# Research Papers — 2025-10 · bundle page 117 of 217

> Full-text markdown of papers #5801–5850 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/117
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/116.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/118.md)

### VLURes: Benchmarking VLM Visual and Linguistic Understanding in Low-Resource Languages

Authors: Jesse Atuhurra, Iqra Ali, Tomoya Iwakura, Hidetaka Kamigaito, Tatsuya Hiraoka
Published: 2025-10-14
Categories: cs.CL, cs.AI, cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.12845v1

Vision Language Models (VLMs) are pivotal for advancing perception in intelligent agents. Yet, evaluation of VLMs remains limited to predominantly English-centric benchmarks in which the image-text pairs comprise short texts. To evaluate VLM fine-grained abilities, in four languages under long-text settings, we introduce a novel multilingual benchmark VLURes featuring eight vision-and-language tasks, and a pioneering unrelatedness task, to probe the fine-grained Visual and Linguistic Understanding capabilities of VLMs across English, Japanese, and low-resource languages, Swahili, and Urdu. Our datasets, curated from web resources in the target language, encompass ten diverse image categories and rich textual context, introducing valuable vision-language resources for Swahili and Urdu. By prompting VLMs to generate responses and rationales, evaluated automatically and by native speakers, we uncover performance disparities across languages and tasks critical to intelligent agents, such as object recognition, scene understanding, and relationship understanding. We conducted evaluations of ten VLMs with VLURes. The best performing model, GPT-4o, achieves an overall accuracy of 90.8% and lags human performance by 6.7%, though the gap is larger for open-source models. The gap highlights VLURes' critical role in developing intelligent agents to tackle multi-modal visual reasoning.

---

### DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search

Authors: Kartik Narayan, Yang Xu, Tian Cao, Kavya Nerella, Vishal M. Patel, Navid Shiee, Peter Grasch, Chao Jia, Yinfei Yang, Zhe Gan
Published: 2025-10-14
Categories: cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2510.12801v1

Multimodal Large Language Models (MLLMs) in real-world applications require access to external knowledge sources and must remain responsive to the dynamic and ever-changing real-world information in order to address information-seeking and knowledge-intensive user queries. Existing approaches, such as retrieval augmented generation (RAG) methods, search agents, and search equipped MLLMs, often suffer from rigid pipelines, excessive search calls, and poorly constructed search queries, which result in inefficiencies and suboptimal outcomes. To address these limitations, we present DeepMMSearch-R1, the first multimodal LLM capable of performing on-demand, multi-turn web searches and dynamically crafting queries for both image and text search tools. Specifically, DeepMMSearch-R1 can initiate web searches based on relevant crops of the input image making the image search more effective, and can iteratively adapt text search queries based on retrieved information, thereby enabling self-reflection and self-correction. Our approach relies on a two-stage training pipeline: a cold start supervised finetuning phase followed by an online reinforcement learning optimization. For training, we introduce DeepMMSearchVQA, a novel multimodal VQA dataset created through an automated pipeline intermixed with real-world information from web search tools. This dataset contains diverse, multi-hop queries that integrate textual and visual information, teaching the model when to search, what to search for, which search tool to use and how to reason over the retrieved information. We conduct extensive experiments across a range of knowledge-intensive benchmarks to demonstrate the superiority of our approach. Finally, we analyze the results and provide insights that are valuable for advancing multimodal web-search.

---

### Detect Anything via Next Point Prediction

Authors: Qing Jiang, Junan Huo, Xingyu Chen, Yuda Xiong, Zhaoyang Zeng, Yihao Chen, Tianhe Ren, Junzhi Yu, Lei Zhang
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.12798v1

Object detection has long been dominated by traditional coordinate regression-based models, such as YOLO, DETR, and Grounding DINO. Although recent efforts have attempted to leverage MLLMs to tackle this task, they face challenges like low recall rate, duplicate predictions, coordinate misalignment, etc. In this work, we bridge this gap and propose Rex-Omni, a 3B-scale MLLM that achieves state-of-the-art object perception performance. On benchmarks like COCO and LVIS, Rex-Omni attains performance comparable to or exceeding regression-based models (e.g., DINO, Grounding DINO) in a zero-shot setting. This is enabled by three key designs: 1) Task Formulation: we use special tokens to represent quantized coordinates from 0 to 999, reducing the model's learning difficulty and improving token efficiency for coordinate prediction; 2) Data Engines: we construct multiple data engines to generate high-quality grounding, referring, and pointing data, providing semantically rich supervision for training; \3) Training Pipelines: we employ a two-stage training process, combining supervised fine-tuning on 22 million data with GRPO-based reinforcement post-training. This RL post-training leverages geometry-aware rewards to effectively bridge the discrete-to-continuous coordinate prediction gap, improve box accuracy, and mitigate undesirable behaviors like duplicate predictions that stem from the teacher-guided nature of the initial SFT stage. Beyond conventional detection, Rex-Omni's inherent language understanding enables versatile capabilities such as object referring, pointing, visual prompting, GUI grounding, spatial referring, OCR and key-pointing, all systematically evaluated on dedicated benchmarks. We believe that Rex-Omni paves the way for more versatile and language-aware visual perception systems.

---

### DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving

Authors: Yingyan Li, Shuyao Shang, Weisong Liu, Bing Zhan, Haochen Wang, Yuqi Wang, Yuntao Chen, Xiaoman Wang, Yasong An, Chufeng Tang, Lu Hou, Lue Fan et al.
Published: 2025-10-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.12796v2

Scaling Vision-Language-Action (VLA) models on large-scale data offers a promising path to achieving a more generalized driving intelligence. However, VLA models are limited by a ``supervision deficit'': the vast model capacity is supervised by sparse, low-dimensional actions, leaving much of their representational power underutilized. To remedy this, we propose \textbf{DriveVLA-W0}, a training paradigm that employs world modeling to predict future images. This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment. We showcase the paradigm's versatility by instantiating it for two dominant VLA archetypes: an autoregressive world model for VLAs that use discrete visual tokens, and a diffusion world model for those operating on continuous visual features. Building on the rich representations learned from world modeling, we introduce a lightweight action expert to address the inference latency for real-time deployment. Extensive experiments on the NAVSIM v1/v2 benchmark and a 680x larger in-house dataset demonstrate that DriveVLA-W0 significantly outperforms BEV and VLA baselines. Crucially, it amplifies the data scaling law, showing that performance gains accelerate as the training dataset size increases.

---

### CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations

Authors: Caner Korkmaz, Brighton Nuwagira, Barış Coşkunuzer, Tolga Birdal
Published: 2025-10-14
Categories: cs.CV, cs.AI, cs.LG, math.AT, stat.ML
arXiv: https://arxiv.org/abs/2510.12795v1

We present CuMPerLay, a novel differentiable vectorization layer that enables the integration of Cubical Multiparameter Persistence (CMP) into deep learning pipelines. While CMP presents a natural and powerful way to topologically work with images, its use is hindered by the complexity of multifiltration structures as well as the vectorization of CMP. In face of these challenges, we introduce a new algorithm for vectorizing MP homologies of cubical complexes. Our CuMPerLay decomposes the CMP into a combination of individual, learnable single-parameter persistence, where the bifiltration functions are jointly learned. Thanks to the differentiability, its robust topological feature vectors can be seamlessly used within state-of-the-art architectures such as Swin Transformers. We establish theoretical guarantees for the stability of our vectorization under generalized Wasserstein metrics. Our experiments on benchmark medical imaging and computer vision datasets show the benefit CuMPerLay on classification and segmentation performance, particularly in limited-data scenarios. Overall, CuMPerLay offers a promising direction for integrating global structural information into deep networks for structured image analysis.

---

### ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution

Authors: Long Cui, Weiyun Wang, Jie Shao, Zichen Wen, Gen Luo, Linfeng Zhang, Yanting Zhang, Yu Qiao, Wenhai Wang
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.12793v2

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm that enables the model to represent images of varying semantic complexities using different numbers of vision tokens. The key idea behind our method is to employ multiple MLP connectors, each with a different image compression ratio, to downsample the vision tokens based on the semantic complexity of the image. During training, we minimize the KL divergence between the responses conditioned on different MLP connectors. At inference time, we introduce an image router, termed Visual Resolution Router (ViR), that automatically selects the appropriate compression rate for each image patch. Compared with existing dynamic high-resolution strategies, which adjust the number of visual tokens based on image resolutions, our method dynamically adapts the number of visual tokens according to semantic complexity. Experimental results demonstrate that our method can reduce the number of vision tokens by up to 50% while maintaining the model's perception, reasoning, and OCR capabilities. We hope this work will contribute to the development of more efficient MLLMs. The code and models will be released to facilitate future research.

---

### UniFusion: Vision-Language Model as Unified Encoder in Image Generation

Authors: Kevin Li, Manuel Brack, Sudeep Katakol, Hareesh Ravi, Ajinkya Kale
Published: 2025-10-14
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.12789v1

Although recent advances in visual generation have been remarkable, most existing architectures still depend on distinct encoders for images and text. This separation constrains diffusion models' ability to perform cross-modal reasoning and knowledge transfer. Prior attempts to bridge this gap often use the last layer information from VLM, employ multiple visual encoders, or train large unified models jointly for text and image generation, which demands substantial computational resources and large-scale data, limiting its accessibility.We present UniFusion, a diffusion-based generative model conditioned on a frozen large vision-language model (VLM) that serves as a unified multimodal encoder. At the core of UniFusion is the Layerwise Attention Pooling (LAP) mechanism that extracts both high level semantics and low level details from text and visual tokens of a frozen VLM to condition a diffusion generative model. We demonstrate that LAP outperforms other shallow fusion architectures on text-image alignment for generation and faithful transfer of visual information from VLM to the diffusion model which is key for editing. We propose VLM-Enabled Rewriting Injection with Flexibile Inference (VERIFI), which conditions a diffusion transformer (DiT) only on the text tokens generated by the VLM during in-model prompt rewriting. VERIFI combines the alignment of the conditioning distribution with the VLM's reasoning capabilities for increased capabilities and flexibility at inference. In addition, finetuning on editing task not only improves text-image alignment for generation, indicative of cross-modality knowledge transfer, but also exhibits tremendous generalization capabilities. Our model when trained on single image editing, zero-shot generalizes to multiple image references further motivating the unified encoder design of UniFusion.

---

### Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report

Authors: Daniel Feijoo, Paula Garrido-Mellado, Marcos V. Conde, Jaesung Rim, Alvaro Garcia, Sunghyun Cho, Radu Timofte
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.12788v1

This paper reviews the AIM 2025 Efficient Real-World Deblurring using Single Images Challenge, which aims to advance in efficient real-blur restoration. The challenge is based on a new test set based on the well known RSBlur dataset. Pairs of blur and degraded images in this dataset are captured using a double-camera system. Participant were tasked with developing solutions to effectively deblur these type of images while fulfilling strict efficiency constraints: fewer than 5 million model parameters and a computational budget under 200 GMACs. A total of 71 participants registered, with 4 teams finally submitting valid solutions. The top-performing approach achieved a PSNR of 31.1298 dB, showcasing the potential of efficient methods in this domain. This paper provides a comprehensive overview of the challenge, compares the proposed solutions, and serves as a valuable reference for researchers in efficient real-world image deblurring.

---

### Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics

Authors: Benjamin Breen, Marco Del Tredici, Jacob McCarran, Javier Aspuru Mijares, Weichen Winston Yin, Kfir Sulimany, Jacob M. Taylor, Frank H. L. Koppens, Dirk Englund
Published: 2025-10-14
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.12787v4

We present Ax-Prover, a multi-agent system for automated theorem proving in Lean that can solve problems across diverse scientific domains and operate either autonomously or collaboratively with human experts. To achieve this, Ax-Prover approaches scientific problem solving through formal proof generation, a process that demands both creative reasoning and strict syntactic rigor. Ax-Prover meets this challenge by equipping Large Language Models (LLMs), which provide knowledge and reasoning, with Lean tools via the Model Context Protocol (MCP), which ensure formal correctness. To evaluate its performance as an autonomous prover, we benchmark our approach against frontier LLMs and specialized prover models on two public math benchmarks and on two Lean benchmarks we introduce in the fields of abstract algebra and quantum theory. On public datasets, Ax-Prover is competitive with state-of-the-art provers, while it largely outperforms them on the new benchmarks. This shows that, unlike specialized systems that struggle to generalize, our tool-based agentic theorem prover approach offers a generalizable methodology for formal verification across diverse scientific domains. Furthermore, we demonstrate Ax-Prover's assistant capabilities in a practical use case, showing how it enabled an expert mathematician to formalize the proof of a complex cryptography theorem.

---

### MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars

Authors: Felix Taubner, Ruihang Zhang, Mathieu Tuli, Sherwin Bahmani, David B. Lindell
Published: 2025-10-14
Categories: cs.CV, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2510.12785v1

Digital human avatars aim to simulate the dynamic appearance of humans in virtual environments, enabling immersive experiences across gaming, film, virtual reality, and more. However, the conventional process for creating and animating photorealistic human avatars is expensive and time-consuming, requiring large camera capture rigs and significant manual effort from professional 3D artists. With the advent of capable image and video generation models, recent methods enable automatic rendering of realistic animated avatars from a single casually captured reference image of a target subject. While these techniques significantly lower barriers to avatar creation and offer compelling realism, they lack constraints provided by multi-view information or an explicit 3D representation. So, image quality and realism degrade when rendered from viewpoints that deviate strongly from the reference image. Here, we build a video model that generates animatable multi-view videos of digital humans based on a single reference image and target expressions. Our model, MVP4D, is based on a state-of-the-art pre-trained video diffusion model and generates hundreds of frames simultaneously from viewpoints varying by up to 360 degrees around a target subject. We show how to distill the outputs of this model into a 4D avatar that can be rendered in real-time. Our approach significantly improves the realism, temporal consistency, and 3D consistency of generated avatars compared to previous methods.

---

### SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

Authors: Weiyang Jin, Yuwei Niu, Jiaqi Liao, Chengqi Duan, Aoxue Li, Shenghua Gao, Xihui Liu
Published: 2025-10-14
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.12784v2

Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a model's strong visual understanding often fails to transfer to visual generation: it may correctly judge prompt-image alignment while failing to generate a faithful image from the same prompt. This raises a compelling question: Can a model improve itself by using its understanding module to reward its generation module? We introduce SRUM, a self-rewarding post-training framework directly applicable to existing UMMs of various designs. SRUM creates a feedback loop where the model's own understanding module acts as an internal ``evaluator'', providing corrective signals to improve generation without additional human-labeled data or external reward models. To provide comprehensive feedback, SRUM uses a global-local dual reward system: a \textbf{global reward} ensures overall visual semantics and layout, while a \textbf{local reward} refines fine-grained, object-level fidelity. SRUM shows strong generalization, boosting performance on T2I-CompBench from 82.18 to \textbf{88.37} and on T2I-ReasonBench from 43.82 to \textbf{46.75}. Overall, our work establishes a powerful paradigm for enabling a UMM's understanding module to guide and enhance its own generation via self-rewarding.

---

### Cost Analysis of Human-corrected Transcription for Predominately Oral Languages

Authors: Yacouba Diarra, Nouhoum Souleymane Coulibaly, Michael Leventhal
Published: 2025-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.12781v1

Creating speech datasets for low-resource languages is a critical yet poorly understood challenge, particularly regarding the actual cost in human labor. This paper investigates the time and complexity required to produce high-quality annotated speech data for a subset of low-resource languages, low literacy Predominately Oral Languages, focusing on Bambara, a Manding language of Mali. Through a one-month field study involving ten transcribers with native proficiency, we analyze the correction of ASR-generated transcriptions of 53 hours of Bambara voice data. We report that it takes, on average, 30 hours of human labor to accurately transcribe one hour of speech data under laboratory conditions and 36 hours under field conditions. The study provides a baseline and practical insights for a large class of languages with comparable profiles undertaking the creation of NLP resources.

---

### Content Anonymization for Privacy in Long-form Audio

Authors: Cristina Aggazzotti, Ashi Garg, Zexin Cai, Nicholas Andrews
Published: 2025-10-14
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2510.12780v3

Voice anonymization techniques have been found to successfully obscure a speaker's acoustic identity in short, isolated utterances in benchmarks such as the VoicePrivacy Challenge. In practice, however, utterances seldom occur in isolation: long-form audio is commonplace in domains such as interviews, phone calls, and meetings. In these cases, many utterances from the same speaker are available, which pose a significantly greater privacy risk: given multiple utterances from the same speaker, an attacker could exploit an individual's vocabulary, syntax, and turns of phrase to re-identify them, even when their voice is completely disguised. To address this risk, we propose a new approach that performs a contextual rewriting of the transcripts in an ASR-TTS pipeline to eliminate speaker-specific style while preserving meaning. We present results in a long-form telephone conversation setting demonstrating the effectiveness of a content-based attack on voice-anonymized speech. Then we show how the proposed content-based anonymization methods can mitigate this risk while preserving speech utility. Overall, we find that paraphrasing is an effective defense against content-based attacks and recommend that stakeholders adopt this step to ensure anonymity in long-form audio.

---

### Wavefront Coding for Accommodation-Invariant Near-Eye Displays

Authors: Ugur Akpinar, Erdem Sahin, Tina M. Hayward, Apratim Majumder, Rajesh Menon, Atanas Gotchev
Published: 2025-10-14
Categories: physics.optics, cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2510.12778v1

We present a new computational near-eye display method that addresses the vergence-accommodation conflict problem in stereoscopic displays through accommodation-invariance. Our system integrates a refractive lens eyepiece with a novel wavefront coding diffractive optical element, operating in tandem with a pre-processing convolutional neural network. We employ end-to-end learning to jointly optimize the wavefront-coding optics and the image pre-processing module. To implement this approach, we develop a differentiable retinal image formation model that accounts for limiting aperture and chromatic aberrations introduced by the eye optics. We further integrate the neural transfer function and the contrast sensitivity function into the loss model to account for related perceptual effects. To tackle off-axis distortions, we incorporate position dependency into the pre-processing module. In addition to conducting rigorous analysis based on simulations, we also fabricate the designed diffractive optical element and build a benchtop setup, demonstrating accommodation-invariance for depth ranges of up to four diopters.

---

### What If : Understanding Motion Through Sparse Interactions

Authors: Stefan Andreas Baumann, Nick Stracke, Timy Phan, Björn Ommer
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.12777v1

Understanding the dynamics of a physical scene involves reasoning about the diverse ways it can potentially change, especially as a result of local interactions. We present the Flow Poke Transformer (FPT), a novel framework for directly predicting the distribution of local motion, conditioned on sparse interactions termed "pokes". Unlike traditional methods that typically only enable dense sampling of a single realization of scene dynamics, FPT provides an interpretable directly accessible representation of multi-modal scene motion, its dependency on physical interactions and the inherent uncertainties of scene dynamics. We also evaluate our model on several downstream tasks to enable comparisons with prior methods and highlight the flexibility of our approach. On dense face motion generation, our generic pre-trained model surpasses specialized baselines. FPT can be fine-tuned in strongly out-of-distribution tasks such as synthetic datasets to enable significant improvements over in-domain methods in articulated object motion estimation. Additionally, predicting explicit motion distributions directly enables our method to achieve competitive performance on tasks like moving part segmentation from pokes which further demonstrates the versatility of our FPT. Code and models are publicly available at https://compvis.github.io/flow-poke-transformer.

---

### Dr.LLM: Dynamic Layer Routing in LLMs

Authors: Ahmed Heakl, Martin Gubri, Salman Khan, Sangdoo Yun, Seong Joon Oh
Published: 2025-10-14
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.12773v2

Large Language Models (LLMs) process every token through all layers of a transformer stack, causing wasted computation on simple queries and insufficient flexibility for harder ones that need deeper reasoning. Adaptive-depth methods can improve efficiency, but prior approaches rely on costly inference-time search, architectural changes, or large-scale retraining, and in practice often degrade accuracy despite efficiency gains. We introduce Dr. LLM, Dynamic routing of Layers for LLMs, a retrofittable framework that equips pretrained models with lightweight per-layer routers deciding to skip, execute, or repeat a block. Routers are trained with explicit supervision: using Monte Carlo Tree Search (MCTS), we derive high-quality layer configurations that preserve or improve accuracy under a compute budget. Our design, windowed pooling for stable routing, focal loss with class balancing, and bottleneck MLP routers, ensures robustness under class imbalance and long sequences. On ARC (logic) and DART (math), Dr. LLM improves accuracy by up to +3.4%p while saving 5 layers per example on average. Routers generalize to out-of-domain tasks (MMLU, GSM8k, AIME, TruthfulQA, SQuADv2, GPQA, PIQA, AGIEval) with only 0.85% accuracy drop while retaining efficiency, and outperform prior routing methods by up to +7.7%p. Overall, Dr. LLM shows that explicitly supervised routers retrofit frozen LLMs for budget-aware, accuracy-driven inference without altering base weights. Code is available at https://github.com/parameterlab/dr-llm.

---

### Sample-Efficient Omniprediction for Proper Losses

Authors: Isaac Gibbs, Ryan J. Tibshirani
Published: 2025-10-14
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2510.12769v1

We consider the problem of constructing probabilistic predictions that lead to accurate decisions when employed by downstream users to inform actions. For a single decision maker, designing an optimal predictor is equivalent to minimizing a proper loss function corresponding to the negative utility of that individual. For multiple decision makers, our problem can be viewed as a variant of omniprediction in which the goal is to design a single predictor that simultaneously minimizes multiple losses. Existing algorithms for achieving omniprediction broadly fall into two categories: 1) boosting methods that optimize other auxiliary targets such as multicalibration and obtain omniprediction as a corollary, and 2) adversarial two-player game based approaches that estimate and respond to the ``worst-case" loss in an online fashion. We give lower bounds demonstrating that multicalibration is a strictly more difficult problem than omniprediction and thus the former approach must incur suboptimal sample complexity. For the latter approach, we discuss how these ideas can be used to obtain a sample-efficient algorithm through an online-to-batch conversion. This conversion has the downside of returning a complex, randomized predictor. We improve on this method by designing a more direct, unrandomized algorithm that exploits structural elements of the set of proper losses.

---

### Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction

Authors: Fengzhi Guo, Chih-Chuan Hsu, Sihao Ding, Cheng Zhang
Published: 2025-10-14
Categories: cs.CV, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2510.12768v3

Reconstructing dynamic 3D scenes from monocular input is fundamentally under-constrained, with ambiguities arising from occlusion and extreme novel views. While dynamic Gaussian Splatting offers an efficient representation, vanilla models optimize all Gaussian primitives uniformly, ignoring whether they are well or poorly observed. This limitation leads to motion drifts under occlusion and degraded synthesis when extrapolating to unseen views. We argue that uncertainty matters: Gaussians with recurring observations across views and time act as reliable anchors to guide motion, whereas those with limited visibility are treated as less reliable. To this end, we introduce USplat4D, a novel Uncertainty-aware dynamic Gaussian Splatting framework that propagates reliable motion cues to enhance 4D reconstruction. Our approach estimates time-varying per-Gaussian uncertainty and leverages it to construct a spatio-temporal graph for uncertainty-aware optimization. Experiments on diverse real and synthetic datasets show that explicitly modeling uncertainty consistently improves dynamic Gaussian Splatting models, yielding more stable geometry under occlusion and high-quality synthesis at extreme viewpoints.

---

### Language Models Model Language

Authors: Łukasz Borchmann
Published: 2025-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.12766v1

Linguistic commentary on LLMs, heavily influenced by the theoretical frameworks of de Saussure and Chomsky, is often speculative and unproductive. Critics challenge whether LLMs can legitimately model language, citing the need for "deep structure" or "grounding" to achieve an idealized linguistic "competence." We argue for a radical shift in perspective towards the empiricist principles of Witold Mańczak, a prominent general and historical linguist. He defines language not as a "system of signs" or a "computational system of the brain" but as the totality of all that is said and written. Above all, he identifies frequency of use of particular language elements as language's primary governing principle. Using his framework, we challenge prior critiques of LLMs and provide a constructive guide for designing, evaluating, and interpreting language models.

---

### Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark

Authors: Bruno Longarela, Marcos V. Conde, Alvaro Garcia, Radu Timofte
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.12765v1

This paper presents a comprehensive study and benchmark on Efficient Perceptual Super-Resolution (EPSR). While significant progress has been made in efficient PSNR-oriented super resolution, approaches focusing on perceptual quality metrics remain relatively inefficient. Motivated by this gap, we aim to replicate or improve the perceptual results of Real-ESRGAN while meeting strict efficiency constraints: a maximum of 5M parameters and 2000 GFLOPs, calculated for an input size of 960x540 pixels. The proposed solutions were evaluated on a novel dataset consisting of 500 test images of 4K resolution, each degraded using multiple degradation types, without providing the original high-quality counterparts. This design aims to reflect realistic deployment conditions and serves as a diverse and challenging benchmark. The top-performing approach manages to outperform Real-ESRGAN across all benchmark datasets, demonstrating the potential of efficient methods in the perceptual domain. This paper establishes the modern baselines for efficient perceptual super resolution.

---

### AnyUp: Universal Feature Upsampling

Authors: Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona, Michael Oechsle, Federico Tombari, Bernt Schiele, Jan Eric Lenssen
Published: 2025-10-14
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.12764v2

We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for every feature extractor and thus do not generalize to different feature types at inference time. In this work, we propose an inference-time feature-agnostic upsampling architecture to alleviate this limitation and improve upsampling quality. In our experiments, AnyUp sets a new state of the art for upsampled features, generalizes to different feature types, and preserves feature semantics while being efficient and easy to apply to a wide range of downstream tasks.

---

### Disentangling Neurodegeneration with Brain Age Gap Prediction Models: A Graph Signal Processing Perspective

Authors: Saurabh Sihag, Gonzalo Mateos, Alejandro Ribeiro
Published: 2025-10-14
Categories: eess.SP, cs.AI, q-bio.QM
arXiv: https://arxiv.org/abs/2510.12763v1

Neurodegeneration, characterized by the progressive loss of neuronal structure or function, is commonly assessed in clinical practice through reductions in cortical thickness or brain volume, as visualized by structural MRI. While informative, these conventional approaches lack the statistical sophistication required to fully capture the spatially correlated and heterogeneous nature of neurodegeneration, which manifests both in healthy aging and in neurological disorders. To address these limitations, brain age gap has emerged as a promising data-driven biomarker of brain health. The brain age gap prediction (BAGP) models estimate the difference between a person's predicted brain age from neuroimaging data and their chronological age. The resulting brain age gap serves as a compact biomarker of brain health, with recent studies demonstrating its predictive utility for disease progression and severity. However, practical adoption of BAGP models is hindered by their methodological obscurities and limited generalizability across diverse clinical populations. This tutorial article provides an overview of BAGP and introduces a principled framework for this application based on recent advancements in graph signal processing (GSP). In particular, we focus on graph neural networks (GNNs) and introduce the coVariance neural network (VNN), which leverages the anatomical covariance matrices derived from structural MRI. VNNs offer strong theoretical grounding and operational interpretability, enabling robust estimation of brain age gap predictions. By integrating perspectives from GSP, machine learning, and network neuroscience, this work clarifies the path forward for reliable and interpretable BAGP models and outlines future research directions in personalized medicine.

---

### PET Head Motion Estimation Using Supervised Deep Learning with Attention

Authors: Zhuotong Cai, Tianyi Zeng, Jiazhen Zhang, Eléonore V. Lieffrig, Kathryn Fontaine, Chenyu You, Enette Mae Revilla, James S. Duncan, Jingmin Xin, Yihuan Lu, John A. Onofrey
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.12758v1

Head movement poses a significant challenge in brain positron emission tomography (PET) imaging, resulting in image artifacts and tracer uptake quantification inaccuracies. Effective head motion estimation and correction are crucial for precise quantitative image analysis and accurate diagnosis of neurological disorders. Hardware-based motion tracking (HMT) has limited applicability in real-world clinical practice. To overcome this limitation, we propose a deep-learning head motion correction approach with cross-attention (DL-HMC++) to predict rigid head motion from one-second 3D PET raw data. DL-HMC++ is trained in a supervised manner by leveraging existing dynamic PET scans with gold-standard motion measurements from external HMT. We evaluate DL-HMC++ on two PET scanners (HRRT and mCT) and four radiotracers (18F-FDG, 18F-FPEB, 11C-UCB-J, and 11C-LSN3172176) to demonstrate the effectiveness and generalization of the approach in large cohort PET studies. Quantitative and qualitative results demonstrate that DL-HMC++ consistently outperforms state-of-the-art data-driven motion estimation methods, producing motion-free images with clear delineation of brain structures and reduced motion artifacts that are indistinguishable from gold-standard HMT. Brain region of interest standard uptake value analysis exhibits average difference ratios between DL-HMC++ and gold-standard HMT to be 1.2 plus-minus 0.5% for HRRT and 0.5 plus-minus 0.2% for mCT. DL-HMC++ demonstrates the potential for data-driven PET head motion correction to remove the burden of HMT, making motion correction accessible to clinical populations beyond research settings. The code is available at https://github.com/maxxxxxxcai/DL-HMC-TMI.

---

### E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization

Authors: Wenpu Li, Bangyan Liao, Yi Zhou, Qi Xu, Pian Wan, Peidong Liu
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.12753v2

The estimation of optical flow and 6-DoF ego-motion, two fundamental tasks in 3D vision, has typically been addressed independently. For neuromorphic vision (e.g., event cameras), however, the lack of robust data association makes solving the two problems separately an ill-posed challenge, especially in the absence of supervision via ground truth. Existing works mitigate this ill-posedness by either enforcing the smoothness of the flow field via an explicit variational regularizer or leveraging explicit structure-and-motion priors in the parametrization to improve event alignment. The former notably introduces bias in results and computational overhead, while the latter, which parametrizes the optical flow in terms of the scene depth and the camera motion, often converges to suboptimal local minima. To address these issues, we propose an unsupervised framework that jointly optimizes egomotion and optical flow via implicit spatial-temporal and geometric regularization. First, by modeling camera's egomotion as a continuous spline and optical flow as an implicit neural representation, our method inherently embeds spatial-temporal coherence through inductive biases. Second, we incorporate structure-and-motion priors through differential geometric constraints, bypassing explicit depth estimation while maintaining rigorous geometric consistency. As a result, our framework (called E-MoFlow) unifies egomotion and optical flow estimation via implicit regularization under a fully unsupervised paradigm. Experiments demonstrate its versatility to general 6-DoF motion scenarios, achieving state-of-the-art performance among unsupervised methods and competitive even with supervised approaches.

---

### KoALA: KL-L0 Adversarial Detector via Label Agreement

Authors: Siqi Li, Yasser Shoukry
Published: 2025-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.12752v2

Deep neural networks are highly susceptible to adversarial attacks, which pose significant risks to security- and safety-critical applications. We present KoALA (KL-L0 Adversarial detection via Label Agreement), a novel, semantics-free adversarial detector that requires no architectural changes or adversarial retraining. KoALA operates on a simple principle: it detects an adversarial attack when class predictions from two complementary similarity metrics disagree. These metrics - KL divergence and an L0-based similarity - are specifically chosen to detect different types of perturbations. The KL divergence metric is sensitive to dense, low-amplitude shifts, while the L0-based similarity is designed for sparse, high-impact changes. We provide a formal proof of correctness for our approach. The only training required is a simple fine-tuning step on a pre-trained image encoder using clean images to ensure the embeddings align well with both metrics. This makes KoALA a lightweight, plug-and-play solution for existing models and various data modalities. Our extensive experiments on ResNet/CIFAR-10 and CLIP/Tiny-ImageNet confirm our theoretical claims. When the theorem's conditions are met, KoALA consistently and effectively detects adversarial examples. On the full test sets, KoALA achieves a precision of 0.96 and a recall of 0.97 on ResNet/CIFAR-10, and a precision of 0.71 and a recall of 0.94 on CLIP/Tiny-ImageNet.

---

### VQArt-Bench: A semantically rich VQA Benchmark for Art and Cultural Heritage

Authors: A. Alfarano, L. Venturoli, D. Negueruela del Castillo
Published: 2025-10-14
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.12750v1

Multimodal Large Language Models (MLLMs) have demonstrated significant capabilities in joint visual and linguistic tasks. However, existing Visual Question Answering (VQA) benchmarks often fail to evaluate deep semantic understanding, particularly in complex domains like visual art analysis. Confined to simple syntactic structures and surface-level attributes, these questions fail to capture the diversity and depth of human visual inquiry. This limitation incentivizes models to exploit statistical shortcuts rather than engage in visual reasoning. To address this gap, we introduce VQArt-Bench, a new, large-scale VQA benchmark for the cultural heritage domain. This benchmark is constructed using a novel multi-agent pipeline where specialized agents collaborate to generate nuanced, validated, and linguistically diverse questions. The resulting benchmark is structured along relevant visual understanding dimensions that probe a model's ability to interpret symbolic meaning, narratives, and complex visual relationships. Our evaluation of 14 state-of-the-art MLLMs on this benchmark reveals significant limitations in current models, including a surprising weakness in simple counting tasks and a clear performance gap between proprietary and open-source models.

---

### SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding

Authors: Zhiliu Yang, Jinyu Dai, Jianyuan Zhang, Zhu Yang
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.12749v1

The scene perception, understanding, and simulation are fundamental techniques for embodied-AI agents, while existing solutions are still prone to segmentation deficiency, dynamic objects' interference, sensor data sparsity, and view-limitation problems. This paper proposes a novel framework, named SPORTS, for holistic scene understanding via tightly integrating Video Panoptic Segmentation (VPS), Visual Odometry (VO), and Scene Rendering (SR) tasks into an iterative and unified perspective. Firstly, VPS designs an adaptive attention-based geometric fusion mechanism to align cross-frame features via enrolling the pose, depth, and optical flow modality, which automatically adjust feature maps for different decoding stages. And a post-matching strategy is integrated to improve identities tracking. In VO, panoptic segmentation results from VPS are combined with the optical flow map to improve the confidence estimation of dynamic objects, which enhances the accuracy of the camera pose estimation and completeness of the depth map generation via the learning-based paradigm. Furthermore, the point-based rendering of SR is beneficial from VO, transforming sparse point clouds into neural fields to synthesize high-fidelity RGB views and twin panoptic views. Extensive experiments on three public datasets demonstrate that our attention-based feature fusion outperforms most existing state-of-the-art methods on the odometry, tracking, segmentation, and novel view synthesis tasks.

---

### FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution

Authors: Junhao Zhuang, Shi Guo, Xin Cai, Xiaohui Li, Yihao Liu, Chun Yuan, Tianfan Xue
Published: 2025-10-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.12747v1

Diffusion models have recently advanced video restoration, but applying them to real-world video super-resolution (VSR) remains challenging due to high latency, prohibitive computation, and poor generalization to ultra-high resolutions. Our goal in this work is to make diffusion-based VSR practical by achieving efficiency, scalability, and real-time performance. To this end, we propose FlashVSR, the first diffusion-based one-step streaming framework towards real-time VSR. FlashVSR runs at approximately 17 FPS for 768x1408 videos on a single A100 GPU by combining three complementary innovations: (i) a train-friendly three-stage distillation pipeline that enables streaming super-resolution, (ii) locality-constrained sparse attention that cuts redundant computation while bridging the train-test resolution gap, and (iii) a tiny conditional decoder that accelerates reconstruction without sacrificing quality. To support large-scale training, we also construct VSR-120K, a new dataset with 120k videos and 180k images. Extensive experiments show that FlashVSR scales reliably to ultra-high resolutions and achieves state-of-the-art performance with up to 12x speedup over prior one-step diffusion VSR models. We will release the code, pretrained models, and dataset to foster future research in efficient diffusion-based VSR.

---

### Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps

Authors: Do Tien Hai, Trung Nguyen Mai, TrungTin Nguyen, Nhat Ho, Binh T. Nguyen, Christopher Drovandi
Published: 2025-10-14
Categories: stat.ML, cs.LG, math.ST, stat.CO, stat.ME
arXiv: https://arxiv.org/abs/2510.12744v2

We develop a unified statistical framework for softmax-gated Gaussian mixture of experts (SGMoE) that addresses three long-standing obstacles in parameter estimation and model selection: (i) non-identifiability of gating parameters up to common translations, (ii) intrinsic gate-expert interactions that induce coupled differential relations in the likelihood, and (iii) the tight numerator-denominator coupling in the softmax-induced conditional density. Our approach introduces Voronoi-type loss functions aligned with the gate-partition geometry and establishes finite-sample convergence rates for the maximum likelihood estimator (MLE). In over-specified models, we reveal a link between the MLE's convergence rate and the solvability of an associated system of polynomial equations characterizing near-nonidentifiable directions. For model selection, we adapt dendrograms of mixing measures to SGMoE, yielding a consistent, sweep-free selector of the number of experts that attains pointwise-optimal parameter rates under overfitting while avoiding multi-size training. Simulations on synthetic data corroborate the theory, accurately recovering the expert count and achieving the predicted rates for parameter estimation while closely approximating the regression function. Under model misspecification (e.g., $ε$-contamination), the dendrogram selection criterion is robust, recovering the true number of mixture components, while the Akaike information criterion, the Bayesian information criterion, and the integrated completed likelihood tend to overselect as sample size grows. On a maize proteomics dataset of drought-responsive traits, our dendrogram-guided SGMoE selects two experts, exposes a clear mixing-measure hierarchy, stabilizes the likelihood early, and yields interpretable genotype-phenotype maps, outperforming standard criteria without multi-size training.

---

### CTRL-Rec: Controlling Recommender Systems With Natural Language

Authors: Micah Carroll, Adeline Foote, Kevin Feng, Marcus Williams, Anca Dragan, W. Bradley Knox, Smitha Milli
Published: 2025-10-14
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.12742v1

When users are dissatisfied with recommendations from a recommender system, they often lack fine-grained controls for changing them. Large language models (LLMs) offer a solution by allowing users to guide their recommendations through natural language requests (e.g., "I want to see respectful posts with a different perspective than mine"). We propose a method, CTRL-Rec, that allows for natural language control of traditional recommender systems in real-time with computational efficiency. Specifically, at training time, we use an LLM to simulate whether users would approve of items based on their language requests, and we train embedding models that approximate such simulated judgments. We then integrate these user-request-based predictions into the standard weighting of signals that traditional recommender systems optimize. At deployment time, we require only a single LLM embedding computation per user request, allowing for real-time control of recommendations. In experiments with the MovieLens dataset, our method consistently allows for fine-grained control across a diversity of requests. In a study with 19 Letterboxd users, we find that CTRL-Rec was positively received by users and significantly enhanced users' sense of control and satisfaction with recommendations compared to traditional controls.

---

### Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare

Authors: Adam Tupper, Christian Gagné
Published: 2025-10-14
Categories: cs.CV, cs.DC
arXiv: https://arxiv.org/abs/2510.12741v1

Foundation models open up new possibilities for the use of AI in healthcare. However, even when pre-trained on health data, they still need to be fine-tuned for specific downstream tasks. Furthermore, although foundation models reduce the amount of training data required to achieve good performance, obtaining sufficient data is still a challenge. This is due, in part, to restrictions on sharing and aggregating data from different sources to protect patients' privacy. One possible solution to this is to fine-tune foundation models via federated learning across multiple participating clients (i.e., hospitals, clinics, etc.). In this work, we propose a new personalized federated fine-tuning method that learns orthogonal LoRA adapters to disentangle general and client-specific knowledge, enabling each client to fully exploit both their own data and the data of others. Our preliminary results on real-world federated medical imaging tasks demonstrate that our approach is competitive against current federated fine-tuning methods.

---

### Hey, wait a minute: on at-issue sensitivity in Language Models

Authors: Sanghee J. Kim, Kanishka Misra
Published: 2025-10-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.12740v2

Evaluating the naturalness of dialogue in language models (LMs) is not trivial: notions of 'naturalness' vary, and scalable quantitative metrics remain limited. This study leverages the linguistic notion of 'at-issueness' to assess dialogue naturalness and introduces a new method: Divide, Generate, Recombine, and Compare (DGRC). DGRC (i) divides a dialogue as a prompt, (ii) generates continuations for subparts using LMs, (iii) recombines the dialogue and continuations, and (iv) compares the likelihoods of the recombined sequences. This approach mitigates bias in linguistic analyses of LMs and enables systematic testing of discourse-sensitive behavior. Applying DGRC, we find that LMs prefer to continue dialogue on at-issue content, with this effect enhanced in instruct-tuned models. They also reduce their at-issue preference when relevant cues (e.g., "Hey, wait a minute") are present. Although instruct-tuning does not further amplify this modulation, the pattern reflects a hallmark of successful dialogue dynamics.

---

### Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon Effect

Authors: Jon Donnelly, Srikar Katta, Emanuele Borgonovo, Cynthia Rudin
Published: 2025-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.12734v2

Variable importance (VI) methods are often used for hypothesis generation, feature selection, and scientific validation. In the standard VI pipeline, an analyst estimates VI for a single predictive model with only the observed features. However, the importance of a feature depends heavily on which other variables are included in the model, and essential variables are often omitted from observational datasets. Moreover, the VI estimated for one model is often not the same as the VI estimated for another equally-good model - a phenomenon known as the Rashomon Effect. We address these gaps by introducing UNobservables and Inference for Variable importancE using Rashomon SEts (UNIVERSE). Our approach adapts Rashomon sets = the sets of near-optimal models in a dataset - to produce bounds on the true VI even with missing features. We theoretically guarantee the robustness of our approach, show strong performance on semi-synthetic simulations, and demonstrate its utility in a credit risk task.

---

### HYPE: Hybrid Planning with Ego Proposal-Conditioned Predictions

Authors: Hang Yu, Julian Jordan, Julian Schmidt, Silvan Lindner, Alessandro Canevaro, Wilhelm Stork
Published: 2025-10-14
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.12733v2

Safe and interpretable motion planning in complex urban environments needs to reason about bidirectional multi-agent interactions. This reasoning requires to estimate the costs of potential ego driving maneuvers. Many existing planners generate initial trajectories with sampling-based methods and refine them by optimizing on learned predictions of future environment states, which requires a cost function that encodes the desired vehicle behavior. Designing such a cost function can be very challenging, especially if a wide range of complex urban scenarios has to be considered. We propose HYPE: HYbrid Planning with Ego proposal-conditioned predictions, a planner that integrates multimodal trajectory proposals from a learned proposal model as heuristic priors into a Monte Carlo Tree Search (MCTS) refinement. To model bidirectional interactions, we introduce an ego-conditioned occupancy prediction model, enabling consistent, scene-aware reasoning. Our design significantly simplifies cost function design in refinement by considering proposal-driven guidance, requiring only minimalistic grid-based cost terms. Evaluations on large-scale real-world benchmarks nuPlan and DeepUrban show that HYPE effectively achieves state-of-the-art performance, especially in safety and adaptability.

---

### Clutch Control: An Attention-based Combinatorial Bandit for Efficient Mutation in JavaScript Engine Fuzzing

Authors: Myles Foley, Sergio Maffeis, Muhammad Fakhrur Rozi, Takeshi Takahashi
Published: 2025-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.12732v2

JavaScript engines are widely used in web browsers, PDF readers, and server-side applications. The rise in concern over their security has led to the development of several targeted fuzzing techniques. However, existing approaches use random selection to determine where to perform mutations in JavaScript code. We postulate that the problem of selecting better mutation targets is suitable for combinatorial bandits with a volatile number of arms. Thus, we propose CLUTCH, a novel deep combinatorial bandit that can observe variable length JavaScript test case representations, using an attention mechanism from deep learning. Furthermore, using Concrete Dropout, CLUTCH can dynamically adapt its exploration. We show that CLUTCH increases efficiency in JavaScript fuzzing compared to three state-of-the-art solutions by increasing the number of valid test cases and coverage-per-testcase by, respectively, 20.3% and 8.9% on average. In volatile and combinatorial settings we show that CLUTCH outperforms state-of-the-art bandits, achieving at least 78.1% and 4.1% less regret in volatile and combinatorial settings, respectively.

---

### Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behavior

Authors: Minjae Lee, Minsuk Kahng
Published: 2025-10-14
Categories: cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2510.12728v3

Large Language Models (LLMs) are increasingly embedded in applications, and people can shape model behavior by editing prompt instructions. Yet encoding subtle, domain-specific policies into prompts is challenging. Although this process often benefits from concrete test cases, test data and prompt instructions are typically developed as separate artifacts, reflecting traditional machine learning practices in which model tuning was slow and test sets were static. We argue that the fast, iterative nature of prompt engineering calls for removing this separation and enabling a new workflow: data-prompt co-evolution, where a living test set and prompt instructions evolve in tandem. We present an interactive system that operationalizes this workflow. It guides application developers to discover edge cases, articulate rationales for desired behavior, and iteratively evaluate revised prompts against a growing test set. A user study shows our workflow helps people refine prompts systematically, better aligning them with their intended policies. This work points toward more robust and responsible LLM applications through human-in-the-loop development.

---

### Hierarchical Federated Learning for Crop Yield Prediction in Smart Agricultural Production Systems

Authors: Anas Abouaomar, Mohammed El hanjri, Abdellatif Kobbane, Anis Laouiti, Khalid Nafil
Published: 2025-10-14
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2510.12727v1

In this paper, we presents a novel hierarchical federated learning architecture specifically designed for smart agricultural production systems and crop yield prediction. Our approach introduces a seasonal subscription mechanism where farms join crop-specific clusters at the beginning of each agricultural season. The proposed three-layer architecture consists of individual smart farms at the client level, crop-specific aggregators at the middle layer, and a global model aggregator at the top level. Within each crop cluster, clients collaboratively train specialized models tailored to specific crop types, which are then aggregated to produce a higher-level global model that integrates knowledge across multiple crops. This hierarchical design enables both local specialization for individual crop types and global generalization across diverse agricultural contexts while preserving data privacy and reducing communication overhead. Experiments demonstrate the effectiveness of the proposed system, showing that local and crop-layer models closely follow actual yield patterns with consistent alignment, significantly outperforming standard machine learning models. The results validate the advantages of hierarchical federated learning in the agricultural context, particularly for scenarios involving heterogeneous farming environments and privacy-sensitive agricultural data.

---

### Improving Decision Trees through the Lens of Parameterized Local Search

Authors: Juha Harviainen, Frank Sommer, Manuel Sorge
Published: 2025-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.12726v1

Algorithms for learning decision trees often include heuristic local-search operations such as (1) adjusting the threshold of a cut or (2) also exchanging the feature of that cut. We study minimizing the number of classification errors by performing a fixed number of a single type of these operations. Although we discover that the corresponding problems are NP-complete in general, we provide a comprehensive parameterized-complexity analysis with the aim of determining those properties of the problems that explain the hardness and those that make the problems tractable. For instance, we show that the problems remain hard for a small number $d$ of features or small domain size $D$ but the combination of both yields fixed-parameter tractability. That is, the problems are solvable in $(D + 1)^{2d} \cdot |I|^{O(1)}$ time, where $|I|$ is the size of the input. We also provide a proof-of-concept implementation of this algorithm and report on empirical results.

---

### Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages

Authors: Nadine El-Naggar, Tatsuki Kuribayashi, Ted Briscoe
Published: 2025-10-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.12722v1

Whether language models (LMs) have inductive biases that favor typologically frequent grammatical properties over rare, implausible ones has been investigated, typically using artificial languages (ALs) (White and Cotterell, 2021; Kuribayashi et al., 2024). In this paper, we extend these works from two perspectives. First, we extend their context-free AL formalization by adopting Generalized Categorial Grammar (GCG) (Wood, 2014), which allows ALs to cover attested but previously overlooked constructions, such as unbounded dependency and mildly context-sensitive structures. Second, our evaluation focuses more on the generalization ability of LMs to process unseen longer test sentences. Thus, our ALs better capture features of natural languages and our experimental paradigm leads to clearer conclusions -- typologically plausible word orders tend to be easier for LMs to productively generalize.

---

### CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression

Authors: Dayin Gou, Sanghyun Byun, Nilesh Malpeddi, Gabrielle De Micheli, Prathamesh Vaste, Jacob Song, Woo Seong Chung
Published: 2025-10-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.12721v1

Large Language Models (LLMs) typically rely on a large number of parameters for token embedding, leading to substantial storage requirements and memory footprints. In particular, LLMs deployed on edge devices are memory-bound, and reducing the memory footprint by compressing the embedding layer not only frees up the memory bandwidth but also speeds up inference. To address this, we introduce CARVQ, a post-training novel Corrective Adaptor combined with group Residual Vector Quantization. CARVQ relies on the composition of both linear and non-linear maps and mimics the original model embedding to compress to approximately 1.6 bits without requiring specialized hardware to support lower-bit storage. We test our method on pre-trained LLMs such as LLaMA-3.2-1B, LLaMA-3.2-3B, LLaMA-3.2-3B-Instruct, LLaMA-3.1-8B, Qwen2.5-7B, Qwen2.5-Math-7B and Phi-4, evaluating on common generative, discriminative, math and reasoning tasks. We show that in most cases, CARVQ can achieve lower average bitwidth-per-parameter while maintaining reasonable perplexity and accuracy compared to scalar quantization. Our contributions include a novel compression technique that is compatible with state-of-the-art transformer quantization methods and can be seamlessly integrated into any hardware supporting 4-bit memory to reduce the model's memory footprint in memory-constrained devices. This work demonstrates a crucial step toward the efficient deployment of LLMs on edge devices.

---

### Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception

Authors: Ziyang Ma, Ruiyang Xu, Zhenghao Xing, Yunfei Chu, Yuxuan Wang, Jinzheng He, Jin Xu, Pheng-Ann Heng, Kai Yu, Junyang Lin, Eng Siong Chng, Xie Chen
Published: 2025-10-14
Categories: cs.CL, cs.CV, cs.MM, cs.SD
arXiv: https://arxiv.org/abs/2510.12720v2

Fine-grained perception of multimodal information is critical for advancing human-AI interaction. With recent progress in audio-visual technologies, Omni Language Models (OLMs), capable of processing audio and video signals in parallel, have emerged as a promising paradigm for achieving richer understanding and reasoning. However, their capacity to capture and describe fine-grained details remains limited explored. In this work, we present a systematic and comprehensive investigation of omni detailed perception from the perspectives of the data pipeline, models, and benchmark. We first identify an inherent "co-growth" between detail and hallucination in current OLMs. To address this, we propose Omni-Detective, an agentic data generation pipeline integrating tool-calling, to autonomously produce highly detailed yet minimally hallucinatory multimodal data. Based on the data generated with Omni-Detective, we train two captioning models: Audio-Captioner for audio-only detailed perception, and Omni-Captioner for audio-visual detailed perception. Under the cascade evaluation protocol, Audio-Captioner achieves the best performance on MMAU and MMAR among all open-source models, surpassing Gemini 2.5 Flash and delivering performance comparable to Gemini 2.5 Pro. On existing detailed captioning benchmarks, Omni-Captioner sets a new state-of-the-art on VDC and achieves the best trade-off between detail and hallucination on the video-SALMONN 2 testset. Given the absence of a dedicated benchmark for omni detailed perception, we design Omni-Cloze, a novel cloze-style evaluation for detailed audio, visual, and audio-visual captioning that ensures stable, efficient, and reliable assessment. Experimental results and analysis demonstrate the effectiveness of Omni-Detective in generating high-quality detailed captions, as well as the superiority of Omni-Cloze in evaluating such detailed captions.

---

### Multitask finetuning and acceleration of chemical pretrained models for small molecule drug property prediction

Authors: Matthew Adrian, Yunsie Chung, Kevin Boyd, Saee Paliwal, Srimukh Prasad Veccham, Alan C. Cheng
Published: 2025-10-14
Categories: cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2510.12719v1

Chemical pretrained models, sometimes referred to as foundation models, are receiving considerable interest for drug discovery applications. The general chemical knowledge extracted from self-supervised training has the potential to improve predictions for critical drug discovery endpoints, including on-target potency and ADMET properties. Multi-task learning has previously been successfully leveraged to improve predictive models. Here, we show that enabling multitasking in finetuning of chemical pretrained graph neural network models such as Kinetic GROVER Multi-Task (KERMT), an enhanced version of the GROVER model, and Knowledge-guided Pre-training of Graph Transformer (KGPT) significantly improves performance over non-pretrained graph neural network models. Surprisingly, we find that the performance improvement from finetuning KERMT in a multitask manner is most significant at larger data sizes. Additionally, we publish two multitask ADMET data splits to enable more accurate benchmarking of multitask deep learning methods for drug property prediction. Finally, we provide an accelerated implementation of the KERMT model on GitHub, unlocking large-scale pretraining, finetuning, and inference in industrial drug discovery workflows.

---

### Artificial intelligence for simplified patient-centered dosimetry in radiopharmaceutical therapies

Authors: Alejandro Lopez-Montes, Fereshteh Yousefirizi, Yizhou Chen, Yazdan Salimi, Robert Seifert, Ali Afshar-Oromieh, Carlos Uribe, Axel Rominger, Habib Zaidi, Arman Rahmim, Kuangyu Shi
Published: 2025-10-14
Categories: physics.med-ph, cs.AI, physics.app-ph
arXiv: https://arxiv.org/abs/2510.12714v1

KEY WORDS: Artificial Intelligence (AI), Theranostics, Dosimetry, Radiopharmaceutical Therapy (RPT), Patient-friendly dosimetry KEY POINTS - The rapid evolution of radiopharmaceutical therapy (RPT) highlights the growing need for personalized and patient-centered dosimetry. - Artificial Intelligence (AI) offers solutions to the key limitations in current dosimetry calculations. - The main advances on AI for simplified dosimetry toward patient-friendly RPT are reviewed. - Future directions on the role of AI in RPT dosimetry are discussed.

---

### Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection

Authors: Wissam Salhab, Darine Ameyed, Hamid Mcheick, Fehmi Jaafar
Published: 2025-10-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.12713v1

Robustness in AI systems refers to their ability to maintain reliable and accurate performance under various conditions, including out-of-distribution (OOD) samples, adversarial attacks, and environmental changes. This is crucial in safety-critical systems, such as autonomous vehicles, transportation, or healthcare, where malfunctions could have severe consequences. This paper proposes an approach to improve OOD detection without the need of labeled data, thereby increasing the AI systems' robustness. The proposed approach leverages the principles of self-supervised learning, allowing the model to learn useful representations from unlabeled data. Combined with graph-theoretical techniques, this enables the more efficient identification and categorization of OOD samples. Compared to existing state-of-the-art methods, this approach achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) = 0.99.

---

### Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning

Authors: Xingang Guo, Utkarsh Tyagi, Advait Gosai, Paula Vergara, Jayeon Park, Ernesto Gabriel Hernández Montoya, Chen Bo Calvin Zhang, Bin Hu, Yunzhong He, Bing Liu, Rakshith Sharma Srinivasa
Published: 2025-10-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.12712v3

Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient visual cues. Beyond static visual perception, MLLMs must also think with images: dynamically transforming visual content and integrating it with other tools to solve complex tasks. However, this shift from treating vision as passive context to a manipulable cognitive workspace remains underexplored. Most existing benchmarks still follow a think about images paradigm, where images are regarded as static inputs. To address this gap, we introduce VisualToolBench, a visual tool-use reasoning benchmark that rigorously evaluates MLLMs' ability to perceive, transform, and reason across complex visual-textual tasks under the think-with-images paradigm. VisualToolBench comprises 1,204 challenging, open-ended vision tasks (603 single-turn, 601 multi-turn) spanning across five diverse domains, each paired with detailed rubrics to enable systematic evaluation. Our evaluation shows that current MLLMs struggle with tasks requiring effective integration of vision and general-purpose tools. Even the strongest model (GPT-5-think) reaches only 18.68% pass rate. We further observe divergent tool-use behaviors, with OpenAI models benefiting from diverse image manipulations while Gemini-2.5-pro shows no improvement. By introducing the first benchmark centered on think with images, VisualToolBench offers critical insights for advancing visual intelligence in MLLMs.

---

### SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model

Authors: Lin Lin, Jiefeng Long, Zhihe Wan, Yuchi Wang, Dingkang Yang, Shuang Yang, Yueyang Yao, Xu Chen, Zirui Guo, Shengqiang Li, Weiran Li, Hanyu Li et al.
Published: 2025-10-14
Categories: cs.IR, cs.CV
arXiv: https://arxiv.org/abs/2510.12709v3

Multimodal embedding models aim to yield informative unified representations that empower diverse cross-modal tasks. Despite promising developments in the evolution from CLIP-based dual-tower architectures to large vision-language models, prior works still face unavoidable challenges in real-world applications and business scenarios, such as the limited modality support, unstable training mechanisms, and industrial domain gaps. In this work, we introduce SAIL-Embedding, an omni-modal embedding foundation model that addresses these issues through tailored training strategies and architectural design. In the optimization procedure, we propose a multi-stage training scheme to boost the multifaceted effectiveness of representation learning. Specifically, the content-aware progressive training aims to enhance the model's adaptability to diverse downstream tasks and master enriched cross-modal proficiency. The collaboration-aware recommendation enhancement training further adapts multimodal representations for recommendation scenarios by distilling knowledge from sequence-to-item and ID-to-item embeddings while mining user historical interests. Concurrently, we develop the stochastic specialization and dataset-driven pattern matching to strengthen model training flexibility and generalizability. Experimental results show that SAIL-Embedding achieves SOTA performance compared to other methods in different retrieval tasks. In online experiments across various real-world scenarios integrated with our model, we observe a significant increase in Lifetime (LT), which is a crucial indicator for the recommendation experience. For instance, the model delivers the 7-day LT gain of +0.5% in the Douyin-Selected scenario. For the Douyin feed rank model, the match features produced by SAIL-Embedding yield a +0.1% AUC gain.

---

### Hybrid Explanation-Guided Learning for Transformer-Based Chest X-Ray Diagnosis

Authors: Shelley Zixin Shu, Haozhe Luo, Alexander Poellinger, Mauricio Reyes
Published: 2025-10-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.12704v1

Transformer-based deep learning models have demonstrated exceptional performance in medical imaging by leveraging attention mechanisms for feature representation and interpretability. However, these models are prone to learning spurious correlations, leading to biases and limited generalization. While human-AI attention alignment can mitigate these issues, it often depends on costly manual supervision. In this work, we propose a Hybrid Explanation-Guided Learning (H-EGL) framework that combines self-supervised and human-guided constraints to enhance attention alignment and improve generalization. The self-supervised component of H-EGL leverages class-distinctive attention without relying on restrictive priors, promoting robustness and flexibility. We validate our approach on chest X-ray classification using the Vision Transformer (ViT), where H-EGL outperforms two state-of-the-art Explanation-Guided Learning (EGL) methods, demonstrating superior classification accuracy and generalization capability. Additionally, it produces attention maps that are better aligned with human expertise.

---

### CAMNet: Leveraging Cooperative Awareness Messages for Vehicle Trajectory Prediction

Authors: Mattia Grasselli, Angelo Porrello, Carlo Augusto Grazia
Published: 2025-10-14
Categories: cs.AI, cs.NI
arXiv: https://arxiv.org/abs/2510.12703v1

Autonomous driving remains a challenging task, particularly due to safety concerns. Modern vehicles are typically equipped with expensive sensors such as LiDAR, cameras, and radars to reduce the risk of accidents. However, these sensors face inherent limitations: their field of view and line of sight can be obstructed by other vehicles, thereby reducing situational awareness. In this context, vehicle-to-vehicle communication plays a crucial role, as it enables cars to share information and remain aware of each other even when sensors are occluded. One way to achieve this is through the use of Cooperative Awareness Messages (CAMs). In this paper, we investigate the use of CAM data for vehicle trajectory prediction. Specifically, we design and train a neural network, Cooperative Awareness Message-based Graph Neural Network (CAMNet), on a widely used motion forecasting dataset. We then evaluate the model on a second dataset that we created from scratch using Cooperative Awareness Messages, in order to assess whether this type of data can be effectively exploited. Our approach demonstrates promising results, showing that CAMs can indeed support vehicle trajectory prediction. At the same time, we discuss several limitations of the approach, which highlight opportunities for future research.

---

### Beyond Postconditions: Can Large Language Models infer Formal Contracts for Automatic Software Verification?

Authors: Cedric Richter, Heike Wehrheim
Published: 2025-10-14
Categories: cs.SE, cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2510.12702v1

Automatic software verifiers have become increasingly effective at the task of checking software against (formal) specifications. Yet, their adoption in practice has been hampered by the lack of such specifications in real world code. Large Language Models (LLMs) have shown promise in inferring formal postconditions from natural language hints embedded in code such as function names, comments or documentation. Using the generated postconditions as specifications in a subsequent verification, however, often leads verifiers to suggest invalid inputs, hinting at potential issues that ultimately turn out to be false alarms. To address this, we revisit the problem of specification inference from natural language in the context of automatic software verification. In the process, we introduce NL2Contract, the task of employing LLMs to translate informal natural language into formal functional contracts, consisting of postconditions as well as preconditions. We introduce metrics to validate and compare different NL2Contract approaches, using soundness, bug discriminative power of the generated contracts and their usability in the context of automatic software verification as key metrics. We evaluate NL2Contract with different LLMs and compare it to the task of postcondition generation nl2postcond. Our evaluation shows that (1) LLMs are generally effective at generating functional contracts sound for all possible inputs, (2) the generated contracts are sufficiently expressive for discriminating buggy from correct behavior, and (3) verifiers supplied with LLM inferred functional contracts produce fewer false alarms than when provided with postconditions alone. Further investigations show that LLM inferred preconditions generally align well with developers intentions which allows us to use automatic software verifiers to catch real-world bugs.

---

### Topological Signatures of ReLU Neural Network Activation Patterns

Authors: Vicente Bosca, Tatum Rask, Sunia Tanweer, Andrew R. Tawfeek, Branden Stone
Published: 2025-10-14
Categories: cs.LG, cs.AI, cs.CG, math.AT, stat.ML
arXiv: https://arxiv.org/abs/2510.12700v2

This paper explores the topological signatures of ReLU neural network activation patterns. We consider feedforward neural networks with ReLU activation functions and analyze the polytope decomposition of the feature space induced by the network. Mainly, we investigate how the Fiedler partition of the dual graph and show that it appears to correlate with the decision boundary -- in the case of binary classification. Additionally, we compute the homology of the cellular decomposition -- in a regression task -- to draw similar patterns in behavior between the training loss and polyhedral cell-count, as the model is trained.

---