# Research Papers — 2025-10 · bundle page 109 of 217

> Full-text markdown of papers #5401–5450 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/109
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/108.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/110.md)

### FACTS: Table Summarization via Offline Template Generation with Agentic Workflows

Authors: Ye Yuan, Mohammad Amin Shabani, Siqi Liu
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13920v2

Query-focused table summarization requires generating natural language summaries of tabular data conditioned on a user query, enabling users to access insights beyond fact retrieval. Existing approaches face key limitations: table-to-text models require costly fine-tuning and struggle with complex reasoning, prompt-based LLM methods suffer from token-limit and efficiency issues while exposing sensitive data, and prior agentic pipelines often rely on decomposition, planning, or manual templates that lack robustness and scalability. To mitigate these issues, we introduce an agentic workflow, FACTS, a Fast, Accurate, and Privacy-Compliant Table Summarization approach via Offline Template Generation. FACTS produces offline templates, consisting of SQL queries and Jinja2 templates, which can be rendered into natural language summaries and are reusable across multiple tables sharing the same schema. It enables fast summarization through reusable offline templates, accurate outputs with executable SQL queries, and privacy compliance by sending only table schemas to LLMs. Evaluations on widely-used benchmarks show that FACTS consistently outperforms baseline methods, establishing it as a practical solution for real-world query-focused table summarization. Our code is available at https://github.com/BorealisAI/FACTS.

---

### Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling

Authors: Peng Kuang, Yanli Wang, Xiaoyu Han, Yaowenqi Liu, Kaidi Xu, Haohan Wang
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13918v2

Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise is challenged by recent benchmarks where simple majority voting, which ignores PRM signals, occasionally outperforms standard PRM-based selection. This raises a critical question: How can we effectively utilize verification signals from PRMs for TTS? To address this, we start by developing a theoretical framework for optimally combining signals from both the LLM and the PRM. Our framework reveals that the optimal strategy is a weighted aggregation of responses, a strategy whose effectiveness hinges on estimating weights that capture the complex interplay between the models. Based on our theoretical results, we empirically show that these optimal weighting functions differ significantly across LLM-PRM pairs and, notably, often assign substantial negative weights. Motivated by these insights, we propose efficient pre-computation methods to calibrate these weighting functions. Extensive experiments across 5 LLMs and 7 PRMs demonstrate that our calibration method significantly boosts the TTS efficiency, surpassing the performance of vanilla weighted majority voting while using only $21.3\%$ of the computation. Ultimately, our work demonstrates that investing in a more intelligent aggregation strategy can be a more convincing path to performance gains than simply scaling test-time computation.

---

### Multi-View Semi-Supervised Label Distribution Learning with Local Structure Complementarity

Authors: Yanshan Xiao, Kaihong Wu, Bo Liu
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13917v1

Label distribution learning (LDL) is a paradigm that each sample is associated with a label distribution. At present, the existing approaches are proposed for the single-view LDL problem with labeled data, while the multi-view LDL problem with labeled and unlabeled data has not been considered. In this paper, we put forward the multi-view semi-supervised label distribution learning with local structure complementarity (MVSS-LDL) approach, which exploits the local nearest neighbor structure of each view and emphasizes the complementarity of local nearest neighbor structures in multiple views. Specifically speaking, we first explore the local structure of view $v$ by computing the $k$-nearest neighbors. As a result, the $k$-nearest neighbor set of each sample $\boldsymbol{x}_i$ in view $v$ is attained. Nevertheless, this $k$-nearest neighbor set describes only a part of the nearest neighbor information of sample $\boldsymbol{x}_i$. In order to obtain a more comprehensive description of sample $\boldsymbol{x}_i$'s nearest neighbors, we complement the nearest neighbor set in view $v$ by incorporating sample $\boldsymbol{x}_i$'s nearest neighbors in other views. Lastly, based on the complemented nearest neighbor set in each view, a graph learning-based multi-view semi-supervised LDL model is constructed. By considering the complementarity of local nearest neighbor structures, different views can mutually provide the local structural information to complement each other. To the best of our knowledge, this is the first attempt at multi-view LDL. Numerical studies have demonstrated that MVSS-LDL attains explicitly better classification performance than the existing single-view LDL methods.

---

### Element2Vec: Build Chemical Element Representation from Text for Property Prediction

Authors: Yuanhao Li, Keyuan Lai, Tianqi Wang, Qihao Liu, Jiawei Ma, Yuan-Chao Hu
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13916v2

Accurate property data for chemical elements is crucial for materials design and manufacturing, but many of them are difficult to measure directly due to equipment constraints. While traditional methods use the properties of other elements or related properties for prediction via numerical analyses, they often fail to model complex relationships. After all, not all characteristics can be represented as scalars. Recent efforts have been made to explore advanced AI tools such as language models for property estimation, but they still suffer from hallucinations and a lack of interpretability. In this paper, we investigate Element2Vecto effectively represent chemical elements from natural languages to support research in the natural sciences. Given the text parsed from Wikipedia pages, we use language models to generate both a single general-purpose embedding (Global) and a set of attribute-highlighted vectors (Local). Despite the complicated relationship across elements, the computational challenges also exist because of 1) the discrepancy in text distribution between common descriptions and specialized scientific texts, and 2) the extremely limited data, i.e., with only 118 known elements, data for specific properties is often highly sparse and incomplete. Thus, we also design a test-time training method based on self-attention to mitigate the prediction error caused by Vanilla regression clearly. We hope this work could pave the way for advancing AI-driven discovery in materials science.

---

### Readability $\ne$ Learnability: Rethinking the Role of Simplicity in Training Small Language Models

Authors: Ivan Lee, Taylor Berg-Kirkpatrick
Published: 2025-10-15
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13915v1

Recent studies suggest that very small language models (SLMs) can generate surprisingly coherent text when trained on simplified, child-directed corpora such as TinyStories. These findings have been interpreted as evidence that readability -- characterized by accessible vocabulary, familiar narrative structure, and simple syntax -- plays a key role in enabling such capabilities to emerge. In this paper, we challenge that interpretation. We construct synthetic datasets with matched structure but varied readability, and find that readability alone does not predict coherence or learning efficiency in SLMs. Models trained on complex, adult-level text perform comparably to those trained on simplified language, and even exhibit faster development of coherence during training. Instead, we show that statistical simplicity, as measured by n-gram diversity, is a stronger predictor of learnability. Our findings caution against the growing trend of anthropomorphizing language model training -- drawing parallels to human cognitive development without empirical basis -- and argue for more precise reasoning about what properties actually support capability emergence in small models.

---

### Synthesizing Agentic Data for Web Agents with Progressive Difficulty Enhancement Mechanisms

Authors: Shrey Pandit, Xuan-Phi Nguyen, Yifei Ming, Austin Xu, Jiayu Wang, Caiming Xiong, Shafiq Joty
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13913v1

Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools. These tasks remain challenging, as the underlying language models are often not optimized for long-horizon reasoning and exploration. Prior work has proposed workflows for constructing instruction-tuning datasets, often leveraging knowledge graphs. However, such methods typically lack fine-grained control over difficulty and quality, yielding synthetic data that falls short of capturing the complexity required for long-horizon reasoning. Furthermore, many studies conflate data and training effects by comparing models trained under different optimization recipes, making it difficult to isolate and evaluate the effectiveness of the data itself. We introduce a two-pronged data synthesis pipeline that generates question - answer pairs by progressively increasing task complexity until a frontier baseline web agent fails. The baseline agent plays multiple roles in this process: attempting the questions, validating factuality, checking for alternative answers, and enforcing filtering. To evaluate the effectiveness of our synthesis methods, we adopt a controlled training setup based on distillation from strong web agents. Experiments across multiple web-based benchmarks show that our dataset - despite being smaller - enables the training of more effective web agents than existing datasets. In particular, our data exhibits twice the diversity in tool-use actions, allowing models trained on it to achieve stronger performance while avoiding repetitive tool-calling behaviors.

---

### AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs

Authors: María Victoria Carro, Denise Alejandra Mester, Facundo Nieto, Oscar Agustín Stanchi, Guido Ernesto Bergman, Mario Alejandro Leiva, Eitan Sprejer, Luca Nicolás Forziati Gangi, Francisca Gauna Selasco, Juan Gustavo Corvalán, Gerardo I. Simari, María Vanina Martinez
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13912v3

The core premise of AI debate as a scalable oversight technique is that it is harder to lie convincingly than to refute a lie, enabling the judge to identify the correct position. Yet, existing debate experiments have relied on datasets with ground truth, where lying is reduced to defending an incorrect proposition. This overlooks a subjective dimension: lying also requires the belief that the claim defended is false. In this work, we apply debate to subjective questions and explicitly measure large language models' prior beliefs before experiments. Debaters were asked to select their preferred position, then presented with a judge persona deliberately designed to conflict with their identified priors. This setup tested whether models would adopt sycophantic strategies, aligning with the judge's presumed perspective to maximize persuasiveness, or remain faithful to their prior beliefs. We implemented and compared two debate protocols, sequential and simultaneous, to evaluate potential systematic biases. Finally, we assessed whether models were more persuasive and produced higher-quality arguments when defending positions consistent with their prior beliefs versus when arguing against them. Our main findings show that models tend to prefer defending stances aligned with the judge persona rather than their prior beliefs, sequential debate introduces significant bias favoring the second debater, models are more persuasive when defending positions aligned with their prior beliefs, and paradoxically, arguments misaligned with prior beliefs are rated as higher quality in pairwise comparison. These results can inform human judges to provide higher-quality training signals and contribute to more aligned AI systems, while revealing important aspects of human-AI interaction regarding persuasion dynamics in language models.

---

### RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems

Authors: Jingru Lin, Chen Zhang, Stephen Y. Liu, Haizhou Li
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13910v2

Retrieval-Augmented Generation (RAG) mitigates key limitations of Large Language Models (LLMs)-such as factual errors, outdated knowledge, and hallucinations-by dynamically retrieving external information. Recent work extends this paradigm through agentic RAG systems, where LLMs act as agents to iteratively plan, retrieve, and reason over complex queries. However, these systems still struggle with challenging multi-hop questions, and their intermediate reasoning capabilities remain underexplored. To address this, we propose RAGCap-Bench, a capability-oriented benchmark for fine-grained evaluation of intermediate tasks in agentic RAG workflows. We analyze outputs from state-of-the-art systems to identify common tasks and the core capabilities required for their execution, then construct a taxonomy of typical LLM errors to design targeted evaluation questions. Experiments show that "slow-thinking" models with stronger RAGCap performance achieve better end-to-end results, underscoring the benchmark's validity and the importance of enhancing these intermediate capabilities.

---

### Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning

Authors: Xingrui Zhuo, Jiapu Wang, Gongqing Wu, Zhongyuan Wang, Jichen Zhang, Shirui Pan, Xindong Wu
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13909v2

Inductive Knowledge Graph Reasoning (KGR) aims to discover facts in open-domain KGs containing unknown entities and relations, which poses a challenge for KGR models in comprehending uncertain KG components. Existing studies have proposed Knowledge Graph Foundation Models (KGFMs) that learn structural invariances across KGs to handle this uncertainty. Recently, Large Language Models (LLMs) have demonstrated strong capabilities for open-domain knowledge reasoning. As a result, the latest research has focused on LLM-based KGFMs that integrate LLM knowledge with KG context for inductive KGR. However, the intrinsic knowledge of LLMs may be overshadowed by sparse KG context, leading to LLM knowledge distortion, which can cause irreversible damage to model reasoning. Moreover, existing LLM-based KGR methods still struggle to fully constrain generative hallucinations in LLMs, severely limiting the credibility of reasoning results. To address these limitations, we propose a Knowledge Reasoning Language Model (KRLM) that achieves unified coordination between LLM knowledge and KG context throughout the KGR process. Specifically, we design a Knowledge Reasoning Language (KRL) instruction format and a KRL tokenizer to align LLM knowledge with KG representations. Then, we propose a KRL attention layer that coordinates intrinsic LLM knowledge with additional KG context through a dynamic knowledge memory mechanism. Finally, a structure-aware next-entity predictor is proposed, which strictly constrains the reasoning results within a trustworthy knowledge domain. Extensive experimental results on 25 real-world inductive KGR datasets demonstrate the significant superiority of the proposed KRLM\footnote{Our source codes are available at https://anonymous.4open.science/r/KRLM-EA36 in both zero-shot reasoning and fine-tuning scenarios.

---

### PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

Authors: Sihui Ji, Xi Chen, Xin Tao, Pengfei Wan, Hengshuang Zhao
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13809v1

Video generation models nowadays are capable of generating visually realistic videos, but often fail to adhere to physical laws, limiting their ability to generate physically plausible videos and serve as ''world models''. To address this issue, we propose PhysMaster, which captures physical knowledge as a representation for guiding video generation models to enhance their physics-awareness. Specifically, PhysMaster is based on the image-to-video task where the model is expected to predict physically plausible dynamics from the input image. Since the input image provides physical priors like relative positions and potential interactions of objects in the scenario, we devise PhysEncoder to encode physical information from it as an extra condition to inject physical knowledge into the video generation process. The lack of proper supervision on the model's physical performance beyond mere appearance motivates PhysEncoder to apply reinforcement learning with human feedback to physical representation learning, which leverages feedback from generation models to optimize physical representations with Direct Preference Optimization (DPO) in an end-to-end manner. PhysMaster provides a feasible solution for improving physics-awareness of PhysEncoder and thus of video generation, proving its ability on a simple proxy task and generalizability to wide-ranging physical scenarios. This implies that our PhysMaster, which unifies solutions for various physical processes via representation learning in the reinforcement learning paradigm, can act as a generic and plug-in solution for physics-aware video generation and broader applications.

---

### VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models

Authors: Dominick Reilly, Manish Kumar Govind, Le Xue, Srijan Das
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13808v2

Large Vision Language Models (VLMs) excel at general visual reasoning but experience significant performance degradation when deployed in novel domains that exhibit substantial distribution shifts from their pretraining data. Existing domain adaptation methods rely on finetuning standard VLM components; however, depending on which components are updated, these approaches either limit the model's ability to learn domain-specific representations or cause catastrophic forgetting of previously acquired capabilities. We introduce Vision Contextualized Probing (VisCoP), a parameter-efficient adaptation framework that augments the VLM vision encoder with a compact set of learnable visual probes. By learning domain-specific visual representations through these probes while requiring only minimal updates to pretrained model components, VisCoP effectively adapts to new domains without sacrificing existing knowledge. We evaluate VisCoP across three challenging adaptation settings: cross-view (exocentric to egocentric), cross-modal (RGB to depth), and cross-task (human understanding to robot control). Across all scenarios, VisCoP consistently outperforms existing domain adaptation strategies, achieving superior target-domain performance while preserving the pretrained VLM's capabilities on the source domain. These results demonstrate that lightweight visual probing provides an effective and robust solution for adapting VLMs under substantial distribution shifts. Code, models, and evaluation protocols are available at https://github.com/dominickrei/VisCoP.

---

### Generative Universal Verifier as Multimodal Meta-Reasoner

Authors: Xinchen Zhang, Xiaoying Zhang, Youbin Wu, Yanbin Cao, Renrui Zhang, Ruihang Chu, Ling Yang, Yujiu Yang
Published: 2025-10-15
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.13804v1

We introduce Generative Universal Verifier, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of reflection and refinement on visual outcomes during the reasoning and generation process. This work makes three main contributions: (1) We build ViVerBench, a comprehensive benchmark spanning 16 categories of critical tasks for evaluating visual outcomes in multimodal reasoning. Results show that existing VLMs consistently underperform across these tasks, underscoring a substantial gap from human-level capability in reliable visual verification. (2) We design two automated pipelines to construct large-scale visual verification data and train OmniVerifier-7B, the first omni-capable generative verifier trained for universal visual verification and achieves notable gains on ViVerBench(+8.3). Through training, we identify three atomic capabilities in visual verification and demonstrate how they generalize and interact synergistically. (3) We propose OmniVerifier-TTS, a sequential test-time scaling paradigm that leverages the universal verifier to bridge image generation and editing within unified models, enhancing the upper bound of generative ability through iterative fine-grained optimization. Beyond generation, we extend universal verifier to broader world-modeling interleaved reasoning scenarios. Empirically, OmniVerifier-TTS achieves improvements on T2I-ReasonBench(+3.7), and GenEval++(+4.3), outperforming existing parallel test-time scaling methods, such as Best-of-N. By endowing multimodal reasoning with reliable visual verification, OmniVerifier advances both reliable reflection during generation and scalable test-time refinement, marking a step toward more trustworthy and controllable next-generation reasoning systems.

---

### Trace Anything: Representing Any Video in 4D via Trajectory Fields

Authors: Xinhang Liu, Yuxi Xiao, Donny Y. Chen, Jiashi Feng, Yu-Wing Tai, Chi-Keung Tang, Bingyi Kang
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13802v1

Effective spatio-temporal representation is fundamental to modeling, understanding, and predicting dynamics in videos. The atomic unit of a video, the pixel, traces a continuous 3D trajectory over time, serving as the primitive element of dynamics. Based on this principle, we propose representing any video as a Trajectory Field: a dense mapping that assigns a continuous 3D trajectory function of time to each pixel in every frame. With this representation, we introduce Trace Anything, a neural network that predicts the entire trajectory field in a single feed-forward pass. Specifically, for each pixel in each frame, our model predicts a set of control points that parameterizes a trajectory (i.e., a B-spline), yielding its 3D position at arbitrary query time instants. We trained the Trace Anything model on large-scale 4D data, including data from our new platform, and our experiments demonstrate that: (i) Trace Anything achieves state-of-the-art performance on our new benchmark for trajectory field estimation and performs competitively on established point-tracking benchmarks; (ii) it offers significant efficiency gains thanks to its one-pass paradigm, without requiring iterative optimization or auxiliary estimators; and (iii) it exhibits emergent abilities, including goal-conditioned manipulation, motion forecasting, and spatio-temporal fusion. Project page: https://trace-anything.github.io/.

---

### Reasoning in Space via Grounding in the World

Authors: Yiming Chen, Zekun Qi, Wenyao Zhang, Xin Jin, Li Zhang, Peidong Liu
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13800v2

In this paper, we claim that 3D visual grounding is the cornerstone of spatial reasoning and introduce the Grounded-Spatial Reasoner (GS-Reasoner) to explore the effective spatial representations that bridge the gap between them. Existing 3D LLMs suffer from the absence of a unified 3D representation capable of jointly capturing semantic and geometric information. This deficiency is manifested either in poor performance on grounding or in an excessive reliance on external modules, ultimately hindering the seamless integration of grounding and spatial reasoning. To address this, we propose a simple yet effective dual-path pooling mechanism that tightly aligns geometric features with both semantic and positional cues, constructing a unified image patch-based 3D representation that encapsulates all essential information without increasing the number of input tokens. Leveraging this holistic representation, GS-Reasoner is the first 3D LLM that achieves autoregressive grounding entirely without external modules while delivering performance comparable to state-of-the-art models, establishing a unified and self-contained framework for 3D spatial reasoning. To further bridge grounding and spatial reasoning, we introduce the Grounded Chain-of-Thought (GCoT) dataset. This dataset is meticulously curated to include both 3D bounding box annotations for objects referenced in reasoning questions and step-by-step reasoning paths that integrate grounding as a core component of the problem-solving process. Extensive experiments demonstrate that GS-Reasoner achieves impressive results on 3D visual grounding, which in turn significantly enhances its spatial reasoning capabilities, leading to state-of-the-art performance.

---

### BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning

Authors: Jia-Chen Gu, Junyi Zhang, Di Wu, Yuankai Li, Kai-Wei Chang, Nanyun Peng
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13799v2

As retrieval-augmented generation (RAG) tackles complex tasks, increasingly expanded contexts offer richer information, but at the cost of higher latency and increased cognitive load on the model. To mitigate this bottleneck, especially for intricate multi-hop questions, we introduce BRIEF-Pro. It is a universal, lightweight compressor that distills relevant evidence for a given query from retrieved documents into a concise summary for seamless integration into in-context RAG. Using seed data consisting of relatively short contexts (fewer than 1k words), BRIEF-Pro is trained to perform abstractive compression of extended contexts exceeding 10k words across a wide range of scenarios. Furthermore, BRIEF-Pro offers flexible user control over summary length by allowing users to specify the desired number of sentences. Experiments on four open-domain multi-hop question-answering datasets show that BRIEF-Pro generates more concise and relevant summaries, enhancing performance across small, large, and proprietary language models. With the 70B reader model, 32x compression by BRIEF-Pro improves QA performance by 4.67% on average over LongLLMLingua's 9x, while requiring only 23% of its computational overhead.

---

### Breadcrumbs Reasoning: Memory-Efficient Reasoning with Compression Beacons

Authors: Giovanni Monea, Yair Feldman, Shankar Padmanabhan, Kianté Brantley, Yoav Artzi
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13797v3

The scalability of large language models for long-context reasoning is severely constrained by the linear growth of their Transformer key-value cache, which incurs significant memory and computational costs. We posit that as a model generates reasoning tokens, the informational value of past generated tokens diminishes, creating an opportunity for compression. In this work, we propose to periodically compress the generation KV cache with a learned, special-purpose token and evict compressed entries. We train the model to perform this compression via a modified joint distillation and reinforcement learning (RL) framework. Our training method minimizes overhead over the conventional RL process, as it leverages RL outputs for distillation. Empirically, our method achieves a superior memory-accuracy Pareto frontier compared to both the model without cache compression and training-free compression techniques.

---

### The Mechanistic Emergence of Symbol Grounding in Language Models

Authors: Shuyu Wu, Ziqiao Ma, Xiaoxi Luo, Yidong Huang, Josue Torres-Fonseca, Freda Shi, Joyce Chai
Published: 2025-10-15
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.13796v3

Symbol grounding (Harnad, 1990) describes how symbols such as words acquire their meanings by connecting to real-world sensorimotor experiences. Recent work has shown preliminary evidence that grounding may emerge in (vision-)language models trained at scale without using explicit grounding objectives. Yet, the specific loci of this emergence and the mechanisms that drive it remain largely unexplored. To address this problem, we introduce a controlled evaluation framework that systematically traces how symbol grounding arises within the internal computations through mechanistic and causal analysis. Our findings show that grounding concentrates in middle-layer computations and is implemented through the aggregate mechanism, where attention heads aggregate the environmental ground to support the prediction of linguistic forms. This phenomenon replicates in multimodal dialogue and across architectures (Transformers and state-space models), but not in unidirectional LSTMs. Our results provide behavioral and mechanistic evidence that symbol grounding can emerge in language models, with practical implications for predicting and potentially controlling the reliability of generation.

---

### Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs

Authors: Yi Zhang, Bolin Ni, Xin-Sheng Chen, Heng-Rui Zhang, Yongming Rao, Houwen Peng, Qinglin Lu, Han Hu, Meng-Hao Guo, Shi-Min Hu
Published: 2025-10-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.13795v4

Fully open multimodal large language models (MLLMs) currently lag behind proprietary counterparts, primarily due to a significant gap in data quality for supervised fine-tuning (SFT). Existing open-source datasets are often plagued by widespread noise and a critical deficit in complex reasoning data, such as Chain-of-Thought (CoT), which hinders the development of advanced model capabilities. Addressing these challenges, our work makes three primary contributions. First, we introduce Honey-Data-15M, a new SFT dataset comprising approximately 15 million QA pairs, processed through multiple cleaning techniques and enhanced with a novel dual-level (short and long) CoT enrichment strategy. Second, we introduce HoneyPipe, the data curation pipeline, and its underlying framework DataStudio, providing the community with a transparent and adaptable methodology for data curation that moves beyond static dataset releases. Finally, to validate our dataset and pipeline, we train Bee-8B, an 8B model on Honey-Data-15M. Experiments show that Bee-8B establishes a new state-of-the-art (SOTA) for fully open MLLMs, achieving performance that is competitive with, and in some cases surpasses, recent semi-open models such as InternVL3.5-8B. Our work delivers to the community a suite of foundational resources, including: the Honey-Data-15M corpus; the full-stack suite comprising HoneyPipe and DataStudio; training recipes; an evaluation harness; and the model weights. This effort demonstrates that a principled focus on data quality is a key pathway to developing fully open MLLMs that are highly competitive with their semi-open counterparts.

---

### MimicKit: A Reinforcement Learning Framework for Motion Imitation and Control

Authors: Xue Bin Peng
Published: 2025-10-15
Categories: cs.GR, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2510.13794v4

MimicKit is an open-source framework for training motion controllers using motion imitation and reinforcement learning. The codebase provides implementations of commonly-used motion-imitation techniques and RL algorithms. This framework is intended to support research and applications in computer graphics and robotics by providing a unified training framework, along with standardized environment, agent, and data structures. The codebase is designed to be modular and easily configurable, enabling convenient modification and extension to new characters and tasks. The open-source codebase is available at: https://github.com/xbpeng/MimicKit.

---

### NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models

Authors: Nir Goren, Oren Katzir, Abhinav Nakarmi, Eyal Ronen, Mahmood Sharif, Or Patashnik
Published: 2025-10-15
Categories: cs.CV, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.13793v2

With the rapid adoption of diffusion models for visual content generation, proving authorship and protecting copyright have become critical. This challenge is particularly important when model owners keep their models private and may be unwilling or unable to handle authorship issues, making third-party verification essential. A natural solution is to embed watermarks for later verification. However, existing methods require access to model weights and rely on computationally heavy procedures, rendering them impractical and non-scalable. To address these challenges, we propose NoisePrints, a lightweight watermarking scheme that utilizes the random seed used to initialize the diffusion process as a proof of authorship without modifying the generation process. Our key observation is that the initial noise derived from a seed is highly correlated with the generated visual content. By incorporating a hash function into the noise sampling process, we further ensure that recovering a valid seed from the content is infeasible. We also show that sampling an alternative seed that passes verification is infeasible, and demonstrate the robustness of our method under various manipulations. Finally, we show how to use cryptographic zero-knowledge proofs to prove ownership without revealing the seed. By keeping the seed secret, we increase the difficulty of watermark removal. In our experiments, we validate NoisePrints on multiple state-of-the-art diffusion models for images and videos, demonstrating efficient verification using only the seed and output, without requiring access to model weights.

---

### Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach

Authors: Ziqing Lu, Lifeng Lai, Weiyu Xu
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13792v1

Reinforcement learning (RL) for the Markov Decision Process (MDP) has emerged in many security-related applications, such as autonomous driving, financial decisions, and drone/robot algorithms. In order to improve the robustness/defense of RL systems against adversaries, studying various adversarial attacks on RL systems is very important. Most previous work considered deterministic adversarial attack strategies in MDP, which the recipient (victim) agent can defeat by reversing the deterministic attacks. In this paper, we propose a provably ``invincible'' or ``uncounterable'' type of adversarial attack on RL. The attackers apply a rate-distortion information-theoretic approach to randomly change agents' observations of the transition kernel (or other properties) so that the agent gains zero or very limited information about the ground-truth kernel (or other properties) during the training. We derive an information-theoretic lower bound on the recipient agent's reward regret and show the impact of rate-distortion attacks on state-of-the-art model-based and model-free algorithms. We also extend this notion of an information-theoretic approach to other types of adversarial attack, such as state observation attacks.

---

### T3former: Temporal Graph Classification with Topological Machine Learning

Authors: Md. Joshem Uddin, Soham Changani, Baris Coskunuzer
Published: 2025-10-15
Categories: cs.LG, cs.SI, math.AT
arXiv: https://arxiv.org/abs/2510.13789v1

Temporal graph classification plays a critical role in applications such as cybersecurity, brain connectivity analysis, social dynamics, and traffic monitoring. Despite its significance, this problem remains underexplored compared to temporal link prediction or node forecasting. Existing methods often rely on snapshot-based or recurrent architectures that either lose fine-grained temporal information or struggle with long-range dependencies. Moreover, local message-passing approaches suffer from oversmoothing and oversquashing, limiting their ability to capture complex temporal structures. We introduce T3former, a novel Topological Temporal Transformer that leverages sliding-window topological and spectral descriptors as first-class tokens, integrated via a specialized Descriptor-Attention mechanism. This design preserves temporal fidelity, enhances robustness, and enables principled cross-modal fusion without rigid discretization. T3former achieves state-of-the-art performance across multiple benchmarks, including dynamic social networks, brain functional connectivity datasets, and traffic networks. It also offers theoretical guarantees of stability under temporal and structural perturbations. Our results highlight the power of combining topological and spectral insights for advancing the frontier of temporal graph learning.

---

### Adaptive Visual Conditioning for Semantic Consistency in Diffusion-Based Story Continuation

Authors: Seyed Mohammad Mousavi, Morteza Analoui
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13787v1

Story continuation focuses on generating the next image in a narrative sequence so that it remains coherent with both the ongoing text description and the previously observed images. A central challenge in this setting lies in utilizing prior visual context effectively, while ensuring semantic alignment with the current textual input. In this work, we introduce AVC (Adaptive Visual Conditioning), a framework for diffusion-based story continuation. AVC employs the CLIP model to retrieve the most semantically aligned image from previous frames. Crucially, when no sufficiently relevant image is found, AVC adaptively restricts the influence of prior visuals to only the early stages of the diffusion process. This enables the model to exploit visual context when beneficial, while avoiding the injection of misleading or irrelevant information. Furthermore, we improve data quality by re-captioning a noisy dataset using large language models, thereby strengthening textual supervision and semantic alignment. Quantitative results and human evaluations demonstrate that AVC achieves superior coherence, semantic consistency, and visual fidelity compared to strong baselines, particularly in challenging cases where prior visuals conflict with the current input.

---

### The Art of Scaling Reinforcement Learning Compute for LLMs

Authors: Devvrit Khatri, Lovish Madaan, Rishabh Tiwari, Rachit Bansal, Sai Surya Duvvuri, Manzil Zaheer, Inderjit S. Dhillon, David Brandfonbrener, Rishabh Agarwal
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13786v1

Reinforcement learning (RL) has become central to training large language models (LLMs), yet the field lacks predictive scaling methodologies comparable to those established for pre-training. Despite rapidly rising compute budgets, there is no principled understanding of how to evaluate algorithmic improvements for scaling RL compute. We present the first large-scale systematic study, amounting to more than 400,000 GPU-hours, that defines a principled framework for analyzing and predicting RL scaling in LLMs. We fit sigmoidal compute-performance curves for RL training and ablate a wide range of common design choices to analyze their effects on asymptotic performance and compute efficiency. We observe: (1) Not all recipes yield similar asymptotic performance, (2) Details such as loss aggregation, normalization, curriculum, and off-policy algorithm primarily modulate compute efficiency without materially shifting the asymptote, and (3) Stable, scalable recipes follow predictable scaling trajectories, enabling extrapolation from smaller-scale runs. Combining these insights, we propose a best-practice recipe, ScaleRL, and demonstrate its effectiveness by successfully scaling and predicting validation performance on a single RL run scaled up to 100,000 GPU-hours. Our work provides both a scientific framework for analyzing scaling in RL and a practical recipe that brings RL training closer to the predictability long achieved in pre-training.

---

### InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

Authors: Xinyi Chen, Yilun Chen, Yanwei Fu, Ning Gao, Jiaya Jia, Weiyang Jin, Hao Li, Yao Mu, Jiangmiao Pang, Yu Qiao, Yang Tian, Bin Wang et al.
Published: 2025-10-15
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.13778v1

We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its core idea is spatially guided vision-language-action training, where spatial grounding serves as the critical link between instructions and robot actions. InternVLA-M1 employs a two-stage pipeline: (i) spatial grounding pre-training on over 2.3M spatial reasoning data to determine ``where to act'' by aligning instructions with visual, embodiment-agnostic positions, and (ii) spatially guided action post-training to decide ``how to act'' by generating embodiment-aware actions through plug-and-play spatial prompting. This spatially guided training recipe yields consistent gains: InternVLA-M1 outperforms its variant without spatial guidance by +14.6% on SimplerEnv Google Robot, +17% on WidowX, and +4.3% on LIBERO Franka, while demonstrating stronger spatial reasoning capability in box, point, and trace prediction. To further scale instruction following, we built a simulation engine to collect 244K generalizable pick-and-place episodes, enabling a 6.2% average improvement across 200 tasks and 3K+ objects. In real-world clustered pick-and-place, InternVLA-M1 improved by 7.3%, and with synthetic co-training, achieved +20.6% on unseen objects and novel configurations. Moreover, in long-horizon reasoning-intensive scenarios, it surpassed existing works by over 10%. These results highlight spatially guided training as a unifying principle for scalable and resilient generalist robots. Code and models are available at https://github.com/InternRobotics/InternVLA-M1.

---

### UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations

Authors: Dominik J. Mühlematter, Lin Che, Ye Hong, Martin Raubal, Nina Wiedemann
Published: 2025-10-15
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.13774v2

Forecasting urban phenomena such as housing prices and public health indicators requires the effective integration of various geospatial data. Current methods primarily utilize task-specific models, while recent generic models for spatial representations often support only limited modalities and lack multimodal fusion capabilities. To overcome these challenges, we present UrbanFusion, a spatial representation model that features Stochastic Multimodal Fusion (SMF). The framework employs modality-specific encoders to process different types of inputs, including street view imagery, remote sensing data, cartographic maps, and points of interest (POIs) data. These multimodal inputs are integrated via a Transformer-based fusion module that learns unified representations. An extensive evaluation across 41 tasks in 56 cities worldwide demonstrates UrbanFusion's strong generalization and predictive performance compared to state-of-the-art GeoAI models. Specifically, it 1) outperforms prior models on location-encoding, 2) allows multimodal input during inference, and 3) generalizes well to regions unseen during training. UrbanFusion can flexibly utilize any subset of available modalities for a given location during both pretraining and inference, enabling broad applicability across diverse data availability scenarios.

---

### Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs

Authors: Qiwei Yuan, Zhitong Xu, Yinghao Chen, Yiming Xu, Houman Owhadi, Shandian Zhe
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13772v2

Machine learning solvers for partial differential equations (PDEs) have attracted growing interest. However, most existing approaches, such as neural network solvers, rely on stochastic training, which is inefficient and typically requires a great many training epochs. Gaussian process (GP)/kernel-based solvers, while mathematical principled, suffer from scalability issues when handling large numbers of collocation points often needed for challenging or higher-dimensional PDEs. To overcome these limitations, we propose TGPS, a tensor-GP-based solver that introduces factor functions along each input dimension using one-dimensional GPs and combines them via tensor decomposition to approximate the full solution. This design reduces the task to learning a collection of one-dimensional GPs, substantially lowering computational complexity, and enabling scalability to massive collocation sets. For efficient nonlinear PDE solving, we use a partial freezing strategy and Newton's method to linerize the nonlinear terms. We then develop an alternating least squares (ALS) approach that admits closed-form updates, thereby substantially enhancing the training efficiency. We establish theoretical guarantees on the expressivity of our model, together with convergence proof and error analysis under standard regularity assumptions. Experiments on several benchmark PDEs demonstrate that our method achieves superior accuracy and efficiency compared to existing approaches. The code is released at https://github.com/BayesianAIGroup/TGPSolve-NonLinear-PDEs

---

### Scaling Vision Transformers for Functional MRI with Flat Maps

Authors: Connor Lane, Mihir Tripathy, Leema Krishna Murali, Ratna Sagari Grandhi, Shamus Sim Zi Yang, Sam Gijsen, Debojyoti Das, Manish Ram, Utkarsh Kumar Singh, Cesar Kadir Torrico Villanueva, Yuxiang Wei, Will Beddow et al.
Published: 2025-10-15
Categories: cs.CV, cs.AI, q-bio.NC
arXiv: https://arxiv.org/abs/2510.13768v3

We study the problem of training self-supervised foundation models for functional MRI. Our main contributions are: (1) we introduce a new model family (CortexMAE) trained using the masked autoencoder framework on 2.1K hours of open fMRI data, and (2) we release the first open evaluation suite (Brainmarks) for fMRI foundation models. Our core innovation is simple: we adapt the Vision Transformer to fMRI by first converting each 3D fMRI volume to a 2D map using a cortical flat map projection. We directly compare flat maps to both parcellation and volume-based representations. While each has its advantages, flat maps generally perform best. We perform the first systematic scaling analysis for fMRI and observe strict power law scaling, albeit with limits. Finally, we use Brainmarks to do controlled benchmark comparisons. On subject-level trait prediction, we report a challenging null result: no single model achieves clear state-of-the-art performance. Moreover, all models struggle to outperform a simple functional connectivity baseline. On cognitive state decoding, we observe more robust performance, and in this setting our CortexMAE family outperforms prior models by a large margin. Code, models, and datasets are available at https://github.com/MedARC-AI/CortexMAE and https://github.com/MedARC-AI/Brainmarks.

---

### PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference

Authors: Yang Yang, Severi Rissanen, Paul E. Chang, Nasrulloh Loka, Daolang Huang, Arno Solin, Markus Heinonen, Luigi Acerbi
Published: 2025-10-15
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.13763v2

Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging modern generative methods like diffusion models to map observed data to model parameters or future predictions. These approaches yield posterior or posterior-predictive samples for new datasets without requiring further simulator calls after training on simulated parameter-data pairs. However, their applicability is often limited by the prior distribution(s) used to generate model parameters during this training phase. To overcome this constraint, we introduce PriorGuide, a technique specifically designed for diffusion-based amortized inference methods. PriorGuide leverages a novel guidance approximation that enables flexible adaptation of the trained diffusion model to new priors at test time, crucially without costly retraining. This allows users to readily incorporate updated information or expert knowledge post-training, enhancing the versatility of pre-trained inference models.

---

### Progressive multi-fidelity learning with neural networks for physical system predictions

Authors: Paolo Conti, Mengwu Guo, Attilio Frangi, Andrea Manzoni
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13762v2

Highly accurate datasets from numerical or physical experiments are often expensive and time-consuming to acquire, posing a significant challenge for applications that require precise evaluations, potentially across multiple scenarios and in real-time. Even building sufficiently accurate surrogate models can be extremely challenging with limited high-fidelity data. Conversely, less expensive, low-fidelity data can be computed more easily and encompass a broader range of scenarios. By leveraging multi-fidelity information, prediction capabilities of surrogates can be improved. However, in practical situations, data may be different in types, come from sources of different modalities, and not be concurrently available, further complicating the modeling process. To address these challenges, we introduce a progressive multi-fidelity surrogate model. This model can sequentially incorporate diverse data types using tailored encoders. Multi-fidelity regression from the encoded inputs to the target quantities of interest is then performed using neural networks. Input information progressively flows from lower to higher fidelity levels through two sets of connections: concatenations among all the encoded inputs, and additive connections among the final outputs. This dual connection system enables the model to exploit correlations among different datasets while ensuring that each level makes an additive correction to the previous level without altering it. This approach prevents performance degradation as new input data are integrated into the model and automatically adapts predictions based on the available inputs. We demonstrate the effectiveness of the approach on numerical benchmarks and a real-world case study, showing that it reliably integrates multi-modal data and provides accurate predictions, maintaining performance when generalizing across time and parameter variations.

---

### Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark

Authors: Kai Zou, Ziqi Huang, Yuhao Dong, Shulin Tian, Dian Zheng, Hongbo Liu, Jingwen He, Bin Liu, Yu Qiao, Ziwei Liu
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13759v3

Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that inherently couple them. To address this gap, we present Uni-MMMU, a comprehensive and discipline-aware benchmark that systematically unfolds the bidirectional synergy between generation and understanding across eight reasoning-centric domains, including science, coding, mathematics, and puzzles. Each task is bidirectionally coupled, demanding models to (i) leverage conceptual understanding to guide precise visual synthesis, or (ii) utilize generation as a cognitive scaffold for analytical reasoning. Uni-MMMU incorporates verifiable intermediate reasoning steps, unique ground truths, and a reproducible scoring protocol for both textual and visual outputs. Through extensive evaluation of state-of-the-art unified, generation-only, and understanding-only models, we reveal substantial performance disparities and cross-modal dependencies, offering new insights into when and how these abilities reinforce one another, and establishing a reliable foundation for advancing unified models.

---

### A Complete Pipeline for deploying SNNs with Synaptic Delays on Loihi 2

Authors: Balázs Mészáros, James C. Knight, Jonathan Timcheck, Thomas Nowotny
Published: 2025-10-15
Categories: cs.NE, cs.LG
arXiv: https://arxiv.org/abs/2510.13757v1

Spiking Neural Networks are attracting increased attention as a more energy-efficient alternative to traditional Artificial Neural Networks for edge computing. Neuromorphic computing can significantly reduce energy requirements. Here, we present a complete pipeline: efficient event-based training of SNNs with synaptic delays on GPUs and deployment on Intel's Loihi 2 neuromorphic chip. We evaluate our approach on keyword recognition tasks using the Spiking Heidelberg Digits and Spiking Speech Commands datasets, demonstrating that our algorithm can enhance classification accuracy compared to architectures without delays. Our benchmarking indicates almost no accuracy loss between GPU and Loihi 2 implementations, while classification on Loihi 2 is up to 18x faster and uses 250x less energy than on an NVIDIA Jetson Orin Nano.

---

### RECODE: Reasoning Through Code Generation for Visual Question Answering

Authors: Junhong Shen, Mu Cai, Bo Hu, Ameet Talwalkar, David A Ross, Cordelia Schmid, Alireza Fathi
Published: 2025-10-15
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13756v2

Multimodal Large Language Models (MLLMs) struggle with precise reasoning for structured visuals like charts and diagrams, as pixel-based perception lacks a mechanism for verification. To address this, we propose to leverage derendering -- the process of reverse-engineering visuals into executable code -- as a new modality for verifiable visual reasoning. Specifically, we propose RECODE, an agentic framework that first generates multiple candidate programs to reproduce the input image. It then uses a critic to select the most faithful reconstruction and iteratively refines the code. This process not only transforms an ambiguous perceptual task into a verifiable, symbolic problem, but also enables precise calculations and logical inferences later on. On various visual reasoning benchmarks such as CharXiv, ChartQA, and Geometry3K, RECODE significantly outperforms methods that do not leverage code or only use code for drawing auxiliary lines or cropping. Our work demonstrates that grounding visual perception in executable code provides a new path toward more accurate and verifiable multimodal reasoning.

---

### Optimal Bounds for Tyler's M-Estimator for Elliptical Distributions

Authors: Lap Chi Lau, Akshay Ramachandran
Published: 2025-10-15
Categories: math.ST, cs.LG
arXiv: https://arxiv.org/abs/2510.13751v1

A fundamental problem in statistics is estimating the shape matrix of an Elliptical distribution. This generalizes the familiar problem of Gaussian covariance estimation, for which the sample covariance achieves optimal estimation error. For Elliptical distributions, Tyler proposed a natural M-estimator and showed strong statistical properties in the asymptotic regime, independent of the underlying distribution. Numerical experiments show that this estimator performs very well, and that Tyler's iterative procedure converges quickly to the estimator. Franks and Moitra recently provided the first distribution-free error bounds in the finite sample setting, as well as the first rigorous convergence analysis of Tyler's iterative procedure. However, their results exceed the sample complexity of the Gaussian setting by a $\log^{2} d$ factor. We close this gap by proving optimal sample threshold and error bounds for Tyler's M-estimator for all Elliptical distributions, fully matching the Gaussian result. Moreover, we recover the algorithmic convergence even at this lower sample threshold. Our approach builds on the operator scaling connection of Franks and Moitra by introducing a novel pseudorandom condition, which we call $\infty$-expansion. We show that Elliptical distributions satisfy $\infty$-expansion at the optimal sample threshold, and then prove a novel scaling result for inputs satisfying this condition.

---

### Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation

Authors: Zhiqi Huang, Vivek Datla, Chenyang Zhu, Alfy Samuel, Daben Liu, Anoop Kumar, Ritesh Soni
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13750v2

We propose a method for confidence estimation in retrieval-augmented generation (RAG) systems that aligns closely with the correctness of large language model (LLM) outputs. Confidence estimation is especially critical in high-stakes domains such as finance and healthcare, where the cost of an incorrect answer outweighs that of not answering the question. Our approach extends prior uncertainty quantification methods by leveraging raw feed-forward network (FFN) activations as auto-regressive signals, avoiding the information loss inherent in token logits and probabilities after projection and softmax normalization. We model confidence prediction as a sequence classification task, and regularize training with a Huber loss term to improve robustness against noisy supervision. Applied in a real-world financial industry customer-support setting with complex knowledge bases, our method outperforms strong baselines and maintains high accuracy under strict latency constraints. Experiments on Llama 3.1 8B model show that using activations from only the 16th layer preserves accuracy while reducing response latency. Our results demonstrate that activation-based confidence modeling offers a scalable, architecture-aware path toward trustworthy RAG deployment.

---

### Assessing Web Search Credibility and Response Groundedness in Chat Assistants

Authors: Ivan Vykopal, Matúš Pikuliak, Simon Ostermann, Marián Šimko
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13749v2

Chat assistants increasingly integrate web search functionality, enabling them to retrieve and cite external sources. While this promises more reliable answers, it also raises the risk of amplifying misinformation from low-credibility sources. In this paper, we introduce a novel methodology for evaluating assistants' web search behavior, focusing on source credibility and the groundedness of responses with respect to cited sources. Using 100 claims across five misinformation-prone topics, we assess GPT-4o, GPT-5, Perplexity, and Qwen Chat. Our findings reveal differences between the assistants, with Perplexity achieving the highest source credibility, whereas GPT-4o exhibits elevated citation of non-credibility sources on sensitive topics. This work provides the first systematic comparison of commonly used chat assistants for fact-checking behavior, offering a foundation for evaluating AI systems in high-stakes information environments.

---

### Asymptotically optimal reinforcement learning in Block Markov Decision Processes

Authors: Thomas van Vuren, Fiona Sloothaak, Maarten G. Wolf, Jaron Sanders
Published: 2025-10-15
Categories: cs.LG, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2510.13748v1

The curse of dimensionality renders Reinforcement Learning (RL) impractical in many real-world settings with exponentially large state and action spaces. Yet, many environments exhibit exploitable structure that can accelerate learning. To formalize this idea, we study RL in Block Markov Decision Processes (BMDPs). BMDPs model problems with large observation spaces, but where transition dynamics are fully determined by latent states. Recent advances in clustering methods have enabled the efficient recovery of this latent structure. However, a regret analysis that exploits these techniques to determine their impact on learning performance remained open. We are now addressing this gap by providing a regret analysis that explicitly leverages clustering, demonstrating that accurate latent state estimation can indeed effectively speed up learning. Concretely, this paper analyzes a two-phase RL algorithm for BMDPs that first learns the latent structure through random exploration and then switches to an optimism-guided strategy adapted to the uncovered structure. This algorithm achieves a regret that is $O(\sqrt{T}+n)$ on a large class of BMDPs susceptible to clustering. Here, $T$ denotes the number of time steps, $n$ is the cardinality of the observation space, and the Landau notation $O(\cdot)$ holds up to constants and polylogarithmic factors. This improves the best prior bound, $O(\sqrt{T}+n^2)$, especially when $n$ is large. Moreover, we prove that no algorithm can achieve lower regret uniformly on this same class of BMDPs. This establishes that, on this class, the algorithm achieves asymptotic optimality.

---

### InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue

Authors: Wenwen Tong, Hewei Guo, Dongchuan Ran, Jiangnan Chen, Jiefan Lu, Kaibin Wang, Keqiang Li, Xiaoxu Zhu, Jiakui Li, Kehan Li, Xueheng Li, Lumin Li et al.
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13747v2

We introduce InteractiveOmni, a unified and open-source omni-modal large language model for audio-visual multi-turn interaction, ranging from 4B to 8B parameters, designed to lead the field of lightweight models by offering comprehensive omni-modal understanding and speech generation capabilities. To achieve this, we integrate the vision encoder, audio encoder, large language model, and speech decoder into a unified model for understanding and generation tasks. We design a multi-stage training strategy to ensure robust cross-modal capabilities, including pre-training for omni-modal understanding, followed by post-training with speech conversation and audio-visual interaction. To enable human-like long-term conversational ability, we meticulously curate a multi-turn training dataset that enhances the model's ability to handle complex and multi-turn interactions. To effectively evaluate the multi-turn memory and speech interaction capabilities, we construct the multi-modal multi-turn memory benchmark and the multi-turn speech interaction benchmark. Experiments demonstrate that InteractiveOmni significantly outperforms leading open-source models and provides a more intelligent multi-turn audio-visual experience, particularly in its long-term memory capabilities. Notably, InteractiveOmni-4B is comparable to the much larger model like Qwen2.5-Omni-7B on general benchmarks, and it can retain 97% of the performance of the InteractiveOmni-8B while utilizing only 50% of the model size. Achieving state-of-the-art results against similarly sized models across image, audio, video understanding, and speech generation tasks, InteractiveOmni is an accessible, open-source foundation for next-generation intelligent interactive systems.

---

### UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy

Authors: Tianshuo Xu, Kai Wang, Zhifei Chen, Leyi Wu, Tianshui Wen, Fei Chao, Ying-Cong Chen
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13745v2

Computational replication of Chinese calligraphy remains challenging. Existing methods falter, either creating high-quality isolated characters while ignoring page-level aesthetics like ligatures and spacing, or attempting page synthesis at the expense of calligraphic correctness. We introduce \textbf{UniCalli}, a unified diffusion framework for column-level recognition and generation. Training both tasks jointly is deliberate: recognition constrains the generator to preserve character structure, while generation provides style and layout priors. This synergy fosters concept-level abstractions that improve both tasks, especially in limited-data regimes. We curated a dataset of over 8,000 digitized pieces, with ~4,000 densely annotated. UniCalli employs asymmetric noising and a rasterized box map for spatial priors, trained on a mix of synthetic, labeled, and unlabeled data. The model achieves state-of-the-art generative quality with superior ligature continuity and layout fidelity, alongside stronger recognition. The framework successfully extends to other ancient scripts, including Oracle bone inscriptions and Egyptian hieroglyphs. Code and data can be viewed in \href{https://github.com/EnVision-Research/UniCalli}{this URL}.

---

### Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math

Authors: Shrey Pandit, Austin Xu, Xuan-Phi Nguyen, Yifei Ming, Caiming Xiong, Shafiq Joty
Published: 2025-10-15
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.13744v1

Large language model (LLM)-based reasoning systems have recently achieved gold medal-level performance in the IMO 2025 competition, writing mathematical proofs where, to receive full credit, each step must be not only correct but also sufficiently supported. To train LLM-based reasoners in such challenging, open-ended settings, strong verifiers capable of catching step-level mistakes are necessary prerequisites. We introduce Hard2Verify, a human-annotated, step-level verification benchmark produced with over 500 hours of human labor. Hard2Verify is designed to rigorously assess step-level verifiers at the frontier: Verifiers must provide step-level annotations or identify the first error in responses generated by frontier LLMs for very recent, challenging, and open-ended math questions. We evaluate 29 generative critics and process reward models, demonstrating that, beyond a few standouts, open-source verifiers lag closed source models. We subsequently analyze what drives poor performance in step-level verification, the impacts of scaling verifier compute, as well as fundamental questions such as self-verification and verification-generation dynamics.

---

### Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs

Authors: Mustafa Munir, Alex Zhang, Radu Marculescu
Published: 2025-10-15
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13740v1

Vision graph neural networks (ViG) have demonstrated promise in vision tasks as a competitive alternative to conventional convolutional neural nets (CNN) and transformers (ViTs); however, common graph construction methods, such as k-nearest neighbor (KNN), can be expensive on larger images. While methods such as Sparse Vision Graph Attention (SVGA) have shown promise, SVGA's fixed step scale can lead to over-squashing and missing multiple connections to gain the same information that could be gained from a long-range link. Through this observation, we propose a new graph construction method, Logarithmic Scalable Graph Construction (LSGC) to enhance performance by limiting the number of long-range links. To this end, we propose LogViG, a novel hybrid CNN-GNN model that utilizes LSGC. Furthermore, inspired by the successes of multi-scale and high-resolution architectures, we introduce and apply a high-resolution branch and fuse features between our high-resolution and low-resolution branches for a multi-scale high-resolution Vision GNN network. Extensive experiments show that LogViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification and semantic segmentation tasks. Our smallest model, Ti-LogViG, achieves an average top-1 accuracy on ImageNet-1K of 79.9% with a standard deviation of 0.2%, 1.7% higher average accuracy than Vision GNN with a 24.3% reduction in parameters and 35.3% reduction in GMACs. Our work shows that leveraging long-range links in graph construction for ViGs through our proposed LSGC can exceed the performance of current state-of-the-art ViGs. Code is available at https://github.com/mmunir127/LogViG-Official.

---

### Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis

Authors: Zhenxuan Zhang, Peiyuan Jing, Zi Wang, Ula Briski, Coraline Beitone, Yue Yang, Yinzhe Wu, Fanwen Wang, Liutao Yang, Jiahao Huang, Zhifan Gao, Zhaolin Chen et al.
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13735v1

Synthesizing high-quality images from low-field MRI holds significant potential. Low-field MRI is cheaper, more accessible, and safer, but suffers from low resolution and poor signal-to-noise ratio. This synthesis process can reduce reliance on costly acquisitions and expand data availability. However, synthesizing high-field MRI still suffers from a clinical fidelity gap. There is a need to preserve anatomical fidelity, enhance fine-grained structural details, and bridge domain gaps in image contrast. To address these issues, we propose a \emph{cyclic self-supervised diffusion (CSS-Diff)} framework for high-field MRI synthesis from real low-field MRI data. Our core idea is to reformulate diffusion-based synthesis under a cycle-consistent constraint. It enforces anatomical preservation throughout the generative process rather than just relying on paired pixel-level supervision. The CSS-Diff framework further incorporates two novel processes. The slice-wise gap perception network aligns inter-slice inconsistencies via contrastive learning. The local structure correction network enhances local feature restoration through self-reconstruction of masked and perturbed patches. Extensive experiments on cross-field synthesis tasks demonstrate the effectiveness of our method, achieving state-of-the-art performance (e.g., 31.80 $\pm$ 2.70 dB in PSNR, 0.943 $\pm$ 0.102 in SSIM, and 0.0864 $\pm$ 0.0689 in LPIPS). Beyond pixel-wise fidelity, our method also preserves fine-grained anatomical structures compared with the original low-field MRI (e.g., left cerebral white matter error drops from 12.1$\%$ to 2.1$\%$, cortex from 4.2$\%$ to 3.7$\%$). To conclude, our CSS-Diff can synthesize images that are both quantitatively reliable and anatomically consistent.

---

### GAPS: A Clinically Grounded, Automated Benchmark for Evaluating AI Clinicians

Authors: Xiuyuan Chen, Tao Sun, Dexin Su, Ailing Yu, Junwei Liu, Zhe Chen, Gangzeng Jin, Xin Wang, Jingnan Liu, Hansong Xiao, Hualei Zhou, Dongjie Tao et al.
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13734v2

Current benchmarks for AI clinician systems, often based on multiple-choice exams or manual rubrics, fail to capture the depth, robustness, and safety required for real-world clinical practice. To address this, we introduce the GAPS framework, a multidimensional paradigm for evaluating Grounding (cognitive depth), Adequacy (answer completeness), Perturbation (robustness), and Safety. Critically, we developed a fully automated, guideline-anchored pipeline to construct a GAPS-aligned benchmark end-to-end, overcoming the scalability and subjectivity limitations of prior work. Our pipeline assembles an evidence neighborhood, creates dual graph and tree representations, and automatically generates questions across G-levels. Rubrics are synthesized by a DeepResearch agent that mimics GRADE-consistent, PICO-driven evidence review in a ReAct loop. Scoring is performed by an ensemble of large language model (LLM) judges. Validation confirmed our automated questions are high-quality and align with clinician judgment (90% agreement, Cohen's Kappa 0.77). Evaluating state-of-the-art models on the benchmark revealed key failure modes: performance degrades sharply with increased reasoning depth (G-axis), models struggle with answer completeness (A-axis), and they are highly vulnerable to adversarial perturbations (P-axis) as well as certain safety issues (S-axis). This automated, clinically-grounded approach provides a reproducible and scalable method for rigorously evaluating AI clinician systems and guiding their development toward safer, more reliable clinical practice. The benchmark dataset GAPS-NSCLC-preview and evaluation code are publicly available at https://huggingface.co/datasets/AQ-MedAI/GAPS-NSCLC-preview and https://github.com/AQ-MedAI/MedicalAiBenchEval.

---

### LiFMCR: Dataset and Benchmark for Light Field Multi-Camera Registration

Authors: Aymeric Fleith, Julian Zirbel, Daniel Cremers, Niclas Zeller
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13729v1

We present LiFMCR, a novel dataset for the registration of multiple micro lens array (MLA)-based light field cameras. While existing light field datasets are limited to single-camera setups and typically lack external ground truth, LiFMCR provides synchronized image sequences from two high-resolution Raytrix R32 plenoptic cameras, together with high-precision 6-degrees of freedom (DoF) poses recorded by a Vicon motion capture system. This unique combination enables rigorous evaluation of multi-camera light field registration methods. As a baseline, we provide two complementary registration approaches: a robust 3D transformation estimation via a RANSAC-based method using cross-view point clouds, and a plenoptic PnP algorithm estimating extrinsic 6-DoF poses from single light field images. Both explicitly integrate the plenoptic camera model, enabling accurate and scalable multi-camera registration. Experiments show strong alignment with the ground truth, supporting reliable multi-view light field processing. Project page: https://lifmcr.github.io/

---

### From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails

Authors: Ravi Pandya, Madison Bland, Duy P. Nguyen, Changliu Liu, Jaime Fernández Fisac, Andrea Bajcsy
Published: 2025-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.13727v2

Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful content, but about preempting downstream hazards like financial or physical harm. Yet, most AI guardrails continue to rely on output classification based on labeled datasets and human-specified criteria,making them brittle to new hazardous situations. Even when unsafe conditions are flagged, this detection offers no path to recovery: typically, the AI system simply refuses to act--which is not always a safe choice. In this work, we argue that agentic AI safety is fundamentally a sequential decision problem: harmful outcomes arise from the AI system's continually evolving interactions and their downstream consequences on the world. We formalize this through the lens of safety-critical control theory, but within the AI model's latent representation of the world. This enables us to build predictive guardrails that (i) monitor an AI system's outputs (actions) in real time and (ii) proactively correct risky outputs to safe ones, all in a model-agnostic manner so the same guardrail can be wrapped around any AI model. We also offer a practical training recipe for computing such guardrails at scale via safety-critical reinforcement learning. Our experiments in simulated driving and e-commerce settings demonstrate that control-theoretic guardrails can reliably steer LLM agents clear of catastrophic outcomes (from collisions to bankruptcy) while preserving task performance, offering a principled dynamic alternative to today's flag-and-block guardrails.

---

### FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access

Authors: Aditya Tanikanti, Benoit Côté, Yanfei Guo, Le Chen, Nickolaus Saint, Ryan Chard, Ken Raffenetti, Rajeev Thakur, Thomas Uram, Ian Foster, Michael E. Papka, Venkatram Vishwanath
Published: 2025-10-15
Categories: cs.DC, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.13724v1

We present the Federated Inference Resource Scheduling Toolkit (FIRST), a framework enabling Inference-as-a-Service across distributed High-Performance Computing (HPC) clusters. FIRST provides cloud-like access to diverse AI models, like Large Language Models (LLMs), on existing HPC infrastructure. Leveraging Globus Auth and Globus Compute, the system allows researchers to run parallel inference workloads via an OpenAI-compliant API on private, secure environments. This cluster-agnostic API allows requests to be distributed across federated clusters, targeting numerous hosted models. FIRST supports multiple inference backends (e.g., vLLM), auto-scales resources, maintains "hot" nodes for low-latency execution, and offers both high-throughput batch and interactive modes. The framework addresses the growing demand for private, secure, and scalable AI inference in scientific workflows, allowing researchers to generate billions of tokens daily on-premises without relying on commercial cloud infrastructure.

---

### Assessing the Geographic Generalization and Physical Consistency of Generative Models for Climate Downscaling

Authors: Carlo Saccardi, Maximilian Pierzyna, Haitz Sáez de Ocáriz Borde, Simone Monaco, Cristian Meo, Pietro Liò, Rudolf Saathof, Geethu Joseph, Justin Dauwels
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13722v1

Kilometer-scale weather data is crucial for real-world applications but remains computationally intensive to produce using traditional weather simulations. An emerging solution is to use deep learning models, which offer a faster alternative for climate downscaling. However, their reliability is still in question, as they are often evaluated using standard machine learning metrics rather than insights from atmospheric and weather physics. This paper benchmarks recent state-of-the-art deep learning models and introduces physics-inspired diagnostics to evaluate their performance and reliability, with a particular focus on geographic generalization and physical consistency. Our experiments show that, despite the seemingly strong performance of models such as CorrDiff, when trained on a limited set of European geographies (e.g., central Europe), they struggle to generalize to other regions such as Iberia, Morocco in the south, or Scandinavia in the north. They also fail to accurately capture second-order variables such as divergence and vorticity derived from predicted velocity fields. These deficiencies appear even in in-distribution geographies, indicating challenges in producing physically consistent predictions. We propose a simple initial solution: introducing a power spectral density loss function that empirically improves geographic generalization by encouraging the reconstruction of small-scale physical structures. The code for reproducing the experimental results can be found at https://github.com/CarloSaccardi/PSD-Downscaling

---

### NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching

Authors: Run Luo, Xiaobo Xia, Lu Wang, Longze Chen, Renke Shan, Jing Luo, Min Yang, Tat-Seng Chua
Published: 2025-10-15
Categories: cs.CL, cs.AI, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.13721v2

Next-generation multimodal foundation models capable of any-to-any cross-modal generation and multi-turn interaction will serve as core components of artificial general intelligence systems, playing a pivotal role in human-machine interaction. However, most existing multimodal models remain constrained by autoregressive architectures, whose inherent limitations prevent a balanced integration of understanding and generation capabilities. Although hybrid and decoupling strategies have been explored to address these tasks within unified frameworks separately, their redundant, non-integrated designs limit their applicability to broader scenarios, such as cross-modal retrieval. In this work, we introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms. By leveraging metric-induced probability paths and kinetic optimal velocities, NExT-OMNI natively supports any-to-any understanding and generation with enhanced response efficiency, while enabling broader application scenarios through concise unified representations rather than task-decoupled designs. Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks, while outperforming prior unified models in multi-turn multimodal interaction and cross-modal retrieval, highlighting its architectural advantages as a next-generation multimodal foundation model. To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.

---

### Circle of Willis Centerline Graphs: A Dataset and Baseline Algorithm

Authors: Fabio Musio, Norman Juchler, Kaiyuan Yang, Suprosanna Shit, Chinmay Prabhakar, Bjoern Menze, Sven Hirsch
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13720v1

The Circle of Willis (CoW) is a critical network of arteries in the brain, often implicated in cerebrovascular pathologies. Voxel-level segmentation is an important first step toward an automated CoW assessment, but a full quantitative analysis requires centerline representations. However, conventional skeletonization techniques often struggle to extract reliable centerlines due to the CoW's complex geometry, and publicly available centerline datasets remain scarce. To address these challenges, we used a thinning-based skeletonization algorithm to extract and curate centerline graphs and morphometric features from the TopCoW dataset, which includes 200 stroke patients, each imaged with MRA and CTA. The curated graphs were used to develop a baseline algorithm for centerline and feature extraction, combining U-Net-based skeletonization with A* graph connection. Performance was evaluated on a held-out test set, focusing on anatomical accuracy and feature robustness. Further, we used the extracted features to predict the frequency of fetal PCA variants, confirm theoretical bifurcation optimality relations, and detect subtle modality differences. The baseline algorithm consistently reconstructed graph topology with high accuracy (F1 = 1), and the average Euclidean node distance between reference and predicted graphs was below one voxel. Features such as segment radius, length, and bifurcation ratios showed strong robustness, with median relative errors below 5% and Pearson correlations above 0.95. Our results demonstrate the utility of learning-based skeletonization combined with graph connection for anatomically plausible centerline extraction. We emphasize the importance of going beyond simple voxel-based measures by evaluating anatomical accuracy and feature robustness. The dataset and baseline algorithm have been released to support further method development and clinical research.

---

### DeDelayed: Deleting Remote Inference Delay via On-Device Correction

Authors: Dan Jacobellis, Mateen Ulhaq, Fabien Racapé, Hyomin Choi, Neeraja J. Yadwadkar
Published: 2025-10-15
Categories: eess.IV, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.13714v3

Video comprises the vast majority of bits that are generated daily, and is the primary signal driving current innovations in robotics, remote sensing, and wearable technology. Yet, the most powerful video understanding models are too expensive for the resource-constrained platforms used in these applications. One approach is to offload inference to the cloud; this gives access to GPUs capable of processing high-resolution videos in real time. But even with reliable, high-bandwidth communication channels, the combined latency of video encoding, model inference, and round-trip communication prohibits use for certain real-time applications. The alternative is to use fully local inference; but this places extreme constraints on computational and power costs, requiring smaller models and lower resolution, leading to degraded accuracy. To address these challenges, we propose Dedelayed, a real-time inference system that divides computation between a remote model operating on delayed video frames and a local model with access to the current frame. The remote model is trained to make predictions on anticipated future frames, which the local model incorporates into its prediction for the current frame. The local and remote models are jointly optimized with an autoencoder that limits the transmission bitrate required by the available downlink communication channel. We evaluate Dedelayed on the task of real-time streaming video segmentation using the BDD100k driving dataset. For a round trip delay of 100 ms, Dedelayed improves performance by 6.4 mIoU compared to fully local inference and 9.8 mIoU compared to remote inference -- an equivalent improvement to using a model ten times larger. We release our training code, pretrained models, and python library at https://github.com/InterDigitalInc/dedelayed .

---