Showing 1–50 of 296 results for author: Guo, P

Attention-Guided Flow-Matching for Sparse 3D Geological Generation

Authors: Zhixiang Lu, Mengqi Han, Peixin Guo, Tianming Bai, Jionglong Su, Fei Fang, Sifan Song

Abstract: Constructing high-resolution 3D geological models from sparse 1D borehole and 2D surface data is a highly ill-posed inverse problem. Traditional heuristic and implicit modeling methods fundamentally fail to capture non-linear topological discontinuities under extreme sparsity, often yielding unrealistic artifacts. Furthermore, while deep generative architectures like Diffusion Models have revoluti… ▽ More Constructing high-resolution 3D geological models from sparse 1D borehole and 2D surface data is a highly ill-posed inverse problem. Traditional heuristic and implicit modeling methods fundamentally fail to capture non-linear topological discontinuities under extreme sparsity, often yielding unrealistic artifacts. Furthermore, while deep generative architectures like Diffusion Models have revolutionized continuous domains, they suffer from severe representation collapse when conditioned on sparse categorical grids. To bridge this gap, we propose 3D-GeoFlow, the first Attention-Guided Continuous Flow Matching framework tailored for sparse multimodal geological modeling. By reformulating discrete categorical generation as a simulation-free, continuous vector field regression optimized via Mean Squared Error, our model establishes stable, deterministic optimal transport paths. Crucially, we integrate 3D Attention Gates to dynamically propagate localized borehole features across the volumetric latent space, ensuring macroscopic structural coherence. To validate our framework, we curated a large-scale multimodal dataset comprising 2,200 procedurally generated 3D geological cases. Extensive out-of-distribution (OOD) evaluations demonstrate that 3D-GeoFlow achieves a paradigm shift, significantly outperforming heuristic interpolations and standard diffusion baselines. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Lightweight LLM Agent Memory with Small Language Models

Authors: Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, Yang Yang

Abstract: Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low online overhead but suffer from unstable accuracy due to limited query construction and candidate filtering. In contrast, many systems use repeated large-model… ▽ More Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low online overhead but suffer from unstable accuracy due to limited query construction and candidate filtering. In contrast, many systems use repeated large-model calls for online memory operations, improving accuracy but accumulating latency over long interactions. We propose LightMem, a lightweight memory system for better agent memory driven by Small Language Models (SLMs). LightMem modularizes memory retrieval, writing, and long-term consolidation, and separates online processing from offline consolidation to enable efficient memory invocation under bounded compute. We organize memory into short-term memory (STM) for immediate conversational context, mid-term memory (MTM) for reusable interaction summaries, and long-term memory (LTM) for consolidated knowledge, and uses user identifiers to support independent retrieval and incremental maintenance in multi-user settings. Online, LightMem operates under a fixed retrieval budget and selects memories via a two-stage procedure: vector-based coarse retrieval followed by semantic consistency re-ranking. Offline, it abstracts reusable interaction evidence and incrementally integrates it into LTM. Experiments show gains across model scales, with an average F1 improvement of about 2.5 on LoCoMo, more effective and low median latency (83 ms retrieval; 581 ms end-to-end). △ Less

Submitted 9 April, 2026; originally announced April 2026.

Comments: accept by ACL 2026

Beyond Facts: Benchmarking Distributional Reading Comprehension in Large Language Models

Authors: Pei-Fu Guo, Ya-An Tsai, Chun-Chia Hsu, Kai-Xin Chen, Yun-Da Tsai, Kai-Wei Chang, Nanyun Peng, Mi-Yen Yeh, Shou-De Lin

Abstract: While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many real-world tasks require understanding distributional information, such as population-level trends and preferences expressed across collections of text. We introduce Text2DistBench, a reading comprehension benchmark for evaluating LLMs' ability to inf… ▽ More While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many real-world tasks require understanding distributional information, such as population-level trends and preferences expressed across collections of text. We introduce Text2DistBench, a reading comprehension benchmark for evaluating LLMs' ability to infer distributional knowledge from natural language. Built from real-world YouTube comments about movie and music entities, the benchmark provides models with entity metadata and associated comments, and requires them to answer distributional questions, such as estimating the proportions of positive and negative comments, or identifying the most and second most frequent topics discussed among viewers. To support reliable and long-term evaluation, the construction pipeline of Text2DistBench is fully automated and continuously updated to incorporate newly emerging entities over time. Experiments across multiple LLMs show that while models substantially outperform random baselines, performance varies widely across different distribution types and characteristics. These findings highlight both the capabilities and limitations of current LLMs in distributional reading comprehension and demonstrate the value of Text2DistBench as a practical and scalable testbed for future research. △ Less

Submitted 13 March, 2026; originally announced April 2026.

Action Images: End-to-End Policy Learning via Multiview Video Generation

Authors: Haoyu Zhen, Zixian Gao, Qiao Sun, Yilin Zhao, Yuncong Yang, Yilun Du, Pengsheng Guo, Tsun-Hsuan Wang, Yi-Ling Qiao, Chuang Gan

Abstract: World action models (WAMs) have emerged as a promising direction for robot policy learning, as they can leverage powerful video backbones to model the future states. However, existing approaches often rely on separate action modules, or use action representations that are not pixel-grounded, making it difficult to fully exploit the pretrained knowledge of video models and limiting transfer across… ▽ More World action models (WAMs) have emerged as a promising direction for robot policy learning, as they can leverage powerful video backbones to model the future states. However, existing approaches often rely on separate action modules, or use action representations that are not pixel-grounded, making it difficult to fully exploit the pretrained knowledge of video models and limiting transfer across viewpoints and environments. In this work, we present Action Images, a unified world action model that formulates policy learning as multiview video generation. Instead of encoding control as low-dimensional tokens, we translate 7-DoF robot actions into interpretable action images: multi-view action videos that are grounded in 2D pixels and explicitly track robot-arm motion. This pixel-grounded action representation allows the video backbone itself to act as a zero-shot policy, without a separate policy head or action module. Beyond control, the same unified model supports video-action joint generation, action-conditioned video generation, and action labeling under a shared representation. On RLBench and real-world evaluations, our model achieves the strongest zero-shot success rates and improves video-action joint generation quality over prior video-space world models, suggesting that interpretable action images are a promising route to policy learning. △ Less

Submitted 14 April, 2026; v1 submitted 7 April, 2026; originally announced April 2026.

Comments: Project Page: https://actionimages.github.io/

Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining

Authors: Junxuan Li, Rawal Khirodkar, Chengan He, Zhongshi Jiang, Giljoo Nam, Lingchen Yang, Jihyun Lee, Egor Zakharov, Zhaoen Su, Rinat Abdrashitov, Yuan Dong, Julieta Martinez, Kai Li, Qingyang Tan, Takaaki Shiratori, Matthew Hu, Peihong Guo, Xuhua Huang, Ariyan Zarei, Marco Pesavento, Yichen Xu, He Wen, Teng Deng, Wyatt Borsos, Anjali Thakrar , et al. (15 additional authors not shown)

Abstract: High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans with precise control over expressions and poses, but it struggles to generalize to real-world data due to limited scale and the domain gap between the studio environment and the real world. On the other hand, recent large-s… ▽ More High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans with precise control over expressions and poses, but it struggles to generalize to real-world data due to limited scale and the domain gap between the studio environment and the real world. On the other hand, recent large-scale avatar models trained on millions of in-the-wild samples show promise for generalization across a wide range of identities, yet the resulting avatars are often of low-quality due to inherent 3D ambiguities. To address this, we present Large-Scale Codec Avatars (LCA), a high-fidelity, full-body 3D avatar model that generalizes to world-scale populations in a feedforward manner, enabling efficient inference. Inspired by the success of large language models and vision foundation models, we present, for the first time, a pre/post-training paradigm for 3D avatar modeling at scale: we pretrain on 1M in-the-wild videos to learn broad priors over appearance and geometry, then post-train on high-quality curated data to enhance expressivity and fidelity. LCA generalizes across hair styles, clothing, and demographics while providing precise, fine-grained facial expressions and finger-level articulation control, with strong identity preservation. Notably, we observe emergent generalization to relightability and loose garment support to unconstrained inputs, and zero-shot robustness to stylized imagery, despite the absence of direct supervision. △ Less

Submitted 7 April, 2026; v1 submitted 2 April, 2026; originally announced April 2026.

Comments: Accepted in CVPR2026. Website: https://junxuan-li.github.io/lca

CTFS : Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labels

Authors: Ping Guo, Chengzhou Li, Guanchen Meng, Qi Jia, Jinyuan Liu, Zhu Liu, Yu Liu, Zhongxuan Luo, Xin Fan

Abstract: As one of the most important underwater sensing technologies, forward-looking sonar exhibits unique imaging characteristics. Sonar images are often affected by severe speckle noise, low texture contrast, acoustic shadows, and geometric distortions. These factors make it difficult for traditional teacher-student frameworks to achieve satisfactory performance in sonar semantic segmentation tasks und… ▽ More As one of the most important underwater sensing technologies, forward-looking sonar exhibits unique imaging characteristics. Sonar images are often affected by severe speckle noise, low texture contrast, acoustic shadows, and geometric distortions. These factors make it difficult for traditional teacher-student frameworks to achieve satisfactory performance in sonar semantic segmentation tasks under extremely limited labeled data conditions. To address this issue, we propose a Collaborative Teacher Semantic Segmentation Framework for forward-looking sonar images. This framework introduces a multi-teacher collaborative mechanism composed of one general teacher and multiple sonar-specific teachers. By adopting a multi-teacher alternating guidance strategy, the student model can learn general semantic representations while simultaneously capturing the unique characteristics of sonar images, thereby achieving more comprehensive and robust feature modeling. Considering the challenges of sonar images, which can lead teachers to generate a large number of noisy pseudo-labels, we further design a cross-teacher reliability assessment mechanism. This mechanism dynamically quantifies the reliability of pseudo-labels by evaluating the consistency and stability of predictions across multiple views and multiple teachers, thereby mitigating the negative impact caused by noisy pseudo-labels. Notably, on the FLSMD dataset, when only 2% of the data is labeled, our method achieves a 5.08% improvement in mIoU compared to other state-of-the-art approaches. △ Less

Submitted 22 March, 2026; originally announced March 2026.

Comments: Accepted to CVPR 2026 Findings

Beyond the Desk: Barriers and Future Opportunities for AI to Assist Scientists in Embodied Physical Tasks

Authors: Irene Hou, Alexander Qin, Lauren Cheng, Philip J. Guo

Abstract: More scientists are now using AI, but prior studies have examined only how they use it 'at the desk' for computer-based work. However, given that scientific work often happens 'beyond the desk' at lab and field sites, we conducted the first study of how scientific practitioners use AI for embodied physical tasks. We interviewed 12 scientific practitioners doing hands-on lab and fieldwork in domain… ▽ More More scientists are now using AI, but prior studies have examined only how they use it 'at the desk' for computer-based work. However, given that scientific work often happens 'beyond the desk' at lab and field sites, we conducted the first study of how scientific practitioners use AI for embodied physical tasks. We interviewed 12 scientific practitioners doing hands-on lab and fieldwork in domains like nuclear fusion, primate cognition, and biochemistry, and found three barriers to AI adoption in these settings: 1) experimental setups are too high-stakes to risk AI errors, 2) constrained environments make it hard to use AI, and 3) AI cannot match the tacit knowledge of humans. Participants then developed speculative designs for future AI assistants to 1) monitor task status, 2) organize lab-wide knowledge, 3) monitor scientists' health, 4) do field scouting, 5) do hands-on chores. Our findings point toward AI as background infrastructure to support physical work rather than replacing human expertise. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Comments: 16 pages, 4 figures, 1 table. Accepted to CHI 2026 (preprint)

Manufacturing Micro-Patterned Surfaces with Multi-Robot Systems

Authors: Annalisa T. Taylor, Malachi Landis, Ping Guo, Todd D. Murphey

Abstract: Applying micro-patterns to surfaces has been shown to impart useful physical properties such as drag reduction and hydrophobicity. However, current manufacturing techniques cannot produce micro-patterned surfaces at scale due to high-cost machinery and inefficient coverage techniques such as raster-scanning. In this work, we use multiple robots, each equipped with a patterning tool, to manufacture… ▽ More Applying micro-patterns to surfaces has been shown to impart useful physical properties such as drag reduction and hydrophobicity. However, current manufacturing techniques cannot produce micro-patterned surfaces at scale due to high-cost machinery and inefficient coverage techniques such as raster-scanning. In this work, we use multiple robots, each equipped with a patterning tool, to manufacture these surfaces. To allow these robots to coordinate during the patterning task, we use the ergodic control algorithm, which specifies coverage objectives using distributions. We demonstrate that robots can divide complicated coverage objectives by communicating compressed representations of their trajectory history both in simulations and experimental trials. Further, we show that robot-produced patterning can lower the coefficient of friction of metallic surfaces. This work demonstrates that distributed multi-robot systems can coordinate to manufacture products that were previously unrealizable at scale. △ Less

Submitted 18 March, 2026; originally announced March 2026.

Surg$Σ$: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence

Authors: Zhitao Zeng, Mengya Xu, Jian Jiang, Pengfei Guo, Yunqiu Xu, Zhu Zhuo, Chang Han Low, Yufan He, Dong Yang, Chenxi Lin, Yiming Gu, Jiaxin Guo, Yutong Ban, Daguang Xu, Qi Dou, Yueming Jin

Abstract: Surgical intelligence has the potential to improve the safety and consistency of surgical care, yet most existing surgical AI frameworks remain task-specific and struggle to generalize across procedures and institutions. Although multimodal foundation models, particularly multimodal large language models, have demonstrated strong cross-task capabilities across various medical domains, their advanc… ▽ More Surgical intelligence has the potential to improve the safety and consistency of surgical care, yet most existing surgical AI frameworks remain task-specific and struggle to generalize across procedures and institutions. Although multimodal foundation models, particularly multimodal large language models, have demonstrated strong cross-task capabilities across various medical domains, their advancement in surgery remains constrained by the lack of large-scale, systematically curated multimodal data. To address this challenge, we introduce Surg$Σ$, a spectrum of large-scale multimodal data and foundation models for surgical intelligence. At the core of this framework lies Surg$Σ$-DB, a large-scale multimodal data foundation designed to support diverse surgical tasks. Surg$Σ$-DB consolidates heterogeneous surgical data sources (including open-source datasets, curated in-house clinical collections and web-source data) into a unified schema, aiming to improve label consistency and data standardization across heterogeneous datasets. Surg$Σ$-DB spans 6 clinical specialties and diverse surgical types, providing rich image- and video-level annotations across 18 practical surgical tasks covering understanding, reasoning, planning, and generation, at an unprecedented scale (over 5.98M conversations). Beyond conventional multimodal conversations, Surg$Σ$-DB incorporates hierarchical reasoning annotations, providing richer semantic cues to support deeper contextual understanding in complex surgical scenarios. We further provide empirical evidence through recently developed surgical foundation models built upon Surg$Σ$-DB, illustrating the practical benefits of large-scale multimodal annotations, unified semantic design, and structured reasoning annotations for improving cross-task generalization and interpretability. △ Less

Submitted 17 March, 2026; originally announced March 2026.

MSC Class: 68T45 ACM Class: I.2.10

SAW: Toward a Surgical Action World Model via Controllable and Scalable Video Generation

Authors: Sampath Rapuri, Lalithkumar Seenivasan, Dominik Schneider, Roger Soberanis-Mukul, Yufan He, Hao Ding, Jiru Xu, Chenhao Yu, Chenyan Jing, Pengfei Guo, Daguang Xu, Mathias Unberath

Abstract: A surgical world model capable of generating realistic surgical action videos with precise control over tool-tissue interactions can address fundamental challenges in surgical AI and simulation -- from data scarcity and rare event synthesis to bridging the sim-to-real gap for surgical automation. However, current video generation methods, the very core of such surgical world models, require expens… ▽ More A surgical world model capable of generating realistic surgical action videos with precise control over tool-tissue interactions can address fundamental challenges in surgical AI and simulation -- from data scarcity and rare event synthesis to bridging the sim-to-real gap for surgical automation. However, current video generation methods, the very core of such surgical world models, require expensive annotations or complex structured intermediates as conditioning signals at inference, limiting their scalability. Other approaches exhibit limited temporal consistency across complex laparoscopic scenes and do not possess sufficient realism. We propose Surgical Action World (SAW) -- a step toward surgical action world modeling through video diffusion conditioned on four lightweight signals: language prompts encoding tool-action context, a reference surgical scene, tissue affordance mask, and 2D tool-tip trajectories. We design a conditional video diffusion approach that reformulates video-to-video diffusion into trajectory-conditioned surgical action synthesis. The backbone diffusion model is fine-tuned on a custom-curated dataset of 12,044 laparoscopic clips with lightweight spatiotemporal conditioning signals, leveraging a depth consistency loss to enforce geometric plausibility without requiring depth at inference. SAW achieves state-of-the-art temporal consistency (CD-FVD: 199.19 vs. 546.82) and strong visual quality on held-out test data. Furthermore, we demonstrate its downstream utility for (a) surgical AI, where augmenting rare actions with SAW-generated videos improves action recognition (clipping F1-score: 20.93% to 43.14%; cutting: 0.00% to 8.33%) on real test data, and (b) surgical simulation, where rendering tool-tissue interaction videos from simulator-derived trajectory points toward a visually faithful simulation engine. △ Less

Submitted 13 March, 2026; originally announced March 2026.

Comments: The manuscript is under review

Few-for-Many Personalized Federated Learning

Authors: Ping Guo, Tiantian Zhang, Xi Lin, Xiang Li, Zhi-Ri Tang, Qingfu Zhang

Abstract: Personalized Federated Learning (PFL) aims to train customized models for clients with highly heterogeneous data distributions while preserving data privacy. Existing approaches often rely on heuristics like clustering or model interpolation, which lack principled mechanisms for balancing heterogeneous client objectives. Serving $M$ clients with distinct data distributions is inherently a multi-ob… ▽ More Personalized Federated Learning (PFL) aims to train customized models for clients with highly heterogeneous data distributions while preserving data privacy. Existing approaches often rely on heuristics like clustering or model interpolation, which lack principled mechanisms for balancing heterogeneous client objectives. Serving $M$ clients with distinct data distributions is inherently a multi-objective optimization problem, where achieving optimal personalization ideally requires $M$ distinct models on the Pareto front. However, maintaining $M$ separate models poses significant scalability challenges in federated settings with hundreds or thousands of clients. To address this challenge, we reformulate PFL as a few-for-many optimization problem that maintains only $K$ shared server models ($K \ll M$) to collectively serve all $M$ clients. We prove that this framework achieves near-optimal personalization: the approximation error diminishes as $K$ increases and each client's model converges to each client's optimum as data grows. Building on this reformulation, we propose FedFew, a practical algorithm that jointly optimizes the $K$ server models through efficient gradient-based updates. Unlike clustering-based approaches that require manual client partitioning or interpolation-based methods that demand careful hyperparameter tuning, FedFew automatically discovers the optimal model diversity through its optimization process. Experiments across vision, NLP, and real-world medical imaging datasets demonstrate that FedFew, with just 3 models, consistently outperforms other state-of-the-art approaches. Code is available at https://github.com/pgg3/FedFew. △ Less

Submitted 12 March, 2026; originally announced March 2026.

Fast and Optimal Differentially Private Frequent-Substring Mining

Authors: Peaker Guo, Rayne Holland, Hao Wu

Abstract: Given a dataset of $n$ user-contributed strings, each of length at most $\ell$, a key problem is how to identify all frequent substrings while preserving each user's privacy. Recent work by Bernardini et al. (PODS'25) introduced a $\varepsilon$-differentially private algorithm achieving near-optimal error, but at the prohibitive cost of $O(n^2\ell^4)$ space and processing time. In this work, we pr… ▽ More Given a dataset of $n$ user-contributed strings, each of length at most $\ell$, a key problem is how to identify all frequent substrings while preserving each user's privacy. Recent work by Bernardini et al. (PODS'25) introduced a $\varepsilon$-differentially private algorithm achieving near-optimal error, but at the prohibitive cost of $O(n^2\ell^4)$ space and processing time. In this work, we present a new $\varepsilon$-differentially private algorithm that retains the same near-optimal error guarantees while reducing space complexity to $O(n \ell+ |Σ| )$ and time complexity to $O(n \ell\log |Σ| + |Σ| )$, for input alphabet $Σ$. Our approach builds on a top-down exploration of candidate substrings but introduces two new innovations: (i) a refined candidate-generation strategy that leverages the structural properties of frequent prefixes and suffixes, and (ii) pruning of the search space guided by frequency relations. These techniques eliminate the quadratic blow-ups inherent in prior work, enabling scalable frequent substring mining under differential privacy. △ Less

Submitted 10 March, 2026; originally announced March 2026.

Comments: 21 pages, 2 figures, 1 table

Mario: Multimodal Graph Reasoning with Large Language Models

Authors: Yuanfu Sun, Kang Li, Pengkang Guo, Jiajin Liu, Qiaoyu Tan

Abstract: Recent advances in large language models (LLMs) have opened new avenues for multimodal reasoning. Yet, most existing methods still rely on pretrained vision-language models (VLMs) to encode image-text pairs in isolation, ignoring the relational structure that real-world multimodal data naturally form. This motivates reasoning on multimodal graphs (MMGs), where each node has textual and visual attr… ▽ More Recent advances in large language models (LLMs) have opened new avenues for multimodal reasoning. Yet, most existing methods still rely on pretrained vision-language models (VLMs) to encode image-text pairs in isolation, ignoring the relational structure that real-world multimodal data naturally form. This motivates reasoning on multimodal graphs (MMGs), where each node has textual and visual attributes and edges provide structural cues. Enabling LLM-based reasoning on such heterogeneous multimodal signals while preserving graph topology introduces two key challenges: resolving weak cross-modal consistency and handling heterogeneous modality preference. To address this, we propose Mario, a unified framework that simultaneously resolves the two above challenges and enables effective LLM-based reasoning over MMGs. Mario consists of two innovative stages. Firstly, a graph-conditioned VLM design that jointly refines textual and visual features through fine-grained cross-modal contrastive learning guided by graph topology. Secondly, a modality-adaptive graph instruction tuning mechanism that organizes aligned multimodal features into graph-aware instruction views and employs a learnable router to surface, for each node and its neighborhood, the most informative modality configuration to the LLM. Extensive experiments across diverse MMG benchmarks demonstrate that Mario consistently outperforms state-of-the-art graph models in both supervised and zero-shot scenarios for node classification and link prediction. The code will be made available at https://github.com/sunyuanfu/Mario. △ Less

Submitted 26 March, 2026; v1 submitted 5 March, 2026; originally announced March 2026.

Comments: CVPR 2026

"Bespoke Bots": Diverse Instructor Needs for Customizing Generative AI Classroom Chatbots

Authors: Irene Hou, Zeyu Xiong, Philip J. Guo, April Yi Wang

Abstract: Instructors are increasingly experimenting with AI chatbots for classroom support. To investigate how instructors adapt chatbots to their own contexts, we first analyzed existing resources that provide prompts for educational purposes. We identified ten common categories of customization, such as persona, guardrails, and personalization. We then conducted interviews with ten university STEM instru… ▽ More Instructors are increasingly experimenting with AI chatbots for classroom support. To investigate how instructors adapt chatbots to their own contexts, we first analyzed existing resources that provide prompts for educational purposes. We identified ten common categories of customization, such as persona, guardrails, and personalization. We then conducted interviews with ten university STEM instructors and asked them to card-sort the categories into priorities. We found that instructors consistently prioritized the ability to customize chatbot behavior to align with course materials and pedagogical strategies and de-prioritized customizing persona/tone. However, their prioritization of other categories varied significantly by course size, discipline, and teaching style, even across courses taught by the same individual, highlighting that no single design can meet all contexts. These findings suggest that modular AI chatbots may provide a promising path forward. We offer design implications for educational developers building the next generation of customizable classroom AI systems. △ Less

Submitted 10 February, 2026; originally announced March 2026.

Comments: 10 pages, 1 figure. Accepted to CHI 2026

Humanoid Robots as First Assistants in Endoscopic Surgery

Authors: Sue Min Cho, Jan Emily Mangulabnan, Han Zhang, Zhekai Mao, Yufan He, Pengfei Guo, Daguang Xu, Gregory Hager, Masaru Ishii, Mathias Unberath

Abstract: Humanoid robots have become a focal point of technological ambition, with claims of surgical capability within years in mainstream discourse. These projections are aspirational yet lack empirical grounding. To date, no humanoid has assisted a surgeon through an actual procedure, let alone performed one. The work described here breaks this new ground. Here we report a proof of concept in which a te… ▽ More Humanoid robots have become a focal point of technological ambition, with claims of surgical capability within years in mainstream discourse. These projections are aspirational yet lack empirical grounding. To date, no humanoid has assisted a surgeon through an actual procedure, let alone performed one. The work described here breaks this new ground. Here we report a proof of concept in which a teleoperated Unitree G1 provided endoscopic visualization while an attending otolaryngologist performed a cadaveric sphenoidectomy. The procedure was completed successfully, with stable visualization maintained throughout. Teleoperation allowed assessment of whether the humanoid form factor could meet the physical demands of surgical assistance in terms of sustenance and precision; the cognitive demands were satisfied -- for now -- by the operator. Post-procedure analysis identified engineering targets for clinical translation, alongside near-term opportunities such as autonomous diagnostic scoping. This work establishes form-factor feasibility for humanoid surgical assistance while identifying challenges for continued development. △ Less

Submitted 27 February, 2026; originally announced February 2026.

The Smallest String Attractors of Fibonacci and Period-Doubling Words

Authors: Mutsunori Banbara, Hideo Bannai, Peaker Guo, Dominik Köppl, Takuya Mieno, Yoshio Okamoto

Abstract: A string attractor of a string $T[1..|T|]$ is a set of positions $Γ$ of $T$ such that any substring $w$ of $T$ has an occurrence that crosses a position in $Γ$, i.e., there is a position $i$ such that $w = T[i..i+|w|-1]$ and the intersection $[i,i+|w|-1]\cap Γ$ is nonempty. The size of the smallest string attractor of Fibonacci words is known to be $2$. We completely characterize the set of all sm… ▽ More A string attractor of a string $T[1..|T|]$ is a set of positions $Γ$ of $T$ such that any substring $w$ of $T$ has an occurrence that crosses a position in $Γ$, i.e., there is a position $i$ such that $w = T[i..i+|w|-1]$ and the intersection $[i,i+|w|-1]\cap Γ$ is nonempty. The size of the smallest string attractor of Fibonacci words is known to be $2$. We completely characterize the set of all smallest string attractors of Fibonacci words, and show a recursive formula describing the $2^{n-4} + 2^{\lceil n/2 \rceil - 2}$ distinct position pairs that are the smallest string attractors of the $n$th Fibonacci word for $n \geq 7$. Similarly, the size of the smallest string attractor of period-doubling words is known to be $2$. We also completely characterize the set of all smallest string attractors of period-doubling words, and show a formula describing the two distinct position pairs that are the smallest string attractors of the $n$th period-doubling word for $n\geq 2$. Our results show that strings with the same smallest attractor size can have a drastically different number of distinct smallest attractors. △ Less

Submitted 17 February, 2026; originally announced February 2026.

Sensitivity of Repetitiveness Measures to String Reversal

Authors: Hideo Bannai, Yuto Fujie, Peaker Guo, Shunsuke Inenaga, Yuto Nakashima, Simon J. Puglisi, Cristian Urbina

Abstract: We study the impact that string reversal can have on several repetitiveness measures. First, we exhibit an infinite family of strings where the number, $r$, of runs in the run-length encoding of the Burrows--Wheeler transform (BWT) can increase additively by $Θ(n)$ when reversing the string. This substantially improves the known $Ω(\log n)$ lower-bound for the additive sensitivity of $r$ and it is… ▽ More We study the impact that string reversal can have on several repetitiveness measures. First, we exhibit an infinite family of strings where the number, $r$, of runs in the run-length encoding of the Burrows--Wheeler transform (BWT) can increase additively by $Θ(n)$ when reversing the string. This substantially improves the known $Ω(\log n)$ lower-bound for the additive sensitivity of $r$ and it is asymptotically tight. We generalize our result to other variants of the BWT, including the variant with an appended end-of-string symbol and the bijective BWT. We show that an analogous result holds for the size $z$ of the Lempel--Ziv 77 (LZ) parsing of the text, and also for some of its variants, including the non-overlapping LZ parsing, and the LZ-end parsing. Moreover, we describe a family of strings for which the ratio $z(w^R)/z(w)$ approaches $3$ from below as $|w|\rightarrow \infty$. We also show an asymptotically tight lower-bound of $Θ(n)$ for the additive sensitivity of the size $v$ of the smallest lexicographic parsing to string reversal. Finally, we show that the multiplicative sensitivity of $v$ to reversing the string is $Θ(\log n)$, and this lower-bound is also tight. Overall, our results expose the limitations of repetitiveness measures that are widely used in practice, against string reversal -- a simple and natural data transformation. △ Less

Submitted 15 February, 2026; originally announced February 2026.

Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making

Authors: Baichuan-M3 Team, :, Chengfeng Dou, Fan Yang, Fei Li, Jiyuan Jia, Qiang Ju, Shuai Wang, Tianpeng Li, Xiangrong Zeng, Yijie Zhou, Hongda Zhang, Jinyang Tai, Linzhuang Sun, Peidong Guo, Yichuan Mo, Xiaochuan Wang, Hengfu Cui, Zhishou Zhang

Abstract: We introduce Baichuan-M3, a medical-enhanced large language model engineered to shift the paradigm from passive question-answering to active, clinical-grade decision support. Addressing the limitations of existing systems in open-ended consultations, Baichuan-M3 utilizes a specialized training pipeline to model the systematic workflow of a physician. Key capabilities include: (i) proactive informa… ▽ More We introduce Baichuan-M3, a medical-enhanced large language model engineered to shift the paradigm from passive question-answering to active, clinical-grade decision support. Addressing the limitations of existing systems in open-ended consultations, Baichuan-M3 utilizes a specialized training pipeline to model the systematic workflow of a physician. Key capabilities include: (i) proactive information acquisition to resolve ambiguity; (ii) long-horizon reasoning that unifies scattered evidence into coherent diagnoses; and (iii) adaptive hallucination suppression to ensure factual reliability. Empirical evaluations demonstrate that Baichuan-M3 achieves state-of-the-art results on HealthBench, the newly introduced HealthBench-Hallu and ScanBench, significantly outperforming GPT-5.2 in clinical inquiry, advisory and safety. The models are publicly available at https://huggingface.co/collections/baichuan-inc/baichuan-m3. △ Less

Submitted 6 February, 2026; originally announced February 2026.

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning

Authors: Jingyao Wang, Peizheng Guo, Wenwen Qiang, Jiahuan Zhou, Huijie Guo, Changwen Zheng, Hui Xiong

Abstract: Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coupled to final correctness and pay little attention to the underlying reasoning process: trajectories with sound reasoning but wrong answers receive low credit, while lucky guesses with flawed logic may be highly rewarded, affecting reasoning generalizat… ▽ More Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coupled to final correctness and pay little attention to the underlying reasoning process: trajectories with sound reasoning but wrong answers receive low credit, while lucky guesses with flawed logic may be highly rewarded, affecting reasoning generalization. From a causal perspective, we interpret multi-candidate reasoning for a fixed question as a family of counterfactual experiments with theoretical supports. Building on this, we propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns. It proposes an episodic causal counterfactual reward that jointly captures (i) robustness, encouraging the answer distribution induced by a reasoning step to remain stable under counterfactual perturbations; and (ii) effectiveness, enforcing sufficient variability so that the learned reasoning strategy can transfer across questions. We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust. Extensive experiments on diverse benchmarks demonstrate its advantages. △ Less

Submitted 6 February, 2026; originally announced February 2026.

AgenticLab: A Real-World Robot Agent Platform that Can See, Think, and Act

Authors: Pengyuan Guo, Zhonghao Mai, Zhengtong Xu, Kaidi Zhang, Heng Zhang, Zichen Miao, Arash Ajoudani, Zachary Kingston, Qiang Qiu, Yu She

Abstract: Recent advances in large vision-language models (VLMs) have demonstrated generalizable open-vocabulary perception and reasoning, yet their real-robot manipulation capability remains unclear for long-horizon, closed-loop execution in unstructured, in-the-wild environments. Prior VLM-based manipulation pipelines are difficult to compare across different research groups' setups, and many evaluations… ▽ More Recent advances in large vision-language models (VLMs) have demonstrated generalizable open-vocabulary perception and reasoning, yet their real-robot manipulation capability remains unclear for long-horizon, closed-loop execution in unstructured, in-the-wild environments. Prior VLM-based manipulation pipelines are difficult to compare across different research groups' setups, and many evaluations rely on simulation, privileged state, or specially designed setups. We present AgenticLab, a model-agnostic robot agent platform and benchmark for open-world manipulation. AgenticLab provides a closed-loop agent pipeline for perception, task decomposition, online verification, and replanning. Using AgenticLab, we benchmark state-of-the-art VLM-based agents on real-robot tasks in unstructured environments. Our benchmark reveals several failure modes that offline vision-language tests (e.g., VQA and static image understanding) fail to capture, including breakdowns in multi-step grounding consistency, object grounding under occlusion and scene changes, and insufficient spatial reasoning for reliable manipulation. We will release the full hardware and software stack to support reproducible evaluation and accelerate research on general-purpose robot agents. △ Less

Submitted 9 March, 2026; v1 submitted 2 February, 2026; originally announced February 2026.

Comments: Added appendix

Quality-Diversity Optimization as Multi-Objective Optimization

Authors: Xi Lin, Ping Guo, Yilu Liu, Qingfu Zhang, Jianyong Sun

Abstract: The Quality-Diversity (QD) optimization aims to discover a collection of high-performing solutions that simultaneously exhibit diverse behaviors within a user-defined behavior space. This paradigm has stimulated significant research interest and demonstrated practical utility in domains including robot control, creative design, and adversarial sample generation. A variety of QD algorithms with dis… ▽ More The Quality-Diversity (QD) optimization aims to discover a collection of high-performing solutions that simultaneously exhibit diverse behaviors within a user-defined behavior space. This paradigm has stimulated significant research interest and demonstrated practical utility in domains including robot control, creative design, and adversarial sample generation. A variety of QD algorithms with distinct design principles have been proposed in recent years. Instead of proposing a new QD algorithm, this work introduces a novel reformulation by casting the QD optimization as a multi-objective optimization (MOO) problem with a huge number of optimization objectives. By establishing this connection, we enable the direct adoption of well-established MOO methods, particularly set-based scalarization techniques, to solve QD problems through a collaborative search process. We further provide a theoretical analysis demonstrating that our approach inherits theoretical guarantees from MOO while providing desirable properties for the QD optimization. Experimental studies across several QD applications confirm that our method achieves performance competitive with state-of-the-art QD algorithms. △ Less

Submitted 30 January, 2026; originally announced February 2026.

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

Authors: Ji Shi, Peiming Guo, Meishan Zhang, Miao Zhang, Xuebo Liu, Min Zhang, Weili Guan

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

Submitted 30 January, 2026; originally announced January 2026.

Comments: 17 pages, 3 figures

RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels

Authors: Chengzhou Li, Ping Guo, Guanchen Meng, Qi Jia, Jinyuan Liu, Zhu Liu, Xiaokang Liu, Yu Liu, Zhongxuan Luo, Xin Fan

Abstract: Object detection in sonar images is a key technology in underwater detection systems. Compared to natural images, sonar images contain fewer texture details and are more susceptible to noise, making it difficult for non-experts to distinguish subtle differences between classes. This leads to their inability to provide precise annotation data for sonar images. Therefore, designing effective object… ▽ More Object detection in sonar images is a key technology in underwater detection systems. Compared to natural images, sonar images contain fewer texture details and are more susceptible to noise, making it difficult for non-experts to distinguish subtle differences between classes. This leads to their inability to provide precise annotation data for sonar images. Therefore, designing effective object detection methods for sonar images with extremely limited labels is particularly important. To address this, we propose a teacher-student framework called RSOD, which aims to fully learn the characteristics of sonar images and develop a pseudo-label strategy suitable for these images to mitigate the impact of limited labels. First, RSOD calculates a reliability score by assessing the consistency of the teacher's predictions across different views. To leverage this score, we introduce an object mixed pseudo-label method to tackle the shortage of labeled data in sonar images. Finally, we optimize the performance of the student by implementing a reliability-guided adaptive constraint. By taking full advantage of unlabeled data, the student can perform well even in situations with extremely limited labels. Notably, on the UATD dataset, our method, using only 5% of labeled data, achieves results that can compete against those of our baseline algorithm trained on 100% labeled data. We also collected a new dataset to provide more valuable data for research in the field of sonar. △ Less

Submitted 18 January, 2026; originally announced January 2026.

Comments: Accepted by AAAI 2026,9 pages,10 figures

STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models

Authors: Xiangyu Shi, Junyang Ding, Xu Zhao, Sinong Zhan, Payal Mohapatra, Daniel Quispe, Kojo Welbeck, Jian Cao, Wei Chen, Ping Guo, Qi Zhu

Abstract: Computer-aided design (CAD) is vital to modern manufacturing, yet model creation remains labor-intensive and expertise-heavy. To enable non-experts to translate intuitive design intent into manufacturable artifacts, recent large language models-based text-to-CAD efforts focus on command sequences or script-based formats like CadQuery. However, these formats are kernel-dependent and lack universali… ▽ More Computer-aided design (CAD) is vital to modern manufacturing, yet model creation remains labor-intensive and expertise-heavy. To enable non-experts to translate intuitive design intent into manufacturable artifacts, recent large language models-based text-to-CAD efforts focus on command sequences or script-based formats like CadQuery. However, these formats are kernel-dependent and lack universality for manufacturing. In contrast, the Standard for the Exchange of Product Data (STEP, ISO 10303) file is a widely adopted, neutral boundary representation (B-rep) format directly compatible with manufacturing, but its graph-structured, cross-referenced nature poses unique challenges for auto-regressive LLMs. To address this, we curate a dataset of ~40K STEP-caption pairs and introduce novel preprocessing tailored for the graph-structured format of STEP, including a depth-first search-based reserialization that linearizes cross-references while preserving locality and chain-of-thought(CoT)-style structural annotations that guide global coherence. We integrate retrieval-augmented generation to ground predictions in relevant examples for supervised fine-tuning, and refine generation quality through reinforcement learning with a specific Chamfer Distance-based geometric reward. Experiments demonstrate consistent gains of our STEP-LLM in geometric fidelity over the Text2CAD baseline, with improvements arising from multiple stages of our framework: the RAG module substantially enhances completeness and renderability, the DFS-based reserialization strengthens overall accuracy, and the RL further reduces geometric discrepancy. Both metrics and visual comparisons confirm that STEP-LLM generates shapes with higher fidelity than Text2CAD. These results show the feasibility of LLM-driven STEP model generation from natural language, showing its potential to democratize CAD design for manufacturing. △ Less

Submitted 18 January, 2026; originally announced January 2026.

Comments: Accepted to the Design, Automation & Test in Europe Conference (DATE) 2026

Machine Learning-Driven Creep Law Discovery Across Alloy Compositional Space

Authors: Hongshun Chen, Ryan Zhou, Rujing Zha, Zihan Chen, Wenpan Li, Rowan Rolark, John Patrick Reidy, Jian Cao, Ping Guo, David C. Dunand, Horacio D. Espinosa

Abstract: Hihg-temperature creep characterization of structural alloys traditionally relies on serial uniaxial tests, which are highly inefficient for exploring the large search space of alloy compositions and for material discovery. Here, we introduce a machine-learning-assisted, high-throughput framework for creep law identification based on a dimple array bulge instrument (DABI) configuration, which enab… ▽ More Hihg-temperature creep characterization of structural alloys traditionally relies on serial uniaxial tests, which are highly inefficient for exploring the large search space of alloy compositions and for material discovery. Here, we introduce a machine-learning-assisted, high-throughput framework for creep law identification based on a dimple array bulge instrument (DABI) configuration, which enables parallel creep testing of 25 dimples, each fabricated from a different alloy, in a single experiment. Full-field surface displacements of dimples undergoing time-dependent creep-induced bulging under inert gas pressure are measured by 3D digital image correlation. We train a recurrent neural network (RNN) as a surrogate model, mapping creep parameters and loading conditions to the time-dependent deformation response of DABI. Coupling this surrogate with a particle swarm optimization scheme enables rapid and global inverse identification with sparsity regularization of creep parameters from experiment displacement-time histories. In addition, we propose a phenomenological creep law with a time-dependent stress exponent that captures the sigmoidal primary creep observed in wrought INCONEL 625 and extracts its temperature dependence from DABI test at multiple temperatures. Furthermore, we employ a general creep law combining several conventional forms together with regularized inversion to identify the creep laws for 47 additional Fe-, Ni-, and Co-rich alloys and to automatically select the dominant functional form for each alloy. This workflow combined with DABI experiment provides a quantitative, high-throughput creep characterization platform that is compatible with data mining, composition-property modeling, and nonlinear structural optimization with creep behavior across a large alloy design space. △ Less

Submitted 13 January, 2026; originally announced January 2026.

Comments: 27 pages, 7 figures

Code Evolution for Control: Synthesizing Policies via LLM-Driven Evolutionary Search

Authors: Ping Guo, Chao Li, Yinglan Feng, Chaoning Zhang

Abstract: Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it often suffers from high sample complexity, reward shaping difficulties, and produces opaque neural network policies that are hard to interpret or verify. Manual des… ▽ More Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it often suffers from high sample complexity, reward shaping difficulties, and produces opaque neural network policies that are hard to interpret or verify. Manual design, on the other hand, requires substantial domain expertise and struggles to scale across diverse tasks. In this work, we demonstrate that LLM-driven evolutionary search can effectively synthesize interpretable control policies in the form of executable code. By treating policy synthesis as a code evolution problem, we harness the LLM's prior knowledge of programming patterns and control heuristics while employing evolutionary search to explore the solution space systematically. We implement our approach using EvoToolkit, a framework that seamlessly integrates LLM-driven evolution with customizable fitness evaluation. Our method iteratively evolves populations of candidate policy programs, evaluating them against task-specific objectives and selecting superior individuals for reproduction. This process yields compact, human-readable control policies that can be directly inspected, modified, and formally verified. This work highlights the potential of combining foundation models with evolutionary computation for synthesizing trustworthy control policies in autonomous systems. Code is available at https://github.com/pgg3/EvoControl. △ Less

Submitted 11 January, 2026; originally announced January 2026.

OpenAI GPT-5 System Card

Authors: Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, Akshay Nathan, Alan Luo, Alec Helyar, Aleksander Madry, Aleksandr Efremov, Aleksandra Spyra, Alex Baker-Whitcomb, Alex Beutel, Alex Karpenko, Alex Makelov, Alex Neitz, Alex Wei, Alexandra Barr, Alexandre Kirchmeyer, Alexey Ivanov , et al. (459 additional authors not shown)

Abstract: This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in… ▽ More This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach. △ Less

Submitted 19 December, 2025; originally announced January 2026.

Cosmos-H-Surgical: Learning Surgical Robot Policies from Videos via World Modeling

Authors: Yufan He, Pengfei Guo, Mengya Xu, Zhaoshuo Li, Andriy Myronenko, Dillan Imans, Bingjie Liu, Dongren Yang, Mingxue Gu, Yongnan Ji, Yueming Jin, Ren Zhao, Baiyong Shen, Daguang Xu

Abstract: Data scarcity remains a fundamental barrier to achieving fully autonomous surgical robots. While large scale vision language action (VLA) models have shown impressive generalization in household and industrial manipulation by leveraging paired video action data from diverse domains, surgical robotics suffers from the paucity of datasets that include both visual observations and accurate robot kine… ▽ More Data scarcity remains a fundamental barrier to achieving fully autonomous surgical robots. While large scale vision language action (VLA) models have shown impressive generalization in household and industrial manipulation by leveraging paired video action data from diverse domains, surgical robotics suffers from the paucity of datasets that include both visual observations and accurate robot kinematics. In contrast, vast corpora of surgical videos exist, but they lack corresponding action labels, preventing direct application of imitation learning or VLA training. In this work, we aim to alleviate this problem by learning policy models from Cosmos-H-Surgical, a world model designed for surgical physical AI. We curated the Surgical Action Text Alignment (SATA) dataset with detailed action description specifically for surgical robots. Then we built Cosmos-H-Surgical based on the most advanced physical AI world model and SATA. It's able to generate diverse, generalizable and realistic surgery videos. We are also the first to use an inverse dynamics model to infer pseudokinematics from synthetic surgical videos, producing synthetic paired video action data. We demonstrate that a surgical VLA policy trained with these augmented data significantly outperforms models trained only on real demonstrations on a real surgical robot platform. Our approach offers a scalable path toward autonomous surgical skill acquisition by leveraging the abundance of unlabeled surgical video and generative world modeling, thus opening the door to generalizable and data efficient surgical robot policies. △ Less

Submitted 10 March, 2026; v1 submitted 28 December, 2025; originally announced December 2025.

PhononBench:A Large-Scale Phonon-Based Benchmark for Dynamical Stability in Crystal Generation

Authors: Xiao-Qi Han, Peng-Jie Guo, Ze-Feng Gao, Zhong-Yi Lu

Abstract: In this work, we introduce PhononBench, the first large-scale benchmark for dynamical stability in AI-generated crystals. Leveraging the recently developed MatterSim interatomic potential, which achieves DFT-level accuracy in phonon predictions across more than 10,000 materials, PhononBench enables efficient large-scale phonon calculations and dynamical-stability analysis for 108,843 crystal struc… ▽ More In this work, we introduce PhononBench, the first large-scale benchmark for dynamical stability in AI-generated crystals. Leveraging the recently developed MatterSim interatomic potential, which achieves DFT-level accuracy in phonon predictions across more than 10,000 materials, PhononBench enables efficient large-scale phonon calculations and dynamical-stability analysis for 108,843 crystal structures generated by six leading crystal generation models. PhononBench reveals a widespread limitation of current generative models in ensuring dynamical stability: the average dynamical-stability rate across all generated structures is only 25.83%, with the top-performing model, MatterGen, reaching just 41.0%. Further case studies show that in property-targeted generation-illustrated here by band-gap conditioning with MatterGen--the dynamical-stability rate remains as low as 23.5% even at the optimal band-gap condition of 0.5 eV. In space-group-controlled generation, higher-symmetry crystals exhibit better stability (e.g., cubic systems achieve rates up to 49.2%), yet the average stability across all controlled generations is still only 34.4%. An important additional outcome of this study is the identification of 28,119 crystal structures that are phonon-stable across the entire Brillouin zone, providing a substantial pool of reliable candidates for future materials exploration. By establishing the first large-scale dynamical-stability benchmark, this work systematically highlights the current limitations of crystal generation models and offers essential evaluation criteria and guidance for their future development toward the design and discovery of physically viable materials. All model-generated crystal structures, phonon calculation results, and the high-throughput evaluation workflows developed in PhononBench will be openly released at https://github.com/xqh19970407/PhononBench △ Less

Submitted 26 December, 2025; v1 submitted 24 December, 2025; originally announced December 2025.

Comments: 19 pages, 6 figures

SDUM: A Scalable Deep Unrolled Model for Universal MRI Reconstruction

Authors: Puyang Wang, Pengfei Guo, Keyi Chai, Jinyuan Zhou, Daguang Xu, Shanshan Jiang

Abstract: Clinical MRI encompasses diverse imaging protocols--spanning anatomical targets (cardiac, brain, knee), contrasts (T1, T2, mapping), sampling patterns (Cartesian, radial, spiral, kt-space), and acceleration factors--yet current deep learning reconstructions are typically protocol-specific, hindering generalization and deployment. We introduce Scalable Deep Unrolled Model (SDUM), a universal framew… ▽ More Clinical MRI encompasses diverse imaging protocols--spanning anatomical targets (cardiac, brain, knee), contrasts (T1, T2, mapping), sampling patterns (Cartesian, radial, spiral, kt-space), and acceleration factors--yet current deep learning reconstructions are typically protocol-specific, hindering generalization and deployment. We introduce Scalable Deep Unrolled Model (SDUM), a universal framework combining a Restormer-based reconstructor, a learned coil sensitivity map estimator (CSME), sampling-aware weighted data consistency (SWDC), universal conditioning (UC) on cascade index and protocol metadata, and progressive cascade expansion training. SDUM exhibits foundation-model-like scaling behavior: reconstruction quality follows PSNR ${\sim}$ log(parameters) with correlation $r{=}0.986$ ($R^2{=}0.973$) up to 18 cascades, demonstrating predictable performance gains with model depth. A single SDUM trained on heterogeneous data achieves state-of-the-art results across all four CMRxRecon2025 challenge tracks--multi-center, multi-disease, 5T, and pediatric--without task-specific fine-tuning, surpassing specialized baselines by up to ${+}1.0$~dB. On CMRxRecon2024, SDUM outperforms the winning method PromptMR+ by ${+}0.55$~dB; on fastMRI brain, it exceeds PC-RNN by ${+}1.8$~dB. Ablations validate each component: SWDC ${+}0.43$~dB over standard DC, per-cascade CSME ${+}0.51$~dB, UC ${+}0.38$~dB. These results establish SDUM as a practical path toward universal, scalable MRI reconstruction. △ Less

Submitted 11 March, 2026; v1 submitted 18 December, 2025; originally announced December 2025.

Comments: https://github.com/NVIDIA-Medtech/NV-Raw2insights-MRI

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure

Authors: Lulu Xue, Shengshan Hu, Linqiang Qian, Peijin Guo, Yechao Zhang, Minghui Li, Yanjun Zhang, Dayong Ye, Leo Yu Zhang

Abstract: Machine unlearning is a newly popularized technique for removing specific training data from a trained model, enabling it to comply with data deletion requests. While it protects the rights of users requesting unlearning, it also introduces new privacy risks. Prior works have primarily focused on the privacy of data that has been unlearned, while the risks to retained data remain largely unexplore… ▽ More Machine unlearning is a newly popularized technique for removing specific training data from a trained model, enabling it to comply with data deletion requests. While it protects the rights of users requesting unlearning, it also introduces new privacy risks. Prior works have primarily focused on the privacy of data that has been unlearned, while the risks to retained data remain largely unexplored. To address this gap, we focus on the privacy risks of retained data and, for the first time, reveal the vulnerabilities introduced by machine unlearning under the dual-view setting, where an adversary can query both the original and the unlearned models. From an information-theoretic perspective, we introduce the concept of {privacy knowledge gain} and demonstrate that the dual-view setting allows adversaries to obtain more information than querying either model alone, thereby amplifying privacy leakage. To effectively demonstrate this threat, we propose DVIA, a Dual-View Inference Attack, which extracts membership information on retained data using black-box queries to both models. DVIA eliminates the need to train an attack model and employs a lightweight likelihood ratio inference module for efficient inference. Experiments across different datasets and model architectures validate the effectiveness of DVIA and highlight the privacy risks inherent in the dual-view setting. △ Less

Submitted 17 December, 2025; originally announced December 2025.

Comments: Accepeted by AAAI2026

FactorPortrait: Controllable Portrait Animation via Disentangled Expression, Pose, and Viewpoint

Authors: Jiapeng Tang, Kai Li, Chengxiang Yin, Liuhao Ge, Fei Jiang, Jiu Xu, Matthias Nießner, Christian Häne, Timur Bagautdinov, Egor Zakharov, Peihong Guo

Abstract: We introduce FactorPortrait, a video diffusion method for controllable portrait animation that enables lifelike synthesis from disentangled control signals of facial expressions, head movement, and camera viewpoints. Given a single portrait image, a driving video, and camera trajectories, our method animates the portrait by transferring facial expressions and head movements from the driving video… ▽ More We introduce FactorPortrait, a video diffusion method for controllable portrait animation that enables lifelike synthesis from disentangled control signals of facial expressions, head movement, and camera viewpoints. Given a single portrait image, a driving video, and camera trajectories, our method animates the portrait by transferring facial expressions and head movements from the driving video while simultaneously enabling novel view synthesis from arbitrary viewpoints. We utilize a pre-trained image encoder to extract facial expression latents from the driving video as control signals for animation generation. Such latents implicitly capture nuanced facial expression dynamics with identity and pose information disentangled, and they are efficiently injected into the video diffusion transformer through our proposed expression controller. For camera and head pose control, we employ Plücker ray maps and normal maps rendered from 3D body mesh tracking. To train our model, we curate a large-scale synthetic dataset containing diverse combinations of camera viewpoints, head poses, and facial expression dynamics. Extensive experiments demonstrate that our method outperforms existing approaches in realism, expressiveness, control accuracy, and view consistency. △ Less

Submitted 12 December, 2025; originally announced December 2025.

Comments: Project page: https://tangjiapeng.github.io/FactorPortrait/

Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction

Authors: Nex-AGI Team, :, Yuxuan Cai, Lu Chen, Qiaoling Chen, Yuyang Ding, Liwen Fan, Wenjie Fu, Yufei Gao, Honglin Guo, Pinxue Guo, Zhenhua Han, Zhengfu He, Hanglei Hu, Kai Hu, Shengjia Hua, Tianyu Huai, Baodai Huang, Li Ji, Zhen Jiang, Zhikai Lei, Bufan Li, Jiahang Lin, Lizhi Lin, Jinxiu Liu , et al. (41 additional authors not shown)

Abstract: The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms -- from static imitation to incentive-driven decision making. However, this transition is significantly impeded by the lack of scalable infrastructure capable of constructing high-quality interaction signals for effective policy learning. To address this… ▽ More The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms -- from static imitation to incentive-driven decision making. However, this transition is significantly impeded by the lack of scalable infrastructure capable of constructing high-quality interaction signals for effective policy learning. To address this, we introduce a comprehensive method designed to systematically scale the diversity and complexity of interactive environments. Our method realizes this scaling by addressing three orthogonal dimensions: (1) Complexity: NexAU, a flexible agent framework that supports building complex agent hierarchies via simple configurations; (2) Diversity: NexA4A automatically generates diverse agent hierarchies from natural language to cover infinite domains; and (3) Fidelity: NexGAP bridges the simulation-reality gap by integrating dynamic real-world environment for grounded trajectories synthesis. We train Nex-N1 upon the diverse and complex interactive environments established by our infrastructure. Empirical results on benchmarks such as SWE-bench and tau2 demonstrate that Nex-N1 consistently outperforms SOTA open-source models and achieves competitive performance against frontier proprietary models on complex agentic tasks. We open-source the Nex ecosystem and model weights to facilitate further research. △ Less

Submitted 4 December, 2025; originally announced December 2025.

DeRA: Decoupled Representation Alignment for Video Tokenization

Authors: Pengbo Guo, Junke Wang, Zhen Xing, Chengxu Liu, Daoguo Dong, Xueming Qian, Zuxuan Wu

Abstract: This paper presents DeRA, a novel 1D video tokenizer that decouples the spatial-temporal representation learning in video tokenization to achieve better training efficiency and performance. Specifically, DeRA maintains a compact 1D latent space while factorizing video encoding into appearance and motion streams, which are aligned with pretrained vision foundation models to capture the spatial sema… ▽ More This paper presents DeRA, a novel 1D video tokenizer that decouples the spatial-temporal representation learning in video tokenization to achieve better training efficiency and performance. Specifically, DeRA maintains a compact 1D latent space while factorizing video encoding into appearance and motion streams, which are aligned with pretrained vision foundation models to capture the spatial semantics and temporal dynamics in videos separately. To address the gradient conflicts introduced by the heterogeneous supervision, we further propose the Symmetric Alignment-Conflict Projection (SACP) module that proactively reformulates gradients by suppressing the components along conflicting directions. Extensive experiments demonstrate that DeRA outperforms LARP, the previous state-of-the-art video tokenizer by 25% on UCF-101 in terms of rFVD. Moreover, using DeRA for autoregressive video generation, we also achieve new state-of-the-art results on both UCF-101 class-conditional generation and K600 frame prediction. △ Less

Submitted 4 December, 2025; originally announced December 2025.

ALARM: Automated MLLM-Based Anomaly Detection in Complex-EnviRonment Monitoring with Uncertainty Quantification

Authors: Congjing Zhang, Feng Lin, Xinyi Zhao, Pei Guo, Wei Li, Lin Chen, Chaoyue Zhao, Shuai Huang

Abstract: The advance of Large Language Models (LLMs) has greatly stimulated research interest in developing multi-modal LLM (MLLM)-based visual anomaly detection (VAD) algorithms that can be deployed in complex environments. The challenge is that in these complex environments, the anomalies are sometimes highly contextual and also ambiguous, and thereby, uncertainty quantification (UQ) is a crucial capacit… ▽ More The advance of Large Language Models (LLMs) has greatly stimulated research interest in developing multi-modal LLM (MLLM)-based visual anomaly detection (VAD) algorithms that can be deployed in complex environments. The challenge is that in these complex environments, the anomalies are sometimes highly contextual and also ambiguous, and thereby, uncertainty quantification (UQ) is a crucial capacity for an MLLM-based VAD system to succeed. In this paper, we introduce our UQ-supported MLLM-based VAD framework called ALARM. ALARM integrates UQ with quality-assurance techniques like reasoning chain, self-reflection, and MLLM ensemble for robust and accurate performance and is designed based on a rigorous probabilistic inference pipeline and computational process. Extensive empirical evaluations are conducted using the real-world smart-home benchmark data and wound image classification data, which shows ALARM's superior performance and its generic applicability across different domains for reliable decision-making. △ Less

Submitted 1 December, 2025; originally announced December 2025.

Data-Centric Visual Development for Self-Driving Labs

Authors: Anbang Liu, Guanzhong Hu, Jiayi Wang, Ping Guo, Han Liu

Abstract: Self-driving laboratories offer a promising path toward reducing the labor-intensive, time-consuming, and often irreproducible workflows in the biological sciences. Yet their stringent precision requirements demand highly robust models whose training relies on large amounts of annotated data. However, this kind of data is difficult to obtain in routine practice, especially negative samples. In thi… ▽ More Self-driving laboratories offer a promising path toward reducing the labor-intensive, time-consuming, and often irreproducible workflows in the biological sciences. Yet their stringent precision requirements demand highly robust models whose training relies on large amounts of annotated data. However, this kind of data is difficult to obtain in routine practice, especially negative samples. In this work, we focus on pipetting, the most critical and precision sensitive action in SDLs. To overcome the scarcity of training data, we build a hybrid pipeline that fuses real and virtual data generation. The real track adopts a human-in-the-loop scheme that couples automated acquisition with selective human verification to maximize accuracy with minimal effort. The virtual track augments the real data using reference-conditioned, prompt-guided image generation, which is further screened and validated for reliability. Together, these two tracks yield a class-balanced dataset that enables robust bubble detection training. On a held-out real test set, a model trained entirely on automatically acquired real images reaches 99.6% accuracy, and mixing real and generated data during training sustains 99.4% accuracy while reducing collection and review load. Our approach offers a scalable and cost-effective strategy for supplying visual feedback data to SDL workflows and provides a practical solution to data scarcity in rare event detection and broader vision tasks. △ Less

Submitted 1 December, 2025; originally announced December 2025.

Comments: 11 pages, 4 figures

LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs

Authors: Pei-Fu Guo, Yun-Da Tsai, Chun-Chia Hsu, Kai-Xin Chen, Ya-An Tsai, Kai-Wei Chang, Nanyun Peng, Mi-Yen Yeh, Shou-De Lin

Abstract: Evaluating cross-lingual knowledge transfer in large language models is challenging, as correct answers in a target language may arise either from genuine transfer or from prior exposure during pre-training. We present LiveCLKTBench, an automated generation pipeline specifically designed to isolate and measure cross-lingual knowledge transfer. Our pipeline identifies self-contained, time-sensitive… ▽ More Evaluating cross-lingual knowledge transfer in large language models is challenging, as correct answers in a target language may arise either from genuine transfer or from prior exposure during pre-training. We present LiveCLKTBench, an automated generation pipeline specifically designed to isolate and measure cross-lingual knowledge transfer. Our pipeline identifies self-contained, time-sensitive knowledge entities from real-world domains, filters them based on temporal occurrence, and verifies them against the model's knowledge. The documents of these valid entities are then used to generate factual questions, which are translated into multiple languages to evaluate transferability across linguistic boundaries. Using LiveCLKTBench, we evaluate several LLMs across five languages and observe that cross-lingual transfer is strongly influenced by linguistic distance and often asymmetric across language directions. While larger models improve transfer, the gains diminish with scale and vary across domains. These findings provide new insights into multilingual transfer and demonstrate the value of LiveCLKTBench as a reliable benchmark for future research. △ Less

Submitted 11 April, 2026; v1 submitted 3 November, 2025; originally announced November 2025.

Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration

Authors: Huijie Guo, Jingyao Wang, Peizheng Guo, Xingchen Shen, Changwen Zheng, Wenwen Qiang

Abstract: In this paper, we explore the transferability of SSL by addressing two central questions: (i) what is the representation transferability of SSL, and (ii) how can we effectively model this transferability? Transferability is defined as the ability of a representation learned from one task to support the objective of another. Inspired by the meta-learning paradigm, we construct multiple SSL tasks… ▽ More In this paper, we explore the transferability of SSL by addressing two central questions: (i) what is the representation transferability of SSL, and (ii) how can we effectively model this transferability? Transferability is defined as the ability of a representation learned from one task to support the objective of another. Inspired by the meta-learning paradigm, we construct multiple SSL tasks within each training batch to support explicitly modeling transferability. Based on empirical evidence and causal analysis, we find that although introducing task-level information improves transferability, it is still hindered by task conflict. To address this issue, we propose a Task Conflict Calibration (TC$^2$) method to alleviate the impact of task conflict. Specifically, it first splits batches to create multiple SSL tasks, infusing task-level information. Next, it uses a factor extraction network to produce causal generative factors for all tasks and a weight extraction network to assign dedicated weights to each sample, employing data reconstruction, orthogonality, and sparsity to ensure effectiveness. Finally, TC$^2$ calibrates sample representations during SSL training and integrates into the pipeline via a two-stage bi-level optimization framework to boost the transferability of learned representations. Experimental results on multiple downstream tasks demonstrate that our method consistently improves the transferability of SSL models. △ Less

Submitted 16 November, 2025; originally announced November 2025.

Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding

Authors: Pinxue Guo, Chongruo Wu, Xinyu Zhou, Lingyi Hong, Zhaoyu Chen, Jinglun Li, Kaixun Jiang, Sen-ching Samson Cheung, Wei Zhang, Wenqiang Zhang

Abstract: Multimodal Large Language Models (MLLMs) have unlocked powerful cross-modal capabilities, but still significantly suffer from hallucinations. As such, accurate detection of hallucinations in MLLMs is imperative for ensuring their reliability in practical applications. To this end, guided by the principle of "Seeing is Believing", we introduce VBackChecker, a novel reference-free hallucination dete… ▽ More Multimodal Large Language Models (MLLMs) have unlocked powerful cross-modal capabilities, but still significantly suffer from hallucinations. As such, accurate detection of hallucinations in MLLMs is imperative for ensuring their reliability in practical applications. To this end, guided by the principle of "Seeing is Believing", we introduce VBackChecker, a novel reference-free hallucination detection framework that verifies the consistency of MLLMgenerated responses with visual inputs, by leveraging a pixellevel Grounding LLM equipped with reasoning and referring segmentation capabilities. This reference-free framework not only effectively handles rich-context scenarios, but also offers interpretability. To facilitate this, an innovative pipeline is accordingly designed for generating instruction-tuning data (R-Instruct), featuring rich-context descriptions, grounding masks, and hard negative samples. We further establish R^2 -HalBench, a new hallucination benchmark for MLLMs, which, unlike previous benchmarks, encompasses real-world, rich-context descriptions from 18 MLLMs with high-quality annotations, spanning diverse object-, attribute, and relationship-level details. VBackChecker outperforms prior complex frameworks and achieves state-of-the-art performance on R^2 -HalBench, even rivaling GPT-4o's capabilities in hallucination detection. It also surpasses prior methods in the pixel-level grounding task, achieving over a 10% improvement. All codes, data, and models are available at https://github.com/PinxueGuo/VBackChecker. △ Less

Submitted 15 November, 2025; originally announced November 2025.

Adaptive Digital Twin of Sheet Metal Forming via Proper Orthogonal Decomposition-Based Koopman Operator with Model Predictive Control

Authors: Yi-Ping Chen, Derick Suarez, Ying-Kuan Tsai, Vispi Karkaria, Guanzhong Hu, Zihan Chen, Ping Guo, Jian Cao, Wei Chen

Abstract: Digital Twin (DT) technologies are transforming manufacturing by enabling real-time prediction, monitoring, and control of complex processes. Yet, applying DT to deformation-based metal forming remains challenging because of the strongly coupled spatial-temporal behavior and the nonlinear relationship between toolpath and material response. For instance, sheet-metal forming by the English wheel, a… ▽ More Digital Twin (DT) technologies are transforming manufacturing by enabling real-time prediction, monitoring, and control of complex processes. Yet, applying DT to deformation-based metal forming remains challenging because of the strongly coupled spatial-temporal behavior and the nonlinear relationship between toolpath and material response. For instance, sheet-metal forming by the English wheel, a highly flexible but artisan-dependent process, still lacks digital counterparts that can autonomously plan and adapt forming strategies. This study presents an adaptive DT framework that integrates Proper Orthogonal Decomposition (POD) for physics-aware dimensionality reduction with a Koopman operator for representing nonlinear system in a linear lifted space for the real-time decision-making via model predictive control (MPC). To accommodate evolving process conditions or material states, an online Recursive Least Squares (RLS) algorithm is introduced to update the operator coefficients in real time, enabling continuous adaptation of the DT model as new deformation data become available. The proposed framework is experimentally demonstrated on a robotic English Wheel sheet metal forming system, where deformation fields are measured and modeled under varying toolpaths. Results show that the adaptive DT is capable of controlling the forming process to achieve the given target shape by effectively capturing non-stationary process behaviors. Beyond this case study, the proposed framework establishes a generalizable approach for interpretable, adaptive, and computationally-efficient DT of nonlinear manufacturing systems, bridging reduced-order physics representations with data-driven adaptability to support autonomous process control and optimization. △ Less

Submitted 13 November, 2025; originally announced November 2025.

Boosting In-Silicon Directed Evolution with Fine-Tuned Protein Language Model and Tree Search

Authors: Yaodong Yang, Yang Wang, Jinpeng Li, Pei Guo, Da Han, Guangyong Chen, Pheng-Ann Heng

Abstract: Protein evolution through amino acid mutations is a cornerstone of life sciences. Recent advances in protein language models have shown rich evolutionary patterns, offering unprecedented potential for in-silicon directed evolution. However, existing directed evolution methods largely rely on heuristic evolution strategies and have yet to efficiently integrate the transformative protein language mo… ▽ More Protein evolution through amino acid mutations is a cornerstone of life sciences. Recent advances in protein language models have shown rich evolutionary patterns, offering unprecedented potential for in-silicon directed evolution. However, existing directed evolution methods largely rely on heuristic evolution strategies and have yet to efficiently integrate the transformative protein language models with advanced optimization techniques, such as reinforcement learning, to adaptively learn superior evolution policies. To bridge this gap, we propose AlphaDE, a novel framework that evolves protein sequences by harnessing the innovative paradigms of large language models, such as fine-tuning and test-time inference. First, AlphaDE fine-tunes pretrained protein language models using masked language modeling on homologous protein sequences to activate the evolutionary plausibility of the interested protein family. Second, AlphaDE introduces test-time inference based on Monte Carlo tree search, which effectively evolves proteins with evolutionary guidance from the fine-tuned protein language model. Extensive benchmark experiments show that AlphaDE remarkably outperforms previous state-of-the-art methods even with few-shot fine-tuning. A case study further demonstrates that AlphaDE supports condensing the protein sequence space of avGFP through computational evolution. △ Less

Submitted 6 January, 2026; v1 submitted 12 November, 2025; originally announced November 2025.

Comments: working in progress, 20 pages, 6 figures, 16 tables, updating template

HQ-SVC: Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios

Authors: Bingsong Bai, Yizhong Geng, Fengping Wang, Cong Wang, Puyuan Guo, Yingming Gao, Ya Li

Abstract: Zero-shot singing voice conversion (SVC) transforms a source singer's timbre to an unseen target speaker's voice while preserving melodic content without fine-tuning. Existing methods model speaker timbre and vocal content separately, losing essential acoustic information that degrades output quality while requiring significant computational resources. To overcome these limitations, we propose HQ-… ▽ More Zero-shot singing voice conversion (SVC) transforms a source singer's timbre to an unseen target speaker's voice while preserving melodic content without fine-tuning. Existing methods model speaker timbre and vocal content separately, losing essential acoustic information that degrades output quality while requiring significant computational resources. To overcome these limitations, we propose HQ-SVC, an efficient framework for high-quality zero-shot SVC. HQ-SVC first extracts jointly content and speaker features using a decoupled codec. It then enhances fidelity through pitch and volume modeling, preserving critical acoustic information typically lost in separate modeling approaches, and progressively refines outputs via differentiable signal processing and diffusion techniques. Evaluations confirm HQ-SVC significantly outperforms state-of-the-art zero-shot SVC methods in conversion quality and efficiency. Beyond voice conversion, HQ-SVC achieves superior voice naturalness compared to specialized audio super-resolution methods while natively supporting voice super-resolution tasks. △ Less

Submitted 15 November, 2025; v1 submitted 11 November, 2025; originally announced November 2025.

Comments: Accepted by AAAI 2026 main technical track

HiF-DTA: Hierarchical Feature Learning Network for Drug-Target Affinity Prediction

Authors: Minghui Li, Yuanhang Wang, Peijin Guo, Wei Wan, Shengshan Hu, Shengqing Hu

Abstract: Accurate prediction of Drug-Target Affinity (DTA) is crucial for reducing experimental costs and accelerating early screening in computational drug discovery. While sequence-based deep learning methods avoid reliance on costly 3D structures, they still overlook simultaneous modeling of global sequence semantic features and local topological structural features within drugs and proteins, and repres… ▽ More Accurate prediction of Drug-Target Affinity (DTA) is crucial for reducing experimental costs and accelerating early screening in computational drug discovery. While sequence-based deep learning methods avoid reliance on costly 3D structures, they still overlook simultaneous modeling of global sequence semantic features and local topological structural features within drugs and proteins, and represent drugs as flat sequences without atomic-level, substructural-level, and molecular-level multi-scale features. We propose HiF-DTA, a hierarchical network that adopts a dual-pathway strategy to extract both global sequence semantic and local topological features from drug and protein sequences, and models drugs multi-scale to learn atomic, substructural, and molecular representations fused via a multi-scale bilinear attention module. Experiments on Davis, KIBA, and Metz datasets show HiF-DTA outperforms state-of-the-art baselines, with ablations confirming the importance of global-local extraction and multi-scale fusion. △ Less

Submitted 31 October, 2025; originally announced October 2025.

Comments: Accepted by International Conference on Bioinformatics and Biomedicine (BIBM 25)

Reasoning Visual Language Model for Chest X-Ray Analysis

Authors: Andriy Myronenko, Dong Yang, Baris Turkbey, Mariam Aboian, Sena Azamat, Esra Akcicek, Hongxu Yin, Pavlo Molchanov, Marc Edgar, Yufan He, Pengfei Guo, Yucheng Tang, Daguang Xu

Abstract: Vision-language models (VLMs) have shown strong promise for medical image analysis, but most remain opaque, offering predictions without the transparent, stepwise reasoning clinicians rely on. We present a framework that brings chain-of-thought (CoT) reasoning to chest X-ray interpretation. Inspired by reasoning-first training paradigms, our approach is designed to learn how experts reason, not ju… ▽ More Vision-language models (VLMs) have shown strong promise for medical image analysis, but most remain opaque, offering predictions without the transparent, stepwise reasoning clinicians rely on. We present a framework that brings chain-of-thought (CoT) reasoning to chest X-ray interpretation. Inspired by reasoning-first training paradigms, our approach is designed to learn how experts reason, not just what they conclude, by aligning intermediate steps with observable image evidence and radiology workflow. Beyond accuracy, the explicit reasoning traces support clinical auditability: they reveal why a conclusion was reached, which alternatives were considered, and where uncertainty remains, enabling quality assurance, error analysis, and safer human-AI collaboration. Our model couples high-fidelity visual encoding with a two-stage training recipe: a reasoning-style supervised fine-tuning (SFT) followed by reinforcement learning (RL) that uses verifiable rewards over a list of X-ray abnormalities. The model outputs reasoning that mirrors radiologists systematic thought process, uncertainty, and differential diagnosis. In out-of-distribution evaluation, the approach achieves competitive multi-label classification while improving interpretability. In a reader study with expert radiologists, full reasoning traces increased confidence, supported error auditing, and reduced time to finalize reports. We release code and the model NV-Reason-CXR-3B to support community progress toward trustworthy, explainable AI in chest radiography and other medical imaging tasks where reasoning quality is as critical as prediction quality. △ Less

Submitted 29 October, 2025; v1 submitted 27 October, 2025; originally announced October 2025.

Comments: NV-Reason-CXR-3B

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking

Authors: Xinyu Zhou, Tongxin Pan, Lingyi Hong, Pinxue Guo, Haijing Guo, Zhaoyu Chen, Kaixun Jiang, Wenqiang Zhang

Abstract: UAV tracking can be widely applied in scenarios such as disaster rescue, environmental monitoring, and logistics transportation. However, existing UAV tracking methods predominantly emphasize speed and lack exploration in semantic awareness, which hinders the search region from extracting accurate localization information from the template. The limitation results in suboptimal performance under ty… ▽ More UAV tracking can be widely applied in scenarios such as disaster rescue, environmental monitoring, and logistics transportation. However, existing UAV tracking methods predominantly emphasize speed and lack exploration in semantic awareness, which hinders the search region from extracting accurate localization information from the template. The limitation results in suboptimal performance under typical UAV tracking challenges such as camera motion, fast motion, and low resolution, etc. To address this issue, we propose a dynamic semantic aware correlation modeling tracking framework. The core of our framework is a Dynamic Semantic Relevance Generator, which, in combination with the correlation map from the Transformer, explore semantic relevance. The approach enhances the search region's ability to extract important information from the template, improving accuracy and robustness under the aforementioned challenges. Additionally, to enhance the tracking speed, we design a pruning method for the proposed framework. Therefore, we present multiple model variants that achieve trade-offs between speed and accuracy, enabling flexible deployment according to the available computational resources. Experimental results validate the effectiveness of our method, achieving competitive performance on multiple UAV tracking datasets. The code is available at https://github.com/zxyyxzz/DSATrack. △ Less

Submitted 24 October, 2025; originally announced October 2025.

Comments: Accepted by NeurIPS2025

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

Authors: Ibrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit, Hadrien Reynaud, Dong Yang, Pengfei Guo, Marc Edgar, Daguang Xu, Bernhard Kainz, Bjoern Menze

Abstract: Recent progress in vision-language modeling for 3D medical imaging has been fueled by large-scale computed tomography (CT) corpora with paired free-text reports, stronger architectures, and powerful pretrained models. This has enabled applications such as automated report generation and text-conditioned 3D image synthesis. Yet, current approaches struggle with high-resolution, long-sequence volume… ▽ More Recent progress in vision-language modeling for 3D medical imaging has been fueled by large-scale computed tomography (CT) corpora with paired free-text reports, stronger architectures, and powerful pretrained models. This has enabled applications such as automated report generation and text-conditioned 3D image synthesis. Yet, current approaches struggle with high-resolution, long-sequence volumes: contrastive pretraining often yields vision encoders that are misaligned with clinical language, and slice-wise tokenization blurs fine anatomy, reducing diagnostic performance on downstream tasks. We introduce BTB3D (Better Tokens for Better 3D), a causal convolutional encoder-decoder that unifies 2D and 3D training and inference while producing compact, frequency-aware volumetric tokens. A three-stage training curriculum enables (i) local reconstruction, (ii) overlapping-window tiling, and (iii) long-context decoder refinement, during which the model learns from short slice excerpts yet generalizes to scans exceeding 300 slices without additional memory overhead. BTB3D sets a new state-of-the-art on two key tasks: it improves BLEU scores and increases clinical F1 by 40% over CT2Rep, CT-CHAT, and Merlin for report generation; and it reduces FID by 75% and halves FVD compared to GenerateCT and MedSyn for text-to-CT synthesis, producing anatomically consistent 512*512*241 volumes. These results confirm that precise three-dimensional tokenization, rather than larger language backbones alone, is essential for scalable vision-language modeling in 3D medical imaging. The codebase is available at: https://github.com/ibrahimethemhamamci/BTB3D △ Less

Submitted 23 October, 2025; originally announced October 2025.

Comments: NeurIPS 2025

EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models

Authors: Ping Guo, Chenyu Zhu, Siyuan Chen, Fei Liu, Xi Lin, Zhichao Lu, Qingfu Zhang

Abstract: CUDA kernel optimization has become a critical bottleneck for AI performance, as deep learning training and inference efficiency directly depends on highly optimized GPU kernels. Despite the promise of Large Language Models (LLMs) for automating kernel optimization, this field suffers from a fragmented ecosystem of isolated and incomparable approaches with unclear problem formulations. Further… ▽ More CUDA kernel optimization has become a critical bottleneck for AI performance, as deep learning training and inference efficiency directly depends on highly optimized GPU kernels. Despite the promise of Large Language Models (LLMs) for automating kernel optimization, this field suffers from a fragmented ecosystem of isolated and incomparable approaches with unclear problem formulations. Furthermore, general-purpose LLM code evolution methods cannot meet strict correctness requirements of CUDA kernel optimization. We address these fundamental challenges by first formalizing CUDA kernel optimization as a code optimization task with a clear objective, constraints, and evaluation metrics. We then establish the first systematic LLM-based code evolution framework, EvoEngineer, that provides guidance for designing and adapting optimization strategies to achieve a balance between performance and correctness. Finally, we implement a kernel optimization system based on this framework and conduct extensive experiments on 91 real-world CUDA kernels. Our results demonstrate that EvoEngineer achieves a principled balance between performance and correctness, with the highest averaged median speedup of \textbf{2.72}$\times$ over baseline CUDA kernels and a code validity rate of \textbf{69.8}\%, outperforming existing methods on both dimensions. Our method achieves a maximum speedup of \textbf{36.75}$\times$ among all operations over PyTorch kernels and delivers the highest speedup on \textbf{28} (\textbf{56.0\%}) of 50 operations that achieve over \textbf{2$\times$} acceleration. △ Less

Submitted 4 October, 2025; originally announced October 2025.

Comments: Under Review of ICLR 2026

CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching

Authors: Chen Chen, Pengsheng Guo, Liangchen Song, Jiasen Lu, Rui Qian, Xinze Wang, Tsu-Jui Fu, Wei Liu, Yinfei Yang, Alex Schwing

Abstract: Conditional generative modeling aims to learn a conditional data distribution from samples containing data-condition pairs. For this, diffusion and flow-based methods have attained compelling results. These methods use a learned (flow) model to transport an initial standard Gaussian noise that ignores the condition to the conditional data distribution. The model is hence required to learn both mas… ▽ More Conditional generative modeling aims to learn a conditional data distribution from samples containing data-condition pairs. For this, diffusion and flow-based methods have attained compelling results. These methods use a learned (flow) model to transport an initial standard Gaussian noise that ignores the condition to the conditional data distribution. The model is hence required to learn both mass transport and conditional injection. To ease the demand on the model, we propose Condition-Aware Reparameterization for Flow Matching (CAR-Flow) -- a lightweight, learned shift that conditions the source, the target, or both distributions. By relocating these distributions, CAR-Flow shortens the probability path the model must learn, leading to faster training in practice. On low-dimensional synthetic data, we visualize and quantify the effects of CAR-Flow. On higher-dimensional natural image data (ImageNet-256), equipping SiT-XL/2 with CAR-Flow reduces FID from 2.07 to 1.68, while introducing less than 0.6% additional parameters. △ Less

Submitted 23 October, 2025; v1 submitted 23 September, 2025; originally announced September 2025.

ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents

Authors: Yichen Wang, Hangtao Zhang, Hewen Pan, Ziqi Zhou, Xianlong Wang, Peijin Guo, Lulu Xue, Shengshan Hu, Minghui Li, Leo Yu Zhang

Abstract: Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has increasingly explored adversarial attacks on VLMs to reveal their vulnerabilities. However, these attacks either rely on overly strong assumptions, requiring full kn… ▽ More Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has increasingly explored adversarial attacks on VLMs to reveal their vulnerabilities. However, these attacks either rely on overly strong assumptions, requiring full knowledge of the victim VLM, which is impractical for attacking VLM-based agents, or exhibit limited effectiveness. The latter stems from disrupting most semantic information in the image, which leads to a misalignment between the perception and the task context defined by system prompts. This inconsistency interrupts the VLM's reasoning process, resulting in invalid outputs that fail to affect interactions in the physical world. To this end, we propose a fine-grained adversarial attack framework, ADVEDM, which modifies the VLM's perception of only a few key objects while preserving the semantics of the remaining regions. This attack effectively reduces conflicts with the task context, making VLMs output valid but incorrect decisions and affecting the actions of agents, thus posing a more substantial safety threat in the physical world. We design two variants of based on this framework, ADVEDM-R and ADVEDM-A, which respectively remove the semantics of a specific object from the image and add the semantics of a new object into the image. The experimental results in both general scenarios and EDM tasks demonstrate fine-grained control and excellent attack performance. △ Less

Submitted 20 September, 2025; originally announced September 2025.

Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining

Authors: Ping Guo, Yubing Ren, Binbin Liu, Fengze Liu, Haobin Lin, Yifan Zhang, Bingni Zhang, Taifeng Wang, Yin Zheng

Abstract: Large language models (LLMs) have become integral to a wide range of applications worldwide, driving an unprecedented global demand for effective multilingual capabilities. Central to achieving robust multilingual performance is the strategic allocation of language proportions within training corpora. However, determining optimal language ratios is highly challenging due to intricate cross-lingual… ▽ More Large language models (LLMs) have become integral to a wide range of applications worldwide, driving an unprecedented global demand for effective multilingual capabilities. Central to achieving robust multilingual performance is the strategic allocation of language proportions within training corpora. However, determining optimal language ratios is highly challenging due to intricate cross-lingual interactions and sensitivity to dataset scale. This paper introduces Climb (Cross-Lingual Interaction-aware Multilingual Balancing), a novel framework designed to systematically optimize multilingual data allocation. At its core, Climb introduces a cross-lingual interaction-aware language ratio, explicitly quantifying each language's effective allocation by capturing inter-language dependencies. Leveraging this ratio, Climb proposes a principled two-step optimization procedure--first equalizing marginal benefits across languages, then maximizing the magnitude of the resulting language allocation vectors--significantly simplifying the inherently complex multilingual optimization problem. Extensive experiments confirm that Climb can accurately measure cross-lingual interactions across various multilingual settings. LLMs trained with Climb-derived proportions consistently achieve state-of-the-art multilingual performance, even achieving competitive performance with open-sourced LLMs trained with more tokens. △ Less

Submitted 18 September, 2025; originally announced September 2025.