# Research Papers — 2026-02 · bundle page 196 of 210

> Full-text markdown of papers #9751–9800 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/196
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/195.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/197.md)

### Interpretability in Deep Time Series Models Demands Semantic Alignment

Authors: Giovanni De Felice, Riccardo D'Elia, Alberto Termine, Pietro Barbiero, Giuseppe Marra, Silvia Santini
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02239v2

Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal model computations, without addressing whether they align or not with how a human would reason about the studied phenomenon. Instead, we state interpretability in deep time series models should pursue semantic alignment: predictions should be expressed in terms of variables that are meaningful to the end user, mediated by spatial and temporal mechanisms that admit user-dependent constraints. In this paper, we formalize this requirement and state that, once established, semantic alignment must be preserved under temporal evolution: a constraint with no analog in static settings. Provided with this definition, we outline a blueprint for semantically aligned deep time series models, identify properties that support trust, and discuss implications for model design.

---

### Geometry- and Relation-Aware Diffusion for EEG Super-Resolution

Authors: Laura Yao, Gengwei Zhang, Moajjem Chowdhury, Yunmei Liu, Tianlong Chen
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02238v1

Recent electroencephalography (EEG) spatial super-resolution (SR) methods, while showing improved quality by either directly predicting missing signals from visible channels or adapting latent diffusion-based generative modeling to temporal data, often lack awareness of physiological spatial structure, thereby constraining spatial generation performance. To address this issue, we introduce TopoDiff, a geometry- and relation-aware diffusion model for EEG spatial super-resolution. Inspired by how human experts interpret spatial EEG patterns, TopoDiff incorporates topology-aware image embeddings derived from EEG topographic representations to provide global geometric context for spatial generation, together with a dynamic channel-relation graph that encodes inter-electrode relationships and evolves with temporal dynamics. This design yields a spatially grounded EEG spatial super-resolution framework with consistent performance improvements. Across multiple EEG datasets spanning diverse applications, including SEED/SEED-IV for emotion recognition, PhysioNet motor imagery (MI/MM), and TUSZ for seizure detection, our method achieves substantial gains in generation fidelity and leads to notable improvements in downstream EEG task performance.

---

### Adaptive Control in Autonomous Driving via Real-Time Recurrent RL

Authors: Julian Lemmel, Felix Resch, Mónika Farsang, Ramin Hasani, Daniela Rus, Radu Grosu
Published: 2026-02-02
Categories: cs.RO, cs.LG, cs.NE, eess.SY
arXiv: https://arxiv.org/abs/2602.02236v4

We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a memory-efficient algorithm that updates policy parameters at every time step without backpropagation through time. We extend RTRRL to support LrcSSM, a recently proposed nonlinear diagonal state-space model, and combine offline behavioral cloning with online RTRRL fine-tuning to adapt policies to distribution shifts at deployment. We validate the approach in the CarRacing simulation and on a 1:10-scale RoboRacer platform equipped with an event camera, where a pretrained policy is fine-tuned online during real-world line-following. To our knowledge, this is the first demonstration of online RL fine-tuning with event-camera observations on standard (non-spiking) hardware in closed-loop control. LrcSSM-based policies improve fastest and most consistently across both settings.

---

### LiFlow: Flow Matching for 3D LiDAR Scene Completion

Authors: Andrea Matteazzi, Dietmar Tutsch
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02232v1

In autonomous driving scenarios, the collected LiDAR point clouds can be challenged by occlusion and long-range sparsity, limiting the perception of autonomous driving systems. Scene completion methods can infer the missing parts of incomplete 3D LiDAR scenes. Recent methods adopt local point-level denoising diffusion probabilistic models, which require predicting Gaussian noise, leading to a mismatch between training and inference initial distributions. This paper introduces the first flow matching framework for 3D LiDAR scene completion, improving upon diffusion-based methods by ensuring consistent initial distributions between training and inference. The model employs a nearest neighbor flow matching loss and a Chamfer distance loss to enhance both local structure and global coverage in the alignment of point clouds. LiFlow achieves state-of-the-art performance across multiple metrics. Code: https://github.com/matteandre/LiFlow.

---

### SEDformer: Event-Synchronous Spiking Transformers for Irregular Telemetry Time Series Forecasting

Authors: Ziyu Zhou, Yuchen Fang, Weilin Ruan, Shiyu Wang, James Kwok, Yuxuan Liang
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02230v2

Telemetry streams from large-scale Internet-connected systems (e.g., IoT deployments and online platforms) naturally form an irregular multivariate time series (IMTS) whose accurate forecasting is operationally vital. A closer examination reveals a defining Sparsity-Event Duality (SED) property of IMTS, i.e., long stretches with sparse or no observations are punctuated by short, dense bursts where most semantic events (observations) occur. However, existing Graph- and Transformer-based forecasters ignore SED: pre-alignment to uniform grids with heavy padding violates sparsity by inflating sequences and forcing computation at non-informative steps, while relational recasting weakens event semantics by disrupting local temporal continuity. These limitations motivate a more faithful and natural modeling paradigm for IMTS that aligns with its SED property. We find that Spiking Neural Networks meet this requirement, as they communicate via sparse binary spikes and update in an event-driven manner, aligning naturally with the SED nature of IMTS. Therefore, we present SEDformer, an SED-enhanced Spiking Transformer for telemetry IMTS forecasting that couples: (1) a SED-based Spike Encoder converts raw observations into event synchronous spikes using an Event-Aligned LIF neuron, (2) an Event-Preserving Temporal Downsampling module compresses long gaps while retaining salient firings and (3) a stack of SED-based Spike Transformer blocks enable intra-series dependency modeling with a membrane-based linear attention driven by EA-LIF spiking features. Experiments on public telemetry IMTS datasets show that SEDformer attains state-of-the-art forecasting accuracy while reducing energy and memory usage, providing a natural and efficient path for modeling IMTS.

---

### Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts

Authors: Guangyi Zhang, Yunlong Cai, Guanding Yu, Osvaldo Simeone
Published: 2026-02-02
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2602.02229v2

We study the problem of monitoring model performance in dynamic environments where labeled data are limited. To this end, we propose prediction-powered risk monitoring (PPRM), a semi-supervised risk-monitoring approach based on prediction-powered inference (PPI). PPRM constructs anytime-valid lower bounds on the running risk by combining synthetic labels with a small set of true labels. Harmful shifts are detected via a threshold-based comparison with an upper bound on the nominal risk, satisfying assumption-free finite-sample guarantees on the type-I error. We demonstrate the effectiveness of PPRM through extensive experiments on image classification, large language model (LLM), and telecommunications monitoring tasks.

---

### Show, Don't Tell: Morphing Latent Reasoning into Image Generation

Authors: Harold Haodong Chen, Xinxiang Yin, Wen-Jie Shu, Hongfei Zhang, Zixin Zhang, Chenfei Liao, Litao Guo, Qifeng Chen, Ying-Cong Chen
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02227v1

Text-to-image (T2I) generation has achieved remarkable progress, yet existing methods often lack the ability to dynamically reason and refine during generation--a hallmark of human creativity. Current reasoning-augmented paradigms most rely on explicit thought processes, where intermediate reasoning is decoded into discrete text at fixed steps with frequent image decoding and re-encoding, leading to inefficiencies, information loss, and cognitive mismatches. To bridge this gap, we introduce LatentMorph, a novel framework that seamlessly integrates implicit latent reasoning into the T2I generation process. At its core, LatentMorph introduces four lightweight components: (i) a condenser for summarizing intermediate generation states into compact visual memory, (ii) a translator for converting latent thoughts into actionable guidance, (iii) a shaper for dynamically steering next image token predictions, and (iv) an RL-trained invoker for adaptively determining when to invoke reasoning. By performing reasoning entirely in continuous latent spaces, LatentMorph avoids the bottlenecks of explicit reasoning and enables more adaptive self-refinement. Extensive experiments demonstrate that LatentMorph (I) enhances the base model Janus-Pro by $16\%$ on GenEval and $25\%$ on T2I-CompBench; (II) outperforms explicit paradigms (e.g., TwiG) by $15\%$ and $11\%$ on abstract reasoning tasks like WISE and IPV-Txt, (III) while reducing inference time by $44\%$ and token consumption by $51\%$; and (IV) exhibits $71\%$ cognitive alignment with human intuition on reasoning invocation.

---

### Spectral Superposition: A Theory of Feature Geometry

Authors: Georgi Ivanov, Narmeen Oozeer, Shivam Raval, Tasana Pejovic, Shriyash Upadhyay, Amir Abdullah
Published: 2026-02-02
Categories: cs.LG, cs.AI, math.SP, stat.ML
arXiv: https://arxiv.org/abs/2602.02224v1

Neural networks represent more features than they have dimensions via superposition, forcing features to share representational space. Current methods decompose activations into sparse linear features but discard geometric structure. We develop a theory for studying the geometric structre of features by analyzing the spectra (eigenvalues, eigenspaces, etc.) of weight derived matrices. In particular, we introduce the frame operator $F = WW^\top$, which gives us a spectral measure that describes how each feature allocates norm across eigenspaces. While previous tools could describe the pairwise interactions between features, spectral methods capture the global geometry (``how do all features interact?''). In toy models of superposition, we use this theory to prove that capacity saturation forces spectral localization: features collapse onto single eigenspaces, organize into tight frames, and admit discrete classification via association schemes, classifying all geometries from prior work (simplices, polygons, antiprisms). The spectral measure formalism applies to arbitrary weight matrices, enabling diagnosis of feature localization beyond toy settings. These results point toward a broader program: applying operator theory to interpretability.

---

### Evaluating OCR Performance for Assistive Technology: Effects of Walking Speed, Camera Placement, and Camera Type

Authors: Junchi Feng, Nikhil Ballem, Mahya Beheshti, Giles Hamilton-Fletcher, Todd Hudson, Maurizio Porfiri, William H. Seiple, John-Ross Rizzo
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02223v2

Optical character recognition (OCR), a process that converts printed or handwritten text into machine-readable form, is widely used in assistive technology for people with blindness and low vision. Yet most evaluations rely on static datasets that do not reflect the challenges of mobile use. In this study, we systematically evaluated OCR performance under both static and dynamic conditions. Static tests measured detection range across distances of 1-7 meters and viewing angles of 0-75 degrees horizontally. Dynamic tests examined the impact of motion by varying walking speed from slow (0.8 m/s) to very fast (1.8 m/s) and compared three camera mounting positions: head-mounted, shoulder-mounted, and handheld. We evaluated both a smartphone and smart glasses, using the phone's main and ultra-wide cameras. Four OCR engines were benchmarked to assess accuracy at different distances and viewing angles: Google Vision, PaddleOCR 3.0, EasyOCR, and Tesseract. PaddleOCR 3.0 was then used to evaluate OCR performance under dynamic walking conditions. Accuracy was computed at the character-level using the Levenshtein ratio against manually defined ground truth. Results showed that recognition accuracy declined with increased walking speed and wider viewing angles. Google Vision achieved the highest overall accuracy, with PaddleOCR close behind as the strongest open-source alternative. Across devices, the phone's main camera achieved the highest accuracy, and a shoulder-mounted placement yielded the highest average among body positions; however, differences among shoulder, head, and hand were not statistically significant.

---

### MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection

Authors: Ruiqi Liu, Manni Cui, Ziheng Qin, Zhiyuan Yan, Ruoxin Chen, Yi Han, Zhiheng Li, Junkai Chen, ZhiJin Chen, Kaiqing Lin, Jialiang Shen, Lubin Weng et al.
Published: 2026-02-02
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2602.02222v1

High-fidelity generative models have narrowed the perceptual gap between synthetic and real images, posing serious threats to media security. Most existing AI-generated image (AIGI) detectors rely on artifact-based classification and struggle to generalize to evolving generative traces. In contrast, human judgment relies on stable real-world regularities, with deviations from the human cognitive manifold serving as a more generalizable signal of forgery. Motivated by this insight, we reformulate AIGI detection as a Reference-Comparison problem that verifies consistency with the real-image manifold rather than fitting specific forgery cues. We propose MIRROR (Manifold Ideal Reference ReconstructOR), a framework that explicitly encodes reality priors using a learnable discrete memory bank. MIRROR projects an input into a manifold-consistent ideal reference via sparse linear combination, and uses the resulting residuals as robust detection signals. To evaluate whether detectors reach the "superhuman crossover" required to replace human experts, we introduce the Human-AIGI benchmark, featuring a psychophysically curated human-imperceptible subset. Across 14 benchmarks, MIRROR consistently outperforms prior methods, achieving gains of 2.1% on six standard benchmarks and 8.1% on seven in-the-wild benchmarks. On Human-AIGI, MIRROR reaches 89.6% accuracy across 27 generators, surpassing both lay users and visual experts, and further approaching the human perceptual limit as pretrained backbones scale. The code is publicly available at: https://github.com/349793927/MIRROR

---

### Using Correspondence Patterns to Identify Irregular Words in Cognate sets Through Leave-One-Out Validation

Authors: Frederic Blum, Johann-Mattis List
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02221v1

Regular sound correspondences constitute the principal evidence in historical language comparison. Despite the heuristic focus on regularity, it is often more an intuitive judgement than a quantified evaluation, and irregularity is more common than expected from the Neogrammarian model. Given the recent progress of computational methods in historical linguistics and the increased availability of standardized lexical data, we are now able to improve our workflows and provide such a quantitative evaluation. Here, we present the balanced average recurrence of correspondence patterns as a new measure of regularity. We also present a new computational method that uses this measure to identify cognate sets that lack regularity with respect to their correspondence patterns. We validate the method through two experiments, using simulated and real data. In the experiments, we employ leave-one-out validation to measure the regularity of cognate sets in which one word form has been replaced by an irregular one, checking how well our method identifies the forms causing the irregularity. Our method achieves an overall accuracy of 85\% with the datasets based on real data. We also show the benefits of working with subsamples of large datasets and how increasing irregularity in the data influences our results. Reflecting on the broader potential of our new regularity measure and the irregular cognate identification method based on it, we conclude that they could play an important role in improving the quality of existing and future datasets in computer-assisted language comparison.

---

### LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation

Authors: Bo Miao, Weijia Liu, Jun Luo, Lachlan Shinnick, Jian Liu, Thomas Hamilton-Smith, Yuhe Yang, Zijie Wu, Vanja Videnovic, Feras Dayoub, Anton van den Hengel
Published: 2026-02-02
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2602.02220v2

Language-conditioned goal navigation (LGN) requires agents to locate user-specified targets without step-by-step guidance. However, existing benchmarks largely focus on category-level goals or rely on instance descriptions generated by vision-language models (VLMs), which often contain ambiguities and semantic errors, limiting systematic and reliable evaluation. We introduce HieraNav, an open-vocabulary LGN task with goals specified at four hierarchical semantic levels: scene, room, region, and instance. To this end, we present Language as a Map (LangMap), to our knowledge the first real-world 3D indoor navigation benchmark with human-verified semantic annotations to support tasks across all four goal levels. LangMap provides region labels and discriminative region and instance descriptions covering 414 object categories, produced through a rigorous contrastive annotation protocol comparing same-scene regions and instances, and contains over 18K tasks. Each target is paired with concise and detailed descriptions, enabling evaluation across instruction styles. Quantitative and qualitative analyses validate our annotation quality; notably, our instance descriptions outperform GOAT-Bench annotations by 23 percentage points in text-to-view matching. We further introduce PlaNaVid, a strong RGB-only baseline that combines Bounded Diverse Memory (BDM) with high-level planning to prime a reactive policy for multi-goal navigation. PlaNaVid achieves top-tier success rates without depth, 3D scene representations, or object masks. Further analysis shows that memory and richer context boost performance, while long-tailed categories, small objects, distant targets, and multi-goal completion remain open challenges. The benchmark is available at https://bo-miao.github.io/LangMap

---

### Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge

Authors: Yuzheng Xu, Tosho Hirasawa, Tadashi Kozuno, Yoshitaka Ushiku
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02219v3

Large language models are widely employed as evaluators, a paradigm commonly referred to as LLM-as-a-judge. Prior research has predominantly examined point-wise or pair-wise evaluation protocols; in contrast, our focus is on rubric-based evaluation, which has been attracting increasing attention owing to its utility for training models in domains where verification is otherwise difficult. In this work, we show that rubric-based evaluation implicitly resembles a multiple-choice setting and therefore exhibits position bias: LLMs tend to prefer score options that appear at specific positions within the rubric list. Through controlled experiments across multiple models and datasets, we demonstrate that this position bias is consistent. Its direction, however, is model-specific: some judges favor the first option, while others favor the last. We further identify a second, orthogonal axis of bias: when a prompt scores several criteria simultaneously, the ordering of the criteria itself shifts the resulting scores. We additionally explore permuting the order of the rubric options as a means of mitigating position bias, and find that although the bias can be attenuated, improvements in the correlation between model judgments and human annotations are obtained primarily for models that exhibit strong bias. Our results recast rubric-based LLM-as-a-judge as a multiple-choice problem with measurable, model-specific position bias, and we further confirm that only a small number of random order permutations are sufficient to reduce the error introduced by this bias for the majority of models.

---

### Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge

Authors: Yuzheng Xu, Tosho Hirasawa, Tadashi Kozuno, Yoshitaka Ushiku
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02219v2

Large language models are widely employed as evaluators, a paradigm commonly referred to as LLM-as-a-judge. Prior research has predominantly examined point-wise or pair-wise evaluation protocols; in contrast, our focus is on rubric-based evaluation, which has been attracting increasing attention owing to its utility for training models in domains where verification is otherwise difficult. In this work, we show that rubric-based evaluation implicitly resembles a multiple-choice setting and therefore exhibits position bias: LLMs tend to prefer score options that appear at specific positions within the rubric list. Through controlled experiments across multiple models and datasets, we demonstrate that this position bias is consistent. Its direction, however, is model-specific: some judges favor the first option, while others favor the last. We further identify a second, orthogonal axis of bias: when a prompt scores several criteria simultaneously, the ordering of the criteria itself shifts the resulting scores. We additionally explore permuting the order of the rubric options as a means of mitigating position bias, and find that although the bias can be attenuated, improvements in the correlation between model judgments and human annotations are obtained primarily for models that exhibit strong bias. Our results recast rubric-based LLM-as-a-judge as a multiple-choice problem with measurable, model-specific position bias, and we further confirm that only a small number of random order permutations are sufficient to reduce the error introduced by this bias for the majority of models.

---

### Scientific Theory of a Black-Box: A Life Cycle-Scale XAI Framework Based on Constructive Empiricism

Authors: Sebastian Müller, Vanessa Toborek, Eike Stadtländer, Tamás Horváth, Brendan Balcerak Jackson, Christian Bauckhage
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02215v1

Explainable AI (XAI) offers a growing number of algorithms that aim to answer specific questions about black-box models. What is missing is a principled way to consolidate explanatory information about a fixed black-box model into a persistent, auditable artefact, that accompanies the black-box throughout its life cycle. We address this gap by introducing the notion of a scientific theory of a black (SToBB). Grounded in Constructive Empiricism, a SToBB fulfils three obligations: (i) empirical adequacy with respect to all available observations of black-box behaviour, (ii) adaptability via explicit update commitments that restore adequacy when new observations arrive, and (iii) auditability through transparent documentation of assumptions, construction choices, and update behaviour. We operationalise these obligations as a general framework that specifies an extensible observation base, a traceable hypothesis class, algorithmic components for construction and revision, and documentation sufficient for third-party assessment. Explanations for concrete stakeholder needs are then obtained by querying the maintained record through interfaces, rather than by producing isolated method outputs. As a proof of concept, we instantiate a complete SToBB for a neural-network classifier on a tabular task and introduce the Constructive Box Theoriser (CoBoT) algorithm, an online procedure that constructs and maintains an empirically adequate rule-based surrogate as observations accumulate. Together, these contributions position SToBBs as a life cycle-scale, inspectable point of reference that supports consistent, reusable analyses and systematic external scrutiny.

---

### Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

Authors: Hongzhou Zhu, Min Zhao, Guande He, Hang Su, Chongxuan Li, Jun Zhu
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02214v5

To achieve real-time interactive video generation, current methods distill pretrained bidirectional video diffusion models into few-step autoregressive (AR) models, facing an architectural gap when full attention is replaced by causal attention. However, existing approaches do not bridge this gap theoretically. They initialize the AR student via ODE distillation, which requires frame-level injectivity, where each noisy frame must map to a unique clean frame under the PF-ODE of an AR teacher. Distilling an AR student from a bidirectional teacher violates this condition, preventing recovery of the teacher's flow map and instead inducing a conditional-expectation solution, which degrades performance. To address this issue, we propose Causal Forcing, which uses an autoregressive teacher for ODE initialization to bridge the architectural gap, and then applies the same DMD procedure as in Self Forcing. Empirical results show that our method outperforms all baselines across all metrics, surpassing the SOTA Self Forcing by 19.3\% in Dynamic Degree, 8.7\% in VisionReward, and 16.7\% in Instruction Following. Project page: \href{https://thu-ml.github.io/CausalForcing.github.io/}{https://thu-ml.github.io/CausalForcing.github.io/}; the code: \href{https://github.com/thu-ml/Causal-Forcing}{https://github.com/thu-ml/Causal-Forcing}.

---

### Generating Physically Sound Designs from Text and a Set of Physical Constraints

Authors: Gregory Barber, Todd C. Henry, Mulugeta A. Haile
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02213v1

We present TIDES, a text informed design approach for generating physically sound designs based on a textual description and a set of physical constraints. TIDES jointly optimizes structural (topology) and visual properties. A pre-trained text-image model is used to measure the design's visual alignment with a text prompt and a differentiable physics simulator is used to measure its physical performance. We evaluate TIDES on a series of structural optimization problems operating under different load and support conditions, at different resolutions, and experimentally in the lab by performing the 3-point bending test on 2D beam designs that are extruded and 3D printed. We find that it can jointly optimize the two objectives and return designs that satisfy engineering design requirements (compliance and density) while utilizing features specified by text.

---

### MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models

Authors: Zheyuan Zhou, Liang Du, Zixun Sun, Xiaoyu Zhou, Ruimin Ye, Qihao Chen, Yinda Chen, Lemiao Qiu
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02212v1

Despite significant progress in Visual-Language-Action (VLA), in highly complex and dynamic environments that involve real-time unpredictable interactions (such as 3D open worlds and large-scale PvP games), existing approaches remain inefficient at extracting action-critical signals from redundant sensor streams. To tackle this, we introduce MAIN-VLA, a framework that explicitly Models the Abstraction of Intention and eNvironment to ground decision-making in deep semantic alignment rather than superficial pattern matching. Specifically, our Intention Abstraction (IA) extracts verbose linguistic instructions and their associated reasoning into compact, explicit semantic primitives, while the Environment Semantics Abstraction (ESA) projects overwhelming visual streams into a structured, topological affordance representation. Furthermore, aligning these two abstract modalities induces an emergent attention-concentration effect, enabling a parameter-free token-pruning strategy that filters out perceptual redundancy without degrading performance. Extensive experiments in open-world Minecraft and large-scale PvP environments (Game for Peace and Valorant) demonstrate that MAIN-VLA sets a new state-of-the-art, which achieves superior decision quality, stronger generalization, and cutting-edge inference efficiency.

---

### Towards AI Evaluation in Domain-Specific RAG Systems: The AgriHubi Case Study

Authors: Md. Toufique Hasan, Ayman Asad Khan, Mika Saari, Vaishnavi Bankhele, Pekka Abrahamsson
Published: 2026-02-02
Categories: cs.CL, cs.AI, cs.IR, cs.SE
arXiv: https://arxiv.org/abs/2602.02208v1

Large language models show promise for knowledge-intensive domains, yet their use in agriculture is constrained by weak grounding, English-centric training data, and limited real-world evaluation. These issues are amplified for low-resource languages, where high-quality domain documentation exists but remains difficult to access through general-purpose models. This paper presents AgriHubi, a domain-adapted retrieval-augmented generation (RAG) system for Finnish-language agricultural decision support. AgriHubi integrates Finnish agricultural documents with open PORO family models and combines explicit source grounding with user feedback to support iterative refinement. Developed over eight iterations and evaluated through two user studies, the system shows clear gains in answer completeness, linguistic accuracy, and perceived reliability. The results also reveal practical trade-offs between response quality and latency when deploying larger models. This study provides empirical guidance for designing and evaluating domain-specific RAG systems in low-resource language settings.

---

### Sinhala Physical Common Sense Reasoning Dataset for Global PIQA

Authors: Nisansa de Silva, Surangika Ranathunga
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02207v1

This paper presents the first-ever Sinhala physical common sense reasoning dataset created as part of Global PIQA. It contains 110 human-created and verified data samples, where each sample consists of a prompt, the corresponding correct answer, and a wrong answer. Most of the questions refer to the Sri Lankan context, where Sinhala is an official language.

---

### Fat-Cat: Document-Driven Metacognitive Multi-Agent System for Complex Reasoning

Authors: Tong Yang, Yemin Wang, Chaoning Zhang, Aming Wu
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02206v2

The effectiveness of LLM-based agents is often limited not by model capacity alone, but by how efficiently contextual information is utilized at runtime. Existing agent frameworks rely on rigid, syntax-heavy state representations such as nested JSON, which require models to devote a substantial portion of their limited attention to syntactic processing rather than semantic reasoning. In this paper, we propose Fat-Cat, a document-driven agent architecture that improves the signal-to-noise ratio of state management. By integrating three key components: (1) a Semantic File System that represents agent state as Markdown documents aligned with common pre-training corpora, (2) a Textual Strategy Evolution module that accumulates task-solving knowledge without parameter updates, and (3) a Closed-Loop Watcher that monitors reasoning trajectories to reduce hallucinations. Extensive reasoning, retrieval, and coding benchmarks, Fat-Cat consistently improves agent performance. It enables the Kimi-k2 model to outperform the proprietary GPT-4o baseline on HotPotQA. Replacing the document-based state with JSON leads to performance drop, while empirically validating the critical necessity of document-driven state modeling over rigid syntax. The code is available at https://github.com/answeryt/Fat-Cat.

---

### Cardinality-Preserving Attention Channels for Graph Transformers in Molecular Property Prediction

Authors: Abhijit Gupta
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02201v5

Molecular property prediction is crucial for drug discovery when labeled data are scarce. This work presents CardinalGraphFormer, a graph transformer augmented with a query-conditioned cardinality-preserving attention (CPA) channel that retains dynamic support-size signals complementary to static centrality embeddings. The approach combines structured sparse attention with Graphormer-inspired biases (shortest-path distance, centrality, direct-bond features) and unified dual-objective self-supervised pretraining (masked reconstruction and contrastive alignment of augmented views). Evaluation on 11 public benchmarks spanning MoleculeNet, OGB, and TDC ADMET demonstrates consistent improvements over protocol-matched baselines under matched pretraining, optimization, and hyperparameter tuning. Rigorous ablations confirm CPA's contributions and rule out simple size shortcuts. Code and reproducibility artifacts are provided.

---

### More Than a Quick Glance: Overcoming the Greedy Bias in KV-Cache Compression

Authors: Aryan Sood, Tanvi Sharma, Vansh Agrawal
Published: 2026-02-02
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.02199v1

While Large Language Models (LLMs) can theoretically support extensive context windows, their actual deployment is constrained by the linear growth of Key-Value (KV) cache memory. Prevailing compression strategies mitigate this through various pruning mechanisms, yet trade-off semantic recall for memory efficiency. In this work, we present LASER-KV (Layer Accumulated Selection with Exact-LSH Recall), a framework designed to test the limits of KV compression under a strict accumulative budgeting policy. We deviate from the standard fixed summary size approach by implementing a block-wise accumulation strategy governed by a protection divisor (n). This allows us to isolate the effects of compression from sliding window artifacts. Our experiments on the Babilong benchmark reveal performance degradation in previous compression methods by 15-30% on various long context tasks. LASER-KV maintains stable performance, achieving superior accuracies by a margin of upto 10% at 128k. These findings challenge the prevailing assumption that attention scores alone are a sufficient proxy for token utility.

---

### Hierarchical Adaptive Eviction for KV Cache Management in Multimodal Language Models

Authors: Xindian Ma, Yidi Lu, Peng Zhang, Jing Zhang
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02197v1

The integration of visual information into Large Language Models (LLMs) has enabled Multimodal LLMs (MLLMs), but the quadratic memory and computational costs of Transformer architectures remain a bottleneck. Existing KV cache eviction strategies fail to address the heterogeneous attention distributions between visual and text tokens, leading to suboptimal efficiency or degraded performance. In this paper, we propose Hierarchical Adaptive Eviction (HAE), a KV cache eviction framework that optimizes text-visual token interaction in MLLMs by implementing Dual-Attention Pruning during pre-filling (leveraging visual token sparsity and attention variance) and a Dynamic Decoding Eviction Strategy (inspired by OS Recycle Bins) during decoding. HAE minimizes KV cache usage across layers, reduces computational overhead via index broadcasting, and theoretically ensures superior information integrity and lower error bounds compared to greedy strategies, enhancing efficiency in both comprehension and generation tasks. Empirically, HAE reduces KV-Cache memory by 41\% with minimal accuracy loss (0.3\% drop) in image understanding tasks and accelerates story generation inference by 1.5x while maintaining output quality on Phi3.5-Vision-Instruct model.

---

### TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents

Authors: Hang Yan, Xinyu Che, Fangzhi Xu, Qiushi Sun, Zichen Ding, Kanzhi Cheng, Jian Zhang, Tao Qin, Jun Liu, Qika Lin
Published: 2026-02-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02196v2

Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment. We define this paradigm as Test-Time Improvement (TTI). However, the mechanisms under how and why TTI succeed or fail remain poorly understood, and existing evaluation metrics fail to capture their task optimization efficiency, behavior adaptation after erroneous actions, and the specific utility of working memory for task completion. To address these gaps, we propose Test-time Improvement Diagnostic Evaluation (TIDE), an agent-agnostic and environment-agnostic framework that decomposes TTI into three comprehensive and interconnected dimensions. The framework measures (1) the overall temporal dynamics of task completion and (2) identifies whether performance is primarily constrained by recursive looping behaviors or (3) by burdensome accumulated memory. Through extensive experiments across diverse agents and environments, TIDE highlights that improving agent performance requires more than scaling internal reasoning, calling for explicitly optimizing the interaction dynamics between the agent and the environment.

---

### State Rank Dynamics in Linear Attention LLMs

Authors: Ao Sun, Hongtao Zhang, Heng Zhou, Yixuan Ma, Yiran Qin, Tongrui Su, Yan Liu, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02195v1

Linear Attention Large Language Models (LLMs) offer a compelling recurrent formulation that compresses context into a fixed-size state matrix, enabling constant-time inference. However, the internal dynamics of this compressed state remain largely opaque. In this work, we present a comprehensive study on the runtime state dynamics of state-of-the-art Linear Attention models. We uncover a fundamental phenomenon termed State Rank Stratification, characterized by a distinct spectral bifurcation among linear attention heads: while one group maintains an effective rank oscillating near zero, the other exhibits rapid growth that converges to an upper bound. Extensive experiments across diverse inference contexts reveal that these dynamics remain strikingly consistent, indicating that the identity of a head,whether low-rank or high-rank,is an intrinsic structural property acquired during pre-training, rather than a transient state dependent on the input data. Furthermore, our diagnostic probes reveal a surprising functional divergence: low-rank heads are indispensable for model reasoning, whereas high-rank heads exhibit significant redundancy. Leveraging this insight, we propose Joint Rank-Norm Pruning, a zero-shot strategy that achieves a 38.9\% reduction in KV-cache overhead while largely maintaining model accuracy.

---

### SSI-DM: Singularity Skipping Inversion of Diffusion Models

Authors: Chen Min, Enze Jiang, Jishen Peng, Zheng Ma
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02193v2

Inverting real images into the noise space is essential for editing tasks using diffusion models, yet existing methods produce non-Gaussian noise with poor editability due to the inaccuracy in early noising steps. We identify the root cause: a mathematical singularity that renders inversion fundamentally ill-posed. We propose Singularity Skipping Inversion of Diffusion Models (SSI-DM), which bypasses this singular region by adding small noise before standard inversion. This simple approach produces inverted noise with natural Gaussian properties while maintaining reconstruction fidelity. As a plug-and-play technique compatible with general diffusion models, our method achieves superior performance on public image datasets for reconstruction and interpolation tasks, providing a principled and efficient solution to diffusion model inversion.

---

### ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning

Authors: Jingwei Song, Meng Chen, Jie Xiao, Qingnan Ren, Jiaqi Huang, Yangshen Deng, Chris Tong, Wanyi Chen, Suli Wang, Zhisheng Chen, Ziqian Bi, Shuo Lu et al.
Published: 2026-02-02
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2602.02192v5

Reinforcement learning (RL) is a critical stage in post-training large language models (LLMs), involving repeated interaction between rollout generation, reward evaluation, and centralized learning. Distributing rollout execution offers opportunities to leverage more cost-efficient inference resources, but introduces challenges in wide-area coordination and policy dissemination. We present ECHO-2, a distributed RL framework for post-training with remote inference workers and non-negligible dissemination latency. ECHO-2 combines centralized learning with distributed rollouts and treats bounded policy staleness as a user-controlled parameter, enabling rollout generation, dissemination, and training to overlap. We introduce an overlap-based capacity model that relates training time, dissemination latency, and rollout throughput, yielding a practical provisioning rule for sustaining learner utilization. To mitigate dissemination bottlenecks and lower cost, ECHO-2 employs peer-assisted pipelined broadcast and cost-aware activation of heterogeneous workers. Experiments on GRPO post-training of LLMs ranging from 4B to 32B parameters under real wide-area bandwidth regimes show that ECHO-2 significantly improves cost efficiency while preserving RL reward comparable to strong baselines.

---

### PCA of probability measures: Sparse and Dense sampling regimes

Authors: Gachon Erell, Jérémie Bigot, Elsa Cazelles
Published: 2026-02-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.02190v2

A common approach to perform PCA on probability measures is to embed them into a Hilbert space where standard functional PCA techniques apply. While convergence rates for estimating the embedding of a single measure from $m$ samples are well understood, the literature has not addressed the setting involving multiple measures. In this paper, we study PCA in a double asymptotic regime where $n$ probability measures are observed, each through $m$ samples. We derive convergence rates of the form $n^{-1/2} + m^{-α}$ for the empirical covariance operator and the PCA excess risk, where $α>0$ depends on the chosen embedding. This characterizes the relationship between the number $n$ of measures and the number $m$ of samples per measure, revealing a sparse (small $m$) to dense (large $m$) transition in the convergence behavior. Moreover, we prove that the dense-regime rate is minimax optimal for the empirical covariance error. Our numerical experiments validate these theoretical rates and demonstrate that appropriate subsampling preserves PCA accuracy while reducing computational cost.

---

### Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization

Authors: Xia Jiang, Jing Chen, Cong Zhang, Jie Gao, Chengpeng Hu, Chenhao Zhang, Yaoxin Wu, Yingqian Zhang
Published: 2026-02-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02188v2

While large language models (LLMs) have shown strong performance in math and logic reasoning, their ability to handle combinatorial optimization (CO) -- searching high-dimensional solution spaces under hard constraints -- remains underexplored. To bridge the gap, we introduce NLCO, a \textbf{N}atural \textbf{L}anguage \textbf{C}ombinatorial \textbf{O}ptimization benchmark that evaluates LLMs on end-to-end CO reasoning: given a language-described decision-making scenario, the model must output a discrete solution without writing code or calling external solvers. NLCO covers 43 CO problems and is organized using a four-layer taxonomy of variable types, constraint families, global patterns, and objective classes, enabling fine-grained evaluation. We provide solver-annotated solutions and comprehensively evaluate LLMs by feasibility, solution optimality, and reasoning efficiency. Experiments across a wide range of modern LLMs show that high-performing models achieve strong feasibility and solution quality on small instances, but both degrade as instance size grows, even if more tokens are used for reasoning. We also observe systematic effects across the taxonomy: set-based tasks are relatively easy, whereas graph-structured problems and bottleneck objectives lead to more frequent failures.

---

### Learning Topology-Aware Implicit Field for Unified Pulmonary Tree Modeling with Incomplete Topological Supervision

Authors: Ziqiao Weng, Jiancheng Yang, Kangxian Xie, Bo Zhou, Weidong Cai
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02186v2

Pulmonary trees extracted from CT images frequently exhibit topological incompleteness, such as missing or disconnected branches, which substantially degrades downstream anatomical analysis and limits the applicability of existing pulmonary tree modeling pipelines. Current approaches typically rely on dense volumetric processing, explicit graph reasoning, or generic point cloud completion priors, leading to limited efficiency, weak structural awareness, and reduced robustness under realistic structural corruption. We propose TopoField, a topology-aware implicit modeling framework that treats topology repair as a first-class modeling problem and enables unified multi-task inference for pulmonary tree analysis. TopoField represents pulmonary anatomy using sparse surface and skeleton point clouds and learns a continuous implicit field that supports topology repair without relying on complete or explicit disconnection annotations, by training on synthetically introduced structural disruptions over \textit{already} incomplete trees. Building upon the repaired implicit representation, anatomical labeling and lung segment reconstruction are jointly inferred through task-specific implicit functions within a single forward pass. Extensive experiments on the Lung3D+ dataset demonstrate that TopoField consistently improves topological completeness and achieves accurate anatomical labeling and lung segment reconstruction under challenging incomplete scenarios. We further validate TopoField on real incomplete outputs from an external segmentation model, demonstrating its applicability to realistic segmentation pipelines. Owing to its implicit formulation, TopoField attains high computational efficiency, completing all tasks in just over one second per case, highlighting its practicality for large-scale and time-sensitive clinical applications.

---

### Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models

Authors: Yu Zeng, Wenxuan Huang, Zhen Fang, Shuang Chen, Yufan Shen, Yishuo Cai, Xiaoman Wang, Zhenfei Yin, Lin Chen, Zehui Chen, Shiting Huang, Yiming Zhao et al.
Published: 2026-02-02
Categories: cs.CV, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.02185v2

Multimodal Large Language Models (MLLMs) have advanced VQA and now support Vision-DeepResearch systems that use search engines for complex visual-textual fact-finding. However, evaluating these visual and textual search abilities is still difficult, and existing benchmarks have two major limitations. First, existing benchmarks are not visual search-centric: answers that should require visual search are often leaked through cross-textual cues in the text questions or can be inferred from the prior world knowledge in current MLLMs. Second, overly idealized evaluation scenario: On the image-search side, the required information can often be obtained via near-exact matching against the full image, while the text-search side is overly direct and insufficiently challenging. To address these issues, we construct the Vision-DeepResearch benchmark (VDR-Bench) comprising 2,000 VQA instances. All questions are created via a careful, multi-stage curation pipeline and rigorous expert review, designed to assess the behavior of Vision-DeepResearch systems under realistic real-world conditions. Moreover, to address the insufficient visual retrieval capabilities of current MLLMs, we propose a simple multi-round cropped-search workflow. This strategy is shown to effectively improve model performance in realistic visual retrieval scenarios. Overall, our results provide practical guidance for the design of future multimodal deep-research systems. The code will be released in https://github.com/Osilly/Vision-DeepResearch.

---

### Malware Detection Through Memory Analysis

Authors: Sarah Nassar
Published: 2026-02-02
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.02184v1

This paper summarizes the research conducted for a malware detection project using the Canadian Institute for Cybersecurity's MalMemAnalysis-2022 dataset. The purpose of the project was to explore the effectiveness and efficiency of machine learning techniques for the task of binary classification (i.e., benign or malicious) as well as multi-class classification to further include three malware sub-types (i.e., benign, ransomware, spyware, or Trojan horse). The XGBoost model type was the final model selected for both tasks due to the trade-off between strong detection capability and fast inference speed. The binary classifier achieved a testing subset accuracy and F1 score of 99.98\%, while the multi-class version reached an accuracy of 87.54\% and an F1 score of 81.26\%, with an average F1 score over the malware sub-types of 75.03\%. In addition to the high modelling performance, XGBoost is also efficient in terms of classification speed. It takes about 37.3 milliseconds to classify 50 samples in sequential order in the binary setting and about 43.2 milliseconds in the multi-class setting. The results from this research project help advance the efforts made towards developing accurate and real-time obfuscated malware detectors for the goal of improving online privacy and safety. *This project was completed as part of ELEC 877 (AI for Cybersecurity) in the Winter 2024 term.

---

### Evaluating Metalinguistic Knowledge in Large Language Models across the World's Languages

Authors: Tjaša Arčon, Matej Klemen, Marko Robnik-Šikonja, Kaja Dobrovoljc
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02182v2

LLMs are routinely evaluated on language use, yet their explicit knowledge about linguistic structure remains poorly understood. Existing linguistic benchmarks focus on narrow phenomena, emphasize high-resource languages, and rarely test metalinguistic knowledge - explicit reasoning about language structure. We present a multilingual evaluation of metalinguistic knowledge in LLMs, based on the World Atlas of Language Structures (WALS), documenting 192 linguistic features across 2,660 languages. We convert WALS features into natural-language multiple-choice questions and evaluate models across documented languages. Using accuracy and macro F1, and comparing to chance and majority-class baselines, we assess performance and analyse variation across linguistic domains and language-related factors. Results show limited metalinguistic knowledge: GPT-4o performs best but achieves moderate accuracy (0.367), while open-source models lag. Although all models perform above chance, they fail to outperform the majority-class baseline, suggesting they capture broad cross-linguistic patterns but lack fine-grained distinctions. Performance varies by domain, partly reflecting differences in online visibility. At the language level, accuracy correlates with digital language status: languages with greater digital presence and resources are evaluated more accurately, while low-resource languages perform worse. Analysis of predictive factors confirms that resource-related indicators (Wikipedia size, corpus availability) are more informative than geographic, genealogical, or sociolinguistic factors. Overall, LLM metalinguistic knowledge appears fragmented and shaped mainly by data availability, rather than broadly generalizable grammatical competence. We release the benchmark as an open-source dataset to support evaluation across languages and encourage greater global linguistic diversity in future LLMs.

---

### STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs

Authors: Weikang Meng, Liangyu Huo, Yadan Luo, Jiawen Guan, Jingyi Zhang, Yingjian Li, Zheng Zhang
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02180v1

Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexity of standard softmax attention. Existing methods perform token routing based on sliding-window partitions, resulting in position-based selection and fails to capture token-specific global importance. Meanwhile, linear attention further suffers from distribution shift caused by learnable feature maps that distort pretrained feature magnitudes. Motivated by these limitations, we propose STILL, an intra-layer hybrid linearization framework for efficiently linearizing LLMs. STILL introduces a Self-Saliency Score with strong local-global consistency, enabling accurate token selection using sliding-window computation, and retains salient tokens for sparse softmax attention while summarizing the remaining context via linear attention. To preserve pretrained representations, we design a Norm-Preserved Feature Map (NP-Map) that decouples feature direction from magnitude and reinjects pretrained norms. We further adopt a unified training-inference architecture with chunk-wise parallelization and delayed selection to improve hardware efficiency. Experiments show that STILL matches or surpasses the original pretrained model on commonsense and general reasoning tasks, and achieves up to a 86.2% relative improvement over prior linearized attention methods on long-context benchmarks.

---

### SurvKAN: A Fully Parametric Survival Model Based on Kolmogorov-Arnold Networks

Authors: Marina Mastroleo, Alberto Archetti, Federico Mastroleo, Matteo Matteucci
Published: 2026-02-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.02179v1

Accurate prediction of time-to-event outcomes is critical for clinical decision-making, treatment planning, and resource allocation in modern healthcare. While classical survival models such as Cox remain widely adopted in standard practice, they rely on restrictive assumptions, including linear covariate relationships and proportional hazards over time, that often fail to capture real-world clinical dynamics. Recent deep learning approaches like DeepSurv and DeepHit offer improved expressivity but sacrifice interpretability, limiting clinical adoption where trust and transparency are paramount. Hybrid models incorporating Kolmogorov-Arnold Networks (KANs), such as CoxKAN, have begun to address this trade-off but remain constrained by the semi-parametric Cox framework. In this work we introduce SurvKAN, a fully parametric, time-continuous survival model based on KAN architectures that eliminates the proportional hazards constraint. SurvKAN treats time as an explicit input to a KAN that directly predicts the log-hazard function, enabling end-to-end training on the full survival likelihood. Our architecture preserves interpretability through learnable univariate functions that indicate how individual features influence risk over time. Extensive experiments on standard survival benchmarks demonstrate that SurvKAN achieves competitive or superior performance compared to classical and state-of-the-art baselines across concordance and calibration metrics. Additionally, interpretability analyses reveal clinically meaningful patterns that align with medical domain knowledge.

---

### AR-MAP: Are Autoregressive Large Language Models Implicit Teachers for Diffusion Large Language Models?

Authors: Liang Lin, Feng Xiong, Zengbin Wang, Kun Wang, Junhao Dong, Xuecai Hu, Yong Wang, Xiangxiang Chu
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02178v2

Diffusion Large Language Models (DLLMs) have emerged as a powerful alternative to autoregressive models, enabling parallel token generation across multiple positions. However, preference alignment of DLLMs remains challenging due to high variance introduced by Evidence Lower Bound (ELBO)-based likelihood estimation. In this work, we propose AR-MAP, a novel transfer learning framework that leverages preference-aligned autoregressive LLMs (AR-LLMs) as implicit teachers for DLLM alignment. We reveal that DLLMs can effectively absorb alignment knowledge from AR-LLMs through simple weight scaling, exploiting the shared architectural structure between these divergent generation paradigms. Crucially, our approach circumvents the high variance and computational overhead of direct DLLM alignment and comprehensive experiments across diverse preference alignment tasks demonstrate that AR-MAP achieves competitive or superior performance compared to existing DLLM-specific alignment methods, achieving 69.08\% average score across all tasks and models. Our Code is available at https://github.com/AMAP-ML/AR-MAP.

---

### CIEC: Coupling Implicit and Explicit Cues for Multimodal Weakly Supervised Manipulation Localization

Authors: Xinquan Yu, Wei Lu, Xiangyang Luo, Rui Yang
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02175v2

To mitigate the threat of misinformation, multimodal manipulation localization has garnered growing attention. Consider that current methods rely on costly and time-consuming fine-grained annotations, such as patch/token-level annotations. This paper proposes a novel framework named Coupling Implicit and Explicit Cues (CIEC), which aims to achieve multimodal weakly-supervised manipulation localization for image-text pairs utilizing only coarse-grained image/sentence-level annotations. It comprises two branches, image-based and text-based weakly-supervised localization. For the former, we devise the Textual-guidance Refine Patch Selection (TRPS) module. It integrates forgery cues from both visual and textual perspectives to lock onto suspicious regions aided by spatial priors. Followed by the background silencing and spatial contrast constraints to suppress interference from irrelevant areas. For the latter, we devise the Visual-deviation Calibrated Token Grounding (VCTG) module. It focuses on meaningful content words and leverages relative visual bias to assist token localization. Followed by the asymmetric sparse and semantic consistency constraints to mitigate label noise and ensure reliability. Extensive experiments demonstrate the effectiveness of our CIEC, yielding results comparable to fully supervised methods on several evaluation metrics.

---

### Generalized Optimal Classification Trees: A Mixed-Integer Programming Approach

Authors: Jiancheng Tu, Wenqi Fan, Zhibin Wu
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02173v1

Global optimization of decision trees is a long-standing challenge in combinatorial optimization, yet such models play an important role in interpretable machine learning. Although the problem has been investigated for several decades, only recent advances in discrete optimization have enabled practical algorithms for solving optimal classification tree problems on real-world datasets. Mixed-integer programming (MIP) offers a high degree of modeling flexibility, and we therefore propose a MIP-based framework for learning optimal classification trees under nonlinear performance metrics, such as the F1-score, that explicitly addresses class imbalance. To improve scalability, we develop problem-specific acceleration techniques, including a tailored branch-and-cut algorithm, an instance-reduction scheme, and warm-start strategies. We evaluate the proposed approach on 50 benchmark datasets. The computational results show that the framework can efficiently optimize nonlinear metrics while achieving strong predictive performance and reduced solution times compared with existing methods.

---

### Lung Nodule Image Synthesis Driven by Two-Stage Generative Adversarial Networks

Authors: Lu Cao, Xiquan He, Junying Zeng, Chaoyun Mai, Min Luo
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02171v1

The limited sample size and insufficient diversity of lung nodule CT datasets severely restrict the performance and generalization ability of detection models. Existing methods generate images with insufficient diversity and controllability, suffering from issues such as monotonous texture features and distorted anatomical structures. Therefore, we propose a two-stage generative adversarial network (TSGAN) to enhance the diversity and spatial controllability of synthetic data by decoupling the morphological structure and texture features of lung nodules. In the first stage, StyleGAN is used to generate semantic segmentation mask images, encoding lung nodules and tissue backgrounds to control the anatomical structure of lung nodule images; The second stage uses the DL-Pix2Pix model to translate the mask map into CT images, employing local importance attention to capture local features, while utilizing dynamic weight multi-head window attention to enhance the modeling capability of lung nodule texture and background. Compared to the original dataset, the accuracy improved by 4.6% and mAP by 4% on the LUNA16 dataset. Experimental results demonstrate that TSGAN can enhance the quality of synthetic images and the performance of detection models.

---

### Self-Evolving Coordination Protocol in Multi-Agent AI Systems: An Exploratory Systems Feasibility Study

Authors: Jose Manuel de la Chica Rodriguez, Juan Manuel Vera Díaz
Published: 2026-02-02
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2602.02170v1

Contemporary multi-agent systems increasingly rely on internal coordination mechanisms to combine, arbitrate, or constrain the outputs of heterogeneous components. In safety-critical and regulated domains such as finance, these mechanisms must satisfy strict formal requirements, remain auditable, and operate within explicitly bounded limits. Coordination logic therefore functions as a governance layer rather than an optimization heuristic. This paper presents an exploratory systems feasibility study of Self-Evolving Coordination Protocols (SECP): coordination protocols that permit limited, externally validated self-modification while preserving fixed formal invariants. We study a controlled proof-of-concept setting in which six fixed Byzantine consensus protocol proposals are evaluated by six specialized decision modules. All coordination regimes operate under identical hard constraints, including Byzantine fault tolerance (f < n/3), O(n2) message complexity, complete non-statistical safety and liveness arguments, and bounded explainability. Four coordination regimes are compared in a single-shot design: unanimous hard veto, weighted scalar aggregation, SECP v1.0 (an agent-designed non-scalar protocol), and SECP v2.0 (the result of one governed modification). Outcomes are evaluated using a single metric, proposal coverage, defined as the number of proposals accepted. A single recursive modification increased coverage from two to three accepted proposals while preserving all declared invariants. The study makes no claims regarding statistical significance, optimality, convergence, or learning. Its contribution is architectural: it demonstrates that bounded self-modification of coordination protocols is technically implementable, auditable, and analyzable under explicit formal constraints, establishing a foundation for governed multi-agent systems.

---

### Real-Time 2D LiDAR Object Detection Using Three-Frame RGB Scan Encoding

Authors: Soheil Behnam Roudsari, Alexandre S. Brandão, Felipe N. Martins
Published: 2026-02-02
Categories: eess.SP, cs.CV, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2602.02167v1

Indoor service robots need perception that is robust, more privacy-friendly than RGB video, and feasible on embedded hardware. We present a camera-free 2D LiDAR object detection pipeline that encodes short-term temporal context by stacking three consecutive scans as RGB channels, yielding a compact YOLOv8n input without occupancy-grid construction while preserving angular structure and motion cues. Evaluated in Webots across 160 randomized indoor scenarios with strict scenario-level holdout, the method achieves 98.4% mAP@0.5 (0.778 mAP@0.5:0.95) with 94.9% precision and 94.7% recall on four object classes. On a Raspberry Pi 5, it runs in real time with a mean post-warm-up end-to-end latency of 47.8ms per frame, including scan encoding and postprocessing. Relative to a closely related occupancy-grid LiDAR-YOLO pipeline reported on the same platform, the proposed representation is associated with substantially lower reported end-to-end latency. Although results are simulation-based, they suggest that lightweight temporal encoding can enable accurate and real-time LiDAR-only detection for embedded indoor robotics without capturing RGB appearance.

---

### Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents

Authors: Pengfei He, Ash Fox, Lesly Miculicich, Stefan Friedli, Daniel Fabian, Burak Gokturk, Jiliang Tang, Chen-Yu Lee, Tomas Pfister, Long T. Le
Published: 2026-02-02
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2602.02164v2

Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of experience reuse. We propose Co-RedTeam, a security-aware multi-agent framework designed to mirror real-world red-teaming workflows by integrating security-domain knowledge, code-aware analysis, execution-grounded iterative reasoning, and long-term memory. Co-RedTeam decomposes vulnerability analysis into coordinated discovery and exploitation stages, enabling agents to plan, execute, validate, and refine actions based on real execution feedback while learning from prior trajectories. Extensive evaluations on challenging security benchmarks demonstrate that Co-RedTeam consistently outperforms strong baselines across diverse backbone models, achieving over 60% success rate in vulnerability exploitation and over 10% absolute improvement in vulnerability detection. Ablation and iteration studies further confirm the critical role of execution feedback, structured interaction, and memory for building robust and generalizable cybersecurity agents.

---

### Reg4Pru: Regularisation Through Random Token Routing for Token Pruning

Authors: Julian Wyatt, Ronald Clark, Irina Voiculescu
Published: 2026-02-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.02163v2

Transformers are widely adopted in modern vision models due to their strong ability to scale with dataset size and generalisability. However, this comes with a major drawback: computation scales quadratically to the total number of tokens. Numerous methods have been proposed to mitigate this. For example, we consider token pruning with reactivating tokens from preserved representations, but the increased computational efficiency of this method results in decreased stability from the preserved representations, leading to poorer dense prediction performance at deeper layers. In this work, we introduce Reg4Pru, a training regularisation technique that mitigates token-pruning performance loss for segmentation. We compare our models on the FIVES blood vessel segmentation dataset and find that Reg4Pru improves average precision by an absolute 46% compared to the same model trained without routing. This increase is observed using a configuration that achieves a 29% relative speedup in wall-clock time compared to the non-pruned baseline. These findings indicate that Reg4Pru is a valuable regulariser for token reduction strategies.

---

### Interpretable Tabular Foundation Models via In-Context Kernel Regression

Authors: Ratmir Miftachov, Bruno Charron, Simon Valentin
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02162v1

Tabular foundation models like TabPFN and TabICL achieve state-of-the-art performance through in-context learning, yet their architectures remain fundamentally opaque. We introduce KernelICL, a framework to enhance tabular foundation models with quantifiable sample-based interpretability. Building on the insight that in-context learning is akin to kernel regression, we make this mechanism explicit by replacing the final prediction layer with kernel functions (Gaussian, dot-product, kNN) so that every prediction is a transparent weighted average of training labels. We introduce a two-dimensional taxonomy that formally unifies standard kernel methods, modern neighbor-based approaches, and attention mechanisms under a single framework, and quantify inspectability via the perplexity of the weight distribution over training samples. On 55 TALENT benchmark datasets, KernelICL achieves performance on par with existing tabular foundation models, demonstrating that explicit kernel constraints on the final layer enable inspectable predictions without sacrificing performance.

---

### Generating Causal Temporal Interaction Graphs for Counterfactual Validation of Temporal Link Prediction

Authors: Aniq Ur Rahman, Justin P. Coon
Published: 2026-02-02
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2602.02161v1

Temporal link prediction (TLP) models are commonly evaluated based on predictive accuracy, yet such evaluations do not assess whether these models capture the causal mechanisms that govern temporal interactions. In this work, we propose a framework for counterfactual validation of TLP models by generating causal temporal interaction graphs (CTIGs) with known ground-truth causal structure. We first introduce a structural equation model for continuous-time event sequences that supports both excitatory and inhibitory effects, and then extend this mechanism to temporal interaction graphs. To compare causal models, we propose a distance metric based on cross-model predictive error, and empirically validate the hypothesis that predictors trained on one causal model degrade when evaluated on sufficiently distant models. Finally, we instantiate counterfactual evaluation under (i) controlled causal shifts between generating models and (ii) timestamp shuffling as a stochastic distortion with measurable causal distance. Our framework provides a foundation for causality-aware benchmarking.

---

### D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use

Authors: Bowen Xu, Shaoyu Wu, Hao Jiang, Kai Liu, Xin Chen, Lulu Hu, Bin Yang
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02160v1

Effective tool use and reasoning are essential capabilities for large reasoning models~(LRMs) to address complex real-world problems. Through empirical analysis, we identify that current LRMs lack the capability of sub-task decomposition in complex tool use scenarios, leading to Lazy Reasoning. To address this, we propose a two-stage training framework D-CORE~(\underline{\textbf{D}}ecomposing tasks and \underline{\textbf{Co}}mposing \underline{\textbf{Re}}asoning processes) that first incentivize the LRMs' task decomposition reasoning capability via self-distillation, followed by diversity-aware reinforcement learning~(RL) to restore LRMs' reflective reasoning capability. D-CORE achieves robust tool-use improvements across diverse benchmarks and model scales. Experiments on BFCLv3 demonstrate superiority of our method: D-CORE-8B reaches 77.7\% accuracy, surpassing the best-performing 8B model by 5.7\%. Meanwhile, D-CORE-14B establishes a new state-of-the-art at 79.3\%, outperforming 70B models despite being 5$\times$ smaller. The source code is available at https://github.com/alibaba/EfficientAI.

---

### Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing

Authors: Lingkun Long, Yushi Huang, Shihao Bai, Ruihao Gong, Jun Zhang, Ao Zhou, Jianlei Yang
Published: 2026-02-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.02159v1

Diffusion Large Language Models (dLLMs) deliver strong long-context processing capability in a non-autoregressive decoding paradigm. However, the considerable computational cost of bidirectional full attention limits the inference efficiency. Although sparse attention is promising, existing methods remain ineffective. This stems from the need to estimate attention importance for tokens yet to be decoded, while the unmasked token positions are unknown during diffusion. In this paper, we present Focus-dLLM, a novel training-free attention sparsification framework tailored for accurate and efficient long-context dLLM inference. Based on the finding that token confidence strongly correlates across adjacent steps, we first design a past confidence-guided indicator to predict unmasked regions. Built upon this, we propose a sink-aware pruning strategy to accurately estimate and remove redundant attention computation, while preserving highly influential attention sinks. To further reduce overhead, this strategy reuses identified sink locations across layers, leveraging the observed cross-layer consistency. Experimental results show that our method offers more than $29\times$ lossless speedup under $32K$ context length. The code is publicly available at: https://github.com/Longxmas/Focus-dLLM

---

### Traffic-Aware Navigation in Road Networks

Authors: Sarah Nassar
Published: 2026-02-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.02158v1

This project compares three graph search approaches for the task of traffic-aware navigation in Kingston's road network. These approaches include a single-run multi-query preprocessing algorithm (Floyd-Warshall-Ingerman), continuous single-query real-time search (Dijkstra's and A*), and an algorithm combining both approaches to balance between their trade-offs by first finding the top K shortest paths then iterating over them in real time (Yen's). Dijkstra's and A* resulted in the most traffic-aware optimal solutions with minimal preprocessing required. Floyd-Warshall-Ingerman was the fastest in real time but provided distance based paths with no traffic awareness. Yen's algorithm required significant preprocessing but balanced between the other two approaches in terms of runtime speed and optimality. Each approach presents advantages and disadvantages that need to be weighed depending on the circumstances of specific deployment contexts to select the best custom solution. *This project was completed as part of ELEC 844 (Search and Planning Algorithms for Robotics) in the Fall 2025 term.

---

### Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing

Authors: Egor Serov, Ilya Kuleshov, Alexey Zaytsev
Published: 2026-02-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.02157v2

Neural Controlled Differential Equations (Neural CDEs) provide a powerful continuous-time framework for sequence modeling, yet the roughness of the driving control path often restricts their efficiency. Standard splines introduce high-frequency variations that force adaptive solvers to take excessively small steps, driving up the Number of Function Evaluations (NFE). We propose a novel approach to Neural CDE path construction that replaces exact interpolation with Kernel and Gaussian Process (GP) smoothing, enabling explicit control over trajectory regularity. To recover details lost during smoothing, we propose an attention-based Multi-View CDE (MV-CDE) and its convolutional extension (MVC-CDE), which employ learnable queries to inform path reconstruction. This framework allows the model to distribute representational capacity across multiple trajectories, each capturing distinct temporal patterns. Empirical results demonstrate that our method, MVC-CDE with GP, achieves state-of-the-art accuracy while significantly reducing NFEs and total inference time compared to spline-based baselines.

---