeconomic dimensions. Our evaluation uses an extended version of the HumSet dataset with refined literal toponym annotations. Results show that LLM-based methods substantially improve both the precision and fairness of geolocation extraction from humanitarian texts, particularly for underrepresented regions. By bridging advances in LLM reasoning with principles of responsible and inclusive AI, this work contributes to more equitable geospatial data systems for humanitarian response, advancing the goal of leaving no place behind in crisis analytics.

---

### AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection

Authors: Junru Zhang, Lang Feng, Haoran Shi, Xu Guo, Han Yu, Yabo Dong, Duanqing Xu
Published: 2026-02-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.08868v2

Time-series anomaly detection (TSAD) with multimodal large language models (MLLMs) is an emerging area, yet a persistent challenge remains: MLLMs rely on coarse time-series heuristics but struggle with multi-dimensional, detailed reasoning, which is vital for understanding complex time-series data. We present AnomSeer to address this by reinforcing the model to ground its reasoning in precise, structural details of time series, unifying anomaly classification, localization, and explanation. At its core, an expert chain-of-thought trace is generated to provide a verifiable, fine-grained reasoning from classical analyses (e.g., statistical measures, frequency transforms). Building on this, we propose a novel time-series grounded policy optimization (TimerPO) that incorporates two additional components beyond standard reinforcement learning: a time-series grounded advantage based on optimal transport and an orthogonal projection to ensure this auxiliary granular signal does not interfere with the primary detection objective. Across diverse anomaly scenarios, AnomSeer, with Qwen2.5-VL-3B/7B-Instruct, outperforms larger commercial baselines (e.g., GPT-4o) in classification and localization accuracy, particularly on point- and frequency-driven exceptions. Moreover, it produces plausible time-series reasoning traces that support its conclusions.

---

### Understanding Dynamic Compute Allocation in Recurrent Transformers

Authors: Ibraheem Muhammad Moosa, Suhas Lohit, Ye Wang, Moitreya Chatterjee, Wenpeng Yin
Published: 2026-02-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.08864v1

Token-level adaptive computation seeks to reduce inference cost by allocating more computation to harder tokens and less to easier ones. However, prior work is primarily evaluated on natural-language benchmarks using task-level metrics, where token-level difficulty is unobservable and confounded with architectural factors, making it unclear whether compute allocation truly aligns with underlying complexity. We address this gap through three contributions. First, we introduce a complexity-controlled evaluation paradigm using algorithmic and synthetic language tasks with parameterized difficulty, enabling direct testing of token-level compute allocation. Second, we propose ANIRA, a unified recurrent Transformer framework that supports per-token variable-depth computation while isolating compute allocation decisions from other model factors. Third, we use this framework to conduct a systematic analysis of token-level adaptive computation across alignment with complexity, generalization, and decision timing. Our results show that compute allocation aligned with task complexity can emerge without explicit difficulty supervision, but such alignment does not imply algorithmic generalization: models fail to extrapolate to unseen input sizes despite allocating additional computation. We further find that early compute decisions rely on static structural cues, whereas online halting more closely tracks algorithmic execution state.

---

### Near-optimal Swap Regret Minimization for Convex Losses

Authors: Lunjia Hu, Jon Schneider, Yifan Wu
Published: 2026-02-09
Categories: cs.LG, cs.DS, stat.ML
arXiv: https://arxiv.org/abs/2602.08862v1

We give a randomized online algorithm that guarantees near-optimal $\widetilde O(\sqrt T)$ expected swap regret against any sequence of $T$ adaptively chosen Lipschitz convex losses on the unit interval. This improves the previous best bound of $\widetilde O(T^{2/3})$ and answers an open question of Fishelson et al. (2025b). In addition, our algorithm is efficient: it runs in $\mathsf{poly}(T)$ time. A key technical idea we develop to obtain this result is to discretize the unit interval into bins at multiple scales of granularity and simultaneously use all scales to make randomized predictions, which we call multi-scale binning and may be of independent interest. A direct corollary of our result is an efficient online algorithm for minimizing the calibration error for general elicitable properties. This result does not require the Lipschitzness assumption of the identification function needed in prior work, making it applicable to median calibration, for which we achieve the first $\widetilde O(\sqrt T)$ calibration error guarantee.

---

### TiFRe: Text-guided Video Frame Reduction for Efficient Video Multi-modal Large Language Models

Authors: Xiangtian Zheng, Zishuo Wang, Yuxin Peng
Published: 2026-02-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.08861v1

With the rapid development of Large Language Models (LLMs), Video Multi-Modal Large Language Models (Video MLLMs) have achieved remarkable performance in video-language tasks such as video understanding and question answering. However, Video MLLMs face high computational costs, particularly in processing numerous video frames as input, which leads to significant attention computation overhead. A straightforward approach to reduce computational costs is to decrease the number of input video frames. However, simply selecting key frames at a fixed frame rate (FPS) often overlooks valuable information in non-key frames, resulting in notable performance degradation. To address this, we propose Text-guided Video Frame Reduction (TiFRe), a framework that reduces input frames while preserving essential video information. TiFRe uses a Text-guided Frame Sampling (TFS) strategy to select key frames based on user input, which is processed by an LLM to generate a CLIP-style prompt. Pre-trained CLIP encoders calculate the semantic similarity between the prompt and each frame, selecting the most relevant frames as key frames. To preserve video semantics, TiFRe employs a Frame Matching and Merging (FMM) mechanism, which integrates non-key frame information into the selected key frames, minimizing information loss. Experiments show that TiFRe effectively reduces computational costs while improving performance on video-language tasks.

---

### Magnitude Distance: A Geometric Measure of Dataset Similarity

Authors: Sahel Torkamani, Henry Gouk, Rik Sarkar
Published: 2026-02-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.08859v1

Quantifying the distance between datasets is a fundamental question in mathematics and machine learning. We propose \textit{magnitude distance}, a novel distance metric defined on finite datasets using the notion of the \emph{magnitude} of a metric space. The proposed distance incorporates a tunable scaling parameter, $t$, that controls the sensitivity to global structure (small $t$) and finer details (large $t$). We prove several theoretical properties of magnitude distance, including its limiting behavior across scales and conditions under which it satisfies key metric properties. In contrast to classical distances, we show that magnitude distance remains discriminative in high-dimensional settings when the scale is appropriately tuned. We further demonstrate how magnitude distance can be used as a training objective for push-forward generative models. Our experimental results support our theoretical analysis and demonstrate that magnitude distance provides meaningful signals, comparable to established distance-based generative approaches.

---

### FlattenGPT: Depth Compression for Transformer with Layer Flattening

Authors: Ruihan Xu, Qingpei Guo, Yao Zhu, Xiangyang Ji, Ming Yang, Shiliang Zhang
Published: 2026-02-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.08858v1

Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pruning suffer from risks of discarding meaningful cues learned in those blocks, leading to substantial performance degradation. As another line of model compression, channel pruning can better preserve performance, while it cannot reduce model depth and is challenged by inconsistent pruning ratios for individual layers. To pursue better model compression and acceleration, this paper proposes \textbf{FlattenGPT}, a novel way to detect and reduce depth-wise redundancies. By flatting two adjacent blocks into one, it compresses the network depth, meanwhile enables more effective parameter redundancy detection and removal. FlattenGPT allows to preserve the knowledge learned in all blocks, and remains consistent with the original transformer architecture. Extensive experiments demonstrate that FlattenGPT enhances model efficiency with a decent trade-off to performance. It outperforms existing pruning methods in both zero-shot accuracies and WikiText-2 perplexity across various model types and parameter sizes. On LLaMA-2/3 and Qwen-1.5 models, FlattenGPT retains 90-96\% of zero-shot performance with a compression ratio of 20\%. It also outperforms other pruning methods in accelerating LLM inference, making it promising for enhancing the efficiency of transformers.

---