# Research Papers — 2026-01 · bundle page 14 of 189

> Full-text markdown of papers #651–700 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/14
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/13.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/15.md)

### Matterhorn: Masked Time-to-First-Spike Encoding by Reassigning the Silent State for Sparse and Energy-Efficient Spiking Transformers

Authors: Zhanglu Yan, Kaiwen Tang, Zixuan Zhu, Zhenyu Bai, Qianhui Liu, Yongxin Zhu, Weng-Fai Wong
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22876v2

Spiking neural networks (SNNs) promise energy-efficient inference for large language models (LLMs), yet most reported savings rely on compute-operation counts that overlook data movement. Energy characterization of representative spiking transformers on a commercial 22-nm process shows that accumulation contributes less than 3% of total energy, while spike-triggered inter-core transfers and weight reads dominate the cost. This makes time-to-first-spike (TTFS) encoding a natural choice, as it limits each neuron to at most one spike. However, standard TTFS maps the silent state, an all-zero spike train that transmits no events, to the rarely occurring smallest value, while the most common activations still spike. This raises a simple question: why reserve the only cost-free codeword for a rare value? This choice inverts a basic principle of energy-aware coding, under which the zero-event codeword should represent the most common value, rather than a rare extreme. Thus, we introduce masked time-to-first-spike encoding (M-TTFS), which uses a temporal mask to reassign the silent state to the most common activation value, and a dead-zone extension that trades a controlled amount of information for greater sparsity. Built on M-TTFS with dead-zone radius $k{=}1$, our spiking transformer Matterhorn reaches an overall spike rate of 1.64% on GLUE at an average score of 84.64, exceeding the best prior spiking transformer by 1.42 percentage points while consuming 67% less energy, with consistent gains on spiking LLaMA models from 7B to 70B parameters. Together, these results show that under hardware-faithful accounting, the energy advantage of SNNs is not a given: it is earned by encodings that align spikes with the data distribution.

---

### From Labels to Facets: Building a Taxonomically Enriched Turkish Learner Corpus

Authors: Elif Sayar, Tolgahan Türker, Anna Golynskaia Knezhevich, Bihter Dereli, Ayşe Demirhas, Lionel Nicolas, Gülşen Eryiğit
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22875v2

In terms of annotation structure, most learner corpora rely on holistic flat label inventories which, even when extensive, do not explicitly separate multiple linguistic dimensions. This makes linguistically deep annotation difficult and complicates fine-grained analyses aimed at understanding why and how learners produce specific errors. To address these limitations, this paper presents a semi-automated annotation methodology for learner corpora, built upon a recently proposed faceted taxonomy, and implemented through a novel annotation extension framework. The taxonomy provides a theoretically grounded, multi-dimensional categorization that captures the linguistic properties underlying each error instance, thereby enabling standardized, fine-grained, and interpretable enrichment beyond flat annotations. The annotation extension tool, implemented based on the proposed extension framework for Turkish, automatically extends existing flat annotations by inferring additional linguistic and metadata information as facets within the taxonomy to provide richer learner-specific context. It was systematically evaluated and yielded promising performance results, achieving a facet-level accuracy of 95.86%. The resulting taxonomically enriched corpus offers enhanced querying capabilities and supports detailed exploratory analyses across learner corpora, enabling researchers to investigate error patterns through complex linguistic and pedagogical dimensions. This work introduces the first collaboratively annotated and taxonomically enriched Turkish Learner Corpus, a manual annotation guideline with a refined tagset, and an annotation extender. As the first corpus designed in accordance with the recently introduced taxonomy, we expect our study to pave the way for subsequent enrichment efforts of existing error-annotated learner corpora.

---

### EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis

Authors: Li Zhou, Hao Jiang, Junjie Li, Tianrui Wang, Haizhou Li
Published: 2026-01-30
Categories: eess.AS, cs.AI, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2601.22873v1

Achieving precise and controllable emotional expression is crucial for producing natural and context-appropriate speech in text-to-speech (TTS) synthesis. However, many emotion-aware TTS systems, including large language model (LLM)-based designs, rely on scaling fixed emotion embeddings or external guidance, limiting their ability to model emotion-specific latent characteristics. To address this gap, we present EmoShift, a lightweight activation-steering framework incorporating a EmoSteer layer, which learns a steering vector for each target emotion in the output embedding space to capture its latent offset and maintain stable, appropriate expression across utterances and categories. With only 10M trainable parameters,less than 1/30 of full fine-tuning, EmoShift outperforms zero-shot and fully fine-tuned baselines in objective and subjective evaluations, enhancing emotional expressiveness while preserving naturalness and speaker similarity. Further analysis confirms the proposed EmoSteer layer's effectiveness and reveals its potential for controllable emotional intensity in speech synthesis.

---

### Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild

Authors: Alexander Loth, Martin Kappes, Marc-Oliver Pahl
Published: 2026-01-30
Categories: cs.CY, cs.AI, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2601.22871v2

As foundation models (FMs) approach human-level fluency, distinguishing synthetic from organic content has become a key challenge for Trustworthy Web Intelligence. This paper presents JudgeGPT and RogueGPT, a dual-axis framework that decouples "authenticity" from "attribution" to investigate the mechanisms of human susceptibility. Analyzing 918 evaluations across five FMs (including GPT-4 and Llama-2), we employ Structural Causal Models (SCMs) as a principal framework for formulating testable causal hypotheses about detection accuracy. Contrary to partisan narratives, we find that political orientation shows a negligible association with detection performance ($r=-0.10$). Instead, "fake news familiarity" emerges as a candidate mediator ($r=0.35$), suggesting that exposure may function as adversarial training for human discriminators. We identify a "fluency trap" where GPT-4 outputs (HumanMachineScore: 0.20) bypass Source Monitoring mechanisms, rendering them indistinguishable from human text. These findings suggest that "pre-bunking" interventions should target cognitive source monitoring rather than demographic segmentation to ensure trustworthy information ecosystems.

---

### Conditional Compatibility Learning for Context-Dependent Anomaly Detection

Authors: Shashank Mishra, Didier Stricker, Jason Rambach
Published: 2026-01-30
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.22868v3

Anomaly detection usually assumes that abnormality is an intrinsic property of an observation. A defect is a defect, and a rare object is rare, regardless of where it appears. Many real-world anomalies do not work this way. A runner on a track is normal, but the same runner on a highway is not. The subject is unchanged; only the context makes it anomalous. This setting, long recognized as contextual anomaly detection, remains largely underexplored in modern vision-language systems. The difficulty is not merely empirical; it is formal. When anomaly labels depend on the relation between a subject and its context, any detector reasoning from a global representation that conflates subject and context is provably non-identifiable: two different subject-context configurations can map to the same embedding while requiring opposite labels, and no such detector can be correct on both. This impossibility motivates a different formulation: instead of asking whether an observation deviates from a global notion of normality, the model should ask whether subjects are compatible with their surrounding context. We define this as conditional compatibility learning. We instantiate this framework in CC-CLIP, a vision-language architecture that learns disentangled subject- and context-aware representations from a single image and fuses visual evidence through text-conditioned attention. CC-CLIP achieves state-of-the-art results on real-world contextual anomaly detection, substantially outperforming all existing CLIP-based and context-reasoning baselines. A single-branch variant of CC-CLIP also achieves competitive performance on structural anomaly benchmarks.

---

### Degradation-Aware Frequency Regulation of a Heterogeneous Battery Fleet via Reinforcement Learning

Authors: Tanay Raghunandan Srinivasa, Vivek Deulkar, Jia Bhargava, Mohammad Hajiesmaili, Prashant Shenoy
Published: 2026-01-30
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2601.22865v2

Battery energy storage systems are increasingly deployed as fast-responding resources for grid balancing services such as frequency regulation and for mitigating renewable generation uncertainty. However, repeated charging and discharging induces cycling degradation and reduces battery lifetime. This paper studies the real-time scheduling of a heterogeneous battery fleet that collectively tracks a stochastic balancing signal subject to per-battery ramp-rate and capacity constraints, while minimizing long-term cycling degradation. Cycling degradation is fundamentally path-dependent: it is determined by charge-discharge cycles formed by the state-of-charge (SoC) trajectory and is commonly quantified via rainflow cycle counting. This non-Markovian structure makes it difficult to express degradation as an additive per-time-step cost, complicating classical dynamic programming approaches. We address this challenge by formulating the fleet scheduling problem as a Markov decision process (MDP) with constrained action space and designing a dense proxy reward that provides informative feedback at each time step while remaining aligned with long-term cycle-depth reduction. To scale learning to large state-action spaces induced by fine-grained SoC discretization and asymmetric per-battery constraints, we develop a function-approximation reinforcement learning method using an Extreme Learning Machine (ELM) as a random nonlinear feature map combined with linear temporal-difference learning. We evaluate the proposed approach on a toy Markovian signal model and on a Markovian model trained from real-world regulation signal traces obtained from the University of Delaware, and demonstrate consistent reductions in cycle-depth occurrence and degradation metrics compared to baseline scheduling policies.

---

### Under-Canopy Terrain Reconstruction in Dense Forests Using RGB Imaging and Neural 3D Reconstruction

Authors: Refael Sheffer, Chen Pinchover, Haim Zisman, Dror Ozeri, Roee Litman
Published: 2026-01-30
Categories: cs.CV, cs.CY, cs.ET, cs.GR
arXiv: https://arxiv.org/abs/2601.22861v2

Mapping the terrain and understory hidden beneath dense forest canopies is of great interest for numerous applications such as search and rescue, trail mapping, forest inventory tasks, and more. Existing solutions rely on specialized sensors: either heavy, costly airborne LiDAR, or Airborne Optical Sectioning (AOS), which uses thermal synthetic aperture photography and is tailored for person detection. We introduce a novel approach for the reconstruction of canopy-free, photorealistic ground views using only conventional RGB images. Our solution is based on the celebrated Neural Radiance Fields (NeRF), a recent 3D reconstruction method. Additionally, we include specific image capture considerations, which dictate the needed illumination to successfully expose the scene beneath the canopy. To better cope with the poorly lit understory, we employ a low light loss. Finally, we propose two complementary approaches to remove occluding canopy elements by controlling per-ray integration procedure. To validate the value of our approach, we present two possible downstream tasks. For the task of search and rescue (SAR), we demonstrate that our method enables person detection which achieves promising results compared to thermal AOS (using only RGB images). Additionally, we show the potential of our approach for forest inventory tasks like tree counting. These results position our approach as a cost-effective, high-resolution alternative to specialized sensors for SAR, trail mapping, and forest-inventory tasks.

---

### Bayesian Interpolating Neural Network (B-INN): a scalable and reliable Bayesian model for large-scale physical systems

Authors: Chanwook Park, Brian Kim, Jiachen Guo, Wing Kam Liu
Published: 2026-01-30
Categories: math.NA, cs.AI
arXiv: https://arxiv.org/abs/2601.22860v2

Neural networks and machine learning models for uncertainty quantification suffer from limited scalability and poor reliability compared to their deterministic counterparts. In industry-scale active learning settings, where generating a single high-fidelity simulation may require days or weeks of computation and produce data volumes on the order of gigabytes, they quickly become impractical. This paper proposes a scalable and reliable Bayesian surrogate model, termed the Bayesian Interpolating Neural Network (B-INN). The B-INN combines high-order interpolation theory with tensor decomposition and alternating direction algorithm to enable effective dimensionality reduction without compromising predictive accuracy. We theoretically show that the function space of a B-INN is a subset of that of Gaussian processes, while its Bayesian inference exhibits linear complexity, $\mathcal{O}(N)$, with respect to the number of training samples. Numerical experiments demonstrate that B-INNs can be from 20 times to 10,000 times faster with a robust uncertainty estimation compared to Bayesian neural networks and Gaussian processes. These capabilities make B-INN a practical foundation for uncertainty-driven active learning in large-scale industrial simulations, where computational efficiency and robust uncertainty calibration are paramount.

---

### MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering

Authors: Chuanzhe Guo, Jingjing Wu, Sijun He, Yang Chen, Zhaoqi Kuang, Shilong Fan, Bingjin Chen, Siqi Bao, Jing Liu, Hua Wu, Qingfu Zhu, Wanxiang Che et al.
Published: 2026-01-30
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.22859v3

The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bottleneck stemming from the complexity of constructing executable environments across diverse languages. To address this, we introduce MEnvAgent, a Multi-language framework for automated Environment construction that facilitates scalable generation of verifiable task instances. MEnvAgent employs a multi-agent Planning-Execution-Verification architecture to autonomously resolve construction failures and integrates a novel Environment Reuse Mechanism that reduces computational overhead by incrementally patching historical environments. Evaluations on MEnvBench, a new benchmark comprising 1,000 tasks across 10 languages, demonstrate that MEnvAgent outperforms baselines, improving Fail-to-Pass (F2P) rates by 8.6% while reducing time costs by 43%. Additionally, we demonstrate the utility of MEnvAgent by constructing MEnvData-SWE, the largest open-source polyglot dataset of realistic verifiable Docker environments to date, alongside solution trajectories that enable consistent performance gains on SWE tasks across a wide range of models. Our code, benchmark, and dataset are available at https://github.com/ernie-research/MEnvAgent.

---

### Learning to Build Shapes by Extrusion

Authors: Thor Vestergaard Christiansen, Karran Pandey, Alba Reinders, Karan Singh, Morten Rieger Hannemose, J. Andreas Bærentzen
Published: 2026-01-30
Categories: cs.GR, cs.AI
arXiv: https://arxiv.org/abs/2601.22858v2

We introduce Text Encoded Extrusions (TEE), a text-based representation that expresses mesh construction as sequences of face extrusions rather than polygon lists, and a method for generating 3D meshes from TEE using a large language model (LLM). By learning extrusion sequences that assemble a mesh, similar to the way artists create meshes, our approach naturally supports arbitrary output face counts and produces manifold meshes by design, in contrast to recent mesh generative transformer based models. The learnt extrusion sequences can also be applied to existing meshes - enabling editing in addition to generation. To train our model, we decompose a library of quadrilateral meshes with non-self-intersecting face loops into constituent loops, which can be viewed as their building blocks, and finetune an LLM on the steps for reassembling the quadrilateral meshes by performing a sequence of extrusions. We demonstrate that our representation enables reconstruction, novel shape synthesis, and the addition of new features to existing meshes.

---

### OptiMAG: Structure-Semantic Alignment via Unbalanced Optimal Transport

Authors: Yilong Zuo, Xunkai Li, Zhihan Zhang, Qiangqiang Dai, Ronghua Li, Guoren Wang
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22856v1

Multimodal Attributed Graphs (MAGs) have been widely adopted for modeling complex systems by integrating multi-modal information, such as text and images, on nodes. However, we identify a discrepancy between the implicit semantic structure induced by different modality embeddings and the explicit graph structure. For instance, neighbors in the explicit graph structure may be close in one modality but distant in another. Since existing methods typically perform message passing over the fixed explicit graph structure, they inadvertently aggregate dissimilar features, introducing modality-specific noise and impeding effective node representation learning. To address this, we propose OptiMAG, an Unbalanced Optimal Transport-based regularization framework. OptiMAG employs the Fused Gromov-Wasserstein distance to explicitly guide cross-modal structural consistency within local neighborhoods, effectively mitigating structural-semantic conflicts. Moreover, a KL divergence penalty enables adaptive handling of cross-modal inconsistencies. This framework can be seamlessly integrated into existing multimodal graph models, acting as an effective drop-in regularizer. Experiments demonstrate that OptiMAG consistently outperforms baselines across multiple tasks, ranging from graph-centric tasks (e.g., node classification, link prediction) to multimodal-centric generation tasks (e.g., graph2text, graph2image). The source code will be available upon acceptance.

---

### Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification

Authors: Siyi Du, Xinzhe Luo, Declan P. O'Regan, Chen Qin
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22853v3

Multimodal deep learning (MDL) has achieved remarkable success across various domains, yet its practical deployment is often hindered by incomplete multimodal data. Existing incomplete MDL methods either discard missing modalities, risking the loss of valuable task-relevant information, or recover them, potentially introducing irrelevant noise, leading to the discarding-imputation dilemma. To address this dilemma, in this paper, we propose DyMo, a new inference-time dynamic modality selection framework that adaptively identifies and fuses reliable recovered modalities, fully exploring task-relevant information beyond the conventional discard-or-impute paradigm. Central to DyMo is a novel selection algorithm that maximizes multimodal task-relevant information for each test sample. Since direct estimation of such information at test time is intractable due to the unknown data distribution, we theoretically establish a connection between information and the task loss, which we compute at inference time as a tractable proxy. Building on this, a novel principled reward function is proposed to guide modality selection. In addition, we design a flexible multimodal network architecture compatible with arbitrary modality combinations, alongside a tailored training strategy for robust representation learning. Extensive experiments on diverse natural and medical image datasets show that DyMo significantly outperforms state-of-the-art incomplete/dynamic MDL methods across various missing-data scenarios. Our code is available at https://github.com//siyi-wind/DyMo.

---

### Hierarchical Shift Mixing -- Beyond Dense Attention in Transformers

Authors: Robert Forchheimer
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22852v1

Since the introduction of the Transformer architecture for large language models, the softmax-based attention layer has faced increasing scrutinity due to its quadratic-time computational complexity. Attempts have been made to replace it with less complex methods, at the cost of reduced performance in most cases. We introduce Hierarchical Shift Mixing (HSM), a general framework for token mixing that distributes pairwise token interactions across Transformer layers rather than computing them densely within each layer. HSM enables linear-time complexity while remaining agnostic to the specific mixing function. We show that even simple HSM variants achieve performance close to softmax attention, and that hybrid architectures combining HSM with softmax attention can outperform a GPT-style Transformer baseline while reducing computational cost during both training and inference.

---

### When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training

Authors: Felicia Körner, Max Müller-Eberstein, Anna Korhonen, Barbara Plank
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22851v1

Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important -- especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept spaces, thought to support generalization and cross-lingual transfer. However, these prior studies often do not use causal methods, lack deeper error analysis or focus on the final model only, leaving open how these spaces emerge during training. We investigate the development of language-agnostic concept spaces during pretraining of EuroLLM through the causal interpretability method of activation patching. We isolate cross-lingual concept representations, then inject them into a translation prompt to investigate how consistently translations can be altered, independently of the language. We find that shared concept spaces emerge early} and continue to refine, but that alignment with them is language-dependent}. Furthermore, in contrast to prior work, our fine-grained manual analysis reveals that some apparent gains in translation quality reflect shifts in behavior -- like selecting senses for polysemous words or translating instead of copying cross-lingual homographs -- rather than improved translation ability. Our findings offer new insight into the training dynamics of cross-lingual alignment and the conditions under which causal interpretability methods offer meaningful insights in multilingual contexts.

---

### Unconditional flow-based time series generation with equivariance-regularised latent spaces

Authors: Camilo Carvajal Reyes, Felipe Tobar
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22848v1

Flow-based models have proven successful for time-series generation, particularly when defined in lower-dimensional latent spaces that enable efficient sampling. However, how to design latent representations with desirable equivariance properties for time-series generative modelling remains underexplored. In this work, we propose a latent flow-matching framework in which equivariance is explicitly encouraged through a simple regularisation of a pre-trained autoencoder. Specifically, we introduce an equivariance loss that enforces consistency between transformed signals and their reconstructions, and use it to fine-tune latent spaces with respect to basic time-series transformations such as translation and amplitude scaling. We show that these equivariance-regularised latent spaces improve generation quality while preserving the computational advantages of latent flow models. Experiments on multiple real-world datasets demonstrate that our approach consistently outperforms existing diffusion-based baselines in standard time-series generation metrics, while achieving orders-of-magnitude faster sampling. These results highlight the practical benefits of incorporating geometric inductive biases into latent generative models for time series.

---

### How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models

Authors: Leonard Hackel, Tom Burgert, Begüm Demir
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22841v2

Large-scale foundation models (FMs) in remote sensing (RS) (denoted as RS FMs) are developed following paradigms established in computer vision (CV), yet the validity of transferring CV scaling laws to RS has not been systematically examined. We hypothesize that RS FMs enter an overparameterized regime at substantially smaller scales than their CV counterparts, with task-relevant information encoded redundantly across model dimensions. To test this hypothesis, we apply post-hoc slimmability, uniform width reduction of pretrained encoder transformer blocks, as a tool to measure representational redundancy across eight state-of-the-art RS FMs on classification, segmentation, and change detection tasks. RS FMs retain 69% to 109% relative accuracy on RS datasets under aggressive width reduction, while masked autoencoder (MAE) and DINOv2 pretrained on natural images (denoted as CV MAE and CV DINOv2) degrade sharply on ImageNet subsets of matched class count over the same range of computational requirements. A CV MAE evaluated directly on the same RS datasets narrows but does not close the gap, indicating that both dataset characteristics and domain-specific pretraining contribute to the differences between the models. Mechanistic analyses such as feature correlation, explained variance, and effective dimensionality indicate that task-relevant variance concentrates in few principal components and is redundantly encoded across model dimensions. We further show that learned slimmable training improves over post-hoc slimmability for contrastive objectives, while reconstruction-based objectives do not benefit from current slimmable training protocols. Our findings establish post-hoc slimming as a practical deployment strategy for resource-constrained RS applications and as a diagnostic tool for representational redundancy in RS FMs. Upon acceptance, we will publish all code.

---

### Neural Clothing Tryer: Customized Virtual Try-On via Semantic Enhancement and Controlling Diffusion Model

Authors: Zhijing Yang, Weiwei Zhang, Mingliang Yang, Siyuan Peng, Yukai Shi, Junpeng Tan, Tianshui Chen, Liruo Zhong
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22838v1

This work aims to address a novel Customized Virtual Try-ON (Cu-VTON) task, enabling the superimposition of a specified garment onto a model that can be customized in terms of appearance, posture, and additional attributes. Compared with traditional VTON task, it enables users to tailor digital avatars to their individual preferences, thereby enhancing the virtual fitting experience with greater flexibility and engagement. To address this task, we introduce a Neural Clothing Tryer (NCT) framework, which exploits the advanced diffusion models equipped with semantic enhancement and controlling modules to better preserve semantic characterization and textural details of the garment and meanwhile facilitating the flexible editing of the model's postures and appearances. Specifically, NCT introduces a semantic-enhanced module to take semantic descriptions of garments and utilizes a visual-language encoder to learn aligned features across modalities. The aligned features are served as condition input to the diffusion model to enhance the preservation of the garment's semantics. Then, a semantic controlling module is designed to take the garment image, tailored posture image, and semantic description as input to maintain garment details while simultaneously editing model postures, expressions, and various attributes. Extensive experiments on the open available benchmark demonstrate the superior performance of the proposed NCT framework.

---

### NativeTok: Native Visual Tokenization for Improved Image Generation

Authors: Bin Wu, Mengqi Huang, Weinan Jia, Zhendong Mao
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22837v1

VQ-based image generation typically follows a two-stage pipeline: a tokenizer encodes images into discrete tokens, and a generative model learns their dependencies for reconstruction. However, improved tokenization in the first stage does not necessarily enhance the second-stage generation, as existing methods fail to constrain token dependencies. This mismatch forces the generative model to learn from unordered distributions, leading to bias and weak coherence. To address this, we propose native visual tokenization, which enforces causal dependencies during tokenization. Building on this idea, we introduce NativeTok, a framework that achieves efficient reconstruction while embedding relational constraints within token sequences. NativeTok consists of: (1) a Meta Image Transformer (MIT) for latent image modeling, and (2) a Mixture of Causal Expert Transformer (MoCET), where each lightweight expert block generates a single token conditioned on prior tokens and latent features. We further design a Hierarchical Native Training strategy that updates only new expert blocks, ensuring training efficiency. Extensive experiments demonstrate the effectiveness of NativeTok.

---

### Just-in-Time Catching Test Generation at Meta

Authors: Matthew Becker, Yifei Chen, Nicholas Cochran, Pouyan Ghasemi, Abhishek Gulati, Mark Harman, Zachary Haluza, Mehrdad Honarkhah, Herve Robert, Jiacheng Liu, Weini Liu, Sreeja Thummala et al.
Published: 2026-01-30
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.22832v1

We report on Just-in-Time catching test generation at Meta, designed to prevent bugs in large scale backend systems of hundreds of millions of line of code. Unlike traditional hardening tests, which pass at generation time, catching tests are meant to fail, surfacing bugs before code lands. The primary challenge is to reduce development drag from false positive test failures. Analyzing 22,126 generated tests, we show code-change-aware methods improve candidate catch generation 4x over hardening tests and 20x over coincidentally failing tests. To address false positives, we use rule-based and LLM-based assessors. These assessors reduce human review load by 70%. Inferential statistical analysis showed that human-accepted code changes are assessed to have significantly more false positives, while human-rejected changes have significantly more true positives. We reported 41 candidate catches to engineers; 8 were confirmed to be true positives, 4 of which would have led to serious failures had they remained uncaught. Overall, our results show that Just-in-Time catching is scalable, industrially applicable, and that it prevents serious failures from reaching production.

---

### A Comparative Evaluation of Large Vision-Language Models for 2D Object Detection under SOTIF Conditions

Authors: Ji Zhou, Yilin Ding, Yongqi Zhao, Jiachen Xu, Dong Bi, Johannes Betz, Arno Eichberger
Published: 2026-01-30
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2601.22830v2

Reliable environmental perception remains one of the main obstacles for safe operation of automated vehicles. Safety of the Intended Functionality (SOTIF) concerns safety risks from perception insufficiencies, particularly under adverse conditions where conventional detectors often falter. While Large Vision-Language Models (LVLMs) demonstrate promising semantic reasoning, their quantitative effectiveness for safety-critical 2D object detection is underexplored. This paper presents a systematic evaluation of ten representative LVLMs using the PeSOTIF dataset, a benchmark specifically curated for long-tail traffic scenarios and environmental degradations. Performance is quantitatively compared against two specialized detectors: the anchor-based YOLOv5 and the transformer-based RT-DETRv4. Experimental results reveal a critical trade-off: top-performing LVLMs (e.g., Gemini 3) surpass the YOLOv5 in recall by over 25% and closely match RT-DETRv4 under natural visual degradation, while specialized detectors retain an advantage in geometric precision for handcrafted perturbations. These findings highlight the complementary strengths of semantic reasoning versus geometric regression, supporting the use of LVLMs as high-level safety validators in SOTIF-oriented automated driving systems.

---

### Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA

Authors: Zhan Fa, Yue Duan, Jian Zhang, Lei Qi, Wanqi Yang, Yinghuan Shi
Published: 2026-01-30
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2601.22828v1

Continual learning (CL) in vision-language models (VLMs) faces significant challenges in improving task adaptation and avoiding catastrophic forgetting. Existing methods usually have heavy inference burden or rely on external knowledge, while Low-Rank Adaptation (LoRA) has shown potential in reducing these issues by enabling parameter-efficient tuning. However, considering directly using LoRA to alleviate the catastrophic forgetting problem is non-trivial, we introduce a novel framework that restructures a single LoRA module as a decomposable Rank-1 Expert Pool. Our method learns to dynamically compose a sparse, task-specific update by selecting from this expert pool, guided by the semantics of the (CLS) token. In addition, we propose an Activation-Guided Orthogonal (AGO) loss that orthogonalizes critical parts of LoRA weights across tasks. This sparse composition and orthogonalization enable fewer parameter updates, resulting in domain-aware learning while minimizing inter-task interference and maintaining downstream task performance. Extensive experiments across multiple settings demonstrate state-of-the-art results in all metrics, surpassing zero-shot upper bounds in generalization. Notably, it reduces trainable parameters by 96.7% compared to the baseline method, eliminating reliance on external datasets or task-ID discriminators. The merged LoRAs retain less weights and incur no inference latency, making our method computationally lightweight.

---

### Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment

Authors: Mathieu Petitbois, Rémy Portelas, Sylvain Lamprier
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2601.22823v2

We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. In this setting, aligning style with high task performance is particularly challenging due to distribution shift and inherent conflicts between style and reward. Existing methods, despite introducing numerous definitions of style, often fail to reconcile these objectives effectively. To address these challenges, we propose a unified definition of behavior style and instantiate it into a practical framework. Building on this, we introduce Style-Conditioned Implicit Q-Learning (SCIQL), which leverages offline goal-conditioned RL techniques, such as hindsight relabeling and value learning, and combine it with a new Gated Advantage Weighted Regression mechanism to efficiently optimize task performance while preserving style alignment. Experiments demonstrate that SCIQL achieves superior performance on both objectives compared to prior offline methods. Code, datasets and visuals are available in: https://mathieu-petitbois.github.io/projects/sciql/.

---

### User-Adaptive Meta-Learning for Cold-Start Medication Recommendation with Uncertainty Filtering

Authors: Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Dongjie Wang, Mei Liu, Zijun Yao
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22820v1

Large-scale Electronic Health Record (EHR) databases have become indispensable in supporting clinical decision-making through data-driven treatment recommendations. However, existing medication recommender methods often struggle with a user (i.e., patient) cold-start problem, where recommendations for new patients are usually unreliable due to the lack of sufficient prescription history for patient profiling. While prior studies have utilized medical knowledge graphs to connect medication concepts through pharmacological or chemical relationships, these methods primarily focus on mitigating the item cold-start issue and fall short in providing personalized recommendations that adapt to individual patient characteristics. Meta-learning has shown promise in handling new users with sparse interactions in recommender systems. However, its application to EHRs remains underexplored due to the unique sequential structure of EHR data. To tackle these challenges, we propose MetaDrug, a multi-level, uncertainty-aware meta-learning framework designed to address the patient cold-start problem in medication recommendation. MetaDrug proposes a novel two-level meta-adaptation mechanism, including self-adaptation, which adapts the model to new patients using their own medical events as support sets to capture temporal dependencies; and peer-adaptation, which adapts the model using similar visits from peer patients to enrich new patient representations. Meanwhile, to further improve meta-adaptation outcomes, we introduce an uncertainty quantification module that ranks the support visits and filters out the unrelated information for adaptation consistency. We evaluate our approach on the MIMIC-III and Acute Kidney Injury (AKI) datasets. Experimental results on both datasets demonstrate that MetaDrug consistently outperforms state-of-the-art medication recommendation methods on cold-start patients.

---

### Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models

Authors: Charles Westphal, Keivan Navaie, Fernando E. Rosas
Published: 2026-01-30
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.22818v2

Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels. Prior work demonstrated this threat but relied on trivially recoverable encodings. We formalize payload recoverability via classifier accuracy and show previous schemes achieve 100\% recoverability. In response, we introduce low-recoverability steganography, replacing arbitrary mappings with embedding-space-derived ones. For Llama-8B (LoRA) and Ministral-8B (LoRA) trained on TrojanStego prompts, exact secret recovery rises from 17$\rightarrow$30\% (+78\%) and 24$\rightarrow$43\% (+80\%) respectively, while on Llama-70B (LoRA) trained on Wiki prompts, it climbs from 9$\rightarrow$19\% (+123\%), all while reducing payload recoverability. We then discuss detection. We argue that detecting fine-tuning-based steganographic attacks requires approaches beyond traditional steganalysis. Standard approaches measure distributional shift, which is an expected side-effect of fine-tuning. Instead, we propose a mechanistic interpretability approach: linear probes trained on later-layer activations detect the secret with up to 33\% higher accuracy in fine-tuned models compared to base models, even for low-recoverability schemes. This suggests that malicious fine-tuning leaves actionable internal signatures amenable to interpretability-based defenses.

---

### Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features

Authors: Markus Mueller, Kathrin Gruber, Dennis Fok
Published: 2026-01-30
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.22816v3

Advances in generative modeling have recently been adapted to tabular data containing discrete and continuous features. However, generating mixed-type features that combine discrete states with an otherwise continuous distribution in a single feature remains challenging. We advance the state-of-the-art in diffusion models for tabular data with a cascaded approach. We first generate a low-resolution version of a tabular data row, that is, the collection of the purely categorical features and a coarse categorical representation of numerical features. Next, this information is leveraged in the high-resolution flow matching model via a novel guided conditional probability path and data-dependent coupling. The low-resolution representation of numerical features explicitly accounts for discrete outcomes, such as missing or inflated values, and therewith enables a more faithful generation of mixed-type features. We formally prove that this cascade tightens the transport cost bound. The results indicate that our model generates significantly more realistic samples and captures distributional details more accurately, for example, the detection score improves by 51.9\%. Code is available at https://github.com/muellermarkus/tabcascade.

---

### Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

Authors: Andrei Panferov, Erik Schultheis, Soroush Tabesh, Dan Alistarh
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22813v2

The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models such as LLMs. Yet, existing quantized training methods still sacrifice some of the representation capacity of this format in favor of more accurate unbiased quantized gradient estimation by stochastic rounding (SR), losing noticeable accuracy relative to standard FP16 and FP8 training. In this paper, improve the state of the art for quantized training in NVFP4 via a novel unbiased quantization routine for micro-scaled formats, called MS-EDEN, that has more than 2x lower quantization error than SR. We integrate it into a novel fully-NVFP4 quantization scheme for linear layers, called Quartet II. We show analytically that Quartet II achieves consistently better gradient estimation across all major matrix multiplications, both on the forward and on the backward passes. In addition, our proposal synergizes well with recent training improvements aimed specifically at NVFP4. We further validate Quartet II on end-to-end LLM training with up to 1.9B parameters on 38B tokens. We provide kernels for execution on NVIDIA Blackwell GPUs with up to 4.2x speedup over BF16. Our code is available at https://github.com/IST-DASLab/Quartet-II .

---

### FarmMind: Reasoning-Query-Driven Dynamic Segmentation for Farmland Remote Sensing Images

Authors: Haiyang Wu, Weiliang Mu, Jipeng Zhang, Zhong Dandan, Zhuofei Du, Haifeng Li, Tao Chao
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22809v1

Existing methods for farmland remote sensing image (FRSI) segmentation generally follow a static segmentation paradigm, where analysis relies solely on the limited information contained within a single input patch. Consequently, their reasoning capability is limited when dealing with complex scenes characterized by ambiguity and visual uncertainty. In contrast, human experts, when interpreting remote sensing images in such ambiguous cases, tend to actively query auxiliary images (such as higher-resolution, larger-scale, or temporally adjacent data) to conduct cross-verification and achieve more comprehensive reasoning. Inspired by this, we propose a reasoning-query-driven dynamic segmentation framework for FRSIs, named FarmMind. This framework breaks through the limitations of the static segmentation paradigm by introducing a reasoning-query mechanism, which dynamically and on-demand queries external auxiliary images to compensate for the insufficient information in a single input image. Unlike direct queries, this mechanism simulates the thinking process of human experts when faced with segmentation ambiguity: it first analyzes the root causes of segmentation ambiguities through reasoning, and then determines what type of auxiliary image needs to be queried based on this analysis. Extensive experiments demonstrate that FarmMind achieves superior segmentation performance and stronger generalization ability compared with existing methods. The source code and dataset used in this work are publicly available at: https://github.com/WithoutOcean/FarmMind.

---

### Diachronic Stereo Matching for Multi-Date Satellite Imagery

Authors: Elías Masquil, Luca Savant Aira, Roger Marí, Thibaud Ehret, Pablo Musé, Gabriele Facciolo
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22808v1

Recent advances in image-based satellite 3D reconstruction have progressed along two complementary directions. On one hand, multi-date approaches using NeRF or Gaussian-splatting jointly model appearance and geometry across many acquisitions, achieving accurate reconstructions on opportunistic imagery with numerous observations. On the other hand, classical stereoscopic reconstruction pipelines deliver robust and scalable results for simultaneous or quasi-simultaneous image pairs. However, when the two images are captured months apart, strong seasonal, illumination, and shadow changes violate standard stereoscopic assumptions, causing existing pipelines to fail. This work presents the first Diachronic Stereo Matching method for satellite imagery, enabling reliable 3D reconstruction from temporally distant pairs. Two advances make this possible: (1) fine-tuning a state-of-the-art deep stereo network that leverages monocular depth priors, and (2) exposing it to a dataset specifically curated to include a diverse set of diachronic image pairs. In particular, we start from a pretrained MonSter model, trained initially on a mix of synthetic and real datasets such as SceneFlow and KITTI, and fine-tune it on a set of stereo pairs derived from the DFC2019 remote sensing challenge. This dataset contains both synchronic and diachronic pairs under diverse seasonal and illumination conditions. Experiments on multi-date WorldView-3 imagery demonstrate that our approach consistently surpasses classical pipelines and unadapted deep stereo models on both synchronic and diachronic settings. Fine-tuning on temporally diverse images, together with monocular priors, proves essential for enabling 3D reconstruction from previously incompatible acquisition dates. Left image (winter) Right image (autumn) DSM geometry Ours (1.23 m) Zero-shot (3.99 m) LiDAR GT Figure 1. Output geometry for a winter-autumn image pair from Omaha (OMA 331 test scene). Our method recovers accurate geometry desp…

---

### Aligning the Unseen in Attributed Graphs: Interplay between Graph Geometry and Node Attributes Manifold

Authors: Aldric Labarthe, Roland Bouffanais, Julien Randon-Furling
Published: 2026-01-30
Categories: cs.AI, math.DG
arXiv: https://arxiv.org/abs/2601.22806v1

The standard approach to representation learning on attributed graphs -- i.e., simultaneously reconstructing node attributes and graph structure -- is geometrically flawed, as it merges two potentially incompatible metric spaces. This forces a destructive alignment that erodes information about the graph's underlying generative process. To recover this lost signal, we introduce a custom variational autoencoder that separates manifold learning from structural alignment. By quantifying the metric distortion needed to map the attribute manifold onto the graph's Heat Kernel, we transform geometric conflict into an interpretable structural descriptor. Experiments show our method uncovers connectivity patterns and anomalies undetectable by conventional approaches, proving both their theoretical inadequacy and practical limitations.

---

### SOMBRERO: Measuring and Steering Boundary Placement in End-to-End Hierarchical Sequence Models

Authors: Pit Neitemeier, Alessio Serra, Jiaze Li, Sascha Wirges, Lukas Balles, Jan Hendrik Metzen
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.22805v1

Hierarchical sequence models replace fixed tokenization with learned segmentations that compress long byte sequences for efficient autoregressive modeling. While recent end-to-end methods can learn meaningful boundaries from the language-modeling objective alone, it remains difficult to quantitatively assess and systematically steer where compute is spent. We introduce a router-agnostic metric of boundary quality, boundary enrichment B, which measures how strongly chunk starts concentrate on positions with high next-byte surprisal. Guided by this metric, we propose Sombrero, which steers boundary placement toward predictive difficulty via a confidence-alignment boundary loss and stabilizes boundary learning by applying confidence-weighted smoothing at the input level rather than on realized chunks. On 1B scale, across UTF-8 corpora covering English and German text as well as code and mathematical content, Sombrero improves the accuracy-efficiency trade-off and yields boundaries that more consistently align compute with hard-to-predict positions.

---

### CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning

Authors: Ji Shi, Peiming Guo, Meishan Zhang, Miao Zhang, Xuebo Liu, Min Zhang, Weili Guan
Published: 2026-01-30
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2601.22803v1

Code verifiers play a critical role in post-verification for LLM-based code generation, yet existing supervised fine-tuning methods suffer from data scarcity, high failure rates, and poor inference efficiency. While reinforcement learning (RL) offers a promising alternative by optimizing models through execution-driven rewards without labeled supervision, our preliminary results show that naive RL with only functionality rewards fails to generate effective unit tests for difficult branches and samples. We first theoretically analyze showing that branch coverage, sample difficulty, syntactic and functional correctness can be jointly modeled as RL rewards, where optimizing these signals can improve the reliability of unit-test-based verification. Guided by this analysis, we design syntax- and functionality-aware rewards and further propose branch- and sample-difficulty--aware RL using exponential reward shaping and static analysis metrics. With this formulation, CVeDRL achieves state-of-the-art performance with only 0.6B parameters, yielding up to 28.97% higher pass rate and 15.08% higher branch coverage than GPT-3.5, while delivering over $20\times$ faster inference than competitive baselines. Code is available at https://github.com/LIGHTCHASER1/CVeDRL.git

---

### Clipping-Free Policy Optimization for Large Language Models

Authors: Ömer Veysel Çağatan, Barış Akgün, Gözde Gül Şahin, Xuandong Zhao
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22801v1

Reinforcement learning has become central to post-training large language models, yet dominant algorithms rely on clipping mechanisms that introduce optimization issues at scale, including zero-gradient regions, reward hacking, and training instability. We propose Clipping-Free Policy Optimization (CFPO), which replaces heuristic clipping with a convex quadratic penalty derived from Total Variation divergence constraints, yielding an everywhere-differentiable objective that enforces stable policy updates without hard boundaries. We evaluate CFPO across both reasoning and alignment settings. In reasoning, CFPO matches clipping-based methods on downstream benchmarks while extending the stable training regime. In alignment, CFPO mitigates verbosity exploitation and reduces capability degradation, while achieving competitive instruction-following performance. CFPO requires only a one-line code change and no additional hyperparameters. Our results suggest that CFPO is a promising drop-in alternative to clipping-based methods for LLM post-training.

---

### Trackly: A Unified SaaS Platform for User Behavior Analytics and Real Time Rule Based Anomaly Detection

Authors: Md Zahurul Haque, Md. Hafizur Rahman, Yeahyea Sarker
Published: 2026-01-30
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.22800v1

Understanding user behavior is essential for improving digital experiences, optimizing business conversions, and mitigating threats like account takeovers, fraud, and bot attacks. Most platforms separate product analytics and security, creating fragmented visibility and delayed threat detection. Trackly, a scalable SaaS platform, unifies comprehensive user behavior analytics with real time, rule based anomaly detection. It tracks sessions, IP based geo location, device browser fingerprints, and granular events such as page views, add to cart, and checkouts. Suspicious activities logins from new devices or locations, impossible travel (Haversine formula), rapid bot like actions, VPN proxy usage, or multiple accounts per IP are flagged via configurable rules with weighted risk scoring, enabling transparent, explainable decisions. A real time dashboard provides global session maps, DAU MAU, bounce rates, and session durations. Integration is simplified with a lightweight JavaScript SDK and secure REST APIs. Implemented on a multi tenant microservices stack (ASP.NET Core, MongoDB, RabbitMQ, Next.js), Trackly achieved 98.1% accuracy, 97.7% precision, and 2.25% false positives on synthetic datasets, proving its efficiency for SMEs and ecommerce.

---

### HeatMat: Simulation of City Material Impact on Urban Heat Island Effect

Authors: Marie Reinbigler, Romain Rouffet, Peter Naylor, Mikolaj Czerkawski, Nikolaos Dionelis, Elisabeth Brunet, Catalin Fetita, Rosalie Martin
Published: 2026-01-30
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2601.22796v1

The Urban Heat Island (UHI) effect, defined as a significant increase in temperature in urban environments compared to surrounding areas, is difficult to study in real cities using sensor data (satellites or in-situ stations) due to their coarse spatial and temporal resolution. Among the factors contributing to this effect are the properties of urban materials, which differ from those in rural areas. To analyze their individual impact and to test new material configurations, a high-resolution simulation at the city scale is required. Estimating the current materials used in a city, including those on building facades, is also challenging. We propose HeatMat, an approach to analyze at high resolution the individual impact of urban materials on the UHI effect in a real city, relying only on open data. We estimate building materials using street-view images and a pre-trained vision-language model (VLM) to supplement existing OpenStreetMap data, which describes the 2D geometry and features of buildings. We further encode this information into a set of 2D maps that represent the city's vertical structure and material characteristics. These maps serve as inputs for our 2.5D simulator, which models coupled heat transfers and enables random-access surface temperature estimation at multiple resolutions, reaching an x20 speedup compared to an equivalent simulation in 3D.

---

### Sparse or Dense? A Mechanistic Estimation of Computation Density in Transformer-based LLMs

Authors: Corentin Kervadec, Iuliia Lysova, Marco Baroni, Gemma Boleda
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22795v2

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion of the parameters, while only marginally impacting performance. This suggests that the computation is not uniformly distributed across the parameters. We introduce here a technique to systematically quantify computation density in LLMs. In particular, we design a density estimator drawing on mechanistic interpretability. We experimentally test our estimator and find that: (1) contrary to what has been often assumed, LLM processing generally involves dense computation; (2) computation density is dynamic, in the sense that models shift between sparse and dense processing regimes depending on the input; (3) per-input density is significantly correlated across LLMs, suggesting that the same inputs trigger either low or high density. Investigating the factors influencing density, we observe that predicting rarer tokens requires higher density, and increasing context length often decreases the density. We believe that our computation density estimator will contribute to a better understanding of the processing at work in LLMs, challenging their symbolic interpretation.

---

### CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR

Authors: Muhammad Shakeel, Yosuke Fukumoto, Chikara Maeda, Chyi-Jiunn Lin, Shinji Watanabe
Published: 2026-01-30
Categories: eess.AS, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2601.22792v2

We present CALM, a joint Contextual Acoustic-Linguistic Modeling framework for multi-speaker automatic speech recognition (ASR). In personalized AI scenarios, the joint availability of acoustic and linguistic cues naturally motivates the integration of target-speaker conditioning with contextual biasing in overlapping conversations. CALM implements this integration in an end-to-end framework through speaker embedding-driven target-speaker extraction and dynamic vocabulary-based contextual biasing. We evaluate CALM on simulated English (LibriSpeechMix) and Japanese (Corpus of Spontaneous Japanese mixtures, CSJMix). On two-speaker mixtures, CALM reduces biased word error rate (B-WER) from 12.7 to 4.7 on LibriSpeech2Mix and biased character error rate (B-CER) from 16.6 to 8.4 on CSJMix2 (eval3), demonstrating the effectiveness of joint acoustic-linguistic modeling across languages. We additionally report results on the AMI corpus (IHM-mix condition) to validate performance on standardized speech mixtures.

---

### Conditional Performance Guarantee for Large Reasoning Models

Authors: Jianguo Huang, Hao Zeng, Bingyi Jing, Hongxin Wei, Bo An
Published: 2026-01-30
Categories: cs.AI, math.ST
arXiv: https://arxiv.org/abs/2601.22790v1

Large reasoning models have shown strong performance through extended chain-of-thought reasoning, yet their computational cost remains significant. Probably approximately correct (PAC) reasoning provides statistical guarantees for efficient reasoning by adaptively switching between thinking and non-thinking models, but the guarantee holds only in the marginal case and does not provide exact conditional coverage. We propose G-PAC reasoning, a practical framework that provides PAC-style guarantees at the group level by partitioning the input space. We develop two instantiations: Group PAC (G-PAC) reasoning for known group structures and Clustered PAC (C-PAC) reasoning for unknown groupings. We prove that both G-PAC and C-PAC achieve group-conditional risk control, and that grouping can strictly improve efficiency over marginal PAC reasoning in heterogeneous settings. Our experiments on diverse reasoning benchmarks demonstrate that G-PAC and C-PAC successfully achieve group-conditional risk control while maintaining substantial computational savings.

---

### Float8@2bits: Entropy Coding Enables Data-Free Model Compression

Authors: Patrick Putzky, Martin Genzel, Mattes Mollenhauer, Sebastian Schulze, Thomas Wollmann, Stefan Dietzel
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22787v2

Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4 or HQQ) offer maximum accessibility but suffer from functional collapse at extreme bit-rates below 4 bits. On the other hand, techniques leveraging calibration data or extensive recovery training achieve superior fidelity but impose high computational constraints and face uncertain robustness under data distribution shifts. We introduce EntQuant, a framework that unites the advantages of these distinct paradigms. By matching the performance of data-dependent methods with the speed and universality of data-free techniques, EntQuant enables practical utility in the extreme compression regime. Our method decouples numerical precision from storage cost via entropy coding, compressing a 70B parameter model in less than 10 minutes. We demonstrate that EntQuant does not only achieve state-of-the-art results on standard evaluation sets and models, but also retains functional performance on more complex benchmarks with instruction-tuned models, all at modest inference overhead.

---

### Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework

Authors: Hamid Reza Akbari, Mohammad Hossein Sameti, Amir M. Mansourian, Mohammad Hossein Rohban, Hossein Sameti
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22786v1

The pursuit of Artificial General Intelligence (AGI) is a central goal in language model development, in which consciousness-like processing could serve as a key facilitator. While current language models are not conscious, they exhibit behaviors analogous to certain aspects of consciousness. This paper investigates the implementation of a leading theory of consciousness, Integrated Information Theory (IIT), within language models via a reward-based learning paradigm. IIT provides a formal, axiom-based mathematical framework for quantifying consciousness. Drawing inspiration from its core principles, we formulate a novel reward function that quantifies a text's causality, coherence and integration, characteristics associated with conscious processing. Empirically, it is found that optimizing for this IIT-inspired reward leads to more concise text generation. On out of domain tasks, careful tuning achieves up to a 31% reduction in output length while preserving accuracy levels comparable to the base model. In addition to primary task performance, the broader effects of this training methodology on the model's confidence calibration and test-time computational scaling is analyzed. The proposed framework offers significant practical advantages: it is conceptually simple, computationally efficient, requires no external data or auxiliary models, and leverages a general, capability-driven signal rather than task-specific heuristics. Code available at https://github.com/MH-Sameti/LLM_PostTraining.git

---

### Approximating $f$-Divergences with Rank Statistics

Authors: Viktor Stein, José Manuel de Frutos
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.22784v2

We introduce a rank-statistic approximation of $f$-divergences that avoids explicit density-ratio estimation by working directly with the distribution of ranks. For a resolution parameter $K$, we map the mismatch between two univariate distributions $μ$ and $ν$ to a rank histogram on $\{ 0, \ldots, K\}$ and measure its deviation from uniformity via a discrete $f$-divergence, yielding a rank-statistic divergence estimator. We prove that the resulting estimator of the divergence is monotone in $K$, is always a lower bound of the true $f$-divergence, and we establish quantitative convergence rates for $K\to\infty$ under mild regularity of the quantile-domain density ratio. To handle high-dimensional data, we define the sliced rank-statistic $f$-divergence by averaging the univariate construction over random projections, and we provide convergence results for the sliced limit as well. We also derive finite-sample deviation bounds along with asymptotic normality results for the estimator. Finally, we empirically validate the approach by benchmarking against neural baselines and illustrating its use as a learning objective in generative modeling experiments.

---

### Compact Hypercube Embeddings for Fast Text-based Wildlife Observation Retrieval

Authors: Ilyass Moummad, Marius Miron, David Robinson, Kawtar Zaher, Hervé Goëau, Olivier Pietquin, Pierre Bonnet, Emmanuel Chemla, Matthieu Geist, Alexis Joly
Published: 2026-01-30
Categories: cs.IR, cs.CV, cs.LG, cs.MM, cs.SD
arXiv: https://arxiv.org/abs/2601.22783v2

Large-scale biodiversity monitoring platforms increasingly rely on multimodal wildlife observations. While recent foundation models enable rich semantic representations across vision, audio, and language, retrieving relevant observations from massive archives remains challenging due to the computational cost of high-dimensional similarity search. In this work, we introduce compact hypercube embeddings for fast text-based wildlife observation retrieval, a framework that enables efficient text-based search over large-scale wildlife image and audio databases using compact binary representations. Building on the cross-view code alignment hashing framework, we extend lightweight hashing beyond a single-modality setup to align natural language descriptions with visual or acoustic observations in a shared Hamming space. Our approach leverages pretrained wildlife foundation models, including BioCLIP and BioLingual, and adapts them efficiently for hashing using parameter-efficient fine-tuning. We evaluate our method on large-scale benchmarks, including iNaturalist2024 for text-to-image retrieval and iNatSounds2024 for text-to-audio retrieval, as well as multiple soundscape datasets to assess robustness under domain shift. Results show that retrieval using discrete hypercube embeddings achieves competitive, and in several cases superior, performance compared to continuous embeddings, while drastically reducing memory and search cost. Moreover, we observe that the hashing objective consistently improves the underlying encoder representations, leading to stronger retrieval and zero-shot generalization. These results demonstrate that binary, language-based retrieval enables scalable and efficient search over large wildlife archives for biodiversity monitoring systems.

---

### Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent Training

Authors: Linjia Kang, Zhimin Wang, Yongkang Zhang, Duo Wu, Jinghe Wang, Ming Ma, Haopeng Yan, Zhi Wang
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22781v1

Large-scale, high-quality interaction trajectories are essential for advancing mobile Graphical User Interface (GUI) agents. While existing methods typically rely on labor-intensive human demonstrations or automated model exploration to generate GUI trajectories, they lack fine-grained control over task difficulty. This fundamentally restricts learning effectiveness due to the mismatch between the training difficulty and the agent's capabilities. Inspired by how humans acquire skills through progressively challenging tasks, we propose MobileGen, a novel data generation framework that adaptively aligns training difficulty with the GUI agent's capability frontier. Specifically, MobileGen explicitly decouples task difficulty into structural (e.g., trajectory length) and semantic (e.g., task goal) dimensions. It then iteratively evaluates the agent on a curated prior dataset to construct a systematic profile of its capability frontier across these two dimensions. With this profile, the probability distribution of task difficulty is adaptively computed, from which the target difficulty for the next round of training can be sampled. Guided by the sampled difficulty, a multi-agent controllable generator is finally used to synthesize high-quality interaction trajectories along with corresponding task instructions. Extensive experiments show that MobileGen consistently outperforms existing data generation methods by improving the average performance of GUI agents by 1.57 times across multiple challenging benchmarks. This highlights the importance of capability-aligned data generation for effective mobile GUI agent training.

---

### Color Matters: Demosaicing-Guided Color Correlation Training for Generalizable AI-Generated Image Detection

Authors: Nan Zhong, Yiran Xu, Mian Zou
Published: 2026-01-30
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2601.22778v2

As realistic AI-generated images threaten digital authenticity, we address the generalization failure of generative artifact-based detectors by exploiting the intrinsic properties of the camera imaging pipeline. Concretely, we investigate color correlations induced by the color filter array (CFA) and demosaicing, and propose a Demosaicing-guided Color Correlation Training (DCCT) framework for AI-generated image detection. By simulating the CFA sampling pattern, we decompose each color image into a single-channel input (as the condition) and the remaining two channels as the ground-truth targets (for prediction). A self-supervised U-Net is trained to model the conditional distribution of the missing channels from the given one, parameterized via a mixture of logistic functions. Our theoretical analysis reveals that DCCT targets a provable distributional difference in color-correlation features between photographic and AI-generated images. By leveraging these distinct features to construct a binary classifier, DCCT achieves state-of-the-art generalization and robustness, significantly outperforming prior methods across over 20 unseen generators.

---

### RASST: Retrieval-Augmented Simultaneous Speech Translation

Authors: Jiaxuan Luo, Siqi Ouyang, Jiaxing Xu, Lei Li
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22777v2

Simultaneous speech translation produces target text incrementally from partial speech input. Recent speech large language models have markedly improved SST quality but still struggle with rare and domain-specific terminology. Retrieval augmentation has helped in automatic speech recognition and neural machine translation, but extending it to SST is non-trivial: retrieval must be fast and accurate under partial speech, and the model must decide whether and when to apply retrieved terms during incremental generation. We propose Retrieval-Augmented Simultaneous Speech Translation (RASST), which addresses both challenges. For accurate cross-modal retrieval under partial input, RASST trains a lightweight speech-text retriever that produces chunkwise terminology hints for the Speech LLM via multi-scale retrieval. To use these hints correctly, we synthesize training data that teaches the Speech LLM to decide whether and when to apply each retrieved term. Experiments on ACL 60/60 dev set and the ESO test set show that RASST improves terminology accuracy by nearly 40% and overall translation quality by up to 3 BLEU points, with negligible computational overhead.

---

### TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization

Authors: Shichao Ma, Zhiyuan Ma, Ming Yang, Xiaofan Li, Xing Wu, Jintao Du, Yu Cheng, Weiqiang Wang, Qiliang Liu, Zhengyang Zhou, Yang Wang
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22776v2

Multi-turn tool-integrated reasoning enables Large Language Models (LLMs) to solve complex tasks through iterative information retrieval. However, current reinforcement learning (RL) frameworks for search-augmented reasoning predominantly rely on sparse outcome-level rewards, leading to a "Double Homogenization Dilemma." This manifests as (1) Process homogenization, where the thinking, reasoning, and tooling involved in generation are ignored. (2) Intra-group homogenization, coarse-grained outcome rewards often lead to inefficiencies in intra-group advantage estimation with methods like Group Relative Policy Optimization (GRPO) during sampling. To address this, we propose Turn-level Stage-aware Policy Optimization (TSPO). TSPO introduces the First-Occurrence Latent Reward (FOLR) mechanism, allocating partial rewards to the step where the ground-truth answer first appears, thereby preserving process-level signals and increasing reward variance within groups without requiring external reward models or any annotations. Extensive experiments demonstrate that TSPO significantly outperforms state-of-the-art baselines, achieving average performance gains of 24% and 13.6% on Qwen2.5-3B and 7B models, respectively. Code is available at https://github.com/Flipped-May/TSPO.

---

### GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations

Authors: Julia Herbinger, Gabriel Laberge, Maximilian Muschalik, Yann Pequignot, Marvin N. Wright, Fabian Fumagalli
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.22771v1

Feature-based explanation methods aim to quantify how features influence the model's behavior, either locally or globally, but different methods often disagree, producing conflicting explanations. This disagreement arises primarily from two sources: how feature interactions are handled and how feature dependencies are incorporated. We propose GRANITE, a generalized regional explanation framework that partitions the feature space into regions where interaction and distribution influences are minimized. This approach aligns different explanation methods, yielding more consistent and interpretable explanations. GRANITE unifies existing regional approaches, extends them to feature groups, and introduces a recursive partitioning algorithm to estimate such regions. We demonstrate its effectiveness on real-world datasets, providing a practical tool for consistent and interpretable feature explanations.

---

### Beyond Abstract Compliance: Operationalising trust in AI as a moral relationship

Authors: Lameck Mbangula Amugongo, Tutaleni Asino, Nicola J Bidwell
Published: 2026-01-30
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.22769v1

Dominant approaches, e.g. the EU's "Trustworthy AI framework", treat trust as a property that can be designed for, evaluated, and governed according to normative and technical criteria. They do not address how trust is subjectively cultivated and experienced, culturally embedded, and inherently relational. This paper proposes some expanded principles for trust in AI that can be incorporated into common development methods and frame trust as a dynamic, temporal relationship, which involves transparency and mutual respect. We draw on relational ethics and, in particular, African communitarian philosophies, to foreground the nuances of inclusive, participatory processes and long-term relationships with communities. Involving communities throughout the AI lifecycle can foster meaningful relationships with AI design and development teams that incrementally build trust and promote more equitable and context-sensitive AI systems. We illustrate how trust-enabling principles based on African relational ethics can be operationalised, using two use-cases for AI: healthcare and education.

---

### Sparse Attention as Compact Kernel Regression

Authors: Saul Santos, Nuno Gonçalves, Daniel C. McNamee, Marcos Treviso, André F. T Martins
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22766v3

Recent work has revealed a link between self-attention mechanisms in transformers and test-time kernel regression via the Nadaraya-Watson estimator, with standard softmax attention corresponding to a Gaussian kernel. However, a kernel-theoretic understanding of sparse attention mechanisms is currently missing. In this paper, we establish a formal correspondence between sparse attention and compact (bounded support) kernels. We show that normalized ReLU and sparsemax attention arise from Epanechnikov kernel regression under fixed and adaptive normalizations, respectively. More generally, we demonstrate that widely used kernels in nonparametric density estimation -- including Epanechnikov, biweight, and triweight -- correspond to $α$-entmax attention with $α= 1 + \frac{1}{n}$ for $n \in \mathbb{N}$, while the softmax/Gaussian relationship emerges in the limit $n \to \infty$. This unified perspective explains how sparsity naturally emerges from kernel design and provides principled alternatives to heuristic top-$k$ attention and other associative memory mechanisms. Experiments with a kernel-regression-based variant of transformers -- Memory Mosaics -- show that kernel-based sparse attention achieves competitive performance on language modeling, in-context learning, and length generalization tasks, offering a principled framework for designing attention mechanisms.

---

### Bayesian Matrix Completion Under Geometric Constraints

Authors: Rohit Varma Chiluvuri, Santosh Nannuru
Published: 2026-01-30
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2601.22765v1

The completion of a Euclidean distance matrix (EDM) from sparse and noisy observations is a fundamental challenge in signal processing, with applications in sensor network localization, acoustic room reconstruction, molecular conformation, and manifold learning. Traditional approaches, such as rank-constrained optimization and semidefinite programming, enforce geometric constraints but often struggle under sparse or noisy conditions. This paper introduces a hierarchical Bayesian framework that places structured priors directly on the latent point set generating the EDM, naturally embedding geometric constraints. By incorporating a hierarchical prior on latent point set, the model enables automatic regularization and robust noise handling. Posterior inference is performed using a Metropolis-Hastings within Gibbs sampler to handle coupled latent point posterior. Experiments on synthetic data demonstrate improved reconstruction accuracy compared to deterministic baselines in sparse regimes.

---

### How Far Can Pretrained LLMs Go in Symbolic Music? Controlled Comparisons of Supervised and Preference-based Adaptation

Authors: Deepak Kumar, Emmanouil Karystinaios, Gerhard Widmer, Markus Schedl
Published: 2026-01-30
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.22764v1

Music often shares notable parallels with language, motivating the use of pretrained large language models (LLMs) for symbolic music understanding and generation. Despite growing interest, the practical effectiveness of adapting instruction-tuned LLMs to symbolic music remains insufficiently characterized. We present a controlled comparative study of finetuning strategies for ABC-based generation and understanding, comparing an off-the-shelf instruction-tuned backbone to domain-adapted variants and a music-specialized LLM baseline. Across multiple symbolic music corpora and evaluation signals, we provide some insights into adaptation choices for symbolic music applications. We highlight the domain adaptation vs.~preserving prior information tradeoff as well as the distinct behaviour of metrics used to measure the domain adaptation for symbolic music.

---