# Research Papers — 2026-01 · bundle page 68 of 189 > Full-text markdown of papers #3351–3400 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/68 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/67.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/69.md) ### Adaptive Attribute-Decoupled Encryption for Trusted Respiratory Monitoring in Resource-Limited Consumer Healthcare Authors: Xinyu Li, Jinyang Huang, Feng-Qi Cui, Meng Wang, Peng Zhao, Meng Li, Dan Guo, Meng Wang Published: 2026-01-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.16241v2 Respiratory monitoring is an extremely important task in modern medical services. Due to its significant advantages, e.g., non-contact, radar-based respiratory monitoring has attracted widespread attention from both academia and industry. Unfortunately, though it can achieve high monitoring accuracy, consumer electronics-grade radar data inevitably contains User-sensitive Identity Information (USI), which may be maliciously used and further lead to privacy leakage. To track these challenges, by variational mode decomposition (VMD) and adversarial loss-based encryption, we propose a novel Trusted Respiratory Monitoring paradigm, Tru-RM, to perform automated respiratory monitoring through radio signals while effectively anonymizing USI. The key enablers of Tru-RM are Attribute Feature Decoupling (AFD), Flexible Perturbation Encryptor (FPE), and robust Perturbation Tolerable Network (PTN) used for attribute decomposition, identity encryption, and perturbed respiratory monitoring, respectively. Specifically, AFD is designed to decompose the raw radar signals into the universal respiratory component, the personal difference component, and other unrelated components. Then, by using large noise to drown out the other unrelated components, and the phase noise algorithm with a learning intensity parameter to eliminate USI in the personal difference component, FPE is designed to achieve complete user identity information encryption without affecting respiratory features. Finally, by designing the transferred generalized domain-independent network, PTN is employed to accurately detect respiration when waveforms change significantly. Extensive experiments based on various detection distances, respiratory patterns, and durations demonstrate the superior performance of Tru-RM on strong anonymity of USI, and high detection accuracy of perturbed respiratory waveforms. --- ### CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback Authors: Wenhang Ge, Guibao Shen, Jiawei Feng, Luozhou Wang, Hao Lu, Xingye Tian, Xin Tao, Ying-Cong Chen Published: 2026-01-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.16214v1 Recent advances in camera-controlled video diffusion models have significantly improved video-camera alignment. However, the camera controllability still remains limited. In this work, we build upon Reward Feedback Learning and aim to further improve camera controllability. However, directly borrowing existing ReFL approaches faces several challenges. First, current reward models lack the capacity to assess video-camera alignment. Second, decoding latent into RGB videos for reward computation introduces substantial computational overhead. Third, 3D geometric information is typically neglected during video decoding. To address these limitations, we introduce an efficient camera-aware 3D decoder that decodes video latent into 3D representations for reward quantization. Specifically, video latent along with the camera pose are decoded into 3D Gaussians. In this process, the camera pose not only acts as input, but also serves as a projection parameter. Misalignment between the video latent and camera pose will cause geometric distortions in the 3D structure, resulting in blurry renderings. Based on this property, we explicitly optimize pixel-level consistency between the rendered novel views and ground-truth ones as reward. To accommodate the stochastic nature, we further introduce a visibility term that selectively supervises only deterministic regions derived via geometric warping. Extensive experiments conducted on RealEstate10K and WorldScore benchmarks demonstrate the effectiveness of our proposed method. Project page: \href{https://a-bigbao.github.io/CamPilot/}{CamPilot Page}. --- ### Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition Authors: Geo Ahn, Inwoong Lee, Taeoh Kim, Minho Shim, Dongyoon Wee, Jinwoo Choi Published: 2026-01-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.16211v3 Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of previously observed primitives. In this work, we tackle a key failure mode: models predict verbs via object-driven shortcuts (i.e., relying on the labeled object class) rather than temporal evidence. We argue that sparse compositional supervision and verb-object learning asymmetry can promote object-driven shortcut learning. Our analysis with proposed diagnostic metrics shows that existing methods overfit to training co-occurrence patterns and underuse temporal verb cues, resulting in weak generalization to unseen compositions. To address object-driven shortcuts, we propose Robust COmpositional REpresentations (RCORE) with two components. Co-occurrence Prior Regularization (CPR) adds explicit supervision for unseen compositions and regularizes the model against frequent co-occurrence priors by treating them as hard negatives. Temporal Order Regularization for Composition (TORC) enforces temporal-order sensitivity to learn temporally grounded verb representations. Across Sth-com and EK100-com, RCORE reduces shortcut diagnostics and consequently improves compositional generalization. --- ### PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation Authors: Onkar Susladkar, Tushar Prakash, Adheesh Juvekar, Kiet A. Nguyen, Dong-Hwan Jang, Inderjit S Dhillon, Ismini Lourentzou Published: 2026-01-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.16210v2 Discrete video VAEs underpin modern text-to-video generation and video understanding systems, yet existing tokenizers typically learn visual codebooks at a single scale with limited vocabularies and shallow language supervision, leading to poor cross-modal alignment and zero-shot transfer. We introduce PyraTok, a language-aligned pyramidal tokenizer that learns semantically structured discrete latents across multiple spatiotemporal resolutions. PyraTok builds on a pretrained video VAE and a novel Language aligned Pyramidal Quantization (LaPQ) module that discretizes encoder features at several depths using a shared large binary codebook, yielding compact yet expressive video token sequences. To tightly couple visual tokens with language, PyraTok jointly optimizes multi-scale text-guided quantization and a global autoregressive objective over the token hierarchy. Across ten benchmarks, PyraTok delivers state-of-the-art (SOTA) video reconstruction, consistently improves text-to-video quality, and sets new SOTA zero-shot performance on video segmentation, temporal action localization, and video understanding, scaling robustly to up to 4K/8K resolutions. --- ### Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders Authors: Shengbang Tong, Boyang Zheng, Ziteng Wang, Bingda Tang, Nanye Ma, Ellis Brown, Jihan Yang, Rob Fergus, Yann LeCun, Saining Xie Published: 2026-01-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.16208v1 Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet by training in high-dimensional semantic latent spaces. In this work, we investigate whether this framework can scale to large-scale, freeform text-to-image (T2I) generation. We first scale RAE decoders on the frozen representation encoder (SigLIP-2) beyond ImageNet by training on web, synthetic, and text-rendering data, finding that while scale improves general fidelity, targeted data composition is essential for specific domains like text. We then rigorously stress-test the RAE design choices originally proposed for ImageNet. Our analysis reveals that scaling simplifies the framework: while dimension-dependent noise scheduling remains critical, architectural complexities such as wide diffusion heads and noise-augmented decoding offer negligible benefits at scale Building on this simplified framework, we conduct a controlled comparison of RAE against the state-of-the-art FLUX VAE across diffusion transformer scales from 0.5B to 9.8B parameters. RAEs consistently outperform VAEs during pretraining across all model scales. Further, during finetuning on high-quality datasets, VAE-based models catastrophically overfit after 64 epochs, while RAE models remain stable through 256 epochs and achieve consistently better performance. Across all experiments, RAE-based diffusion models demonstrate faster convergence and better generation quality, establishing RAEs as a simpler and stronger foundation than VAEs for large-scale T2I generation. Additionally, because both visual understanding and generation can operate in a shared representation space, the multimodal model can directly reason over generated latents, opening new possibilities for unified models. --- ### Computer Environments Elicit General Agentic Intelligence in LLMs Authors: Daixuan Cheng, Shaohan Huang, Yuxian Gu, Huatong Song, Guoxin Chen, Li Dong, Wayne Xin Zhao, Ji-Rong Wen, Furu Wei Published: 2026-01-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.16206v3 Agentic intelligence in large language models (LLMs) requires not only model intrinsic capabilities but also interactions with external environments. Equipping LLMs with computers now represents a prevailing trend. However, the computer environment's intrinsic value has not been systematically investigated, particularly its potential to elicit general capabilities. Here we introduce LLM-in-Sandbox, which virtualizes the computer as a code sandbox with only basic functionalities, and demonstrate that this minimal setting elicits computer-based meta-capabilities for general task solving: external resource access, file management, and code execution. Without additional training, strong models achieve substantial gains (up to 15.5%) across mathematics, physics, chemistry, biomedicine, long-context understanding, and instruction following, while reducing token consumption by up to 8 times. Furthermore, we develop LLM-in-Sandbox-RL to train models exclusively on non-agentic data within the sandbox, empowering weaker models to harness the environment and internalize these interactions. Our results demonstrate that computer environments elicit general intelligence, yield efficiency gains, and can be harnessed through training, serving as a promising foundation for generalist agents. --- ### Counterfactual Training: Teaching Models Plausible and Actionable Explanations Authors: Patrick Altmeyer, Aleksander Buszydlik, Arie van Deursen, Cynthia C. S. Liem Published: 2026-01-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.16205v1 We propose a novel training regime termed counterfactual training that leverages counterfactual explanations to increase the explanatory capacity of models. Counterfactual explanations have emerged as a popular post-hoc explanation method for opaque machine learning models: they inform how factual inputs would need to change in order for a model to produce some desired output. To be useful in real-world decision-making systems, counterfactuals should be plausible with respect to the underlying data and actionable with respect to the feature mutability constraints. Much existing research has therefore focused on developing post-hoc methods to generate counterfactuals that meet these desiderata. In this work, we instead hold models directly accountable for the desired end goal: counterfactual training employs counterfactuals during the training phase to minimize the divergence between learned representations and plausible, actionable explanations. We demonstrate empirically and theoretically that our proposed method facilitates training models that deliver inherently desirable counterfactual explanations and additionally exhibit improved adversarial robustness. --- ### Feature-Space Smoothing: Certified Robustness of Deep Representations Authors: Song Xia, Meiwen Ding, Chenqi Kong, Wenhan Yang, Xudong Jiang Published: 2026-01-22 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.16200v3 Modern deep learning models exhibit strong capabilities across diverse applications, yet remain vulnerable to malicious inputs that induce erroneous predictions via feature-space distortion. To address this vulnerability, we propose Feature-space Smoothing (FS), a general defense framework that provides certified robustness at the feature representation level. We show that FS converts a given feature encoder into a smoothed variant that is guaranteed to maintain a certified lower bound on the cosine similarity between clean and adversarial features under l_2-bounded perturbations. We then establish that this Feature Cosine Similarity Bound (FCSB) can be extended to the prediction-wise certification under the cosine similarity measure, and the value of FCSB is determined by the encoder intrinsic Gaussian robustness score. Building on those insights, we introduce the Gaussian Smoothness Booster (GSB), a plug-and-play module to improve the encoder Gaussian robustness score. Specifically, the GSB module is plugged to enhance the feature-space consistency and maintain the feature utility for downstream tasks under Gaussian perturbations. This design enables seamless integration of FS on the protected model, e.g., Multimodal Large Language Models (MLLMs), without additional model retraining or alignment, improving its robustness while preserving the performance for downstream task-oriented decoding. Extensive experiments demonstrate that integrating FS consistently provides non-trivial certified robustness and significantly improves task-oriented performance under strong white-box adversarial attacks across diverse models and applications. --- ### Pushing the limits of unconstrained machine-learned interatomic potentials Authors: Filippo Bigi, Paolo Pegolo, Arslan Mazitov, Jonathan Schmidt, Michele Ceriotti Published: 2026-01-22 Categories: physics.chem-ph, stat.ML arXiv: https://arxiv.org/abs/2601.16195v3 Machine-learned interatomic potentials (MLIPs) are increasingly used to replace computationally demanding electronic-structure calculations to model matter at the atomic scale. The most commonly used model architectures are constrained to fulfill a number of physical laws exactly, from geometric symmetries to energy conservation. Evidence is mounting that relaxing some of these constraints can be beneficial to the efficiency and (somewhat surprisingly) accuracy of MLIPs, even though care should be taken to avoid qualitative failures associated with the breaking of physical symmetries. Given the recent trend of scaling up models to larger numbers of parameters and training samples, a very important question is how unconstrained MLIPs behave in this limit. Here we investigate this issue, showing that -- when trained on large datasets -- unconstrained models can be superior in accuracy and speed when compared to physically constrained models. We assess these models both in terms of benchmark accuracy and in terms of usability in practical scenarios, focusing on static simulation workflows such as geometry optimization and lattice dynamics. We conclude that accurate unconstrained models can be applied with confidence, especially since simple inference-time modifications can be used to recover observables that are consistent with the relevant physical symmetries. --- ### A Rolling-Space Branch-and-Price Algorithm for the Multi-Compartment Vehicle Routing Problem with Multiple Time Windows Authors: El Mehdi Er Raqabi, Kevin Dalmeijer, Pascal Van Hentenryck Published: 2026-01-22 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2601.16194v1 This paper investigates the multi-compartment vehicle routing problem with multiple time windows (MCVRPMTW), an extension of the classical vehicle routing problem with time windows that considers vehicles equipped with multiple compartments and customers requiring service across several delivery time windows. The problem incorporates three key compartment-related features: (i) compartment flexibility in the number of compartments, (ii) item-to-compartment compatibility, and (iii) item-to-item compatibility. The problem also accommodates practical operational requirements such as driver breaks. To solve the MCVRPMTW, we develop an exact branch-and-price (B&P) algorithm in which the pricing problem is solved using a labeling algorithm. Several acceleration strategies are introduced to limit symmetry during label extensions, improve the stability of dual solutions in column generation, and enhance the branching process. To handle large-scale instances, we propose a rolling-space B&P algorithm that integrates clustering techniques into the solution framework. Extensive computational experiments on instances inspired by a real-world industrial application demonstrate the effectiveness of the proposed approach and provide useful managerial insights for practical implementation. --- ### 360Anything: Geometry-Free Lifting of Images and Videos to 360° Authors: Ziyi Wu, Daniel Watson, Andrea Tagliasacchi, David J. Fleet, Marcus A. Brubaker, Saurabh Saxena Published: 2026-01-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.16192v2 Lifting perspective images and videos to 360° panoramas enables immersive 3D world generation. Existing approaches often rely on explicit geometric alignment between the perspective and the equirectangular projection (ERP) space. Yet, this requires known camera metadata, obscuring the application to in-the-wild data where such calibration is typically absent or noisy. We propose 360Anything, a geometry-free framework built upon pre-trained diffusion transformers. By treating the perspective input and the panorama target simply as token sequences, 360Anything learns the perspective-to-equirectangular mapping in a purely data-driven way, eliminating the need for camera information. Our approach achieves state-of-the-art performance on both image and video perspective-to-360° generation, outperforming prior works that use ground-truth camera information. We also trace the root cause of the seam artifacts at ERP boundaries to zero-padding in the VAE encoder, and introduce Circular Latent Encoding to facilitate seamless generation. Finally, we show competitive results in zero-shot camera FoV and orientation estimation benchmarks, demonstrating 360Anything's deep geometric understanding and broader utility in computer vision tasks. Additional results are available at https://360anything.github.io/. --- ### Learning to Discover at Test Time Authors: Mert Yuksekgonul, Daniel Koceja, Xinhao Li, Federico Bianchi, Jed McCaleb, Xiaolong Wang, Jan Kautz, Yejin Choi, James Zou, Carlos Guestrin, Yu Sun Published: 2026-01-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.16175v2 How can we use AI to discover a new state of the art for a scientific problem? Prior work in test-time scaling, such as AlphaEvolve, performs search by prompting a frozen LLM. We perform reinforcement learning at test time, so the LLM can continue to train, but now with experience specific to the test problem. This form of continual learning is quite special, because its goal is to produce one great solution rather than many good ones on average, and to solve this very problem rather than generalize to other problems. Therefore, our learning objective and search subroutine are designed to prioritize the most promising solutions. We call this method Test-Time Training to Discover (TTT-Discover). Following prior work, we focus on problems with continuous rewards. We report results for every problem we attempted, across mathematics, GPU kernel engineering, algorithm design, and biology. TTT-Discover sets the new state of the art in almost all of them: (i) Erdős' minimum overlap problem and an autocorrelation inequality; (ii) a GPUMode kernel competition (up to $2\times$ faster than prior art); (iii) past AtCoder algorithm competitions; and (iv) denoising problem in single-cell analysis. Our solutions are reviewed by experts or the organizers. All our results are achieved with an open model, OpenAI gpt-oss-120b, and can be reproduced with our publicly available code, in contrast to previous best results that required closed frontier models. Our test-time training runs are performed using Tinker, an API by Thinking Machines, with a cost of only a few hundred dollars per problem. --- ### Beyond Predictive Uncertainty: Reliable Representation Learning with Structural Constraints Authors: Yiyao Yang Published: 2026-01-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2601.16174v3 Uncertainty estimation in machine learning has traditionally focused on the prediction stage, aiming to quantify confidence in model outputs while treating learned representations as deterministic and reliable by default. In this work, we challenge this implicit assumption and argue that reliability should be regarded as a first-class property of learned representations themselves. We propose a principled framework for reliable representation learning that explicitly models representation-level uncertainty and leverages structural constraints as inductive biases to regularize the space of feasible representations. Our approach introduces uncertainty-aware regularization directly in the representation space, encouraging representations that are not only predictive but also stable, well-calibrated, and robust to noise and structural perturbations. Structural constraints, such as sparsity, relational structure, or feature-group dependencies, are incorporated to define meaningful geometry and reduce spurious variability in learned representations, without assuming fully correct or noise-free structure. Importantly, the proposed framework is independent of specific model architectures and can be integrated with a wide range of representation learning methods. --- ### Inference-Time Diversity in RL-Trained Lean Theorem Provers: A Diagnostic Study Authors: Zachary Burton Published: 2026-01-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.16172v3 RL-trained Lean theorem provers mode-collapse at inference time: on miniF2F-test with DeepSeek-Prover-V1.5-RL, doubling the i.i.d.\ sampling budget from $k{=}32$ to $k{=}64$ produces zero additional solved theorems (42/244 in both cases). A fixed schedule of 15 tactic skeletons breaks this plateau and recovers a $+45%$ relative improvement at $k{=}16$ (mean $Δ= +12.3 \pm 4.2$ theorems across $n{=}3$ seeds, sign preserved in every seed). A controlled diversity ablation rules out the prompt-diversity confound: tactic skeletons help, paraphrases match the baseline, and irrelevant Lean comments actively degrade. A leave-one-out formalization-difficulty stratification reveals a structural-content gradient across the three perturbations. The phenomenon is RL-specific: V1.5-Base proves zero theorems regardless of intervention, identifying RL as the stage that creates the proof capability which subsequently collapses; extending to two additional 7B Lean provers, RL-trained DeepSeek-Prover-V2-7B contributes $+3$ frontier solves no i.i.d. baseline can reach despite a flat aggregate, while SFT-trained Goedel-Prover does not ( $-10.0$ $\pm 4.4$ theorems, $n{=}3$, sign preserved every seed). Inference-time structural diversity is a cheap, complementary axis for RL-trained provers, orthogonal to scaling model size or training compute. --- ### Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning Authors: Moo Jin Kim, Yihuai Gao, Tsung-Yi Lin, Yen-Chen Lin, Yunhao Ge, Grace Lam, Percy Liang, Shuran Song, Ming-Yu Liu, Chelsea Finn, Jinwei Gu Published: 2026-01-22 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2601.16163v1 Recent video generation models demonstrate remarkable ability to capture complex physical interactions and scene evolution over time. To leverage their spatiotemporal priors, robotics works have adapted video models for policy learning but introduce complexity by requiring multiple stages of post-training and new architectural components for action generation. In this work, we introduce Cosmos Policy, a simple approach for adapting a large pretrained video model (Cosmos-Predict2) into an effective robot policy through a single stage of post-training on the robot demonstration data collected on the target platform, with no architectural modifications. Cosmos Policy learns to directly generate robot actions encoded as latent frames within the video model's latent diffusion process, harnessing the model's pretrained priors and core learning algorithm to capture complex action distributions. Additionally, Cosmos Policy generates future state images and values (expected cumulative rewards), which are similarly encoded as latent frames, enabling test-time planning of action trajectories with higher likelihood of success. In our evaluations, Cosmos Policy achieves state-of-the-art performance on the LIBERO and RoboCasa simulation benchmarks (98.5% and 67.1% average success rates, respectively) and the highest average score in challenging real-world bimanual manipulation tasks, outperforming strong diffusion policies trained from scratch, video model-based policies, and state-of-the-art vision-language-action models fine-tuned on the same robot demonstrations. Furthermore, given policy rollout data, Cosmos Policy can learn from experience to refine its world model and value function and leverage model-based planning to achieve even higher success rates in challenging tasks. We release code, models, and training data at https://research.nvidia.com/labs/dir/cosmos-policy/ --- ### Domain-Incremental Continual Learning for Robust and Efficient Keyword Spotting in Resource Constrained Systems Authors: Prakash Dhungana, Sayed Ahmad Salehi Published: 2026-01-22 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2601.16158v1 Keyword Spotting (KWS) systems with small footprint models deployed on edge devices face significant accuracy and robustness challenges due to domain shifts caused by varying noise and recording conditions. To address this, we propose a comprehensive framework for continual learning designed to adapt to new domains while maintaining computational efficiency. The proposed pipeline integrates a dual-input Convolutional Neural Network, utilizing both Mel Frequency Cepstral Coefficients (MFCC) and Mel-spectrogram features, supported by a multi-stage denoising process, involving discrete wavelet transform and spectral subtraction techniques, plus model and prototype update blocks. Unlike prior methods that restrict updates to specific layers, our approach updates the complete quantized model, made possible due to compact model architecture. A subset of input samples are selected during runtime using class prototypes and confidence-driven filtering, which are then pseudo-labeled and combined with rehearsal buffer for incremental model retraining. Experimental results on noisy test dataset demonstrate the framework's effectiveness, achieving 99.63\% accuracy on clean data and maintaining robust performance (exceeding 94\% accuracy) across diverse noisy environments, even at -10 dB Signal-to-Noise Ratio. The proposed framework work confirms that integrating efficient denoising with prototype-based continual learning enables KWS models to operate autonomously and robustly in resource-constrained, dynamic environments. --- ### HVD: Human Vision-Driven Video Representation Learning for Text-Video Retrieval Authors: Zequn Xie, Xin Liu, Boyun Zhang, Yuxiao Lin, Sihang Cai, Tao Jin Published: 2026-01-22 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2601.16155v1 The success of CLIP has driven substantial progress in text-video retrieval. However, current methods often suffer from "blind" feature interaction, where the model struggles to discern key visual information from background noise due to the sparsity of textual queries. To bridge this gap, we draw inspiration from human cognitive behavior and propose the Human Vision-Driven (HVD) model. Our framework establishes a coarse-to-fine alignment mechanism comprising two key components: the Frame Features Selection Module (FFSM) and the Patch Features Compression Module (PFCM). FFSM mimics the human macro-perception ability by selecting key frames to eliminate temporal redundancy. Subsequently, PFCM simulates micro-perception by aggregating patch features into salient visual entities through an advanced attention mechanism, enabling precise entity-level matching. Extensive experiments on five benchmarks demonstrate that HVD not only captures human-like visual focus but also achieves state-of-the-art performance. --- ### Referential Regimes: Transformation-Invariant Identity for Neutral Substrates Authors: Denise M. Case Published: 2026-01-22 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2601.16152v2 Data systems increasingly operate under persistent legal, political, and analytic disagreement, where no single interpretive authority can be assumed. A neutral substrate provides stable shared reference without requiring agreement about causal or normative interpretation: it fixes reference structurally and leaves interpretation to extension layers. This paper derives the identity structure such a substrate requires using a small transformation algebra. Identity is treated as transformation-invariance: a referent is individuated by the admissible operations that preserve it. Once routine record operations are fixed, individuation becomes a structural calculation. That calculation exposes a mismatch between reference kinds and identity regimes. An accountability substrate must refer to six carrier kinds: obligation-bearers, rules, occurrences, scopes, records, and plain referents. Three kinds have more than one admissible basis. A scope may be fixed by extension or structure; a rule by content or structure; a plain referent by locus or object. Decomposition separates the scope readings, refinement separates the rule readings, and forking separates the plain-referent readings. Counting reference kinds gives six, while transformation analysis forces at least nine identity regimes. The three additional regimes add no new kind to the inventory. They arise from identity behavior under ordinary operations, and any attempt to collapse them reappears as a hidden regime that persistent disagreement cannot hold fixed. The result is a conditional lower bound. A richer transformation basis may leave the bound unchanged or force further splits, but it cannot erase a distinction witnessed here. The additional regimes correspond to distinctions often handled by modeling convention, but such conventions cannot substitute for regime-level identity commitments under persistent disagreement. --- ### Pay (Cross) Attention to the Melody: Curriculum Masking for Single-Encoder Melodic Harmonization Authors: Maximos Kaliakatsos-Papakostas, Dimos Makris, Konstantinos Soiledis, Konstantinos-Theodoros Tsamis, Vassilis Katsouros, Emilios Cambouropoulos Published: 2026-01-22 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2601.16150v1 Melodic harmonization, the task of generating harmonic accompaniments for a given melody, remains a central challenge in computational music generation. Recent single encoder transformer approaches have framed harmonization as a masked sequence modeling problem, but existing training curricula inspired by discrete diffusion often result in weak (cross) attention between melody and harmony. This leads to limited exploitation of melodic cues, particularly in out-of-domain contexts. In this work, we introduce a training curriculum, FF (full-to-full), which keeps all harmony tokens masked for several training steps before progressively unmasking entire sequences during training to strengthen melody-harmony interactions. We systematically evaluate this approach against prior curricula across multiple experimental axes, including temporal quantization (quarter vs. sixteenth note), bar-level vs. time-signature conditioning, melody representation (full range vs. pitch class), and inference-time unmasking strategies. Models are trained on the HookTheory dataset and evaluated both in-domain and on a curated collection of jazz standards, using a comprehensive set of metrics that assess chord progression structure, harmony-melody alignment, and rhythmic coherence. Results demonstrate that the proposed FF curriculum consistently outperforms baselines in nearly all metrics, with particularly strong gains in out-of-domain evaluations where harmonic adaptability to novel melodic queues is crucial. We further find that quarter-note quantization, intertwining of bar tokens, and pitch-class melody representations are advantageous in the FF setting. Our findings highlight the importance of training curricula in enabling effective melody conditioning and suggest that full-to-full unmasking offers a robust strategy for single encoder harmonization. --- ### ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion Authors: Remy Sabathier, David Novotny, Niloy J. Mitra, Tom Monnier Published: 2026-01-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.16148v2 Generating animated 3D objects is at the heart of many applications, yet most advanced works are typically difficult to apply in practice because of their limited setup, their long runtime, or their limited quality. We introduce ActionMesh, a generative model that predicts production-ready 3D meshes "in action" in a feed-forward manner. Drawing inspiration from early video models, our key insight is to modify existing 3D diffusion models to include a temporal axis, resulting in a framework we dubbed "temporal 3D diffusion". Specifically, we first adapt the 3D diffusion stage to generate a sequence of synchronized latents representing time-varying and independent 3D shapes. Second, we design a temporal 3D autoencoder that translates a sequence of independent shapes into the corresponding deformations of a pre-defined reference shape, allowing us to build an animation. Combining these two components, ActionMesh generates animated 3D meshes from different inputs like a monocular video, a text description, or even a 3D mesh with a text prompt describing its animation. Besides, compared to previous approaches, our method is fast and produces results that are rig-free and topology consistent, hence enabling rapid iteration and seamless applications like texturing and retargeting. We evaluate our model on standard video-to-4D benchmarks (Consistent4D, Objaverse) and report state-of-the-art performances on both geometric accuracy and temporal consistency, demonstrating that our model can deliver animated 3D meshes with unprecedented speed and quality. --- ### Beat-ssl: Capturing Local ECG Morphology through Heartbeat-level Contrastive Learning with Soft Targets Authors: Muhammad Ilham Rizqyawan, Peter Macfarlane, Stathis Hadjidemetriou, Fani Deligianni Published: 2026-01-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.16147v1 Obtaining labelled ECG data for developing supervised models is challenging. Contrastive learning (CL) has emerged as a promising pretraining approach that enables effective transfer learning with limited labelled data. However, existing CL frameworks either focus solely on global context or fail to exploit ECG-specific characteristics. Furthermore, these methods rely on hard contrastive targets, which may not adequately capture the continuous nature of feature similarity in ECG signals. In this paper, we propose Beat-SSL, a contrastive learning framework that performs dual-context learning through both rhythm-level and heartbeat-level contrasting with soft targets. We evaluated our pretrained model on two downstream tasks: 1) multilabel classification for global rhythm assessment, and 2) ECG segmentation to assess its capacity to learn representations across both contexts. We conducted an ablation study and compared the best configuration with three other methods, including one ECG foundation model. Despite the foundation model's broader pretraining, Beat-SSL reached 93% of its performance in multilabel classification task and surpassed all other methods in the segmentation task by 4%. --- ### Computing Fixpoints of Learned Functions: Chaotic Iteration and Simple Stochastic Games Authors: Paolo Baldan, Sebastian Gurke, Barbara König, Florian Wittbold Published: 2026-01-22 Categories: cs.LO, cs.LG arXiv: https://arxiv.org/abs/2601.16142v1 The problem of determining the (least) fixpoint of (higher-dimensional) functions over the non-negative reals frequently occurs when dealing with systems endowed with a quantitative semantics. We focus on the situation in which the functions of interest are not known precisely but can only be approximated. As a first contribution we generalize an iteration scheme called dampened Mann iteration, recently introduced in the literature. The improved scheme relaxes previous constraints on parameter sequences, allowing learning rates to converge to zero or not converge at all. While seemingly minor, this flexibility is essential to enable the implementation of chaotic iterations, where only a subset of components is updated in each step, allowing to tackle higher-dimensional problems. Additionally, by allowing learning rates to converge to zero, we can relax conditions on the convergence speed of function approximations, making the method more adaptable to various scenarios. We also show that dampened Mann iteration applies immediately to compute the expected payoff in various probabilistic models, including simple stochastic games, not covered by previous work. --- ### Learning to Watermark in the Latent Space of Generative Models Authors: Sylvestre-Alvise Rebuffi, Tuan Tran, Valeriu Lacatusu, Pierre Fernandez, Tomáš Souček, Nikola Jovanović, Tom Sander, Hady Elsahar, Alexandre Mourachko Published: 2026-01-22 Categories: cs.CV, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2601.16140v1 Existing approaches for watermarking AI-generated images often rely on post-hoc methods applied in pixel space, introducing computational overhead and potential visual artifacts. In this work, we explore latent space watermarking and introduce DistSeal, a unified approach for latent watermarking that works across both diffusion and autoregressive models. Our approach works by training post-hoc watermarking models in the latent space of generative models. We demonstrate that these latent watermarkers can be effectively distilled either into the generative model itself or into the latent decoder, enabling in-model watermarking. The resulting latent watermarks achieve competitive robustness while offering similar imperceptibility and up to 20x speedup compared to pixel-space baselines. Our experiments further reveal that distilling latent watermarkers outperforms distilling pixel-space ones, providing a solution that is both more efficient and more robust. --- ### On the Intrinsic Dimensions of Data in Kernel Learning Authors: Rustem Takhanov Published: 2026-01-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.16139v1 The manifold hypothesis suggests that the generalization performance of machine learning methods improves significantly when the intrinsic dimension of the input distribution's support is low. In the context of KRR, we investigate two alternative notions of intrinsic dimension. The first, denoted $d_ρ$, is the upper Minkowski dimension defined with respect to the canonical metric induced by a kernel function $K$ on a domain $Ω$. The second, denoted $d_K$, is the effective dimension, derived from the decay rate of Kolmogorov $n$-widths associated with $K$ on $Ω$. Given a probability measure $μ$ on $Ω$, we analyze the relationship between these $n$-widths and eigenvalues of the integral operator $φ\to \int_ΩK(\cdot,x)φ(x)dμ(x)$. We show that, for a fixed domain $Ω$, the Kolmogorov $n$-widths characterize the worst-case eigenvalue decay across all probability measures $μ$ supported on $Ω$. These eigenvalues are central to understanding the generalization behavior of constrained KRR, enabling us to derive an excess error bound of order $O(n^{-\frac{2+d_K}{2+2d_K} + ε})$ for any $ε> 0$, when the training set size $n$ is large. We also propose an algorithm that estimates upper bounds on the $n$-widths using only a finite sample from $μ$. For distributions close to uniform, we prove that $ε$-accurate upper bounds on all $n$-widths can be computed with high probability using at most $O\left(ε^{-d_ρ}\log\frac{1}ε\right)$ samples, with fewer required for small $n$. Finally, we compute the effective dimension $d_K$ for various fractal sets and present additional numerical experiments. Our results show that, for kernels such as the Laplace kernel, the effective dimension $d_K$ can be significantly smaller than the Minkowski dimension $d_ρ$, even though $d_K = d_ρ$ provably holds on regular domains. --- ### Automatic Classification of Arabic Literature into Historical Eras Authors: Zainab Alhathloul, Irfan Ahmad Published: 2026-01-22 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.16138v1 The Arabic language has undergone notable transformations over time, including the emergence of new vocabulary, the obsolescence of others, and shifts in word usage. This evolution is evident in the distinction between the classical and modern Arabic eras. Although historians and linguists have partitioned Arabic literature into multiple eras, relatively little research has explored the automatic classification of Arabic texts by time period, particularly beyond the domain of poetry. This paper addresses this gap by employing neural networks and deep learning techniques to automatically classify Arabic texts into distinct eras and periods. The proposed models are evaluated using two datasets derived from two publicly available corpora, covering texts from the pre-Islamic to the modern era. The study examines class setups ranging from binary to 15-class classification and considers both predefined historical eras and custom periodizations. Results range from F1-scores of 0.83 and 0.79 on the binary-era classification task using the OpenITI and APCD datasets, respectively, to 0.20 on the 15-era classification task using OpenITI and 0.18 on the 12-era classification task using APCD. --- ### LLM Prompt Evaluation for Educational Applications Authors: Langdon Holmes, Adam Coscia, Scott Crossley, Joon Suh Choi, Wesley Morris Published: 2026-01-22 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.16134v1 As large language models (LLMs) become increasingly common in educational applications, there is a growing need for evidence-based methods to design and evaluate LLM prompts that produce personalized and pedagogically aligned out-puts. This study presents a generalizable, systematic approach for evaluating prompts, demonstrated through an analysis of LLM-generated follow-up questions in a structured dialogue activity. Six prompt templates were designed and tested. The templates incorporated established prompt engineering patterns, with each prompt emphasizing distinct pedagogical strategies. The prompt templates were compared through a tournament-style evaluation framework that can be adapted for other educational applications. The tournament employed the Glicko2 rating system with eight judges evaluating question pairs across three dimensions: format, dialogue support, and appropriateness for learners. Data was sourced from 120 authentic user interactions across three distinct educational deployments. Results showed that a single prompt related to strategic reading out-performed other templates with win probabilities ranging from 81% to 100% in pairwise comparisons. This prompt combined persona and context manager pat-terns and was designed to support metacognitive learning strategies such as self-directed learning. The methodology showcases how educational technology re- searchers can systematically evaluate and improve prompt designs, moving beyond ad-hoc prompt engineering toward evidence-based prompt development for educational applications. --- ### Replicating Human Motivated Reasoning Studies with LLMs Authors: Neeley Pate, Adiba Mahbub Proma, Hangfeng He, James N. Druckman, Daniel C. Molden, Gourab Ghoshal, Ehsan Hoque Published: 2026-01-22 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.16130v2 Motivated reasoning - the idea that individuals processing information may be motivated to either arrive at accurate beliefs or arrive at desired conclusions - has been well-explored as a human phenomenon. However, it remains unclear whether base LLMs are affected by motivational manipulations. Replicating 4 prior political motivated reasoning studies, we find that base LLM behavior does not align with expected human behavior. Furthermore, base LLM behavior across models shares some similarities, such as when selecting to abstain from question answering and incorporating provided arguments into opinions. The results suggest that base LLMs may not emulate human motivated reasoning processes. We emphasize the importance of these findings for researchers using LLMs to for certain tasks such as opinion replication and argument assessment. --- ### Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging Authors: Alphaeus Dmonte, Vidhi Gupta, Daniel J Perry, Mark Arehart Published: 2026-01-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.16127v2 Fine-tuning a task-specific multilingual large language model (LLM) involves training the model on a multilingual dataset with examples in all the required languages. Updating one or more supported languages with additional data or adding support for a new language involves retraining the model, which can be computationally inefficient and creates a severe maintenance bottleneck. Recent research on merging multilingual multitask models has shown promise in terms of improved quality, but its computational and maintenance efficiency remains unstudied. In this work, we provide the first focused analysis of this merging strategy from an efficiency perspective, evaluating it across three independent tasks. We demonstrate significant efficiency gains while maintaining parity in terms of quality: this merging approach reduces the initial training time by up to 50\%. We also demonstrate that updating an individual language and re-merging as part of model maintenance reduces training costs by more than 60\%, compared to re-training the full multilingual model. We show this on both public and proprietary industry datasets confirming that the approach works well for industrial use cases in addition to academic settings already studied in previous work. --- ### Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing Authors: Tingyu Song, Yanzhao Zhang, Mingxin Li, Zhuoning Guo, Dingkun Long, Pengjun Xie, Siyue Zhang, Yilun Zhao, Shu Wu Published: 2026-01-22 Categories: cs.CV, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2601.16125v1 Composed Image Retrieval (CIR) is a pivotal and complex task in multimodal understanding. Current CIR benchmarks typically feature limited query categories and fail to capture the diverse requirements of real-world scenarios. To bridge this evaluation gap, we leverage image editing to achieve precise control over modification types and content, enabling a pipeline for synthesizing queries across a broad spectrum of categories. Using this pipeline, we construct EDIR, a novel fine-grained CIR benchmark. EDIR encompasses 5,000 high-quality queries structured across five main categories and fifteen subcategories. Our comprehensive evaluation of 13 multimodal embedding models reveals a significant capability gap; even state-of-the-art models (e.g., RzenEmbed and GME) struggle to perform consistently across all subcategories, highlighting the rigorous nature of our benchmark. Through comparative analysis, we further uncover inherent limitations in existing benchmarks, such as modality biases and insufficient categorical coverage. Furthermore, an in-domain training experiment demonstrates the feasibility of our benchmark. This experiment clarifies the task challenges by distinguishing between categories that are solvable with targeted data and those that expose intrinsic limitations of current model architectures. --- ### Synthetic Augmentation in Imbalanced Learning: When It Helps, When It Hurts, and How Much to Add Authors: Zhengchi Ma, Anru R. Zhang Published: 2026-01-22 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2601.16120v3 Imbalanced classification often causes standard training procedures to prioritize the majority class and perform poorly on rare but important cases. A classic and widely used remedy is to augment the minority class with synthetic samples, but two basic questions remain under-resolved: when does synthetic augmentation actually help, and how many synthetic samples should be generated? We develop a unified statistical framework for synthetic augmentation in imbalanced learning, studying models trained on imbalanced data augmented with synthetic minority samples. Our theory shows that synthetic data is not always beneficial. In a "local symmetry" regime, imbalance is not the dominant source of error, so adding synthetic samples cannot improve learning rates and can even degrade performance by amplifying generator mismatch. When augmentation can help ("local asymmetry"), the optimal synthetic size depends on generator accuracy and on whether the generator's residual mismatch is directionally aligned with the intrinsic majority-minority shift. This structure can make the best synthetic size deviate from naive full balancing. Practically, we recommend Validation-Tuned Synthetic Size (VTSS): select the synthetic size by minimizing balanced validation loss over a range centered near the fully balanced baseline, while allowing meaningful departures. Extensive simulations and real data analysis further support our findings. --- ### A Case for Hypergraphs to Model and Map SNNs on Neuromorphic Hardware Authors: Marco Ronzani, Cristina Silvano Published: 2026-01-22 Categories: cs.AR, cs.NE arXiv: https://arxiv.org/abs/2601.16118v2 Executing Spiking Neural Networks (SNNs) on neuromorphic hardware poses the problem of mapping neurons to cores. SNNs operate by propagating spikes between neurons that form a graph through synapses. Neuromorphic hardware mimics them through a network-on-chip, transmitting spikes, and a mesh of cores, each managing several neurons. Its operational cost is tied to spike movement and active cores. A mapping comprises two tasks: partitioning the SNN's graph to fit inside cores and placement of each partition on the hardware mesh. Both are NP-hard problems, and as SNNs and hardware scale towards billions of neurons, they become increasingly difficult to tackle effectively. In this work, we propose to raise the abstraction of SNNs from graphs to hypergraphs, redesigning mapping techniques accordingly. The resulting model faithfully captures the replication of spikes inside cores by exposing the notion of hyperedge co-membership between neurons. We further show that the overlap and locality of hyperedges strongly correlate with high-quality mappings, making these properties instrumental in devising mapping algorithms. By exploiting them directly, grouping neurons through shared hyperedges, communication traffic and hardware resource usage can be reduced be yond what just contracting individual connections attains. To substantiate this insight, we consider several partitioning and placement algorithms, some newly devised, others adapted from literature, and compare them over progressively larger and bio-plausible SNNs. Our results show that hypergraph based techniques can achieve better mappings than the state-of-the-art at several execution time regimes. Based on these observations, we identify a promising selection of algorithms to achieve effective mappings at any scale. --- ### Distillation-based Layer Dropping (DLD): Effective End-to-end Framework for Dynamic Speech Networks Authors: Abdul Hannan, Daniele Falavigna, Shah Nawaz, Mubashir Noman, Markus Schedl, Alessio Brutti Published: 2026-01-22 Categories: cs.SD, cs.CV arXiv: https://arxiv.org/abs/2601.16117v2 Edge devices operate in constrained and varying resource settings, requiring dynamic architectures that can adapt to limitations of the available resources. To meet such demands, layer dropping ($\mathcal{LD}$) approach is typically used to transform static models into dynamic ones by skipping parts of the network along with reducing overall computational complexity. However, existing $\mathcal{LD}$ methods greatly impact the dynamic model's performance for low and high dropping cases, deteriorating the performance-computation trade-off. To this end, we propose a distillation-based layer dropping (DLD) framework that effectively combines the capabilities of knowledge distillation and $\mathcal{LD}$ in an end-to-end fashion, thereby achieving state-of-the-art performance for dynamic speech networks. Comprehensive experimentation utilizing well-known speech recognition methods, including conformer and WavLM, on three public benchmarks demonstrates the effectiveness of our framework, reducing the word error rate by $9.32\%$ and $2.25\%$ for high and no dropping cases with $33.3\%$ reduction in training time. --- ### synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barrier Authors: Haq Nawaz Malik, Kh Mohmad Shafi, Tanveer Ahmad Reshi Published: 2026-01-22 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2601.16113v1 Optical Character Recognition (OCR) for low-resource languages remains a significant challenge due to the scarcity of large-scale annotated training datasets. Languages such as Kashmiri, with approximately 7 million speakers and a complex Perso-Arabic script featuring unique diacritical marks, currently lack support in major OCR systems including Tesseract, TrOCR, and PaddleOCR. Manual dataset creation for such languages is prohibitively expensive, time-consuming, and error-prone, often requiring word by word transcription of printed or handwritten text. We present SynthOCR-Gen, an open-source synthetic OCR dataset generator specifically designed for low-resource languages. Our tool addresses the fundamental bottleneck in OCR development by transforming digital Unicode text corpora into ready-to-use training datasets. The system implements a comprehensive pipeline encompassing text segmentation (character, word, n-gram, sentence, and line levels), Unicode normalization with script purity enforcement, multi-font rendering with configurable distribution, and 25+ data augmentation techniques simulating real-world document degradations including rotation, blur, noise, and scanner artifacts. We demonstrate the efficacy of our approach by generating a 600,000-sample word-segmented Kashmiri OCR dataset, which we release publicly on HuggingFace. This work provides a practical pathway for bringing low-resource languages into the era of vision-language AI models, and the tool is openly available for researchers and practitioners working with underserved writing systems worldwide. --- ### Variable Splitting Binary Tree Models Based on Bayesian Context Tree Models for Time Series Segmentation Authors: Yuta Nakahara, Shota Saito, Kohei Horinouchi, Koshi Shimada, Naoki Ichijo, Manabu Kobayashi, Toshiyasu Matsushima Published: 2026-01-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.16112v1 We propose a variable splitting binary tree (VSBT) model based on Bayesian context tree (BCT) models for time series segmentation. Unlike previous applications of BCT models, the tree structure in our model represents interval partitioning on the time domain. Moreover, interval partitioning is represented by recursive logistic regression models. By adjusting logistic regression coefficients, our model can represent split positions at arbitrary locations within each interval. This enables more compact tree representations. For simultaneous estimation of both split positions and tree depth, we develop an effective inference algorithm that combines local variational approximation for logistic regression with the context tree weighting (CTW) algorithm. We present numerical examples on synthetic data demonstrating the effectiveness of our model and algorithm. --- ### Multimodal Climate Disinformation Detection: Integrating Vision-Language Models with External Knowledge Sources Authors: Marzieh Adeli Shamsabad, Hamed Ghodrati Published: 2026-01-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.16108v1 Climate disinformation has become a major challenge in today digital world, especially with the rise of misleading images and videos shared widely on social media. These false claims are often convincing and difficult to detect, which can delay actions on climate change. While vision-language models (VLMs) have been used to identify visual disinformation, they rely only on the knowledge available at the time of training. This limits their ability to reason about recent events or updates. The main goal of this paper is to overcome that limitation by combining VLMs with external knowledge. By retrieving up-to-date information such as reverse image results, online fact-checks, and trusted expert content, the system can better assess whether an image and its claim are accurate, misleading, false, or unverifiable. This approach improves the model ability to handle real-world climate disinformation and supports efforts to protect public understanding of science in a rapidly changing information landscape. --- ### Benchmarking Deep Learning Models for Raman Spectroscopy Across Open-Source Datasets Authors: Adithya Sineesh, Akshita Ramya Kamsali Published: 2026-01-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.16107v2 Deep learning classifiers for Raman spectroscopy are increasingly reported to outperform classical chemometric approaches. However, their evaluations are often conducted in isolation or compared against traditional machine learning methods or trivially adapted vision-based architectures that were not originally proposed for Raman spectroscopy. As a result, direct comparisons between existing deep learning models developed specifically for Raman spectral analysis on shared open-source datasets remain scarce. In this work, we focus on supervised Raman spectra classification where each spectrum is assigned to a predefined material, bacterial/yeast isolate, drug treatment or pharmaceutical compound. To the best of our knowledge, this study presents one of the first benchmarks comparing three or more published Raman-specific deep learning classifiers across multiple open-source Raman datasets. We evaluate five representative Deep Learning (DL) architectures along with two conventional Machine Learning (ML) methods under a unified training and hyperparameter tuning protocol across three open-source Raman datasets selected to support standard evaluation, fine-tuning, and explicit distribution-shift testing. In this comparative study, we primarily focus on classification because the selected open-source datasets provide classification annotations, while annotations for complete structure elucidation are not available. We report classification accuracies and macro-averaged F1 scores to provide a fair and reproducible comparison of the supervised ML and DL models for Raman spectra based classification. --- ### Clustering-Guided Spatial-Spectral Mamba for Hyperspectral Image Classification Authors: Zack Dewis, Yimin Zhu, Zhengsen Xu, Mabel Heffring, Saeid Taleghanidoozdoozan, Quinn Ledingham, Lincoln Linlin Xu Published: 2026-01-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.16098v1 Although Mamba models greatly improve Hyperspectral Image (HSI) classification, they have critical challenges in terms defining efficient and adaptive token sequences for improve performance. This paper therefore presents CSSMamba (Clustering-guided Spatial-Spectral Mamba) framework to better address the challenges, with the following contributions. First, to achieve efficient and adaptive token sequences for improved Mamba performance, we integrate the clustering mechanism into a spatial Mamba architecture, leading to a cluster-guided spatial Mamba module (CSpaMamba) that reduces the Mamba sequence length and improves Mamba feature learning capability. Second, to improve the learning of both spatial and spectral information, we integrate the CSpaMamba module with a spectral mamba module (SpeMamba), leading to a complete clustering-guided spatial-spectral Mamba framework. Third, to further improve feature learning capability, we introduce an Attention-Driven Token Selection mechanism to optimize Mamba token sequencing. Last, to seamlessly integrate clustering into the Mamba model in a coherent manner, we design a Learnable Clustering Module that learns the cluster memberships in an adaptive manner. Experiments on the Pavia University, Indian Pines, and Liao-Ning 01 datasets demonstrate that CSSMamba achieves higher accuracy and better boundary preservation compared to state-of-the-art CNN, Transformer, and Mamba-based methods. --- ### Incremental Multilingual Text2Cypher with Adapter Combination Authors: Makbule Gulcin Ozsoy Published: 2026-01-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.16097v2 Large Language Models enable users to access database using natural language interfaces using tools like Text2SQL, Text2SPARQL, and Text2Cypher, which translate user questions into structured database queries. While these systems improve database accessibility, most research focuses on English with limited multilingual support. This work investigates a scalable multilingual Text2Cypher, aiming to support new languages without re-running full fine-tuning, avoiding manual hyper-parameter tuning, and maintaining performance close to joint multilingual fine-tuning. We train language-specific LoRA adapters for English, Spanish, and Turkish and combined them via uniform linear merging or learned fusion MLP with dynamic gating. Experimental results show that the fusion MLP recovers around 75\% of the accuracy gains from joint multilingual fine-tuning while requiring only a smaller subset of the data, outperforming linear merging across all three languages. This approach enables incremental language expansion to new languages by requiring only one LoRA adapter and a lightweight MLP retraining. Learned adapter fusion offers a practical alternative to expensive joint fine-tuning, balancing performance, data efficiency, and scalability for multilingual Text2Cypher task. --- ### Neural Particle Automata: Learning Self-Organizing Particle Dynamics Authors: Hyunsoo Kim, Ehsan Pajouheshgar, Sabine Süsstrunk, Wenzel Jakob, Jinah Park Published: 2026-01-22 Categories: cs.NE, cs.CV arXiv: https://arxiv.org/abs/2601.16096v3 We introduce Neural Particle Automata (NPA), a Lagrangian generalization of Neural Cellular Automata (NCA) from static lattices to dynamic particle systems. Unlike classical Eulerian NCA where cells are pinned to pixels or voxels, NPA model each cell as a particle with a continuous position and internal state, both updated by a shared, learnable neural rule. This particle-based formulation yields clear individuation of cells, allows heterogeneous dynamics, and concentrates computation only on regions where activity is present. At the same time, particle systems pose challenges: neighborhoods are dynamic, and a naive implementation of local interactions scale quadratically with the number of particles. We address these challenges by replacing grid-based neighborhood perception with differentiable Smoothed Particle Hydrodynamics (SPH) operators backed by memory-efficient, CUDA-accelerated kernels, enabling scalable end-to-end training. Across tasks including morphogenesis, point-cloud classification, and particle-based texture synthesis, we show that NPA retain key NCA behaviors such as robustness and self-regeneration, while enabling new behaviors specific to particle systems. Together, these results position NPA as a compact neural model for learning self-organizing particle dynamics. --- ### SAMTok: Representing Any Mask with Two Words Authors: Yikang Zhou, Tao Zhang, Dengxian Gong, Yuanzheng Wu, Ye Tian, Haochen Wang, Haobo Yuan, Jiacong Wang, Lu Qi, Hao Fei, Anran Wang, Zhuochen Wang et al. Published: 2026-01-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.16093v2 Pixel-wise capabilities are essential for building interactive intelligent systems. However, pixel-wise multi-modal LLMs (MLLMs) remain difficult to scale due to complex region-level encoders, specialized segmentation decoders, and incompatible training objectives. To address these challenges, we present SAMTok, a discrete mask tokenizer that converts any region mask into two special tokens and reconstructs the mask using these tokens with high fidelity. By treating masks as new language tokens, SAMTok enables base MLLMs (such as the QwenVL series) to learn pixel-wise capabilities through standard next-token prediction and simple reinforcement learning, without architectural modifications and specialized loss design. SAMTok builds on SAM2 and is trained on 209M diverse masks using a mask encoder and residual vector quantizer to produce discrete, compact, and information-rich tokens. With 5M SAMTok-formatted mask understanding and generation data samples, QwenVL-SAMTok attains state-of-the-art or comparable results on region captioning, region VQA, grounded conversation, referring segmentation, scene graph parsing, and multi-round interactive segmentation. We further introduce a textual answer-matching reward that enables efficient reinforcement learning for mask generation, delivering substantial improvements on GRES and GCG benchmarks. Our results demonstrate a scalable and straightforward paradigm for equipping MLLMs with strong pixel-wise capabilities. Our code and models are available. --- ### Delayed Assignments in Online Non-Centroid Clustering with Stochastic Arrivals Authors: Saar Cohen Published: 2026-01-22 Categories: cs.MA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.16091v2 Clustering is a fundamental problem, aiming to partition a set of elements, like agents or data points, into clusters such that elements in the same cluster are closer to each other than to those in other clusters. In this paper, we present a new framework for studying online non-centroid clustering with delays, where elements, that arrive one at a time as points in a finite metric space, should be assigned to clusters, but assignments need not be immediate. Specifically, upon arrival, each point's location is revealed, and an online algorithm has to irrevocably assign it to an existing cluster or create a new one containing, at this moment, only this point. However, we allow decisions to be postponed at a delay cost, instead of following the more common assumption of immediate decisions upon arrival. This poses a critical challenge: the goal is to minimize both the total distance costs between points in each cluster and the overall delay costs incurred by postponing assignments. In the classic worst-case arrival model, where points arrive in an arbitrary order, no algorithm has a competitive ratio better than sublogarithmic in the number of points. To overcome this strong impossibility, we focus on a stochastic arrival model, where points' locations are drawn independently across time from an unknown and fixed probability distribution over the finite metric space. We offer hope for beyond worst-case adversaries: we devise an algorithm that is constant competitive in the sense that, as the number of points grows, the ratio between the expected overall costs of the output clustering and an optimal offline clustering is bounded by a constant. --- ### Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics Authors: Sukesh Subaharan Published: 2026-01-22 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.16087v1 Large language model (LLM) agents often exhibit abrupt shifts in tone and persona during extended interaction, reflecting the absence of explicit temporal structure governing agent-level state. While prior work emphasizes turn-local sentiment or static emotion classification, the role of explicit affective dynamics in shaping long-horizon agent behavior remains underexplored. This work investigates whether imposing dynamical structure on an external affective state can induce temporal coherence and controlled recovery in multi-turn dialogue. We introduce an agent-level affective subsystem that maintains a continuous Valence-Arousal-Dominance (VAD) state external to the language model and governed by first- and second-order update rules. Instantaneous affective signals are extracted using a fixed, memoryless estimator and integrated over time via exponential smoothing or momentum-based dynamics. The resulting affective state is injected back into generation without modifying model parameters. Using a fixed 25-turn dialogue protocol, we compare stateless, first-order, and second-order affective dynamics. Stateless agents fail to exhibit coherent trajectories or recovery, while state persistence enables delayed responses and reliable recovery. Second-order dynamics introduce affective inertia and hysteresis that increase with momentum, revealing a trade-off between stability and responsiveness. --- ### Probably Approximately Correct Maximum A Posteriori Inference Authors: Matthew Shorvon, Frederik Mallmann-Trenn, David S. Watson Published: 2026-01-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.16083v2 Computing the conditional mode of a distribution, better known as the maximum a posteriori (MAP) assignment, is a fundamental task in probabilistic inference. However, MAP is generally intractable, and remains hard even under many common structural constraints and approximation schemes. We take a novel approach inspired by multi-armed bandits, recasting MAP as a best arm identification task. We introduce probably approximately correct (PAC) algorithms for MAP that provide provably optimal solutions in both the fixed-confidence and fixed-budget regimes. We characterize tractability conditions using information theoretic measures that can be estimated from finite samples. Our PAC-MAP solvers are efficiently implemented using probabilistic circuits and graphical models with appropriate architectures. The algorithms we develop can be used either as standalone MAP estimators or to improve on standard heuristics, fortifying their solutions with rigorous guarantees. Experiments confirm the benefits of our method in a range of benchmarks. --- ### Masked Modeling for Human Motion Recovery Under Occlusions Authors: Zhiyin Qian, Siwei Zhang, Bharat Lal Bhatnagar, Federica Bogo, Siyu Tang Published: 2026-01-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.16079v2 Human motion reconstruction from monocular videos is a fundamental challenge in computer vision, with broad applications in AR/VR, robotics, and digital content creation, but remains challenging under frequent occlusions in real-world settings. Existing regression-based methods are efficient but fragile to missing observations, while optimization- and diffusion-based approaches improve robustness at the cost of slow inference speed and heavy preprocessing steps. To address these limitations, we leverage recent advances in generative masked modeling and present MoRo: Masked Modeling for human motion Recovery under Occlusions. MoRo is an occlusion-robust, end-to-end generative framework that formulates motion reconstruction as a video-conditioned task, and efficiently recover human motion in a consistent global coordinate system from RGB videos. By masked modeling, MoRo naturally handles occlusions while enabling efficient, end-to-end inference. To overcome the scarcity of paired video-motion data, we design a cross-modality learning scheme that learns multi-modal priors from a set of heterogeneous datasets: (i) a trajectory-aware motion prior trained on MoCap datasets, (ii) an image-conditioned pose prior trained on image-pose datasets, capturing diverse per-frame poses, and (iii) a video-conditioned masked transformer that fuses motion and pose priors, finetuned on video-motion datasets to integrate visual cues with motion dynamics for robust inference. Extensive experiments on EgoBody and RICH demonstrate that MoRo substantially outperforms state-of-the-art methods in accuracy and motion realism under occlusions, while performing on-par in non-occluded scenarios. MoRo achieves real-time inference at 70 FPS on a single H200 GPU. --- ### Explainable AI to Improve Machine Learning Reliability for Industrial Cyber-Physical Systems Authors: Annemarie Jutte, Uraz Odyurt Published: 2026-01-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.16074v2 Industrial Cyber-Physical Systems (CPS) are sensitive infrastructure from both safety and economics perspectives, making their reliability critically important. Machine Learning (ML), specifically deep learning, is increasingly integrated in industrial CPS, but the inherent complexity of ML models results in non-transparent operation. Rigorous evaluation is needed to prevent models from exhibiting unexpected behaviour on future, unseen data. Explainable AI (XAI) can be used to uncover model reasoning, allowing a more extensive analysis of behaviour. We apply XAI to improve predictive performance of ML models intended for an industrial CPS use-case. We analyse the effects of components from time-series data decomposition on model predictions using SHAP values. Through this method, we observe evidence on the lack of sufficient contextual information during model training. By increasing the window size of data instances, informed by the XAI findings for this use-case, we are able to improve model performance. --- ### DSFedMed: Dual-Scale Federated Medical Image Segmentation via Mutual Distillation Between Foundation and Lightweight Models Authors: Hanwen Zhang, Qiaojin Shen, Yuxi Liu, Yuesheng Zhu, Guibo Luo Published: 2026-01-22 Categories: cs.CV, cs.DC arXiv: https://arxiv.org/abs/2601.16073v1 Foundation Models (FMs) have demonstrated strong generalization across diverse vision tasks. However, their deployment in federated settings is hindered by high computational demands, substantial communication overhead, and significant inference costs. We propose DSFedMed, a dual-scale federated framework that enables mutual knowledge distillation between a centralized foundation model and lightweight client models for medical image segmentation. To support knowledge distillation, a set of high-quality medical images is generated to replace real public datasets, and a learnability-guided sample selection strategy is proposed to enhance efficiency and effectiveness in dual-scale distillation. This mutual distillation enables the foundation model to transfer general knowledge to lightweight clients, while also incorporating client-specific insights to refine the foundation model. Evaluations on five medical imaging segmentation datasets show that DSFedMed achieves an average 2 percent improvement in Dice score while reducing communication costs and inference time by nearly 90 percent compared to existing federated foundation model baselines. These results demonstrate significant efficiency gains and scalability for resource-limited federated deployments. --- ### CLASP: An online learning algorithm for Convex Losses And Squared Penalties Authors: Ricardo N. Ferreira, João Xavier, Cláudia Soares Published: 2026-01-22 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2601.16072v2 We study Constrained Online Convex Optimization (COCO), where a learner chooses actions iteratively, observes both unanticipated convex loss and convex constraint, and accumulates loss while incurring penalties for constraint violations. We introduce CLASP (Convex Losses And Squared Penalties), an algorithm that minimizes cumulative loss together with squared constraint violations. Our analysis departs from prior work by fully leveraging the firm non-expansiveness of convex projectors, a proof strategy not previously applied in this setting. For convex losses, CLASP achieves regret $O\left(T^{\max\{β,1-β\}}\right)$ and cumulative squared penalty $O\left(T^{1-β}\right)$ for any $β\in (0,1)$. Most importantly, for strongly convex problems, CLASP provides the first logarithmic guarantees on both regret and cumulative squared penalty. In the strongly convex case, the regret is upper bounded by $O( \log T )$ and the cumulative squared penalty is also upper bounded by $O( \log T )$. --- ### On damage of interpolation to adversarial robustness in regression Authors: Jingfu Peng, Yuhong Yang Published: 2026-01-22 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2601.16070v1 Deep neural networks (DNNs) typically involve a large number of parameters and are trained to achieve zero or near-zero training error. Despite such interpolation, they often exhibit strong generalization performance on unseen data, a phenomenon that has motivated extensive theoretical investigations. Comforting results show that interpolation indeed may not affect the minimax rate of convergence under the squared error loss. In the mean time, DNNs are well known to be highly vulnerable to adversarial perturbations in future inputs. A natural question then arises: Can interpolation also escape from suboptimal performance under a future $X$-attack? In this paper, we investigate the adversarial robustness of interpolating estimators in a framework of nonparametric regression. A finding is that interpolating estimators must be suboptimal even under a subtle future $X$-attack, and achieving perfect fitting can substantially damage their robustness. An interesting phenomenon in the high interpolation regime, which we term the curse of simple size, is also revealed and discussed. Numerical experiments support our theoretical findings. --- ### DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models Authors: Chenyang Li, Jieyuan Liu, Bin Li, Bo Gao, Yilin Yuan, Yangfan He, Yuchen Li, Jingqun Tang Published: 2026-01-22 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2601.16065v1 Vision-Language Action (VLA) models have shown remarkable progress in robotic manipulation by leveraging the powerful perception abilities of Vision-Language Models (VLMs) to understand environments and directly output actions. However, by default, VLA models may overly attend to image tokens in the task-irrelevant region, which we describe as 'distracting tokens'. This behavior can disturb the model from the generation of the desired action tokens in each step, affecting the success rate of tasks. In this paper, we introduce a simple yet effective plug-and-play Distracting Token Pruning (DTP) framework, which dynamically detects and prunes these distracting image tokens. By correcting the model's visual attention patterns, we aim to improve the task success rate, as well as exploring the performance upper boundaries of the model without altering its original architecture or adding additional inputs. Experiments on the SIMPLER Benchmark (Li et al., 2024) show that our method consistently achieving relative improvements in task success rates across different types of novel VLA models, demonstrating generalizability to transformer-based VLAs. Further analysis reveals a negative correlation between the task success rate and the amount of attentions in the task-irrelevant region for all models tested, highlighting a common phenomenon of VLA models that could guide future research. We also publish our code at: https://anonymous.4open.science/r/CBD3. --- ### Phi-SegNet: Phase-Integrated Supervision for Medical Image Segmentation Authors: Shams Nafisa Ali, Taufiq Hasan Published: 2026-01-22 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2601.16064v2 Deep learning has substantially advanced medical image segmentation, yet achieving robust generalization across diverse imaging modalities and anatomical structures remains a major challenge. A key contributor to this limitation lies in how existing architectures, ranging from CNNs to Transformers and their hybrids, primarily encode spatial information while overlooking frequency-domain representations that capture rich structural and textural cues. Although recent studies have begun exploring spectral information at the feature level, supervision-level integration of frequency cues-crucial for fine-grained object localization-remains largely untapped. To this end, we propose Phi-SegNet, a CNN-based architecture that incorporates phase-aware information at both architectural and optimization levels. The network integrates Bi-Feature Mask Former (BFMF) modules that blend neighboring encoder features to reduce semantic gaps, and Reverse Fourier Attention (RFA) blocks that refine decoder outputs using phase-regularized features. A dedicated phase-aware loss aligns these features with structural priors, forming a closed feedback loop that emphasizes boundary precision. Evaluated on five public datasets spanning X-ray, US, histopathology, MRI, and colonoscopy, Phi-SegNet consistently achieved state-of-the-art performance, with an average relative improvement of 1.54+/-1.26% in IoU and 0.98+/-0.71% in F1-score over the next best-performing model. In cross-dataset generalization scenarios involving unseen datasets from the known domain, it also exhibits robust and superior performance, highlighting its adaptability and modality-agnostic design. These findings demonstrate the potential of leveraging spectral priors in both feature representation and supervision, paving the way for generalized segmentation frameworks that excel in fine-grained object localization. Our code is available on GitHub. ---